From 56e01a0357334b461662398db8c89fd6340a5b73 Mon Sep 17 00:00:00 2001
From: Mahesh Binzer-Panchal <mahesh.binzer-panchal@nbis.se>
Date: Tue, 19 Mar 2024 10:09:55 +0100
Subject: [PATCH 001/172] Update assets/schema_input.json

---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index fc4fdb96..332031c2 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -41,7 +41,7 @@
             },
             "rundir": {
                 "type": "string",
-                "format": "file-path",
+                "format": "directory-path",
                 "exists": true,
                 "errorMessage": "Run directory must be a path",
                 "meta": ["rundir"]

From 6c94332bf1ba3738e39c80031f6d83436a4832b4 Mon Sep 17 00:00:00 2001
From: Johannes Alneberg <johannes.alneberg@scilifelab.se>
Date: Wed, 20 Mar 2024 09:16:32 +0100
Subject: [PATCH 002/172] grop instead of project in a single place

Co-authored-by: Adrien Coulier <adrien.coulier@medsci.uu.se>
---
 subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index e1f8e4de..cdbb6400 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -84,7 +84,7 @@ workflow PIPELINE_INITIALISATION {
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
-                def id_string = "${meta.sample}_${meta.group ?: "ungrouped"}_${meta.lane}"
+                def id_string = "${meta.sample}_${meta.project ?: "ungrouped"}_${meta.lane}"
                 def updated_meta = meta + [ id: id_string ]
                 if (!fastq_2) {
                     return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]

From 4779844462856d017d7ecdcba13cf018198caf3b Mon Sep 17 00:00:00 2001
From: Johannes Alneberg <alneberg@kth.se>
Date: Wed, 20 Mar 2024 09:51:59 +0100
Subject: [PATCH 003/172] Updated test profile input

---
 conf/test.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/conf/test.config b/conf/test.config
index fbbffdd6..38e9ee32 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -22,7 +22,7 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+    input  = 'https://raw.githubusercontent.com/KarNair/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

From 28e0137e65c001682ce5e3257ea6fe6248ccf85e Mon Sep 17 00:00:00 2001
From: Johannes Alneberg <johannes.alneberg@scilifelab.se>
Date: Wed, 20 Mar 2024 14:51:35 +0100
Subject: [PATCH 004/172] Update assets/schema_input.json

Co-authored-by: Karthik Nair <35717861+KarNair@users.noreply.github.com>
---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 332031c2..9fb321b5 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -41,7 +41,7 @@
             },
             "rundir": {
                 "type": "string",
-                "format": "directory-path",
+                "format": "path",
                 "exists": true,
                 "errorMessage": "Run directory must be a path",
                 "meta": ["rundir"]

From a31040e055e38f8a530a99fcc865b2bf9f2e14b9 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 18 Mar 2024 15:16:00 +0100
Subject: [PATCH 005/172] Generate reports per lane, group and rundir

---
 conf/modules.config       |  20 ++++++-
 main.nf                   |   5 +-
 workflows/seqinspector.nf | 120 ++++++++++++++++++++++++++++++++++----
 3 files changed, 133 insertions(+), 12 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index e3ea8fa6..296ca786 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -35,7 +35,25 @@ process {
         publishDir = [
             path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            saveAs: {
+                filename -> 
+                    switch (filename) {
+                        case 'versions.yml':
+                            null
+                            break
+                        case ~/L\d+_multiqc_(report\.html|plots|data)/:
+                            "lanes/L${(filename =~ /L(\d+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            break
+                        case ~/G-.+_multiqc_(report\.html|plots|data)/:
+                            "groups/G-${(filename =~ /G-(.+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            break
+                        case ~/D-.+_multiqc_(report\.html|plots|data)/:
+                            "rundirs/D-${(filename =~ /D-(.+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            break
+                        default:
+                            filename
+                    }
+            }
         ]
     }
 
diff --git a/main.nf b/main.nf
index 1e9c2ede..58afd1fe 100644
--- a/main.nf
+++ b/main.nf
@@ -58,7 +58,10 @@ workflow NFCORE_SEQINSPECTOR {
     )
 
     emit:
-    multiqc_report = SEQINSPECTOR.out.multiqc_report // channel: /path/to/multiqc_report.html
+    global_report = SEQINSPECTOR.out.global_report // channel: /path/to/multiqc_report.html
+    lane_reports = SEQINSPECTOR.out.lane_reports // channel: /path/to/multiqc_report.html
+    group_report = SEQINSPECTOR.out.group_reports // channel: /path/to/multiqc_report.html
+    rundir_report = SEQINSPECTOR.out.rundir_reports // channel: /path/to/multiqc_report.html
 
 }
 /*
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 9ae3384b..b6fd3bc4 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -5,7 +5,10 @@
 */
 
 include { FASTQC                 } from '../modules/nf-core/fastqc/main'
-include { MULTIQC                } from '../modules/nf-core/multiqc/main'
+include { MULTIQC } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_LANE } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_GROUP } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_RUNDIR } from '../modules/nf-core/multiqc/main'
 include { paramsSummaryMap       } from 'plugin/nf-validation'
 include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'
 include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline'
@@ -26,6 +29,8 @@ workflow SEQINSPECTOR {
 
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
+    ch_multiqc_extra_files = Channel.empty()
+    ch_multiqc_reports = Channel.empty()
 
     //
     // MODULE: Run FastQC
@@ -33,7 +38,7 @@ workflow SEQINSPECTOR {
     FASTQC (
         ch_samplesheet
     )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
     //
@@ -46,26 +51,121 @@ workflow SEQINSPECTOR {
     //
     // MODULE: MultiQC
     //
-    ch_multiqc_config                     = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
-    ch_multiqc_custom_config              = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty()
+    ch_multiqc_config              = params.multiqc_config ? 
+        Channel.fromPath(params.multiqc_config, checkIfExists: true) :
+        Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
     ch_multiqc_logo                       = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty()
     summary_params                        = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json")
     ch_workflow_summary                   = Channel.value(paramsSummaryMultiqc(summary_params))
     ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
     ch_methods_description                = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description))
-    ch_multiqc_files                      = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-    ch_multiqc_files                      = ch_multiqc_files.mix(ch_collated_versions)
-    ch_multiqc_files                      = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false))
+    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_collated_versions)
+    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false))
 
     MULTIQC (
-        ch_multiqc_files.collect(),
+        ch_multiqc_files
+            .map { meta, file -> file }
+            .mix(ch_multiqc_extra_files)
+            .collect(),
         ch_multiqc_config.toList(),
-        ch_multiqc_custom_config.toList(),
+        Channel.empty().toList(),
+        ch_multiqc_logo.toList()
+    )
+
+    multiqc_extra_files = ch_multiqc_extra_files.toList()
+
+    // Generate reports by lane
+    lane_mqc_files = ch_multiqc_files
+        .map { meta, sample -> [ "L${meta.lane}", meta, sample ] }
+        .groupTuple()
+        .tap { mqc_by_lane }
+        .collectFile{
+            lane, meta, samples -> [
+                "${lane}_multiqc_extra_config.yml",
+                "output_fn_name: \"${lane}_multiqc_report.html\"\ndata_dir_name: \"${lane}_multiqc_data\"\nplots_dir_name: \"${lane}_multiqc_plots\""
+            ]
+        }
+        .map { file -> def fileparts = file.name.split("_")
+             [ fileparts[0], file ] 
+        }
+        .join(mqc_by_lane)
+        .multiMap { lane, config, meta , samples_per_lane ->
+            samples_per_lane: samples_per_lane
+            config: config
+        }
+
+    MULTIQC_PER_LANE(
+        lane_mqc_files.samples_per_lane
+            .map { samples -> samples + multiqc_extra_files.value },
+        ch_multiqc_config.toList(),
+        lane_mqc_files.config,
+        ch_multiqc_logo.toList()
+    )
+
+    // Generate reports by group
+    group_mqc_files = ch_multiqc_files
+        .filter { meta, sample -> meta.group }
+        .map { meta, sample -> [ "G-${meta.group}", meta, sample ] }
+        .groupTuple()
+        .tap { mqc_by_group }
+        .collectFile{
+            group, meta, samples -> [
+                "${group}_multiqc_extra_config.yml",
+                "output_fn_name: \"${group}_multiqc_report.html\"\ndata_dir_name: \"${group}_multiqc_data\"\nplots_dir_name: \"${group}_multiqc_plots\""
+            ]
+        }
+        .map { file -> def fileparts = file.name.split("_")
+             [ fileparts[0], file ] 
+        }
+        .join(mqc_by_group)
+        .multiMap { group, config, meta , samples_per_group ->
+            samples_per_group: samples_per_group
+            config: config
+        }
+
+    MULTIQC_PER_GROUP(
+        group_mqc_files.samples_per_group
+            .map { samples -> samples + multiqc_extra_files.value },
+        ch_multiqc_config.toList(),
+        group_mqc_files.config,
+        ch_multiqc_logo.toList()
+    )
+
+    // Generate reports by rundir
+    rundir_mqc_files = ch_multiqc_files
+        .filter { meta, sample -> meta.rundir }
+        .map { meta, sample -> [ "D-${meta.rundir.name}", meta, sample ] }
+        .groupTuple()
+        .tap { mqc_by_rundir }
+        .collectFile{
+            rundir, meta, samples -> [
+                "${rundir}_multiqc_extra_config.yml",
+                "output_fn_name: \"${rundir}_multiqc_report.html\"\ndata_dir_name: \"${rundir}_multiqc_data\"\nplots_dir_name: \"${rundir}_multiqc_plots\""
+            ]
+        }
+        .map { file -> def fileparts = file.name.split("_")
+             [ fileparts[0], file ] 
+        }
+        .join(mqc_by_rundir)
+        .multiMap { rundir, config, meta , samples_per_rundir ->
+            samples_per_rundir: samples_per_rundir
+            config: config
+        }
+
+    MULTIQC_PER_RUNDIR(
+        rundir_mqc_files.samples_per_rundir
+            .map { samples -> samples + multiqc_extra_files.value },
+        ch_multiqc_config.toList(),
+        rundir_mqc_files.config,
         ch_multiqc_logo.toList()
     )
 
     emit:
-    multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html
+    global_report = MULTIQC.out.report.toList()             // channel: /path/to/multiqc_report.html
+    lane_reports = MULTIQC_PER_LANE.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
+    group_reports = MULTIQC_PER_GROUP.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
+    rundir_reports = MULTIQC_PER_RUNDIR.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
     versions       = ch_versions                 // channel: [ path(versions.yml) ]
 }
 

From 0da58701e706f23001df33bf997bf671ea37a787 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Thu, 28 Mar 2024 16:21:45 +0100
Subject: [PATCH 006/172] Improve formatting

---
 conf/modules.config       |  2 +-
 main.nf                   |  6 ++--
 workflows/seqinspector.nf | 71 +++++++++++++++++++++++++--------------
 3 files changed, 50 insertions(+), 29 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 296ca786..8b7a9c69 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -52,7 +52,7 @@ process {
                             break
                         default:
                             filename
-                    }
+                }
             }
         ]
     }
diff --git a/main.nf b/main.nf
index 58afd1fe..1ee043e9 100644
--- a/main.nf
+++ b/main.nf
@@ -58,9 +58,9 @@ workflow NFCORE_SEQINSPECTOR {
     )
 
     emit:
-    global_report = SEQINSPECTOR.out.global_report // channel: /path/to/multiqc_report.html
-    lane_reports = SEQINSPECTOR.out.lane_reports // channel: /path/to/multiqc_report.html
-    group_report = SEQINSPECTOR.out.group_reports // channel: /path/to/multiqc_report.html
+    global_report = SEQINSPECTOR.out.global_report  // channel: /path/to/multiqc_report.html
+    lane_reports = SEQINSPECTOR.out.lane_reports    // channel: /path/to/multiqc_report.html
+    group_report = SEQINSPECTOR.out.group_reports   // channel: /path/to/multiqc_report.html
     rundir_report = SEQINSPECTOR.out.rundir_reports // channel: /path/to/multiqc_report.html
 
 }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index b6fd3bc4..f0a269a0 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -4,15 +4,17 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { FASTQC                 } from '../modules/nf-core/fastqc/main'
-include { MULTIQC } from '../modules/nf-core/multiqc/main'
-include { MULTIQC as MULTIQC_PER_LANE } from '../modules/nf-core/multiqc/main'
-include { MULTIQC as MULTIQC_PER_GROUP } from '../modules/nf-core/multiqc/main'
+include { FASTQC                        } from '../modules/nf-core/fastqc/main'
+
+include { MULTIQC                       } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_LANE   } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_GROUP  } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_RUNDIR } from '../modules/nf-core/multiqc/main'
-include { paramsSummaryMap       } from 'plugin/nf-validation'
-include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'
-include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline'
-include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_seqinspector_pipeline'
+
+include { paramsSummaryMap              } from 'plugin/nf-validation'
+include { paramsSummaryMultiqc          } from '../subworkflows/nf-core/utils_nfcore_pipeline'
+include { softwareVersionsToYAML        } from '../subworkflows/nf-core/utils_nfcore_pipeline'
+include { methodsDescriptionText        } from '../subworkflows/local/utils_nfcore_seqinspector_pipeline'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -27,10 +29,10 @@ workflow SEQINSPECTOR {
 
     main:
 
-    ch_versions = Channel.empty()
-    ch_multiqc_files = Channel.empty()
+    ch_versions            = Channel.empty()
+    ch_multiqc_files       = Channel.empty()
     ch_multiqc_extra_files = Channel.empty()
-    ch_multiqc_reports = Channel.empty()
+    ch_multiqc_reports     = Channel.empty()
 
     //
     // MODULE: Run FastQC
@@ -45,23 +47,42 @@ workflow SEQINSPECTOR {
     // Collate and save software versions
     //
     softwareVersionsToYAML(ch_versions)
-        .collectFile(storeDir: "${params.outdir}/pipeline_info", name: 'nf_core_pipeline_software_mqc_versions.yml', sort: true, newLine: true)
-        .set { ch_collated_versions }
+        .collectFile(
+            storeDir: "${params.outdir}/pipeline_info",
+            name: 'nf_core_pipeline_software_mqc_versions.yml',
+            sort: true,
+            newLine: true
+        ).set { ch_collated_versions }
 
     //
     // MODULE: MultiQC
     //
-    ch_multiqc_config              = params.multiqc_config ? 
+    ch_multiqc_config = params.multiqc_config ?
         Channel.fromPath(params.multiqc_config, checkIfExists: true) :
         Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
-    ch_multiqc_logo                       = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty()
-    summary_params                        = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json")
-    ch_workflow_summary                   = Channel.value(paramsSummaryMultiqc(summary_params))
-    ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
-    ch_methods_description                = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description))
-    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_collated_versions)
-    ch_multiqc_extra_files                      = ch_multiqc_extra_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false))
+    ch_multiqc_logo   = params.multiqc_logo ?
+        Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
+        Channel.empty()
+
+    summary_params                        = paramsSummaryMap(
+        workflow, parameters_schema: "nextflow_schema.json")
+    ch_workflow_summary                   = Channel.value(
+        paramsSummaryMultiqc(summary_params))
+    ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
+        file(params.multiqc_methods_description, checkIfExists: true) :
+        file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
+    ch_methods_description                = Channel.value(
+        methodsDescriptionText(ch_multiqc_custom_methods_description))
+
+    ch_multiqc_extra_files = ch_multiqc_extra_files.mix(
+        ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+    ch_multiqc_extra_files = ch_multiqc_extra_files.mix(ch_collated_versions)
+    ch_multiqc_extra_files = ch_multiqc_extra_files.mix(
+        ch_methods_description.collectFile(
+            name: 'methods_description_mqc.yaml',
+            sort: false
+        )
+    )
 
     MULTIQC (
         ch_multiqc_files
@@ -163,10 +184,10 @@ workflow SEQINSPECTOR {
 
     emit:
     global_report = MULTIQC.out.report.toList()             // channel: /path/to/multiqc_report.html
-    lane_reports = MULTIQC_PER_LANE.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
-    group_reports = MULTIQC_PER_GROUP.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
+    lane_reports = MULTIQC_PER_LANE.out.report.toList()     // channel: [ /path/to/multiqc_report.html ]
+    group_reports = MULTIQC_PER_GROUP.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
     rundir_reports = MULTIQC_PER_RUNDIR.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
-    versions       = ch_versions                 // channel: [ path(versions.yml) ]
+    versions       = ch_versions                            // channel: [ path(versions.yml) ]
 }
 
 /*

From d233d8f4052208b4e572ddb1e8d561387df1cce5 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Thu, 28 Mar 2024 16:56:51 +0100
Subject: [PATCH 007/172] Improve output sorting

---
 conf/modules.config | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 8b7a9c69..3b2fc025 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -42,13 +42,25 @@ process {
                             null
                             break
                         case ~/L\d+_multiqc_(report\.html|plots|data)/:
-                            "lanes/L${(filename =~ /L(\d+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            def lane = (filename =~ /L(\d+)_multiqc_(report\.html|plots|data)/)[0][1]
+                            def new_filename = filename.replaceFirst(
+                                "(?<prefix>.*)L${lane}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                '${prefix}${suffix}')
+                            "lanes/L${lane}/${new_filename}"
                             break
                         case ~/G-.+_multiqc_(report\.html|plots|data)/:
-                            "groups/G-${(filename =~ /G-(.+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            def group = (filename =~ /G-(.+)_multiqc_(report\.html|plots|data)/)[0][1]
+                            def new_filename = filename.replaceFirst(
+                                "(?<prefix>.*)G-${group}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                '${prefix}${suffix}')
+                            "groups/${group}/${new_filename}"
                             break
                         case ~/D-.+_multiqc_(report\.html|plots|data)/:
-                            "rundirs/D-${(filename =~ /D-(.+)_multiqc_(report\.html|plots|data)/)[0][1]}/${filename}"
+                            def rundir = (filename =~ /D-(.+)_multiqc_(report\.html|plots|data)/)[0][1]
+                            def new_filename = filename.replaceFirst(
+                                "(?<prefix>.*)D-${rundir}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                '${prefix}${suffix}')
+                            "rundirs/${rundir}/${new_filename}"
                             break
                         default:
                             filename

From 307e43c6a21c77ad30c8f02997c3220568d35fb2 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 8 Apr 2024 14:11:47 +0200
Subject: [PATCH 008/172] Use `group` instead of `project`

---
 assets/schema_input.json                                      | 4 ++--
 subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 9fb321b5..1648944f 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -19,11 +19,11 @@
                 "errorMessage": "Lane ID must be a number",
                 "meta": ["lane"]
             },
-            "project": {
+            "group": {
                 "type": "string",
                 "pattern": "^\\S+$",
                 "errorMessage": "Project ID cannot contain spaces",
-                "meta": ["project"]
+                "meta": ["group"]
             },
             "fastq_1": {
                 "type": "string",
diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index cdbb6400..e1f8e4de 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -84,7 +84,7 @@ workflow PIPELINE_INITIALISATION {
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
-                def id_string = "${meta.sample}_${meta.project ?: "ungrouped"}_${meta.lane}"
+                def id_string = "${meta.sample}_${meta.group ?: "ungrouped"}_${meta.lane}"
                 def updated_meta = meta + [ id: id_string ]
                 if (!fastq_2) {
                     return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]

From 627cf940a2a6b5f7cca7cbb692af1cf74293a289 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 8 Apr 2024 14:21:59 +0200
Subject: [PATCH 009/172] Fix output channel

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 1ee043e9..9de4f94e 100644
--- a/main.nf
+++ b/main.nf
@@ -104,7 +104,7 @@ workflow {
         params.outdir,
         params.monochrome_logs,
         params.hook_url,
-        NFCORE_SEQINSPECTOR.out.multiqc_report
+        NFCORE_SEQINSPECTOR.out.global_report,
     )
 }
 

From c9ba02866dc35a1b345476645ece7f9a6e48cc8b Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 8 Apr 2024 14:22:17 +0200
Subject: [PATCH 010/172] Fix linting

---
 conf/modules.config                                         | 2 +-
 .../local/utils_nfcore_seqinspector_pipeline/main.nf        | 1 -
 workflows/seqinspector.nf                                   | 6 +++---
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 3b2fc025..44a35137 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -36,7 +36,7 @@ process {
             path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,
             saveAs: {
-                filename -> 
+                filename ->
                     switch (filename) {
                         case 'versions.yml':
                             null
diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index e1f8e4de..9001400e 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -101,7 +101,6 @@ workflow PIPELINE_INITIALISATION {
         //     meta, fastqs ->
         //         return [ meta, fastqs.flatten() ]
         // }
-        .view()
         .set { ch_samplesheet }
 
     emit:
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index f0a269a0..815bc40f 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -108,7 +108,7 @@ workflow SEQINSPECTOR {
             ]
         }
         .map { file -> def fileparts = file.name.split("_")
-             [ fileparts[0], file ] 
+            [ fileparts[0], file ]
         }
         .join(mqc_by_lane)
         .multiMap { lane, config, meta , samples_per_lane ->
@@ -137,7 +137,7 @@ workflow SEQINSPECTOR {
             ]
         }
         .map { file -> def fileparts = file.name.split("_")
-             [ fileparts[0], file ] 
+            [ fileparts[0], file ]
         }
         .join(mqc_by_group)
         .multiMap { group, config, meta , samples_per_group ->
@@ -166,7 +166,7 @@ workflow SEQINSPECTOR {
             ]
         }
         .map { file -> def fileparts = file.name.split("_")
-             [ fileparts[0], file ] 
+            [ fileparts[0], file ]
         }
         .join(mqc_by_rundir)
         .multiMap { rundir, config, meta , samples_per_rundir ->

From 2cfc91d449bac7c1a6d22d125fd57e3d8592a51b Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 8 Apr 2024 15:48:41 +0200
Subject: [PATCH 011/172] Give credits back to NGI

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 5e2bc4ca..abe0d4ef 100644
--- a/README.md
+++ b/README.md
@@ -80,11 +80,11 @@ For more details about the output files and reports, please refer to the
 
 ## Credits
 
-nf-core/seqinspector was originally written by Adrien Coulier.
+nf-core/seqinspector was originally written by the Swedish [@NationalGenomicsInfrastructure](https://github.com/NationalGenomicsInfrastructure/).
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+- [@mahesh-panchal](https://github.com/mahesh-panchal)
 
 ## Contributions and Support
 

From fbfb02dbba5945fcfcf8d431cccd7a230eea5ff5 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 9 Apr 2024 09:26:32 +0200
Subject: [PATCH 012/172] Fix file names

---
 conf/modules.config       | 18 +++++++++---------
 workflows/seqinspector.nf | 24 ++++++++++++++++++------
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 44a35137..b2e48f3d 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -41,24 +41,24 @@ process {
                         case 'versions.yml':
                             null
                             break
-                        case ~/L\d+_multiqc_(report\.html|plots|data)/:
-                            def lane = (filename =~ /L(\d+)_multiqc_(report\.html|plots|data)/)[0][1]
+                        case ~/\[LANE:\d+\]_multiqc_(report\.html|plots|data)/:
+                            def lane = (filename =~ /\[LANE:(\d+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)L${lane}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                "(?<prefix>.*)\\[LANE:${lane}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
                             "lanes/L${lane}/${new_filename}"
                             break
-                        case ~/G-.+_multiqc_(report\.html|plots|data)/:
-                            def group = (filename =~ /G-(.+)_multiqc_(report\.html|plots|data)/)[0][1]
+                        case ~/\[GROUP:.+\]_multiqc_(report\.html|plots|data)/:
+                            def group = (filename =~ /\[GROUP:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)G-${group}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                "(?<prefix>.*)\\[GROUP:${group}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
                             "groups/${group}/${new_filename}"
                             break
-                        case ~/D-.+_multiqc_(report\.html|plots|data)/:
-                            def rundir = (filename =~ /D-(.+)_multiqc_(report\.html|plots|data)/)[0][1]
+                        case ~/\[RUNDIR:.+\]_multiqc_(report\.html|plots|data)/:
+                            def rundir = (filename =~ /\[RUNDIR:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)D-${rundir}_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                "(?<prefix>.*)\\[RUNDIR:${rundir}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
                             "rundirs/${rundir}/${new_filename}"
                             break
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 815bc40f..2acafc3f 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -98,13 +98,17 @@ workflow SEQINSPECTOR {
 
     // Generate reports by lane
     lane_mqc_files = ch_multiqc_files
-        .map { meta, sample -> [ "L${meta.lane}", meta, sample ] }
+        .map { meta, sample -> [ "[LANE:${meta.lane}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_lane }
         .collectFile{
             lane, meta, samples -> [
                 "${lane}_multiqc_extra_config.yml",
-                "output_fn_name: \"${lane}_multiqc_report.html\"\ndata_dir_name: \"${lane}_multiqc_data\"\nplots_dir_name: \"${lane}_multiqc_plots\""
+                """
+                    |output_fn_name: \"${lane}_multiqc_report.html\"
+                    |data_dir_name:  \"${lane}_multiqc_data\"
+                    |plots_dir_name: \"${lane}_multiqc_plots\"
+                """.stripMargin()
             ]
         }
         .map { file -> def fileparts = file.name.split("_")
@@ -127,13 +131,17 @@ workflow SEQINSPECTOR {
     // Generate reports by group
     group_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.group }
-        .map { meta, sample -> [ "G-${meta.group}", meta, sample ] }
+        .map { meta, sample -> [ "[GROUP:${meta.group}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_group }
         .collectFile{
             group, meta, samples -> [
                 "${group}_multiqc_extra_config.yml",
-                "output_fn_name: \"${group}_multiqc_report.html\"\ndata_dir_name: \"${group}_multiqc_data\"\nplots_dir_name: \"${group}_multiqc_plots\""
+                """
+                    |output_fn_name: \"${group}_multiqc_report.html\"
+                    |data_dir_name:  \"${group}_multiqc_data\"
+                    |plots_dir_name: \"${group}_multiqc_plots\"
+                """.stripMargin()
             ]
         }
         .map { file -> def fileparts = file.name.split("_")
@@ -156,13 +164,17 @@ workflow SEQINSPECTOR {
     // Generate reports by rundir
     rundir_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.rundir }
-        .map { meta, sample -> [ "D-${meta.rundir.name}", meta, sample ] }
+        .map { meta, sample -> [ "[RUNDIR:${meta.rundir.name}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_rundir }
         .collectFile{
             rundir, meta, samples -> [
                 "${rundir}_multiqc_extra_config.yml",
-                "output_fn_name: \"${rundir}_multiqc_report.html\"\ndata_dir_name: \"${rundir}_multiqc_data\"\nplots_dir_name: \"${rundir}_multiqc_plots\""
+                """
+                    |output_fn_name: \"${rundir}_multiqc_report.html\"
+                    |data_dir_name:  \"${rundir}_multiqc_data\"
+                    |plots_dir_name: \"${rundir}_multiqc_plots\"
+                """.stripMargin()
             ]
         }
         .map { file -> def fileparts = file.name.split("_")

From 8a19929d03832ecaf95a50962898882de04e6884 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 3 May 2024 09:50:42 +0200
Subject: [PATCH 013/172] Set up tests

---
 .gitignore                           |  1 +
 nf-test.config                       |  8 ++++++++
 tests/main.nf.test                   | 20 +++++++++++++++++++
 tests/nextflow.config                |  5 +++++
 tests/workflows/seqinspector.nf.test | 30 ++++++++++++++++++++++++++++
 5 files changed, 64 insertions(+)
 create mode 100644 nf-test.config
 create mode 100644 tests/main.nf.test
 create mode 100644 tests/nextflow.config
 create mode 100644 tests/workflows/seqinspector.nf.test

diff --git a/.gitignore b/.gitignore
index 5124c9ac..089a4079 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,3 +6,4 @@ results/
 testing/
 testing*
 *.pyc
+.nf-test
diff --git a/nf-test.config b/nf-test.config
new file mode 100644
index 00000000..6969c085
--- /dev/null
+++ b/nf-test.config
@@ -0,0 +1,8 @@
+config {
+
+    testsDir "tests"
+    workDir ".nf-test"
+    configFile "tests/nextflow.config"
+    profile "test,docker"
+
+}
diff --git a/tests/main.nf.test b/tests/main.nf.test
new file mode 100644
index 00000000..72498b5b
--- /dev/null
+++ b/tests/main.nf.test
@@ -0,0 +1,20 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf"
+    script "main.nf"
+
+    test("Should run without failures") {
+
+        when {
+            params {
+                outdir = "tests/results"
+            }
+        }
+
+        then {
+            assert workflow.success
+        }
+
+    }
+
+}
diff --git a/tests/nextflow.config b/tests/nextflow.config
new file mode 100644
index 00000000..c19b1ad0
--- /dev/null
+++ b/tests/nextflow.config
@@ -0,0 +1,5 @@
+/*
+========================================================================================
+    Nextflow config file for running tests
+========================================================================================
+*/
diff --git a/tests/workflows/seqinspector.nf.test b/tests/workflows/seqinspector.nf.test
new file mode 100644
index 00000000..bbb529dd
--- /dev/null
+++ b/tests/workflows/seqinspector.nf.test
@@ -0,0 +1,30 @@
+nextflow_workflow {
+
+    name "Test Workflow SEQINSPECTOR"
+    script "workflows/seqinspector.nf"
+    workflow "SEQINSPECTOR"
+
+    test("Should run without failures pipeline") {
+
+        when {
+            params {
+                // define parameters here. Example:
+                // outdir = "tests/results"
+            }
+            workflow {
+                """
+                // define inputs of the workflow here. Example:
+                // input[0] = file("https://raw.githubusercontent.com/nf-core/test-datasets/e47966b63444ec0fcdef23bfc410eeca22535ac7/testdata/MiSeq/samplesheet.csv")
+                input[0] = file("assets/samplesheet.csv")
+                """
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert snapshot(workflow.out).match()
+        }
+
+    }
+
+}

From eba628ef9389a13214e6c9663965d6ea56d7e994 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 12:18:42 +0200
Subject: [PATCH 014/172] point test conf upstream

---
 conf/test.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/conf/test.config b/conf/test.config
index 38e9ee32..2c26a9c1 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -22,7 +22,7 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/KarNair/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv'
+    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

From 23f69d1302457fc32295c3c77bd41d443bb96d9e Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 13:05:47 +0200
Subject: [PATCH 015/172] project -> group

---
 assets/samplesheet.csv | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index fbe5de2d..fef3b4e6 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,3 +1,3 @@
-sample,lane,project,fastq_1,fastq_2,rundir
+sample,lane,group,fastq_1,fastq_2,rundir
 SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
 SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir

From 1ebf3f1adc86f3c50020a56f95430b06f3a5000a Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 13:06:48 +0200
Subject: [PATCH 016/172] project -> group

---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 1648944f..7115bfab 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -22,7 +22,7 @@
             "group": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Project ID cannot contain spaces",
+                "errorMessage": "Group ID cannot contain spaces",
                 "meta": ["group"]
             },
             "fastq_1": {

From b0bf471667c0547654afd14d668e8f70aab55185 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 13:53:31 +0200
Subject: [PATCH 017/172] make lane non-compulsory

---
 assets/schema_input.json  | 2 +-
 workflows/seqinspector.nf | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 7115bfab..c9800d5d 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -47,7 +47,7 @@
                 "meta": ["rundir"]
             }
         },
-        "required": ["sample", "lane", "fastq_1"],
+        "required": ["sample", "fastq_1"],
         "dependentRequired": {
             "fastq_2": ["fastq_1"]
         }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 2acafc3f..018e079d 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -98,6 +98,7 @@ workflow SEQINSPECTOR {
 
     // Generate reports by lane
     lane_mqc_files = ch_multiqc_files
+        .filter { meta, sample -> meta.lane }
         .map { meta, sample -> [ "[LANE:${meta.lane}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_lane }

From 9e0eca39baf5b58760ec4117b4faefde4a512f09 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 15:59:10 +0200
Subject: [PATCH 018/172] remove unused file

---
 assets/samplesheet.csv | 3 ---
 1 file changed, 3 deletions(-)
 delete mode 100644 assets/samplesheet.csv

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
deleted file mode 100644
index fef3b4e6..00000000
--- a/assets/samplesheet.csv
+++ /dev/null
@@ -1,3 +0,0 @@
-sample,lane,group,fastq_1,fastq_2,rundir
-SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
-SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir

From 98e60bf160cb6a4476d55b38a44095e67f79eeea Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 3 May 2024 16:38:52 +0200
Subject: [PATCH 019/172] revamp nf-test, run once for each sequencing platform

---
 tests/MiSeq.main.nf.test             | 23 +++++++++++++++++++++
 tests/NovaSeq6000.main.nf.test       | 23 +++++++++++++++++++++
 tests/PromethION.main.nf.test        | 23 +++++++++++++++++++++
 tests/main.nf.test                   | 20 -------------------
 tests/nextflow.config                | 11 ++++++++++
 tests/workflows/seqinspector.nf.test | 30 ----------------------------
 6 files changed, 80 insertions(+), 50 deletions(-)
 create mode 100644 tests/MiSeq.main.nf.test
 create mode 100644 tests/NovaSeq6000.main.nf.test
 create mode 100644 tests/PromethION.main.nf.test
 delete mode 100644 tests/main.nf.test
 delete mode 100644 tests/workflows/seqinspector.nf.test

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
new file mode 100644
index 00000000..0246a75b
--- /dev/null
+++ b/tests/MiSeq.main.nf.test
@@ -0,0 +1,23 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on MiSeq data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("MiSeq data test") {
+
+        when {
+            params {
+                outdir = "tests/results/MiSeq"
+                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv"
+            }
+        }
+
+        then {
+            assert workflow.success
+        }
+
+    }
+
+}
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
new file mode 100644
index 00000000..7c410e57
--- /dev/null
+++ b/tests/NovaSeq6000.main.nf.test
@@ -0,0 +1,23 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on NovaSeq6000 data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("NovaSeq6000 data test") {
+
+        when {
+            params {
+                outdir = "tests/results/NovaSeq6000"
+                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/NovaSeq6000/samplesheet.csv"
+            }
+        }
+
+        then {
+            assert workflow.success
+        }
+
+    }
+
+}
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
new file mode 100644
index 00000000..9987c953
--- /dev/null
+++ b/tests/PromethION.main.nf.test
@@ -0,0 +1,23 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on PromethION data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("PromethION data test") {
+
+        when {
+            params {
+                outdir = "tests/results/PromethION"
+                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/PromethION/samplesheet.csv"
+            }
+        }
+
+        then {
+            assert workflow.success
+        }
+
+    }
+
+}
diff --git a/tests/main.nf.test b/tests/main.nf.test
deleted file mode 100644
index 72498b5b..00000000
--- a/tests/main.nf.test
+++ /dev/null
@@ -1,20 +0,0 @@
-nextflow_pipeline {
-
-    name "Test Workflow main.nf"
-    script "main.nf"
-
-    test("Should run without failures") {
-
-        when {
-            params {
-                outdir = "tests/results"
-            }
-        }
-
-        then {
-            assert workflow.success
-        }
-
-    }
-
-}
diff --git a/tests/nextflow.config b/tests/nextflow.config
index c19b1ad0..422545be 100644
--- a/tests/nextflow.config
+++ b/tests/nextflow.config
@@ -3,3 +3,14 @@
     Nextflow config file for running tests
 ========================================================================================
 */
+
+params {
+    config_profile_name        = 'nf-test profile'
+    config_profile_description = 'Configuration profile to use for nf-test.'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '3.GB'
+    max_time   = '2.h'
+
+}
diff --git a/tests/workflows/seqinspector.nf.test b/tests/workflows/seqinspector.nf.test
deleted file mode 100644
index bbb529dd..00000000
--- a/tests/workflows/seqinspector.nf.test
+++ /dev/null
@@ -1,30 +0,0 @@
-nextflow_workflow {
-
-    name "Test Workflow SEQINSPECTOR"
-    script "workflows/seqinspector.nf"
-    workflow "SEQINSPECTOR"
-
-    test("Should run without failures pipeline") {
-
-        when {
-            params {
-                // define parameters here. Example:
-                // outdir = "tests/results"
-            }
-            workflow {
-                """
-                // define inputs of the workflow here. Example:
-                // input[0] = file("https://raw.githubusercontent.com/nf-core/test-datasets/e47966b63444ec0fcdef23bfc410eeca22535ac7/testdata/MiSeq/samplesheet.csv")
-                input[0] = file("assets/samplesheet.csv")
-                """
-            }
-        }
-
-        then {
-            assert workflow.success
-            assert snapshot(workflow.out).match()
-        }
-
-    }
-
-}

From d95c660d8fbdba413920d45a7f7025e9261989c0 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Mon, 6 May 2024 15:54:05 +0200
Subject: [PATCH 020/172] Update modules and subworkflows

---
 modules.json                                       | 4 ++--
 modules/nf-core/fastqc/main.nf                     | 6 ++++++
 subworkflows/nf-core/utils_nfcore_pipeline/main.nf | 8 +++++++-
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/modules.json b/modules.json
index ebbc5dc2..87fe816c 100644
--- a/modules.json
+++ b/modules.json
@@ -7,7 +7,7 @@
                 "nf-core": {
                     "fastqc": {
                         "branch": "master",
-                        "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c",
+                        "git_sha": "285a50500f9e02578d90b3ce6382ea3c30216acd",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
@@ -26,7 +26,7 @@
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
-                        "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",
+                        "git_sha": "92de218a329bfc9a9033116eb5f65fd270e72ba3",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nfvalidation_plugin": {
diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf
index 9e19a74c..d79f1c86 100644
--- a/modules/nf-core/fastqc/main.nf
+++ b/modules/nf-core/fastqc/main.nf
@@ -25,6 +25,11 @@ process FASTQC {
     def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${prefix}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}.${entry.extension}" ] }
     def rename_to = old_new_pairs*.join(' ').join(' ')
     def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ')
+
+    def memory_in_mb = MemoryUnit.of("${task.memory}").toUnit('MB')
+    // FastQC memory value allowed range (100 - 10000)
+    def fastqc_memory = memory_in_mb > 10000 ? 10000 : (memory_in_mb < 100 ? 100 : memory_in_mb)
+
     """
     printf "%s %s\\n" $rename_to | while read old_name new_name; do
         [ -f "\${new_name}" ] || ln -s \$old_name \$new_name
@@ -33,6 +38,7 @@ process FASTQC {
     fastqc \\
         $args \\
         --threads $task.cpus \\
+        --memory $fastqc_memory \\
         $renamed_files
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
index a8b55d6f..14558c39 100644
--- a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
+++ b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf
@@ -65,9 +65,15 @@ def checkProfileProvided(nextflow_cli_args) {
 // Citation string for pipeline
 //
 def workflowCitation() {
+    def temp_doi_ref = ""
+    String[] manifest_doi = workflow.manifest.doi.tokenize(",")
+    // Using a loop to handle multiple DOIs
+    // Removing `https://doi.org/` to handle pipelines using DOIs vs DOI resolvers
+    // Removing ` ` since the manifest.doi is a string and not a proper list
+    for (String doi_ref: manifest_doi) temp_doi_ref += "  https://doi.org/${doi_ref.replace('https://doi.org/', '').replace(' ', '')}\n"
     return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" +
         "* The pipeline\n" +
-        "  ${workflow.manifest.doi}\n\n" +
+        temp_doi_ref + "\n" +
         "* The nf-core framework\n" +
         "  https://doi.org/10.1038/s41587-020-0439-x\n\n" +
         "* Software dependencies\n" +

From e0527ccb6c235fcb01f5fa26e1b192e705b3f873 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 7 May 2024 16:45:09 +0200
Subject: [PATCH 021/172] Fix multiqc extra files

Issue with the previous implementation was that sometimes
MULTIQC_PER_LANE would execute before the extra files were collected
into `ch_multiqc_extra_files`, causing `null` to be added to the list of
files passed to multiqc.
---
 workflows/seqinspector.nf | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 018e079d..65343a8b 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -94,11 +94,17 @@ workflow SEQINSPECTOR {
         ch_multiqc_logo.toList()
     )
 
-    multiqc_extra_files = ch_multiqc_extra_files.toList()
-
     // Generate reports by lane
+    multiqc_extra_files_per_lane = ch_multiqc_files
+        .filter { meta, sample -> meta.lane }
+        .map { meta, sample -> meta.lane }
+        .unique()
+        .map { lane -> [lane:lane] }
+        .cross(ch_multiqc_extra_files)
+
     lane_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.lane }
+        .mix(multiqc_extra_files_per_lane)
         .map { meta, sample -> [ "[LANE:${meta.lane}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_lane }
@@ -122,16 +128,23 @@ workflow SEQINSPECTOR {
         }
 
     MULTIQC_PER_LANE(
-        lane_mqc_files.samples_per_lane
-            .map { samples -> samples + multiqc_extra_files.value },
+        lane_mqc_files.samples_per_lane,
         ch_multiqc_config.toList(),
         lane_mqc_files.config,
         ch_multiqc_logo.toList()
     )
 
     // Generate reports by group
+    multiqc_extra_files_per_group = ch_multiqc_files
+        .filter { meta, sample -> meta.group }
+        .map { meta, sample -> meta.group }
+        .unique()
+        .map { group -> [group:group] }
+        .cross(ch_multiqc_extra_files)
+
     group_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.group }
+        .mix(multiqc_extra_files_per_group)
         .map { meta, sample -> [ "[GROUP:${meta.group}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_group }
@@ -155,16 +168,23 @@ workflow SEQINSPECTOR {
         }
 
     MULTIQC_PER_GROUP(
-        group_mqc_files.samples_per_group
-            .map { samples -> samples + multiqc_extra_files.value },
+        group_mqc_files.samples_per_group,
         ch_multiqc_config.toList(),
         group_mqc_files.config,
         ch_multiqc_logo.toList()
     )
 
     // Generate reports by rundir
+    multiqc_extra_files_per_rundir = ch_multiqc_files
+        .filter { meta, sample -> meta.rundir }
+        .map { meta, sample -> meta.rundir }
+        .unique()
+        .map { rundir -> [rundir:rundir] }
+        .cross(ch_multiqc_extra_files)
+
     rundir_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.rundir }
+        .mix(multiqc_extra_files_per_rundir)
         .map { meta, sample -> [ "[RUNDIR:${meta.rundir.name}]", meta, sample ] }
         .groupTuple()
         .tap { mqc_by_rundir }
@@ -188,8 +208,7 @@ workflow SEQINSPECTOR {
         }
 
     MULTIQC_PER_RUNDIR(
-        rundir_mqc_files.samples_per_rundir
-            .map { samples -> samples + multiqc_extra_files.value },
+        rundir_mqc_files.samples_per_rundir,
         ch_multiqc_config.toList(),
         rundir_mqc_files.config,
         ch_multiqc_logo.toList()

From 42159a132e7f73f2594fcb0e66ca26702311cefb Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 10:29:17 +0200
Subject: [PATCH 022/172] Add test snapshots

---
 tests/MiSeq.main.nf.test            | 25 +++++++++++++++---
 tests/MiSeq.main.nf.test.snap       | 19 ++++++++++++++
 tests/NovaSeq6000.main.nf.test      | 40 ++++++++++++++++++++++++++---
 tests/NovaSeq6000.main.nf.test.snap | 31 ++++++++++++++++++++++
 tests/PromethION.main.nf.test       | 20 ++++++++++++---
 tests/PromethION.main.nf.test.snap  | 15 +++++++++++
 workflows/seqinspector.nf           | 18 +++++--------
 7 files changed, 144 insertions(+), 24 deletions(-)
 create mode 100644 tests/MiSeq.main.nf.test.snap
 create mode 100644 tests/NovaSeq6000.main.nf.test.snap
 create mode 100644 tests/PromethION.main.nf.test.snap

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index 0246a75b..1e72de95 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -9,15 +9,32 @@ nextflow_pipeline {
 
         when {
             params {
-                outdir = "tests/results/MiSeq"
+                outdir = "$outputDir"
                 input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv"
             }
         }
 
         then {
-            assert workflow.success
-        }
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_software_versions.txt"),
 
-    }
+                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_software_versions.txt"),
 
+                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    ).match()
+                }
+            )
+        }
+    }
 }
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
new file mode 100644
index 00000000..e222b515
--- /dev/null
+++ b/tests/MiSeq.main.nf.test.snap
@@ -0,0 +1,19 @@
+{
+    "MiSeq data test": {
+        "content": [
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
+            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
+            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
+            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+        ],
+        "timestamp": "2024-05-08T16:29:33.284003"
+    }
+}
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index 7c410e57..f5de9aa3 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -9,15 +9,47 @@ nextflow_pipeline {
 
         when {
             params {
-                outdir = "tests/results/NovaSeq6000"
+                outdir = "$outputDir"
                 input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/NovaSeq6000/samplesheet.csv"
             }
         }
 
         then {
-            assert workflow.success
-        }
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_software_versions.txt"),
 
-    }
+                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_software_versions.txt"),
 
+                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    ).match()
+                },
+            )
+        }
+    }
 }
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
new file mode 100644
index 00000000..a406b891
--- /dev/null
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -0,0 +1,31 @@
+{
+    "NovaSeq6000 data test": {
+        "content": [
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
+            "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,9b4fd8a6d6e8a9acabecd592f633472e",
+            "multiqc_general_stats.txt:md5,8237b88ceb018d3cb1edcea62d10f4a2",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,9246a5b6b7b0410c79049fc3dbd08e92",
+            "multiqc_general_stats.txt:md5,44328403f423c6f5ac9ee0a8a01e6725",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,84820276fae52d4d492831280ae6207c",
+            "multiqc_general_stats.txt:md5,dd07799e5e4b9d389f9de49a852c3363",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,59ae05d89453da6f57010ffb6466f902",
+            "multiqc_general_stats.txt:md5,e4629691992bfe639c01a84b90563334",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
+            "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+        ],
+        "timestamp": "2024-05-14T10:17:35.440827"
+    }
+}
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index 9987c953..de2beb35 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -9,15 +9,27 @@ nextflow_pipeline {
 
         when {
             params {
-                outdir = "tests/results/PromethION"
+                outdir = "$outputDir"
                 input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/PromethION/samplesheet.csv"
             }
         }
 
         then {
-            assert workflow.success
-        }
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_software_versions.txt"),
 
+                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    ).match()
+                },
+            )
+        }
     }
-
 }
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
new file mode 100644
index 00000000..24e52bd1
--- /dev/null
+++ b/tests/PromethION.main.nf.test.snap
@@ -0,0 +1,15 @@
+{
+    "PromethION data test": {
+        "content": [
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
+            "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
+            "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+        ],
+        "timestamp": "2024-05-08T17:17:23.151259"
+    }
+}
\ No newline at end of file
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 65343a8b..3e2a08dc 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -100,7 +100,7 @@ workflow SEQINSPECTOR {
         .map { meta, sample -> meta.lane }
         .unique()
         .map { lane -> [lane:lane] }
-        .cross(ch_multiqc_extra_files)
+        .combine(ch_multiqc_extra_files)
 
     lane_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.lane }
@@ -118,9 +118,7 @@ workflow SEQINSPECTOR {
                 """.stripMargin()
             ]
         }
-        .map { file -> def fileparts = file.name.split("_")
-            [ fileparts[0], file ]
-        }
+        .map { file -> [ (file =~ /(\[LANE:.+\])/)[0][1], file ] }
         .join(mqc_by_lane)
         .multiMap { lane, config, meta , samples_per_lane ->
             samples_per_lane: samples_per_lane
@@ -140,7 +138,7 @@ workflow SEQINSPECTOR {
         .map { meta, sample -> meta.group }
         .unique()
         .map { group -> [group:group] }
-        .cross(ch_multiqc_extra_files)
+        .combine(ch_multiqc_extra_files)
 
     group_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.group }
@@ -158,9 +156,7 @@ workflow SEQINSPECTOR {
                 """.stripMargin()
             ]
         }
-        .map { file -> def fileparts = file.name.split("_")
-            [ fileparts[0], file ]
-        }
+        .map { file -> [ (file =~ /(\[GROUP:.+\])/)[0][1], file ] }
         .join(mqc_by_group)
         .multiMap { group, config, meta , samples_per_group ->
             samples_per_group: samples_per_group
@@ -180,7 +176,7 @@ workflow SEQINSPECTOR {
         .map { meta, sample -> meta.rundir }
         .unique()
         .map { rundir -> [rundir:rundir] }
-        .cross(ch_multiqc_extra_files)
+        .combine(ch_multiqc_extra_files)
 
     rundir_mqc_files = ch_multiqc_files
         .filter { meta, sample -> meta.rundir }
@@ -198,9 +194,7 @@ workflow SEQINSPECTOR {
                 """.stripMargin()
             ]
         }
-        .map { file -> def fileparts = file.name.split("_")
-            [ fileparts[0], file ]
-        }
+        .map { file -> [ (file =~ /(\[RUNDIR:.+\])/)[0][1], file ] }
         .join(mqc_by_rundir)
         .multiMap { rundir, config, meta , samples_per_rundir ->
             samples_per_rundir: samples_per_rundir

From ef61f9f7e32f63235f0bf574a2fd89c1c119ffcf Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 11:08:13 +0200
Subject: [PATCH 023/172] Remove unused module configuration

---
 conf/base.config    | 3 ---
 conf/modules.config | 8 --------
 2 files changed, 11 deletions(-)

diff --git a/conf/base.config b/conf/base.config
index 8d7dffc6..aab50f93 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -59,7 +59,4 @@ process {
         errorStrategy = 'retry'
         maxRetries    = 2
     }
-    withName:CUSTOM_DUMPSOFTWAREVERSIONS {
-        cache = false
-    }
 }
diff --git a/conf/modules.config b/conf/modules.config
index b2e48f3d..da3d2ca2 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -22,14 +22,6 @@ process {
         ext.args = '--quiet'
     }
 
-    withName: CUSTOM_DUMPSOFTWAREVERSIONS {
-        publishDir = [
-            path: { "${params.outdir}/pipeline_info" },
-            mode: params.publish_dir_mode,
-            pattern: '*_versions.yml'
-        ]
-    }
-
     withName: 'MULTIQC' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

From 51b01e98ca9560154634b08d541475abeffbc35c Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 11:16:41 +0200
Subject: [PATCH 024/172] Update usage docs and restore example samplesheet

---
 assets/samplesheet.csv |  3 +++
 docs/usage.md          | 36 ++++++++++++------------------------
 2 files changed, 15 insertions(+), 24 deletions(-)
 create mode 100644 assets/samplesheet.csv

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
new file mode 100644
index 00000000..fef3b4e6
--- /dev/null
+++ b/assets/samplesheet.csv
@@ -0,0 +1,3 @@
+sample,lane,group,fastq_1,fastq_2,rundir
+SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
+SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir
diff --git a/docs/usage.md b/docs/usage.md
index f926de73..df2be203 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -16,39 +16,27 @@ You will need to create a samplesheet with information about the samples you wou
 --input '[path to samplesheet file]'
 ```
 
-### Multiple runs of the same sample
-
-The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes:
-
-```csv title="samplesheet.csv"
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
-CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz
-CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz
-```
-
 ### Full samplesheet
 
-The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below.
-
-A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice.
-
 ```csv title="samplesheet.csv"
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
-CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz
-CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz
-TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz,
-TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz,
-TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz,
-TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz,
+sample,lane,group,fastq_1,fastq_2,rundir
+CONTROL_REP1,1,,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
+CONTROL_REP2,1,,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
+CONTROL_REP3,1,,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
+TREATMENT_REP1,2,GROUP1,AEG588A4_S4_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
+TREATMENT_REP2,2,GROUP1,AEG588A5_S5_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
+TREATMENT_REP3,2,GROUP2,AEG588A6_S6_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
+TREATMENT_REP3,2,GROUP2,AEG588A6_S6_L004_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
 ```
 
 | Column    | Description                                                                                                                                                                            |
 | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
+| `lane`    | Lane where the sample was processed on an Illumina instrument (optional).                                                                                                              |
+| `group`   | Group the sample belongs too, useful when several groups are pooled together (optional).                                                                                               |
+| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
-| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 

From 7c7f31f715a40c1f5b061099c9cd945214875ab0 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 12:09:51 +0200
Subject: [PATCH 025/172] Update output docs

---
 docs/output.md | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/docs/output.md b/docs/output.md
index 77e4cc1c..f83e1fa0 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -6,8 +6,6 @@ This document describes the output produced by the pipeline. Most of the plots a
 
 The directories listed below will be created in the results directory after the pipeline has finished. All paths are relative to the top-level results directory.
 
-<!-- TODO nf-core: Write this documentation describing your workflow's output -->
-
 ## Pipeline overview
 
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
@@ -48,6 +46,31 @@ The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They m
   - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
   - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
   - `multiqc_plots/`: directory containing static images from the report in various formats.
+  - `lanes/` [1]
+    - `L1/`
+      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+      - `multiqc_plots/`: directory containing static images from the report in various formats.
+    - `L2/`
+      - ...
+  - `groups/` [1]
+    - `GROUPNAME1/`
+      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+      - `multiqc_plots/`: directory containing static images from the report in various formats.
+    - `GROUPNAME2/`
+      - ...
+  - `rundir/` [1]
+    - `RUNDIR1/`
+      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+      - `multiqc_plots/`: directory containing static images from the report in various formats.
+    - `RUNDIR2/`
+      - ...
+
+
+[1] These files will only be generated if `lane`, `group` or `rundir` were specified for some samples.
+
 
 </details>
 

From 1c4f6e07019fad57bce6d5d3473155b2f3b364b3 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 12:16:38 +0200
Subject: [PATCH 026/172] Update changelog

---
 CHANGELOG.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 58a53ef4..6430addb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
+
 ### `Fixed`
 
 ### `Dependencies`

From 211bfafb21f6f8c6b208d33875ddc9e45552973a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 12:20:34 +0200
Subject: [PATCH 027/172] Update samplesheet in readme file

---
 README.md | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index abe0d4ef..edc54ae5 100644
--- a/README.md
+++ b/README.md
@@ -39,26 +39,19 @@
 > [!NOTE]
 > If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
-<!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
-     Explain what rows and columns represent. For instance (please edit as appropriate):
-
 First, prepare a samplesheet with your input data that looks as follows:
 
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample,lane,group,fastq_1,fastq_2,rundir
+CONTROL_REP1,1,GROUP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
 
--->
-
 Now, you can run the pipeline using:
 
-<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
-
 ```bash
 nextflow run nf-core/seqinspector \
    -profile <docker/singularity/.../institute> \

From df4e9cbcbd1f62990f44dd90d9eb0a2990d0c657 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 14 May 2024 12:43:27 +0200
Subject: [PATCH 028/172] Run prettier

---
 docs/output.md | 2 --
 1 file changed, 2 deletions(-)

diff --git a/docs/output.md b/docs/output.md
index f83e1fa0..7af7806c 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -68,10 +68,8 @@ The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They m
     - `RUNDIR2/`
       - ...
 
-
 [1] These files will only be generated if `lane`, `group` or `rundir` were specified for some samples.
 
-
 </details>
 
 [MultiQC](http://multiqc.info) is a visualization tool that generates a single HTML report summarising all samples in your project. Most of the pipeline QC results are visualised in the report and further statistics are available in the report data directory.

From 2303db9a4c28fe0b5a907ab73bc3946f3e3daa3e Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Thu, 16 May 2024 16:00:32 +0200
Subject: [PATCH 029/172] Use testdata base path param in
 tests/MiSeq.main.nf.test

Co-authored-by: Matthias Zepper <6963520+MatthiasZepper@users.noreply.github.com>
---
 tests/MiSeq.main.nf.test | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index 1e72de95..a3dc0a5a 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -10,7 +10,7 @@ nextflow_pipeline {
         when {
             params {
                 outdir = "$outputDir"
-                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv"
+                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/MiSeq/samplesheet.csv"
             }
         }
 

From 1ea8ac0dac6c0cb11e098beb3c516ba0bb6cdc49 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Thu, 16 May 2024 16:01:00 +0200
Subject: [PATCH 030/172] Use testdata base path param in
 tests/NovaSeq6000.main.nf.test

Co-authored-by: Matthias Zepper <6963520+MatthiasZepper@users.noreply.github.com>
---
 tests/NovaSeq6000.main.nf.test | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index f5de9aa3..bc687abe 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -10,7 +10,7 @@ nextflow_pipeline {
         when {
             params {
                 outdir = "$outputDir"
-                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/NovaSeq6000/samplesheet.csv"
+                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/NovaSeq6000/samplesheet.csv"
             }
         }
 

From 048765fd18409769442915dcd403da682dfd852f Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Thu, 16 May 2024 16:01:20 +0200
Subject: [PATCH 031/172] Use testdata base path param in
 tests/PromethION.main.nf.test

Co-authored-by: Matthias Zepper <6963520+MatthiasZepper@users.noreply.github.com>
---
 tests/PromethION.main.nf.test | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index de2beb35..d1969f3e 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -10,7 +10,7 @@ nextflow_pipeline {
         when {
             params {
                 outdir = "$outputDir"
-                input  = "https://raw.githubusercontent.com/nf-core/test-datasets/seqinspector/testdata/PromethION/samplesheet.csv"
+                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/PromethION/samplesheet.csv"
             }
         }
 

From 4329bb97c229bcb4d869e3c2d88af08cab730b37 Mon Sep 17 00:00:00 2001
From: Matthias Zepper <MatthiasZepper@users.noreply.github.com>
Date: Fri, 17 May 2024 11:38:29 +0200
Subject: [PATCH 032/172] Make the tests work with
 'pipelines_testdata_base_path' parameter.

---
 tests/MiSeq.main.nf.test              | 2 +-
 tests/MiSeq.main.nf.test.config       | 7 +++++++
 tests/NovaSeq6000.main.nf.test        | 2 +-
 tests/NovaSeq6000.main.nf.test.config | 7 +++++++
 tests/PromethION.main.nf.test         | 2 +-
 tests/PromethION.main.nf.test.config  | 7 +++++++
 tests/nextflow.config                 | 5 +++++
 7 files changed, 29 insertions(+), 3 deletions(-)
 create mode 100644 tests/MiSeq.main.nf.test.config
 create mode 100644 tests/NovaSeq6000.main.nf.test.config
 create mode 100644 tests/PromethION.main.nf.test.config

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index a3dc0a5a..bfabd954 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -8,9 +8,9 @@ nextflow_pipeline {
     test("MiSeq data test") {
 
         when {
+            config "./MiSeq.main.nf.test.config"
             params {
                 outdir = "$outputDir"
-                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/MiSeq/samplesheet.csv"
             }
         }
 
diff --git a/tests/MiSeq.main.nf.test.config b/tests/MiSeq.main.nf.test.config
new file mode 100644
index 00000000..073a9774
--- /dev/null
+++ b/tests/MiSeq.main.nf.test.config
@@ -0,0 +1,7 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/MiSeq/samplesheet.csv'
+}
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index bc687abe..174e215d 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -8,9 +8,9 @@ nextflow_pipeline {
     test("NovaSeq6000 data test") {
 
         when {
+            config "./NovaSeq6000.main.nf.test.config"
             params {
                 outdir = "$outputDir"
-                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/NovaSeq6000/samplesheet.csv"
             }
         }
 
diff --git a/tests/NovaSeq6000.main.nf.test.config b/tests/NovaSeq6000.main.nf.test.config
new file mode 100644
index 00000000..cad5edd9
--- /dev/null
+++ b/tests/NovaSeq6000.main.nf.test.config
@@ -0,0 +1,7 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
+}
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index d1969f3e..39284786 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -8,9 +8,9 @@ nextflow_pipeline {
     test("PromethION data test") {
 
         when {
+            config "./PromethION.main.nf.test.config"
             params {
                 outdir = "$outputDir"
-                input  = params.pipelines_testdata_base_path + "seqinspector/testdata/PromethION/samplesheet.csv"
             }
         }
 
diff --git a/tests/PromethION.main.nf.test.config b/tests/PromethION.main.nf.test.config
new file mode 100644
index 00000000..e1498a49
--- /dev/null
+++ b/tests/PromethION.main.nf.test.config
@@ -0,0 +1,7 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/PromethION/samplesheet.csv'
+}
diff --git a/tests/nextflow.config b/tests/nextflow.config
index 422545be..8d9ef461 100644
--- a/tests/nextflow.config
+++ b/tests/nextflow.config
@@ -13,4 +13,9 @@ params {
     max_memory = '3.GB'
     max_time   = '2.h'
 
+    pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
+
+    validationSchemaIgnoreParams = 'genomes,igenomes_base,pipelines_testdata_base_path'
+
+
 }

From 3ff850395b52b9ee509901f203c301fd40aa9844 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 17 May 2024 13:28:56 +0200
Subject: [PATCH 033/172] update snapshots, add nf-test.log to gitignore

---
 .gitignore                          |  1 +
 tests/MiSeq.main.nf.test.snap       | 12 ++++++++----
 tests/NovaSeq6000.main.nf.test.snap | 18 +++++++++++-------
 tests/PromethION.main.nf.test.snap  | 10 +++++++---
 4 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/.gitignore b/.gitignore
index 089a4079..72277655 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,3 +7,4 @@ testing/
 testing*
 *.pyc
 .nf-test
+.nf-test.log
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index e222b515..96896382 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -4,16 +4,20 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
         ],
-        "timestamp": "2024-05-08T16:29:33.284003"
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-17T12:59:21.531493"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index a406b891..cbb75383 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,28 +4,32 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
             "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,9b4fd8a6d6e8a9acabecd592f633472e",
             "multiqc_general_stats.txt:md5,8237b88ceb018d3cb1edcea62d10f4a2",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,9246a5b6b7b0410c79049fc3dbd08e92",
             "multiqc_general_stats.txt:md5,44328403f423c6f5ac9ee0a8a01e6725",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,84820276fae52d4d492831280ae6207c",
             "multiqc_general_stats.txt:md5,dd07799e5e4b9d389f9de49a852c3363",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,59ae05d89453da6f57010ffb6466f902",
             "multiqc_general_stats.txt:md5,e4629691992bfe639c01a84b90563334",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
             "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
         ],
-        "timestamp": "2024-05-14T10:17:35.440827"
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-17T13:02:20.874181"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 24e52bd1..951c5550 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -4,12 +4,16 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
             "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
             "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
         ],
-        "timestamp": "2024-05-08T17:17:23.151259"
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-17T12:58:02.572837"
     }
 }
\ No newline at end of file

From 8ac4d76770515159a23f746d4d3fa8c4d3e06ce1 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Fri, 17 May 2024 15:49:01 +0200
Subject: [PATCH 034/172] visualize example run dir corresponsing to
 samplesheet

---
 docs/usage.md | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/docs/usage.md b/docs/usage.md
index 57314973..7a4ec735 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -10,7 +10,7 @@
 
 ## Samplesheet input
 
-You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below.
+You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location.
 
 ```bash
 --input '[path to samplesheet file]'
@@ -18,15 +18,25 @@ You will need to create a samplesheet with information about the samples you wou
 
 ### Full samplesheet
 
+The following simple run dir structure...
+
+```
+run_dir
+├── sample1_lane1_group1_r1.fq.gz
+├── sample2_lane1_group1_r1.fq.gz
+├── sample3_lane2_group2_r1.fq.gz
+└── sample4_lane2_group3_r1.fq.gz
+```
+
+...would be represented in the following samplesheet (shown as .tsv for readability)
+
 ```csv title="samplesheet.csv"
-sample,lane,group,fastq_1,fastq_2,rundir
-CONTROL_REP1,1,,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
-CONTROL_REP2,1,,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
-CONTROL_REP3,1,,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
-TREATMENT_REP1,2,GROUP1,AEG588A4_S4_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
-TREATMENT_REP2,2,GROUP1,AEG588A5_S5_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
-TREATMENT_REP3,2,GROUP2,AEG588A6_S6_L003_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
-TREATMENT_REP3,2,GROUP2,AEG588A6_S6_L004_R1_001.fastq.gz,,200624_A00834_0183_BHMTFYDRXX
+sample  lane  group   fastq_1                                       fastq_2 rundir
+sample1 1     group1  path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir
+sample2 1     group1  path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir
+sample3 2     group2  path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir
+sample4 2     group3  path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir
+
 ```
 
 | Column    | Description                                                                                                                                                                            |
@@ -34,11 +44,11 @@ TREATMENT_REP3,2,GROUP2,AEG588A6_S6_L004_R1_001.fastq.gz,,200624_A00834_0183_BHM
 | `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
 | `lane`    | Lane where the sample was processed on an Illumina instrument (optional).                                                                                                              |
 | `group`   | Group the sample belongs too, useful when several groups are pooled together (optional).                                                                                               |
-| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
+| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
 
-An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
+Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
 ## Running the pipeline
 

From 84c9b3d95c693b722a3e61752ba498b05fc08e57 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 20 May 2024 12:41:50 +0200
Subject: [PATCH 035/172] naming fixes

---
 main.nf                   | 4 ++--
 workflows/seqinspector.nf | 9 ++++-----
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/main.nf b/main.nf
index 9de4f94e..fb00bd5d 100644
--- a/main.nf
+++ b/main.nf
@@ -59,8 +59,8 @@ workflow NFCORE_SEQINSPECTOR {
 
     emit:
     global_report = SEQINSPECTOR.out.global_report  // channel: /path/to/multiqc_report.html
-    lane_reports = SEQINSPECTOR.out.lane_reports    // channel: /path/to/multiqc_report.html
-    group_report = SEQINSPECTOR.out.group_reports   // channel: /path/to/multiqc_report.html
+    lane_reports  = SEQINSPECTOR.out.lane_reports   // channel: /path/to/multiqc_report.html
+    group_reports = SEQINSPECTOR.out.group_reports  // channel: /path/to/multiqc_report.html
     rundir_report = SEQINSPECTOR.out.rundir_reports // channel: /path/to/multiqc_report.html
 
 }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 0eb375dd..50fa481f 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -6,7 +6,7 @@
 
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 
-include { MULTIQC                       } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_LANE   } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_GROUP  } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_RUNDIR } from '../modules/nf-core/multiqc/main'
@@ -84,7 +84,7 @@ workflow SEQINSPECTOR {
         )
     )
 
-    MULTIQC (
+    MULTIQC_GLOBAL (
         ch_multiqc_files
             .map { meta, file -> file }
             .mix(ch_multiqc_extra_files)
@@ -97,9 +97,8 @@ workflow SEQINSPECTOR {
     // Generate reports by lane
     multiqc_extra_files_per_lane = ch_multiqc_files
         .filter { meta, sample -> meta.lane }
-        .map { meta, sample -> meta.lane }
+        .map { meta, sample -> [lane: meta.lane] }
         .unique()
-        .map { lane -> [lane:lane] }
         .combine(ch_multiqc_extra_files)
 
     lane_mqc_files = ch_multiqc_files
@@ -209,7 +208,7 @@ workflow SEQINSPECTOR {
     )
 
     emit:
-    global_report = MULTIQC.out.report.toList()             // channel: /path/to/multiqc_report.html
+    global_report = MULTIQC_GLOBAL.out.report.toList()      // channel: /path/to/multiqc_report.html
     lane_reports = MULTIQC_PER_LANE.out.report.toList()     // channel: [ /path/to/multiqc_report.html ]
     group_reports = MULTIQC_PER_GROUP.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
     rundir_reports = MULTIQC_PER_RUNDIR.out.report.toList() // channel: [ /path/to/multiqc_report.html ]

From aaf17b68f90dcaa123a9bc0c7807c7bba0dc2fbd Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 20 May 2024 12:44:01 +0200
Subject: [PATCH 036/172] nf-core sync

---
 .github/PULL_REQUEST_TEMPLATE.md      |  2 +-
 .github/workflows/linting.yml         | 19 ++++++++++---------
 .github/workflows/linting_comment.yml |  2 +-
 3 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 6de151f7..5d27c53a 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/seqi
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/seqinspector/tree/master/.github/CONTRIBUTING.md)
 - [ ] If necessary, also make a PR on the nf-core/seqinspector _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core lint`).
-- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
+- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`).
 - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.
 - [ ] Output Documentation in `docs/output.md` is updated.
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
index 1fcafe88..073e1876 100644
--- a/.github/workflows/linting.yml
+++ b/.github/workflows/linting.yml
@@ -14,12 +14,13 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
 
-      - name: Set up Python 3.12
-        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
+      - name: Set up Python 3.11
+        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
         with:
-          python-version: "3.12"
+          python-version: 3.11
+          cache: "pip"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -31,14 +32,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
+        uses: nf-core/setup-nextflow@v1
 
-      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
+      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
         with:
-          python-version: "3.12"
+          python-version: "3.11"
           architecture: "x64"
 
       - name: Install dependencies
@@ -59,7 +60,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
+        uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4
         with:
           name: linting-logs
           path: |
diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
index 40acc23f..b706875f 100644
--- a/.github/workflows/linting_comment.yml
+++ b/.github/workflows/linting_comment.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3
+        uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

From e6dfea9ca1fbbb0019e438c6394d62daf1f2cda8 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 20 May 2024 12:44:54 +0200
Subject: [PATCH 037/172] nf-core fixes

---
 .github/PULL_REQUEST_TEMPLATE.md      |  2 +-
 .github/workflows/linting.yml         | 19 +++++++++----------
 .github/workflows/linting_comment.yml |  2 +-
 3 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 5d27c53a..6de151f7 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/seqi
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/seqinspector/tree/master/.github/CONTRIBUTING.md)
 - [ ] If necessary, also make a PR on the nf-core/seqinspector _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core lint`).
-- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`).
+- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.
 - [ ] Output Documentation in `docs/output.md` is updated.
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
index 073e1876..1fcafe88 100644
--- a/.github/workflows/linting.yml
+++ b/.github/workflows/linting.yml
@@ -14,13 +14,12 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
-      - name: Set up Python 3.11
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - name: Set up Python 3.12
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: 3.11
-          cache: "pip"
+          python-version: "3.12"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -32,14 +31,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
           architecture: "x64"
 
       - name: Install dependencies
@@ -60,7 +59,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4
+        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
         with:
           name: linting-logs
           path: |
diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
index b706875f..40acc23f 100644
--- a/.github/workflows/linting_comment.yml
+++ b/.github/workflows/linting_comment.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
+        uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

From 02affeb602655023888b330b0402bcbe2a0e613a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Thu, 30 May 2024 13:18:36 +0200
Subject: [PATCH 038/172] Improve publishDir logic

---
 conf/modules.config                 | 56 +++++++++++++++++++++++++----
 tests/MiSeq.main.nf.test.snap       | 12 +++----
 tests/NovaSeq6000.main.nf.test.snap | 18 ++++------
 tests/PromethION.main.nf.test.snap  | 10 ++----
 4 files changed, 64 insertions(+), 32 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index da3d2ca2..f7e78457 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -22,11 +22,20 @@ process {
         ext.args = '--quiet'
     }
 
-    withName: 'MULTIQC' {
+    withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
             path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'MULTIQC_PER_LANE' {
+        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
+        publishDir = [
+            path: { "${params.outdir}/multiqc/lanes" },
+            mode: params.publish_dir_mode,
             saveAs: {
                 filename ->
                     switch (filename) {
@@ -38,27 +47,62 @@ process {
                             def new_filename = filename.replaceFirst(
                                 "(?<prefix>.*)\\[LANE:${lane}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
-                            "lanes/L${lane}/${new_filename}"
+                            "L${lane}/${new_filename}"
+                            break
+                        default:
+                            filename
+                    }
+            }
+        ]
+    }
+
+    withName: 'MULTIQC_PER_GROUP' {
+        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
+        publishDir = [
+            path: { "${params.outdir}/multiqc/groups" },
+            mode: params.publish_dir_mode,
+            saveAs: {
+                filename ->
+                    switch (filename) {
+                        case 'versions.yml':
+                            null
                             break
                         case ~/\[GROUP:.+\]_multiqc_(report\.html|plots|data)/:
                             def group = (filename =~ /\[GROUP:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
                                 "(?<prefix>.*)\\[GROUP:${group}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
-                            "groups/${group}/${new_filename}"
+                            "${group}/${new_filename}"
+                            break
+                        default:
+                            filename
+                    }
+            }
+        ]
+    }
+
+    withName: 'MULTIQC_PER_RUNDIR' {
+        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
+        publishDir = [
+            path: { "${params.outdir}/multiqc/rundirss" },
+            mode: params.publish_dir_mode,
+            saveAs: {
+                filename ->
+                    switch (filename) {
+                        case 'versions.yml':
+                            null
                             break
                         case ~/\[RUNDIR:.+\]_multiqc_(report\.html|plots|data)/:
                             def rundir = (filename =~ /\[RUNDIR:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
                                 "(?<prefix>.*)\\[RUNDIR:${rundir}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
-                            "rundirs/${rundir}/${new_filename}"
+                            "${rundir}/${new_filename}"
                             break
                         default:
                             filename
-                }
+                    }
             }
         ]
     }
-
 }
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 96896382..87c1a561 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -4,20 +4,16 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
             "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-05-17T12:59:21.531493"
+        "timestamp": "2024-05-30T13:14:20.263485"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index cbb75383..22600251 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,32 +4,28 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
             "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,9b4fd8a6d6e8a9acabecd592f633472e",
             "multiqc_general_stats.txt:md5,8237b88ceb018d3cb1edcea62d10f4a2",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,9246a5b6b7b0410c79049fc3dbd08e92",
             "multiqc_general_stats.txt:md5,44328403f423c6f5ac9ee0a8a01e6725",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,84820276fae52d4d492831280ae6207c",
             "multiqc_general_stats.txt:md5,dd07799e5e4b9d389f9de49a852c3363",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,59ae05d89453da6f57010ffb6466f902",
             "multiqc_general_stats.txt:md5,e4629691992bfe639c01a84b90563334",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
             "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-05-17T13:02:20.874181"
+        "timestamp": "2024-05-30T13:13:49.062282"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 951c5550..0ac213c1 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -4,16 +4,12 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
             "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921",
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
             "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
-            "multiqc_software_versions.txt:md5,b1e01403f9bdaa81ebabd388d5f9a921"
+            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-05-17T12:58:02.572837"
+        "timestamp": "2024-05-30T13:14:40.99246"
     }
 }
\ No newline at end of file

From 8b83f13f95c26d7f336d53fc4f9571c14ab3b247 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 27 Aug 2024 13:17:02 +0200
Subject: [PATCH 039/172] Implement tagging system

---
 README.md                                     |   4 +-
 assets/samplesheet.csv                        |  10 +-
 assets/schema_input.json                      |  16 +--
 conf/modules.config                           |  64 +--------
 docs/output.md                                |  45 +++---
 docs/usage.md                                 |  13 +-
 main.nf                                       |   6 +-
 .../main.nf                                   |   4 +-
 tests/MiSeq.main.nf.test                      |  18 +--
 tests/MiSeq.main.nf.test.snap                 |  14 +-
 tests/NovaSeq6000.main.nf.test                |  53 ++++---
 tests/NovaSeq6000.main.nf.test.snap           |  26 ++--
 tests/PromethION.main.nf.test                 |  13 +-
 tests/PromethION.main.nf.test.snap            |  10 +-
 workflows/seqinspector.nf                     | 131 ++++--------------
 15 files changed, 126 insertions(+), 301 deletions(-)

diff --git a/README.md b/README.md
index 7efdd3e9..31018e7b 100644
--- a/README.md
+++ b/README.md
@@ -44,8 +44,8 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,lane,group,fastq_1,fastq_2,rundir
-CONTROL_REP1,1,GROUP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
+sample,fastq_1,fastq_2,rundir,tags
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,"patient1"
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index fef3b4e6..00019e58 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,3 +1,7 @@
-sample,lane,group,fastq_1,fastq_2,rundir
-SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
-SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir
+sample,fastq_1,fastq_2,rundir,tags
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort2"
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient1"
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient2"
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient3"
diff --git a/assets/schema_input.json b/assets/schema_input.json
index c9800d5d..62922b79 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -13,18 +13,6 @@
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["sample"]
             },
-            "lane": {
-                "type": "integer",
-                "pattern": "^\\d+$",
-                "errorMessage": "Lane ID must be a number",
-                "meta": ["lane"]
-            },
-            "group": {
-                "type": "string",
-                "pattern": "^\\S+$",
-                "errorMessage": "Group ID cannot contain spaces",
-                "meta": ["group"]
-            },
             "fastq_1": {
                 "type": "string",
                 "format": "file-path",
@@ -45,6 +33,10 @@
                 "exists": true,
                 "errorMessage": "Run directory must be a path",
                 "meta": ["rundir"]
+            },
+            "tags": {
+                "type": "string",
+                "meta": ["tags"]
             }
         },
         "required": ["sample", "fastq_1"],
diff --git a/conf/modules.config b/conf/modules.config
index f7e78457..c8838224 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -25,16 +25,16 @@ process {
     withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
-            path: { "${params.outdir}/multiqc" },
+            path: { "${params.outdir}/multiqc/global_report" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
-    withName: 'MULTIQC_PER_LANE' {
+    withName: 'MULTIQC_PER_TAG' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
-            path: { "${params.outdir}/multiqc/lanes" },
+            path: { "${params.outdir}/multiqc/group_reports" },
             mode: params.publish_dir_mode,
             saveAs: {
                 filename ->
@@ -42,62 +42,12 @@ process {
                         case 'versions.yml':
                             null
                             break
-                        case ~/\[LANE:\d+\]_multiqc_(report\.html|plots|data)/:
-                            def lane = (filename =~ /\[LANE:(\d+)\]_multiqc_(report\.html|plots|data)/)[0][1]
+                        case ~/\[TAG:.+\]_multiqc_(report\.html|plots|data)/:
+                            def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[LANE:${lane}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                "(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
-                            "L${lane}/${new_filename}"
-                            break
-                        default:
-                            filename
-                    }
-            }
-        ]
-    }
-
-    withName: 'MULTIQC_PER_GROUP' {
-        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
-        publishDir = [
-            path: { "${params.outdir}/multiqc/groups" },
-            mode: params.publish_dir_mode,
-            saveAs: {
-                filename ->
-                    switch (filename) {
-                        case 'versions.yml':
-                            null
-                            break
-                        case ~/\[GROUP:.+\]_multiqc_(report\.html|plots|data)/:
-                            def group = (filename =~ /\[GROUP:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
-                            def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[GROUP:${group}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
-                                '${prefix}${suffix}')
-                            "${group}/${new_filename}"
-                            break
-                        default:
-                            filename
-                    }
-            }
-        ]
-    }
-
-    withName: 'MULTIQC_PER_RUNDIR' {
-        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
-        publishDir = [
-            path: { "${params.outdir}/multiqc/rundirss" },
-            mode: params.publish_dir_mode,
-            saveAs: {
-                filename ->
-                    switch (filename) {
-                        case 'versions.yml':
-                            null
-                            break
-                        case ~/\[RUNDIR:.+\]_multiqc_(report\.html|plots|data)/:
-                            def rundir = (filename =~ /\[RUNDIR:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
-                            def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[RUNDIR:${rundir}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
-                                '${prefix}${suffix}')
-                            "${rundir}/${new_filename}"
+                            "${tag}/${new_filename}"
                             break
                         default:
                             filename
diff --git a/docs/output.md b/docs/output.md
index 7af7806c..15c29ce2 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -39,36 +39,29 @@ The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They m
 
 ### MultiQC
 
+nf-core/seqinspector will generate the following MultiQC reports:
+
+- one global reports including all the samples listed in the samplesheet
+- one group report per unique tag. These reports compile samples that share the same tag.
+
 <details markdown="1">
 <summary>Output files</summary>
 
 - `multiqc/`
-  - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-  - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-  - `multiqc_plots/`: directory containing static images from the report in various formats.
-  - `lanes/` [1]
-    - `L1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `L2/`
-      - ...
-  - `groups/` [1]
-    - `GROUPNAME1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `GROUPNAME2/`
-      - ...
-  - `rundir/` [1]
-    - `RUNDIR1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `RUNDIR2/`
-      - ...
-
-[1] These files will only be generated if `lane`, `group` or `rundir` were specified for some samples.
+  - `global_report`
+    - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+    - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+    - `multiqc_plots/`: directory containing static images from the report in various formats.
+  - `group_reports`
+    - `tag1/`
+      - `multiqc_report.html`
+      - `multiqc_data/`
+      - `multiqc_plots/`
+    - `tag2/`
+      - `multiqc_report.html`
+      - `multiqc_data/`
+      - `multiqc_plots/`
+    - ...
 
 </details>
 
diff --git a/docs/usage.md b/docs/usage.md
index 7a4ec735..42d596bb 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -31,22 +31,21 @@ run_dir
 ...would be represented in the following samplesheet (shown as .tsv for readability)
 
 ```csv title="samplesheet.csv"
-sample  lane  group   fastq_1                                       fastq_2 rundir
-sample1 1     group1  path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir
-sample2 1     group1  path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir
-sample3 2     group2  path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir
-sample4 2     group3  path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir
+sample  fastq_1                                       fastq_2 rundir          tags
+sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient1"
+sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient2"
+sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir "cohort1,patient3"
+sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "control"
 
 ```
 
 | Column    | Description                                                                                                                                                                            |
 | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
-| `lane`    | Lane where the sample was processed on an Illumina instrument (optional).                                                                                                              |
-| `group`   | Group the sample belongs too, useful when several groups are pooled together (optional).                                                                                               |
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
 | `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
+| `tags`    | Comma-separated list of tags to group samples in special reports.                                                                                                                      |
 
 Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
diff --git a/main.nf b/main.nf
index fb00bd5d..a55408ef 100644
--- a/main.nf
+++ b/main.nf
@@ -58,10 +58,8 @@ workflow NFCORE_SEQINSPECTOR {
     )
 
     emit:
-    global_report = SEQINSPECTOR.out.global_report  // channel: /path/to/multiqc_report.html
-    lane_reports  = SEQINSPECTOR.out.lane_reports   // channel: /path/to/multiqc_report.html
-    group_reports = SEQINSPECTOR.out.group_reports  // channel: /path/to/multiqc_report.html
-    rundir_report = SEQINSPECTOR.out.rundir_reports // channel: /path/to/multiqc_report.html
+    global_report   = SEQINSPECTOR.out.global_report    // channel: /path/to/multiqc_report.html
+    grouped_reports = SEQINSPECTOR.out.grouped_reports  // channel: /path/to/multiqc_report.html
 
 }
 /*
diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index ea9c9b8a..afcfc68b 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -84,8 +84,8 @@ workflow PIPELINE_INITIALISATION {
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
-                def id_string = "${meta.sample}_${meta.group ?: "ungrouped"}_${meta.lane}"
-                def updated_meta = meta + [ id: id_string ]
+                def tags = meta.tags ? meta.tags.tokenize(",") : []
+                def updated_meta = meta + [ id:meta.sample, tags:tags ]
                 if (!fastq_2) {
                     return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]
                 } else {
diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index bfabd954..8fbff4a3 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -18,20 +18,10 @@ nextflow_pipeline {
             assertAll(
                 { assert workflow.success },
                 { assert snapshot(
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/P001/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 }
             )
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 87c1a561..26f0c2a8 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -2,18 +2,10 @@
     "MiSeq data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
-            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
-            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,692b8aed0614ed1655f2c1cbea1ba312",
-            "multiqc_general_stats.txt:md5,630167d67d3f92408cd1a04422c7196f",
+            "multiqc_fastqc.txt:md5,e46e7baa8f57d4cf54d973925b5eadf9",
+            "multiqc_general_stats.txt:md5,a5e626a2e1a3c986092e4f89091cc41c",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "timestamp": "2024-05-30T13:14:20.263485"
+        "timestamp": "2024-08-26T17:55:16.152573"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index 174e215d..f93891bf 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -18,35 +18,30 @@ nextflow_pipeline {
             assertAll(
                 { assert workflow.success },
                 { assert snapshot(
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/lanes/L1/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/S1/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/S2/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/S3/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/S4/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 },
             )
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 22600251..f5c4776b 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -2,30 +2,26 @@
     "NovaSeq6000 data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
-            "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
+            "multiqc_fastqc.txt:md5,e8ed6dca928396b8873d24e60ea1a133",
+            "multiqc_general_stats.txt:md5,fd9d46c5b441908cd07e5373d116db17",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,9b4fd8a6d6e8a9acabecd592f633472e",
-            "multiqc_general_stats.txt:md5,8237b88ceb018d3cb1edcea62d10f4a2",
+            "multiqc_fastqc.txt:md5,ff9b31c6024f11a8135456e7ea01fc8f",
+            "multiqc_general_stats.txt:md5,f36bd6e27e92c25be076efea411d3a8e",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,9246a5b6b7b0410c79049fc3dbd08e92",
-            "multiqc_general_stats.txt:md5,44328403f423c6f5ac9ee0a8a01e6725",
+            "multiqc_fastqc.txt:md5,62d51280dcd7634f6bed95ffe0d8dab8",
+            "multiqc_general_stats.txt:md5,2012002b6a057be981a97fcc96142a6c",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,84820276fae52d4d492831280ae6207c",
-            "multiqc_general_stats.txt:md5,dd07799e5e4b9d389f9de49a852c3363",
+            "multiqc_fastqc.txt:md5,63749e803a2d5fc7ecc7cd93fa68df1f",
+            "multiqc_general_stats.txt:md5,656931993032400dea3d441b8b61b4d2",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,59ae05d89453da6f57010ffb6466f902",
-            "multiqc_general_stats.txt:md5,e4629691992bfe639c01a84b90563334",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,5ba3f4f4ec6026a5f5d55418384dcd3e",
-            "multiqc_general_stats.txt:md5,123cd6b64c9c15607405bcdd45a843d4",
+            "multiqc_fastqc.txt:md5,91cc62e1b4059bdbe4b88affa43378af",
+            "multiqc_general_stats.txt:md5,6e500f82550e00b07c3e7aa1d46ab9e9",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "timestamp": "2024-05-30T13:13:49.062282"
+        "timestamp": "2024-08-26T18:03:33.089142"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index 39284786..8fec8b33 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -18,15 +18,10 @@ nextflow_pipeline {
             assertAll(
                 { assert workflow.success },
                 { assert snapshot(
-                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/groups/r10p41_e8p2_human_runs_jkw/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/multiqc_data/multiqc_software_versions.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 },
             )
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 0ac213c1..e3b34f23 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -2,14 +2,10 @@
     "PromethION data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
-            "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,333360ff12007d64f2bf7673b0658bed",
-            "multiqc_general_stats.txt:md5,b1999255f9a502618d59be2f2e93bad2",
+            "multiqc_fastqc.txt:md5,cecee3cb343c75c80180d3169c6f3ea1",
+            "multiqc_general_stats.txt:md5,e63c25089c4fc10618414ba2254d18c7",
             "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
         ],
-        "timestamp": "2024-05-30T13:14:40.99246"
+        "timestamp": "2024-08-26T17:55:38.755385"
     }
 }
\ No newline at end of file
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 50fa481f..e37df509 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -7,9 +7,7 @@
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
-include { MULTIQC as MULTIQC_PER_LANE   } from '../modules/nf-core/multiqc/main'
-include { MULTIQC as MULTIQC_PER_GROUP  } from '../modules/nf-core/multiqc/main'
-include { MULTIQC as MULTIQC_PER_RUNDIR } from '../modules/nf-core/multiqc/main'
+include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
 
 include { paramsSummaryMap              } from 'plugin/nf-validation'
 include { paramsSummaryMultiqc          } from '../subworkflows/nf-core/utils_nfcore_pipeline'
@@ -94,124 +92,51 @@ workflow SEQINSPECTOR {
         ch_multiqc_logo.toList()
     )
 
-    // Generate reports by lane
-    multiqc_extra_files_per_lane = ch_multiqc_files
-        .filter { meta, sample -> meta.lane }
-        .map { meta, sample -> [lane: meta.lane] }
+    ch_tags = ch_multiqc_files
+        .map { meta, sample -> meta.tags }
+        .flatten()
         .unique()
-        .combine(ch_multiqc_extra_files)
 
-    lane_mqc_files = ch_multiqc_files
-        .filter { meta, sample -> meta.lane }
-        .mix(multiqc_extra_files_per_lane)
-        .map { meta, sample -> [ "[LANE:${meta.lane}]", meta, sample ] }
-        .groupTuple()
-        .tap { mqc_by_lane }
-        .collectFile{
-            lane, meta, samples -> [
-                "${lane}_multiqc_extra_config.yml",
-                """
-                    |output_fn_name: \"${lane}_multiqc_report.html\"
-                    |data_dir_name:  \"${lane}_multiqc_data\"
-                    |plots_dir_name: \"${lane}_multiqc_plots\"
-                """.stripMargin()
-            ]
-        }
-        .map { file -> [ (file =~ /(\[LANE:.+\])/)[0][1], file ] }
-        .join(mqc_by_lane)
-        .multiMap { lane, config, meta , samples_per_lane ->
-            samples_per_lane: samples_per_lane
-            config: config
-        }
-
-    MULTIQC_PER_LANE(
-        lane_mqc_files.samples_per_lane,
-        ch_multiqc_config.toList(),
-        lane_mqc_files.config,
-        ch_multiqc_logo.toList()
-    )
-
-    // Generate reports by group
-    multiqc_extra_files_per_group = ch_multiqc_files
-        .filter { meta, sample -> meta.group }
-        .map { meta, sample -> meta.group }
-        .unique()
-        .map { group -> [group:group] }
-        .combine(ch_multiqc_extra_files)
-
-    group_mqc_files = ch_multiqc_files
-        .filter { meta, sample -> meta.group }
-        .mix(multiqc_extra_files_per_group)
-        .map { meta, sample -> [ "[GROUP:${meta.group}]", meta, sample ] }
-        .groupTuple()
-        .tap { mqc_by_group }
-        .collectFile{
-            group, meta, samples -> [
-                "${group}_multiqc_extra_config.yml",
-                """
-                    |output_fn_name: \"${group}_multiqc_report.html\"
-                    |data_dir_name:  \"${group}_multiqc_data\"
-                    |plots_dir_name: \"${group}_multiqc_plots\"
-                """.stripMargin()
-            ]
-        }
-        .map { file -> [ (file =~ /(\[GROUP:.+\])/)[0][1], file ] }
-        .join(mqc_by_group)
-        .multiMap { group, config, meta , samples_per_group ->
-            samples_per_group: samples_per_group
-            config: config
-        }
-
-    MULTIQC_PER_GROUP(
-        group_mqc_files.samples_per_group,
-        ch_multiqc_config.toList(),
-        group_mqc_files.config,
-        ch_multiqc_logo.toList()
-    )
-
-    // Generate reports by rundir
-    multiqc_extra_files_per_rundir = ch_multiqc_files
-        .filter { meta, sample -> meta.rundir }
-        .map { meta, sample -> meta.rundir }
-        .unique()
-        .map { rundir -> [rundir:rundir] }
+    multiqc_extra_files_per_tag = ch_tags
         .combine(ch_multiqc_extra_files)
 
-    rundir_mqc_files = ch_multiqc_files
-        .filter { meta, sample -> meta.rundir }
-        .mix(multiqc_extra_files_per_rundir)
-        .map { meta, sample -> [ "[RUNDIR:${meta.rundir.name}]", meta, sample ] }
+    // Group samples by tag
+    tagged_mqc_files = ch_tags
+        .combine(ch_multiqc_files)
+        .filter { sample_tag, meta, sample -> sample_tag in meta.tags }
+        .map { sample_tag, meta, sample -> [sample_tag, sample] }
+        .mix(multiqc_extra_files_per_tag)
         .groupTuple()
-        .tap { mqc_by_rundir }
-        .collectFile{
-            rundir, meta, samples -> [
-                "${rundir}_multiqc_extra_config.yml",
+        .tap { mqc_by_tag }
+        .collectFile {
+            sample_tag, samples ->
+            def prefix_tag = "[TAG:${sample_tag}]"
+            [
+                "${prefix_tag}_multiqc_extra_config.yml",
                 """
-                    |output_fn_name: \"${rundir}_multiqc_report.html\"
-                    |data_dir_name:  \"${rundir}_multiqc_data\"
-                    |plots_dir_name: \"${rundir}_multiqc_plots\"
+                    |output_fn_name: \"${prefix_tag}_multiqc_report.html\"
+                    |data_dir_name:  \"${prefix_tag}_multiqc_data\"
+                    |plots_dir_name: \"${prefix_tag}_multiqc_plots\"
                 """.stripMargin()
             ]
         }
-        .map { file -> [ (file =~ /(\[RUNDIR:.+\])/)[0][1], file ] }
-        .join(mqc_by_rundir)
-        .multiMap { rundir, config, meta , samples_per_rundir ->
-            samples_per_rundir: samples_per_rundir
+        .map { file -> [ (file =~ /\[TAG:(.+)\]/)[0][1], file ] }
+        .join(mqc_by_tag)
+        .multiMap { sample_tag, config, samples ->
+            samples_per_tag: samples
             config: config
         }
 
-    MULTIQC_PER_RUNDIR(
-        rundir_mqc_files.samples_per_rundir,
+    MULTIQC_PER_TAG(
+        tagged_mqc_files.samples_per_tag,
         ch_multiqc_config.toList(),
-        rundir_mqc_files.config,
+        tagged_mqc_files.config,
         ch_multiqc_logo.toList()
     )
 
     emit:
     global_report = MULTIQC_GLOBAL.out.report.toList()      // channel: /path/to/multiqc_report.html
-    lane_reports = MULTIQC_PER_LANE.out.report.toList()     // channel: [ /path/to/multiqc_report.html ]
-    group_reports = MULTIQC_PER_GROUP.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
-    rundir_reports = MULTIQC_PER_RUNDIR.out.report.toList() // channel: [ /path/to/multiqc_report.html ]
+    grouped_reports = MULTIQC_PER_TAG.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
     versions       = ch_versions                            // channel: [ path(versions.yml) ]
 }
 

From dabccc2e556be1860eb990d1914208a8e6901cef Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 27 Aug 2024 15:08:20 +0200
Subject: [PATCH 040/172] Update changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6430addb..3aa5bacc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 
 ### `Fixed`

From 8bba88869a4f67143639c61c3972599192140db8 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Tue, 27 Aug 2024 15:52:46 +0200
Subject: [PATCH 041/172] Try adding regex assertion and error for samplesheet
 tags

---
 assets/schema_input.json | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 62922b79..bde27fa7 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -36,6 +36,8 @@
             },
             "tags": {
                 "type": "string",
+                "pattern": "^\\\"([A-Za-z0-9_-]+,\\ ?)*([A-Za-z0-9_-]+)\\\"$",
+                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a comma-separated list flanked by a pair of double-quotes, e.g. \"patient_01, lane1, pos-CTRL_2\"."
                 "meta": ["tags"]
             }
         },

From 6987e93e0e10b39917d56600410db8a61a8f6ec9 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Tue, 27 Aug 2024 15:55:26 +0200
Subject: [PATCH 042/172] Add missing comma

---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index bde27fa7..d4a6dc70 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -37,7 +37,7 @@
             "tags": {
                 "type": "string",
                 "pattern": "^\\\"([A-Za-z0-9_-]+,\\ ?)*([A-Za-z0-9_-]+)\\\"$",
-                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a comma-separated list flanked by a pair of double-quotes, e.g. \"patient_01, lane1, pos-CTRL_2\"."
+                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a comma-separated list flanked by a pair of double-quotes, e.g. \"patient_01, lane1, pos-CTRL_2\".",
                 "meta": ["tags"]
             }
         },

From 363e782a7a68d2364fd73176eb50d24b72c1c02a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 3 Sep 2024 10:35:51 +0200
Subject: [PATCH 043/172] Change example tags to more neutral ones

---
 README.md     | 2 +-
 docs/usage.md | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 31018e7b..679b6f1c 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ First, prepare a samplesheet with your input data that looks as follows:
 
 ```csv
 sample,fastq_1,fastq_2,rundir,tags
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,"patient1"
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,"group1"
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
diff --git a/docs/usage.md b/docs/usage.md
index 42d596bb..621c7c0a 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -32,9 +32,9 @@ run_dir
 
 ```csv title="samplesheet.csv"
 sample  fastq_1                                       fastq_2 rundir          tags
-sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient1"
-sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient2"
-sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir "cohort1,patient3"
+sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir "project1,group1"
+sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir "project1,group1"
+sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir "project1,group2"
 sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "control"
 
 ```

From c1a21de429b24fde2f0e5ad8f313f7a7d1b468ba Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 3 Sep 2024 12:36:42 +0200
Subject: [PATCH 044/172] Check for tag collisions

---
 .../utils_nfcore_seqinspector_pipeline/main.nf     | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index afcfc68b..bb875af6 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -103,6 +103,20 @@ workflow PIPELINE_INITIALISATION {
         // }
         .set { ch_samplesheet }
 
+    ch_samplesheet
+        .map {
+            meta, fastqs -> meta.tags
+        }
+        .flatten()
+        .unique()
+        .map { tag_name -> [tag_name.toLowerCase(), tag_name] }
+        .groupTuple()
+        .map {
+            tag_lowercase, tags ->
+                assert tags.size() == 1 :
+                "Tag name collision: " + tags.join(", ")
+        }
+
     emit:
     samplesheet = ch_samplesheet
     versions    = ch_versions

From 8a43efa8ae3f78dd846f440b42934e50bba0ab91 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 3 Sep 2024 12:58:50 +0200
Subject: [PATCH 045/172] Use columns to separate tags

---
 README.md                                     |  2 +-
 assets/samplesheet.csv                        | 12 ++++----
 assets/schema_input.json                      |  4 +--
 docs/usage.md                                 | 10 +++----
 .../main.nf                                   |  2 +-
 tests/NovaSeq6000.main.nf.test                | 28 +++++++++----------
 6 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/README.md b/README.md
index 679b6f1c..d7cd233f 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ First, prepare a samplesheet with your input data that looks as follows:
 
 ```csv
 sample,fastq_1,fastq_2,rundir,tags
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,"group1"
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,group1
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index 00019e58..ba2542dd 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,7 +1,7 @@
 sample,fastq_1,fastq_2,rundir,tags
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort2"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient1"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient2"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient3"
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group1
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group3
diff --git a/assets/schema_input.json b/assets/schema_input.json
index d4a6dc70..3569ae2f 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -36,8 +36,8 @@
             },
             "tags": {
                 "type": "string",
-                "pattern": "^\\\"([A-Za-z0-9_-]+,\\ ?)*([A-Za-z0-9_-]+)\\\"$",
-                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a comma-separated list flanked by a pair of double-quotes, e.g. \"patient_01, lane1, pos-CTRL_2\".",
+                "pattern": "^([A-Za-z0-9_-]+:)*([A-Za-z0-9_-]+)$",
+                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a column-separated list, e.g. group_01:lane1:pos-CTRL_2.",
                 "meta": ["tags"]
             }
         },
diff --git a/docs/usage.md b/docs/usage.md
index 621c7c0a..38a039c4 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -32,10 +32,10 @@ run_dir
 
 ```csv title="samplesheet.csv"
 sample  fastq_1                                       fastq_2 rundir          tags
-sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir "project1,group1"
-sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir "project1,group1"
-sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir "project1,group2"
-sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "control"
+sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir project1:group1
+sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir project1:group1
+sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir project1:group2
+sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir control
 
 ```
 
@@ -45,7 +45,7 @@ sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "c
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
 | `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
-| `tags`    | Comma-separated list of tags to group samples in special reports.                                                                                                                      |
+| `tags`    | Column-separated list of tags to group samples in special reports.                                                                                                                     |
 
 Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index bb875af6..eec4d09c 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -84,7 +84,7 @@ workflow PIPELINE_INITIALISATION {
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
-                def tags = meta.tags ? meta.tags.tokenize(",") : []
+                def tags = meta.tags ? meta.tags.tokenize(":") : []
                 def updated_meta = meta + [ id:meta.sample, tags:tags ]
                 if (!fastq_2) {
                     return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index f93891bf..d050399e 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -23,20 +23,20 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
 
-                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/cohort1/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/patient1/multiqc_data/multiqc_software_versions.txt"),
-
-                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/patient2/multiqc_data/multiqc_software_versions.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),

From 8779909fe25a35950a999847d0b052b1f188de9c Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 3 Sep 2024 13:55:23 +0200
Subject: [PATCH 046/172] switch to colon-separated tags

---
 README.md                                            |  2 +-
 assets/samplesheet.csv                               | 12 ++++++------
 assets/schema_input.json                             |  4 ++--
 docs/usage.md                                        | 12 ++++++------
 .../local/utils_nfcore_seqinspector_pipeline/main.nf |  2 +-
 5 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/README.md b/README.md
index 31018e7b..acba2cec 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ First, prepare a samplesheet with your input data that looks as follows:
 
 ```csv
 sample,fastq_1,fastq_2,rundir,tags
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,"patient1"
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,lane1:project5:group2
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index 00019e58..de5f1a68 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,7 +1,7 @@
 sample,fastq_1,fastq_2,rundir,tags
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort1"
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,"paired_sample,cohort2"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient1"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient2"
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,"patient3"
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:cohort1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:cohort1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:cohort2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,patient1
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,patient2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,patient3
diff --git a/assets/schema_input.json b/assets/schema_input.json
index d4a6dc70..18941557 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -36,8 +36,8 @@
             },
             "tags": {
                 "type": "string",
-                "pattern": "^\\\"([A-Za-z0-9_-]+,\\ ?)*([A-Za-z0-9_-]+)\\\"$",
-                "errorMessage": "Tags must consist of numbers, letters, underscores or dashes and must be provided as a comma-separated list flanked by a pair of double-quotes, e.g. \"patient_01, lane1, pos-CTRL_2\".",
+                "pattern": "^([a-z0-9_-]+:)*([a-z0-9_-]+)$",
+                "errorMessage": "Tags must be separated by colons and only consist of lowercase letters, numbers, underscores and hyphens.",
                 "meta": ["tags"]
             }
         },
diff --git a/docs/usage.md b/docs/usage.md
index 42d596bb..e2da41de 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -32,10 +32,10 @@ run_dir
 
 ```csv title="samplesheet.csv"
 sample  fastq_1                                       fastq_2 rundir          tags
-sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient1"
-sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir "cohort1,patient2"
-sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir "cohort1,patient3"
-sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "control"
+sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir cohort1:patient1
+sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir cohort1:patient2
+sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir cohort1:patient3
+sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir control
 
 ```
 
@@ -44,8 +44,8 @@ sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir "c
 | `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
-| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
-| `tags`    | Comma-separated list of tags to group samples in special reports.                                                                                                                      |
+| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional).                                                                                               |
+| `tags`    | Colon-separated list of tags to group samples in special reports.                                                                                                                      |
 
 Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index afcfc68b..0ebfdd0a 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -84,7 +84,7 @@ workflow PIPELINE_INITIALISATION {
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
-                def tags = meta.tags ? meta.tags.tokenize(",") : []
+                def tags = meta.tags ? meta.tags.tokenize(":") : []
                 def updated_meta = meta + [ id:meta.sample, tags:tags ]
                 if (!fastq_2) {
                     return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]

From f496b85d07540807a452a094fb9cbc52013cc9f1 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 3 Sep 2024 13:55:30 +0200
Subject: [PATCH 047/172] use testdata with tags

---
 conf/test.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/conf/test.config b/conf/test.config
index 658e75f3..c458ad0f 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -22,7 +22,7 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/MiSeq/samplesheet.csv'
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

From 38e39a9828646f984e7902bd119b802e288624c9 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 3 Sep 2024 14:10:16 +0200
Subject: [PATCH 048/172] Make ids unique

---
 .../local/utils_nfcore_seqinspector_pipeline/main.nf | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index eec4d09c..632acb38 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -87,9 +87,17 @@ workflow PIPELINE_INITIALISATION {
                 def tags = meta.tags ? meta.tags.tokenize(":") : []
                 def updated_meta = meta + [ id:meta.sample, tags:tags ]
                 if (!fastq_2) {
-                    return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]
+                    return [
+                        updated_meta.id + fastq_1.toString().replaceAll('/', '_'),
+                        updated_meta + [ single_end:true ],
+                        [ fastq_1 ]
+                    ]
                 } else {
-                    return [ updated_meta.id, updated_meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
+                    return [
+                        updated_meta.id + fastq_1.toString().replaceAll('/', '_') + '_' + fastq_2.toString().replaceAll('/', '_'),
+                        updated_meta + [ single_end:false ],
+                        [ fastq_1, fastq_2 ]
+                    ]
                 }
         }
         .groupTuple()

From c96a41c0c6f5c4d3b7f8ff0d71242fd876b04325 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 3 Sep 2024 12:26:11 +0000
Subject: [PATCH 049/172] bump multiqc to prevent gitpod crashing, populate the
 new process inputs w. empty channels

---
 modules.json                                  |  2 +-
 modules/nf-core/multiqc/environment.yml       |  2 +-
 modules/nf-core/multiqc/main.nf               | 14 ++++++++++---
 modules/nf-core/multiqc/meta.yml              | 13 ++++++++++++
 modules/nf-core/multiqc/tests/main.nf.test    |  8 ++++++++
 .../nf-core/multiqc/tests/main.nf.test.snap   | 20 +++++++++----------
 modules/nf-core/multiqc/tests/nextflow.config |  5 +++++
 workflows/seqinspector.nf                     |  8 ++++++--
 8 files changed, 55 insertions(+), 17 deletions(-)
 create mode 100644 modules/nf-core/multiqc/tests/nextflow.config

diff --git a/modules.json b/modules.json
index 87fe816c..70f3486c 100644
--- a/modules.json
+++ b/modules.json
@@ -12,7 +12,7 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
+                        "git_sha": "19ca321db5d8bd48923262c2eca6422359633491",
                         "installed_by": ["modules"]
                     }
                 }
diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml
index ca39fb67..a31464c9 100644
--- a/modules/nf-core/multiqc/environment.yml
+++ b/modules/nf-core/multiqc/environment.yml
@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::multiqc=1.21
+  - bioconda::multiqc=1.24.1
diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf
index 47ac352f..ceaec139 100644
--- a/modules/nf-core/multiqc/main.nf
+++ b/modules/nf-core/multiqc/main.nf
@@ -3,14 +3,16 @@ process MULTIQC {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/multiqc:1.21--pyhdfd78af_0' :
-        'biocontainers/multiqc:1.21--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/multiqc:1.24.1--pyhdfd78af_0' :
+        'biocontainers/multiqc:1.24.1--pyhdfd78af_0' }"
 
     input:
     path  multiqc_files, stageAs: "?/*"
     path(multiqc_config)
     path(extra_multiqc_config)
     path(multiqc_logo)
+    path(replace_names)
+    path(sample_names)
 
     output:
     path "*multiqc_report.html", emit: report
@@ -23,16 +25,22 @@ process MULTIQC {
 
     script:
     def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ? "--filename ${task.ext.prefix}.html" : ''
     def config = multiqc_config ? "--config $multiqc_config" : ''
     def extra_config = extra_multiqc_config ? "--config $extra_multiqc_config" : ''
-    def logo = multiqc_logo ? /--cl-config 'custom_logo: "${multiqc_logo}"'/ : ''
+    def logo = multiqc_logo ? "--cl-config 'custom_logo: \"${multiqc_logo}\"'" : ''
+    def replace = replace_names ? "--replace-names ${replace_names}" : ''
+    def samples = sample_names ? "--sample-names ${sample_names}" : ''
     """
     multiqc \\
         --force \\
         $args \\
         $config \\
+        $prefix \\
         $extra_config \\
         $logo \\
+        $replace \\
+        $samples \\
         .
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml
index 45a9bc35..382c08cb 100644
--- a/modules/nf-core/multiqc/meta.yml
+++ b/modules/nf-core/multiqc/meta.yml
@@ -29,6 +29,19 @@ input:
       type: file
       description: Optional logo file for MultiQC
       pattern: "*.{png}"
+  - replace_names:
+      type: file
+      description: |
+        Optional two-column sample renaming file. First column a set of
+        patterns, second column a set of corresponding replacements. Passed via
+        MultiQC's `--replace-names` option.
+      pattern: "*.{tsv}"
+  - sample_names:
+      type: file
+      description: |
+        Optional TSV file with headers, passed to the MultiQC --sample_names
+        argument.
+      pattern: "*.{tsv}"
 output:
   - report:
       type: file
diff --git a/modules/nf-core/multiqc/tests/main.nf.test b/modules/nf-core/multiqc/tests/main.nf.test
index f1c4242e..33316a7d 100644
--- a/modules/nf-core/multiqc/tests/main.nf.test
+++ b/modules/nf-core/multiqc/tests/main.nf.test
@@ -8,6 +8,8 @@ nextflow_process {
     tag "modules_nfcore"
     tag "multiqc"
 
+    config "./nextflow.config"
+
     test("sarscov2 single-end [fastqc]") {
 
         when {
@@ -17,6 +19,8 @@ nextflow_process {
                 input[1] = []
                 input[2] = []
                 input[3] = []
+                input[4] = []
+                input[5] = []
                 """
             }
         }
@@ -41,6 +45,8 @@ nextflow_process {
                 input[1] = Channel.of(file("https://github.com/nf-core/tools/raw/dev/nf_core/pipeline-template/assets/multiqc_config.yml", checkIfExists: true))
                 input[2] = []
                 input[3] = []
+                input[4] = []
+                input[5] = []
                 """
             }
         }
@@ -66,6 +72,8 @@ nextflow_process {
                 input[1] = []
                 input[2] = []
                 input[3] = []
+                input[4] = []
+                input[5] = []
                 """
             }
         }
diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap
index bfebd802..83fa080c 100644
--- a/modules/nf-core/multiqc/tests/main.nf.test.snap
+++ b/modules/nf-core/multiqc/tests/main.nf.test.snap
@@ -2,14 +2,14 @@
     "multiqc_versions_single": {
         "content": [
             [
-                "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d"
+                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
             ]
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-02-29T08:48:55.657331"
+        "timestamp": "2024-07-10T12:41:34.562023"
     },
     "multiqc_stub": {
         "content": [
@@ -17,25 +17,25 @@
                 "multiqc_report.html",
                 "multiqc_data",
                 "multiqc_plots",
-                "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d"
+                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
             ]
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-02-29T08:49:49.071937"
+        "timestamp": "2024-07-10T11:27:11.933869532"
     },
     "multiqc_versions_config": {
         "content": [
             [
-                "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d"
+                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
             ]
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-02-29T08:49:25.457567"
+        "timestamp": "2024-07-10T11:26:56.709849369"
     }
-}
\ No newline at end of file
+}
diff --git a/modules/nf-core/multiqc/tests/nextflow.config b/modules/nf-core/multiqc/tests/nextflow.config
new file mode 100644
index 00000000..c537a6a3
--- /dev/null
+++ b/modules/nf-core/multiqc/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: 'MULTIQC' {
+        ext.prefix = null
+    }
+}
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index e37df509..1ba00c62 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -89,7 +89,9 @@ workflow SEQINSPECTOR {
             .collect(),
         ch_multiqc_config.toList(),
         Channel.empty().toList(),
-        ch_multiqc_logo.toList()
+        ch_multiqc_logo.toList(),
+        Channel.empty().toList(),
+        Channel.empty().toList()
     )
 
     ch_tags = ch_multiqc_files
@@ -131,7 +133,9 @@ workflow SEQINSPECTOR {
         tagged_mqc_files.samples_per_tag,
         ch_multiqc_config.toList(),
         tagged_mqc_files.config,
-        ch_multiqc_logo.toList()
+        ch_multiqc_logo.toList(),
+        Channel.empty().toList(),
+        Channel.empty().toList()
     )
 
     emit:

From 2e269ecc236a66866f8413a1129656ed9c1d816f Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 3 Sep 2024 16:36:59 +0200
Subject: [PATCH 050/172] Allow for uppercase letters

---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 18941557..f2440839 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -36,7 +36,7 @@
             },
             "tags": {
                 "type": "string",
-                "pattern": "^([a-z0-9_-]+:)*([a-z0-9_-]+)$",
+                "pattern": "^([A-Za-z0-9_-]+:)*([A-Za-z0-9_-]+)$",
                 "errorMessage": "Tags must be separated by colons and only consist of lowercase letters, numbers, underscores and hyphens.",
                 "meta": ["tags"]
             }

From c97a597e8165081565d5acb1afdfd61e83f6309c Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 10 Sep 2024 08:54:03 +0200
Subject: [PATCH 051/172] Use samplesheet row in id

Co-authored-by: Matthias Zepper <MatthiasZepper@users.noreply.github.com>
---
 .../local/utils_nfcore_seqinspector_pipeline/main.nf   | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index 632acb38..3c63037b 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -82,19 +82,21 @@ workflow PIPELINE_INITIALISATION {
     //
     Channel
         .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
+        .toList()
+        .flatMap { it.withIndex().collect {  entry, idx -> entry + "${idx+1}" } }
         .map {
-            meta, fastq_1, fastq_2 ->
+            meta, fastq_1, fastq_2, idx ->
                 def tags = meta.tags ? meta.tags.tokenize(":") : []
-                def updated_meta = meta + [ id:meta.sample, tags:tags ]
+                def updated_meta = meta + [ id:"${meta.sample}_${idx}", tags:tags ]
                 if (!fastq_2) {
                     return [
-                        updated_meta.id + fastq_1.toString().replaceAll('/', '_'),
+                        updated_meta.id,
                         updated_meta + [ single_end:true ],
                         [ fastq_1 ]
                     ]
                 } else {
                     return [
-                        updated_meta.id + fastq_1.toString().replaceAll('/', '_') + '_' + fastq_2.toString().replaceAll('/', '_'),
+                        updated_meta.id,
                         updated_meta + [ single_end:false ],
                         [ fastq_1, fastq_2 ]
                     ]

From 1f33928fdc2f9350fbb4ea86e253f5f7cc9b6670 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 10 Sep 2024 09:03:50 +0200
Subject: [PATCH 052/172] Update snapshots

---
 tests/MiSeq.main.nf.test.snap       | 12 ++++++----
 tests/NovaSeq6000.main.nf.test.snap | 36 ++++++++++++++++-------------
 tests/PromethION.main.nf.test.snap  | 12 ++++++----
 3 files changed, 36 insertions(+), 24 deletions(-)

diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 26f0c2a8..9dacaf8a 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -2,10 +2,14 @@
     "MiSeq data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,e46e7baa8f57d4cf54d973925b5eadf9",
-            "multiqc_general_stats.txt:md5,a5e626a2e1a3c986092e4f89091cc41c",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
+            "multiqc_general_stats.txt:md5,962713a1473a318f2cb29bb5290c4c8e",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
-        "timestamp": "2024-08-26T17:55:16.152573"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T08:57:05.870194"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index f5c4776b..3f27e5a2 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -2,26 +2,30 @@
     "NovaSeq6000 data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,e8ed6dca928396b8873d24e60ea1a133",
-            "multiqc_general_stats.txt:md5,fd9d46c5b441908cd07e5373d116db17",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
+            "multiqc_general_stats.txt:md5,d521de54d1e659bf7892105f7d23d4db",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,ff9b31c6024f11a8135456e7ea01fc8f",
-            "multiqc_general_stats.txt:md5,f36bd6e27e92c25be076efea411d3a8e",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
+            "multiqc_general_stats.txt:md5,d52544eb1a505c889a2f9117cf94a5fa",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,62d51280dcd7634f6bed95ffe0d8dab8",
-            "multiqc_general_stats.txt:md5,2012002b6a057be981a97fcc96142a6c",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
+            "multiqc_general_stats.txt:md5,5b1190093085ef073d4bd5818c9cde79",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,63749e803a2d5fc7ecc7cd93fa68df1f",
-            "multiqc_general_stats.txt:md5,656931993032400dea3d441b8b61b4d2",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95",
+            "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
+            "multiqc_general_stats.txt:md5,79c1090dd8a97912893f8491641b9dc9",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,91cc62e1b4059bdbe4b88affa43378af",
-            "multiqc_general_stats.txt:md5,6e500f82550e00b07c3e7aa1d46ab9e9",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
+            "multiqc_general_stats.txt:md5,41611bd5ab9e79425c466bf976b03bdc",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
-        "timestamp": "2024-08-26T18:03:33.089142"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T08:58:26.732622"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index e3b34f23..fb8cda25 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -2,10 +2,14 @@
     "PromethION data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,cecee3cb343c75c80180d3169c6f3ea1",
-            "multiqc_general_stats.txt:md5,e63c25089c4fc10618414ba2254d18c7",
-            "multiqc_software_versions.txt:md5,7452f1f7aae2a8a4066c2ef6cd5ceb95"
+            "multiqc_fastqc.txt:md5,35984961f25a0d4e7352cab4d5650178",
+            "multiqc_general_stats.txt:md5,1465b0b1959e3864b28ecc2340df351b",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
-        "timestamp": "2024-08-26T17:55:38.755385"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T08:58:57.180636"
     }
 }
\ No newline at end of file

From 7ce086a6fddbe96de440a234128576bfc4d6bff5 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 11:12:03 +0000
Subject: [PATCH 053/172] nf-core tools 3.0.2 modules update

---
 modules.json                                  |   4 +-
 modules/nf-core/fastqc/environment.yml        |   2 -
 modules/nf-core/fastqc/main.nf                |   5 +-
 modules/nf-core/fastqc/meta.yml               |  57 +--
 modules/nf-core/fastqc/tests/main.nf.test     | 225 ++++++++---
 .../nf-core/fastqc/tests/main.nf.test.snap    | 370 ++++++++++++++++--
 modules/nf-core/multiqc/environment.yml       |   4 +-
 modules/nf-core/multiqc/main.nf               |   6 +-
 modules/nf-core/multiqc/meta.yml              |  91 +++--
 .../nf-core/multiqc/tests/main.nf.test.snap   |  26 +-
 10 files changed, 603 insertions(+), 187 deletions(-)

diff --git a/modules.json b/modules.json
index 70f3486c..a84d111b 100644
--- a/modules.json
+++ b/modules.json
@@ -7,12 +7,12 @@
                 "nf-core": {
                     "fastqc": {
                         "branch": "master",
-                        "git_sha": "285a50500f9e02578d90b3ce6382ea3c30216acd",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "19ca321db5d8bd48923262c2eca6422359633491",
+                        "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
                         "installed_by": ["modules"]
                     }
                 }
diff --git a/modules/nf-core/fastqc/environment.yml b/modules/nf-core/fastqc/environment.yml
index 1787b38a..691d4c76 100644
--- a/modules/nf-core/fastqc/environment.yml
+++ b/modules/nf-core/fastqc/environment.yml
@@ -1,7 +1,5 @@
-name: fastqc
 channels:
   - conda-forge
   - bioconda
-  - defaults
 dependencies:
   - bioconda::fastqc=0.12.1
diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf
index d79f1c86..d8989f48 100644
--- a/modules/nf-core/fastqc/main.nf
+++ b/modules/nf-core/fastqc/main.nf
@@ -26,7 +26,10 @@ process FASTQC {
     def rename_to = old_new_pairs*.join(' ').join(' ')
     def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ')
 
-    def memory_in_mb = MemoryUnit.of("${task.memory}").toUnit('MB')
+    // The total amount of allocated RAM by FastQC is equal to the number of threads defined (--threads) time the amount of RAM defined (--memory)
+    // https://github.com/s-andrews/FastQC/blob/1faeea0412093224d7f6a07f777fad60a5650795/fastqc#L211-L222
+    // Dividing the task.memory by task.cpu allows to stick to requested amount of RAM in the label
+    def memory_in_mb = MemoryUnit.of("${task.memory}").toUnit('MB') / task.cpus
     // FastQC memory value allowed range (100 - 10000)
     def fastqc_memory = memory_in_mb > 10000 ? 10000 : (memory_in_mb < 100 ? 100 : memory_in_mb)
 
diff --git a/modules/nf-core/fastqc/meta.yml b/modules/nf-core/fastqc/meta.yml
index ee5507e0..4827da7a 100644
--- a/modules/nf-core/fastqc/meta.yml
+++ b/modules/nf-core/fastqc/meta.yml
@@ -16,35 +16,44 @@ tools:
       homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
       documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
       licence: ["GPL-2.0-only"]
+      identifier: biotools:fastqc
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+          List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+          respectively.
 output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
   - html:
-      type: file
-      description: FastQC report
-      pattern: "*_{fastqc.html}"
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.html":
+          type: file
+          description: FastQC report
+          pattern: "*_{fastqc.html}"
   - zip:
-      type: file
-      description: FastQC report archive
-      pattern: "*_{fastqc.zip}"
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.zip":
+          type: file
+          description: FastQC report archive
+          pattern: "*_{fastqc.zip}"
   - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@drpatelh"
   - "@grst"
diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test
index 70edae4d..e9d79a07 100644
--- a/modules/nf-core/fastqc/tests/main.nf.test
+++ b/modules/nf-core/fastqc/tests/main.nf.test
@@ -23,17 +23,14 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            // NOTE The report contains the date inside it, which means that the md5sum is stable per day, but not longer than that. So you can't md5sum it.
-            // looks like this: <div id="header_filename">Mon 2 Oct 2023<br/>test.gz</div>
-            // https://github.com/nf-core/modules/pull/3903#issuecomment-1743620039
-
-            { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
-            { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
-            { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_single") }
+                { assert process.success },
+                // NOTE The report contains the date inside it, which means that the md5sum is stable per day, but not longer than that. So you can't md5sum it.
+                // looks like this: <div id="header_filename">Mon 2 Oct 2023<br/>test.gz</div>
+                // https://github.com/nf-core/modules/pull/3903#issuecomment-1743620039
+                { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
+                { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
+                { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
@@ -54,16 +51,14 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" },
-            { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" },
-            { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" },
-            { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" },
-            { assert path(process.out.html[0][1][0]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-            { assert path(process.out.html[0][1][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_paired") }
+                { assert process.success },
+                { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" },
+                { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" },
+                { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" },
+                { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" },
+                { assert path(process.out.html[0][1][0]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert path(process.out.html[0][1][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
@@ -83,13 +78,11 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
-            { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
-            { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_interleaved") }
+                { assert process.success },
+                { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
+                { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
+                { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
@@ -109,13 +102,11 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
-            { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
-            { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_bam") }
+                { assert process.success },
+                { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" },
+                { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" },
+                { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
@@ -138,22 +129,20 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" },
-            { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" },
-            { assert process.out.html[0][1][2] ==~ ".*/test_3_fastqc.html" },
-            { assert process.out.html[0][1][3] ==~ ".*/test_4_fastqc.html" },
-            { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" },
-            { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" },
-            { assert process.out.zip[0][1][2] ==~ ".*/test_3_fastqc.zip" },
-            { assert process.out.zip[0][1][3] ==~ ".*/test_4_fastqc.zip" },
-            { assert path(process.out.html[0][1][0]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-            { assert path(process.out.html[0][1][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-            { assert path(process.out.html[0][1][2]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-            { assert path(process.out.html[0][1][3]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_multiple") }
+                { assert process.success },
+                { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" },
+                { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" },
+                { assert process.out.html[0][1][2] ==~ ".*/test_3_fastqc.html" },
+                { assert process.out.html[0][1][3] ==~ ".*/test_4_fastqc.html" },
+                { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" },
+                { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" },
+                { assert process.out.zip[0][1][2] ==~ ".*/test_3_fastqc.zip" },
+                { assert process.out.zip[0][1][3] ==~ ".*/test_4_fastqc.zip" },
+                { assert path(process.out.html[0][1][0]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert path(process.out.html[0][1][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert path(process.out.html[0][1][2]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert path(process.out.html[0][1][3]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
@@ -173,21 +162,18 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-
-            { assert process.out.html[0][1] ==~ ".*/mysample_fastqc.html" },
-            { assert process.out.zip[0][1] ==~ ".*/mysample_fastqc.zip" },
-            { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
-
-            { assert snapshot(process.out.versions).match("fastqc_versions_custom_prefix") }
+                { assert process.success },
+                { assert process.out.html[0][1] ==~ ".*/mysample_fastqc.html" },
+                { assert process.out.zip[0][1] ==~ ".*/mysample_fastqc.zip" },
+                { assert path(process.out.html[0][1]).text.contains("<tr><td>File type</td><td>Conventional base calls</td></tr>") },
+                { assert snapshot(process.out.versions).match() }
             )
         }
     }
 
     test("sarscov2 single-end [fastq] - stub") {
 
-        options "-stub"
-
+    options "-stub"
         when {
             process {
                 """
@@ -201,12 +187,123 @@ nextflow_process {
 
         then {
             assertAll (
-            { assert process.success },
-            { assert snapshot(process.out.html.collect { file(it[1]).getName() } +
-                                process.out.zip.collect { file(it[1]).getName() } +
-                                process.out.versions ).match("fastqc_stub") }
+                { assert process.success },
+                { assert snapshot(process.out).match() }
             )
         }
     }
 
+    test("sarscov2 paired-end [fastq] - stub") {
+
+    options "-stub"
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [id: 'test', single_end: false], // meta map
+                    [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ]
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 interleaved [fastq] - stub") {
+
+    options "-stub"
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [id: 'test', single_end: false], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_interleaved.fastq.gz', checkIfExists: true)
+                ])
+            """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 paired-end [bam] - stub") {
+
+    options "-stub"
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [id: 'test', single_end: false], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 multiple [fastq] - stub") {
+
+    options "-stub"
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [id: 'test', single_end: false], // meta map
+                    [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test2_1.fastq.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test2_2.fastq.gz', checkIfExists: true) ]
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 custom_prefix - stub") {
+
+    options "-stub"
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'mysample', single_end:true ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
 }
diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap
index 86f7c311..d5db3092 100644
--- a/modules/nf-core/fastqc/tests/main.nf.test.snap
+++ b/modules/nf-core/fastqc/tests/main.nf.test.snap
@@ -1,88 +1,392 @@
 {
-    "fastqc_versions_interleaved": {
+    "sarscov2 custom_prefix": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:40:07.293713"
+        "timestamp": "2024-07-22T11:02:16.374038"
     },
-    "fastqc_stub": {
+    "sarscov2 single-end [fastq] - stub": {
         "content": [
-            [
-                "test.html",
-                "test.zip",
-                "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
-            ]
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-22T11:02:24.993809"
+    },
+    "sarscov2 custom_prefix - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "mysample",
+                            "single_end": true
+                        },
+                        "mysample.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "mysample",
+                            "single_end": true
+                        },
+                        "mysample.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "mysample",
+                            "single_end": true
+                        },
+                        "mysample.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "mysample",
+                            "single_end": true
+                        },
+                        "mysample.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:31:01.425198"
+        "timestamp": "2024-07-22T11:03:10.93942"
     },
-    "fastqc_versions_multiple": {
+    "sarscov2 interleaved [fastq]": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:40:55.797907"
+        "timestamp": "2024-07-22T11:01:42.355718"
     },
-    "fastqc_versions_bam": {
+    "sarscov2 paired-end [bam]": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:40:26.795862"
+        "timestamp": "2024-07-22T11:01:53.276274"
     },
-    "fastqc_versions_single": {
+    "sarscov2 multiple [fastq]": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:39:27.043675"
+        "timestamp": "2024-07-22T11:02:05.527626"
     },
-    "fastqc_versions_paired": {
+    "sarscov2 paired-end [fastq]": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-22T11:01:31.188871"
+    },
+    "sarscov2 paired-end [fastq] - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-22T11:02:34.273566"
+    },
+    "sarscov2 multiple [fastq] - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:39:47.584191"
+        "timestamp": "2024-07-22T11:03:02.304411"
     },
-    "fastqc_versions_custom_prefix": {
+    "sarscov2 single-end [fastq]": {
         "content": [
             [
                 "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-22T11:01:19.095607"
+    },
+    "sarscov2 interleaved [fastq] - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-22T11:02:44.640184"
+    },
+    "sarscov2 paired-end [bam] - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e1cc25ca8af856014824abd842e93978"
+                ],
+                "zip": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.zip:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.3"
         },
-        "timestamp": "2024-01-31T17:41:14.576531"
+        "timestamp": "2024-07-22T11:02:53.550742"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml
index a31464c9..6f5b867b 100644
--- a/modules/nf-core/multiqc/environment.yml
+++ b/modules/nf-core/multiqc/environment.yml
@@ -1,7 +1,5 @@
-name: multiqc
 channels:
   - conda-forge
   - bioconda
-  - defaults
 dependencies:
-  - bioconda::multiqc=1.24.1
+  - bioconda::multiqc=1.25.1
diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf
index ceaec139..cc0643e1 100644
--- a/modules/nf-core/multiqc/main.nf
+++ b/modules/nf-core/multiqc/main.nf
@@ -3,8 +3,8 @@ process MULTIQC {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/multiqc:1.24.1--pyhdfd78af_0' :
-        'biocontainers/multiqc:1.24.1--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/multiqc:1.25.1--pyhdfd78af_0' :
+        'biocontainers/multiqc:1.25.1--pyhdfd78af_0' }"
 
     input:
     path  multiqc_files, stageAs: "?/*"
@@ -52,7 +52,7 @@ process MULTIQC {
     stub:
     """
     mkdir multiqc_data
-    touch multiqc_plots
+    mkdir multiqc_plots
     touch multiqc_report.html
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml
index 382c08cb..b16c1879 100644
--- a/modules/nf-core/multiqc/meta.yml
+++ b/modules/nf-core/multiqc/meta.yml
@@ -1,5 +1,6 @@
 name: multiqc
-description: Aggregate results from bioinformatics analyses across many samples into a single report
+description: Aggregate results from bioinformatics analyses across many samples into
+  a single report
 keywords:
   - QC
   - bioinformatics tools
@@ -12,53 +13,59 @@ tools:
       homepage: https://multiqc.info/
       documentation: https://multiqc.info/docs/
       licence: ["GPL-3.0-or-later"]
+      identifier: biotools:multiqc
 input:
-  - multiqc_files:
-      type: file
-      description: |
-        List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
-  - multiqc_config:
-      type: file
-      description: Optional config yml for MultiQC
-      pattern: "*.{yml,yaml}"
-  - extra_multiqc_config:
-      type: file
-      description: Second optional config yml for MultiQC. Will override common sections in multiqc_config.
-      pattern: "*.{yml,yaml}"
-  - multiqc_logo:
-      type: file
-      description: Optional logo file for MultiQC
-      pattern: "*.{png}"
-  - replace_names:
-      type: file
-      description: |
-        Optional two-column sample renaming file. First column a set of
-        patterns, second column a set of corresponding replacements. Passed via
-        MultiQC's `--replace-names` option.
-      pattern: "*.{tsv}"
-  - sample_names:
-      type: file
-      description: |
-        Optional TSV file with headers, passed to the MultiQC --sample_names
-        argument.
-      pattern: "*.{tsv}"
+  - - multiqc_files:
+        type: file
+        description: |
+          List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
+  - - multiqc_config:
+        type: file
+        description: Optional config yml for MultiQC
+        pattern: "*.{yml,yaml}"
+  - - extra_multiqc_config:
+        type: file
+        description: Second optional config yml for MultiQC. Will override common sections
+          in multiqc_config.
+        pattern: "*.{yml,yaml}"
+  - - multiqc_logo:
+        type: file
+        description: Optional logo file for MultiQC
+        pattern: "*.{png}"
+  - - replace_names:
+        type: file
+        description: |
+          Optional two-column sample renaming file. First column a set of
+          patterns, second column a set of corresponding replacements. Passed via
+          MultiQC's `--replace-names` option.
+        pattern: "*.{tsv}"
+  - - sample_names:
+        type: file
+        description: |
+          Optional TSV file with headers, passed to the MultiQC --sample_names
+          argument.
+        pattern: "*.{tsv}"
 output:
   - report:
-      type: file
-      description: MultiQC report file
-      pattern: "multiqc_report.html"
+      - "*multiqc_report.html":
+          type: file
+          description: MultiQC report file
+          pattern: "multiqc_report.html"
   - data:
-      type: directory
-      description: MultiQC data dir
-      pattern: "multiqc_data"
+      - "*_data":
+          type: directory
+          description: MultiQC data dir
+          pattern: "multiqc_data"
   - plots:
-      type: file
-      description: Plots created by MultiQC
-      pattern: "*_data"
+      - "*_plots":
+          type: file
+          description: Plots created by MultiQC
+          pattern: "*_data"
   - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@abhi18av"
   - "@bunop"
diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap
index 83fa080c..2fcbb5ff 100644
--- a/modules/nf-core/multiqc/tests/main.nf.test.snap
+++ b/modules/nf-core/multiqc/tests/main.nf.test.snap
@@ -2,14 +2,14 @@
     "multiqc_versions_single": {
         "content": [
             [
-                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
+                "versions.yml:md5,41f391dcedce7f93ca188f3a3ffa0916"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-10T12:41:34.562023"
+        "timestamp": "2024-10-02T17:51:46.317523"
     },
     "multiqc_stub": {
         "content": [
@@ -17,25 +17,25 @@
                 "multiqc_report.html",
                 "multiqc_data",
                 "multiqc_plots",
-                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
+                "versions.yml:md5,41f391dcedce7f93ca188f3a3ffa0916"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-10T11:27:11.933869532"
+        "timestamp": "2024-10-02T17:52:20.680978"
     },
     "multiqc_versions_config": {
         "content": [
             [
-                "versions.yml:md5,6eb13f3b11bbcbfc98ad3166420ff760"
+                "versions.yml:md5,41f391dcedce7f93ca188f3a3ffa0916"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-07-10T11:26:56.709849369"
+        "timestamp": "2024-10-02T17:52:09.185842"
     }
-}
+}
\ No newline at end of file

From a5951302f2b783a4ffe9fd1d3b11474fe48d3db6 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 13:30:37 +0000
Subject: [PATCH 054/172] merge fix

---
 .../local/utils_nfcore_seqinspector_pipeline/main.nf         | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index c2270583..a84e064f 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -74,6 +74,7 @@ workflow PIPELINE_INITIALISATION {
 
     Channel
         .fromList(samplesheetToList(params.input, "${projectDir}/assets/schema_input.json"))
+        .toList()
         .flatMap { it.withIndex().collect {  entry, idx -> entry + "${idx+1}" } }
         .map {
             meta, fastq_1, fastq_2, idx ->
@@ -94,8 +95,8 @@ workflow PIPELINE_INITIALISATION {
                 }
         }
         .groupTuple()
-        .map { samplesheet ->
-            validateInputSamplesheet(samplesheet)
+        .map {
+            validateInputSamplesheet(it) // Applies additional group validation checks that schema_input.json cannot do.
         }
         .transpose() // Replace the map below
         // .map {

From 036408867cb7b852cf1e35089d9bd4edab29bb89 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 13:30:48 +0000
Subject: [PATCH 055/172] update snapshots

---
 tests/MiSeq.main.nf.test.snap       |  8 ++++----
 tests/NovaSeq6000.main.nf.test.snap | 24 ++++++++++++------------
 tests/PromethION.main.nf.test.snap  | 10 +++++-----
 3 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 9dacaf8a..4613d525 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -3,13 +3,13 @@
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
-            "multiqc_general_stats.txt:md5,962713a1473a318f2cb29bb5290c4c8e",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
+            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-09-10T08:57:05.870194"
+        "timestamp": "2024-10-28T13:18:10.3675973"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 3f27e5a2..ee3c22b7 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -3,29 +3,29 @@
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
-            "multiqc_general_stats.txt:md5,d521de54d1e659bf7892105f7d23d4db",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
+            "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
-            "multiqc_general_stats.txt:md5,d52544eb1a505c889a2f9117cf94a5fa",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
+            "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
-            "multiqc_general_stats.txt:md5,5b1190093085ef073d4bd5818c9cde79",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
+            "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
-            "multiqc_general_stats.txt:md5,79c1090dd8a97912893f8491641b9dc9",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
+            "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
-            "multiqc_general_stats.txt:md5,41611bd5ab9e79425c466bf976b03bdc",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
+            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-09-10T08:58:26.732622"
+        "timestamp": "2024-10-28T13:19:13.226135825"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index fb8cda25..026a8cd2 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -2,14 +2,14 @@
     "PromethION data test": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,35984961f25a0d4e7352cab4d5650178",
-            "multiqc_general_stats.txt:md5,1465b0b1959e3864b28ecc2340df351b",
-            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
+            "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
+            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
+            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-09-10T08:58:57.180636"
+        "timestamp": "2024-10-28T13:19:57.261730412"
     }
 }
\ No newline at end of file

From 545af046c6660824322f982f4ac322776c25284c Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 13:38:38 +0000
Subject: [PATCH 056/172] Update CHANGELOG.md

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3aa5bacc..b0b12de1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
+- [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
 
 ### `Fixed`
 

From 88bb65d602ab1434a82b0b9406556cab674194fe Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 13:16:54 +0000
Subject: [PATCH 057/172] add subsampling

---
 modules.json                                  |  5 +
 modules/nf-core/seqtk/sample/environment.yml  |  5 +
 modules/nf-core/seqtk/sample/main.nf          | 58 +++++++++++
 modules/nf-core/seqtk/sample/meta.yml         | 52 ++++++++++
 .../nf-core/seqtk/sample/tests/main.nf.test   | 80 ++++++++++++++++
 .../seqtk/sample/tests/main.nf.test.snap      | 95 +++++++++++++++++++
 .../seqtk/sample/tests/standard.config        |  6 ++
 modules/nf-core/seqtk/sample/tests/tags.yml   |  2 +
 nextflow.config                               |  2 +-
 nextflow_schema.json                          |  7 ++
 workflows/seqinspector.nf                     | 17 +++-
 11 files changed, 327 insertions(+), 2 deletions(-)
 create mode 100644 modules/nf-core/seqtk/sample/environment.yml
 create mode 100644 modules/nf-core/seqtk/sample/main.nf
 create mode 100644 modules/nf-core/seqtk/sample/meta.yml
 create mode 100644 modules/nf-core/seqtk/sample/tests/main.nf.test
 create mode 100644 modules/nf-core/seqtk/sample/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/seqtk/sample/tests/standard.config
 create mode 100644 modules/nf-core/seqtk/sample/tests/tags.yml

diff --git a/modules.json b/modules.json
index 8e632d50..f01f2a64 100644
--- a/modules.json
+++ b/modules.json
@@ -14,6 +14,11 @@
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
                         "installed_by": ["modules"]
+                    },
+                    "seqtk/sample": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
                     }
                 }
             },
diff --git a/modules/nf-core/seqtk/sample/environment.yml b/modules/nf-core/seqtk/sample/environment.yml
new file mode 100644
index 00000000..693aa5c1
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::seqtk=1.4
diff --git a/modules/nf-core/seqtk/sample/main.nf b/modules/nf-core/seqtk/sample/main.nf
new file mode 100644
index 00000000..ea9b839e
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/main.nf
@@ -0,0 +1,58 @@
+process SEQTK_SAMPLE {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqtk:1.4--he4a0461_1' :
+        'biocontainers/seqtk:1.4--he4a0461_1' }"
+
+    input:
+    tuple val(meta), path(reads), val(sample_size)
+
+    output:
+    tuple val(meta), path("*.fastq.gz"), emit: reads
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args   = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (!(args ==~ /.*-s[0-9]+.*/)) {
+        args += " -s100"
+    }
+    if ( !sample_size ) {
+        error "SEQTK/SAMPLE must have a sample_size value included"
+    }
+    """
+    printf "%s\\n" $reads | while read f;
+    do
+        seqtk \\
+            sample \\
+            $args \\
+            \$f \\
+            $sample_size \\
+            | gzip --no-name > ${prefix}_\$(basename \$f)
+    done
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqtk: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo "" | gzip > ${prefix}.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqtk: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/nf-core/seqtk/sample/meta.yml b/modules/nf-core/seqtk/sample/meta.yml
new file mode 100644
index 00000000..42f67d8f
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/meta.yml
@@ -0,0 +1,52 @@
+name: seqtk_sample
+description: Subsample reads from FASTQ files
+keywords:
+  - sample
+  - fastx
+  - reads
+tools:
+  - seqtk:
+      description: Seqtk is a fast and lightweight tool for processing sequences in
+        the FASTA or FASTQ format. Seqtk sample command subsamples sequences.
+      homepage: https://github.com/lh3/seqtk
+      documentation: https://docs.csc.fi/apps/seqtk/
+      tool_dev_url: https://github.com/lh3/seqtk
+      licence: ["MIT"]
+      identifier: biotools:seqtk
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: List of input FastQ files
+        pattern: "*.{fastq.gz}"
+    - sample_size:
+        type: integer
+        description: Number of reads to sample.
+output:
+  - reads:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.fastq.gz":
+          type: file
+          description: Subsampled FastQ files
+          pattern: "*.{fastq.gz}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@kaurravneet4123"
+  - "@sidorov-si"
+  - "@adamrtalbot"
+maintainers:
+  - "@kaurravneet4123"
+  - "@sidorov-si"
+  - "@adamrtalbot"
diff --git a/modules/nf-core/seqtk/sample/tests/main.nf.test b/modules/nf-core/seqtk/sample/tests/main.nf.test
new file mode 100644
index 00000000..c121c9d9
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/tests/main.nf.test
@@ -0,0 +1,80 @@
+nextflow_process {
+
+    name "Test Process SEQTK_SAMPLE"
+    script "modules/nf-core/seqtk/sample/main.nf"
+    process "SEQTK_SAMPLE"
+    config "./standard.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "seqtk"
+    tag "seqtk/sample"
+
+    test("sarscov2_sample_singleend_fqgz") {
+
+        when {
+            process {
+                """
+                input[0] =  [
+                                [ id:'test', single_end:true ],
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                                50
+                            ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2_sample_pairedend_fqgz") {
+
+        when {
+            process {
+                """
+                input[0] =  [
+                                [ id:'test', single_end:true ],
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                                50
+                            ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2_sample_singlend_fqgz_stub") {
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] =  [
+                                [ id:'test', single_end:true ],
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                                50
+                            ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+}
diff --git a/modules/nf-core/seqtk/sample/tests/main.nf.test.snap b/modules/nf-core/seqtk/sample/tests/main.nf.test.snap
new file mode 100644
index 00000000..a9fec3c4
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/tests/main.nf.test.snap
@@ -0,0 +1,95 @@
+{
+    "sarscov2_sample_singlend_fqgz_stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled.fastq.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ],
+                "reads": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled.fastq.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ]
+            }
+        ],
+        "timestamp": "2024-02-22T15:58:45.902956"
+    },
+    "sarscov2_sample_pairedend_fqgz": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled_test_1.fastq.gz:md5,e5f44fafd7351c5abb9925a075132941"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ],
+                "reads": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled_test_1.fastq.gz:md5,e5f44fafd7351c5abb9925a075132941"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ]
+            }
+        ],
+        "timestamp": "2024-02-22T15:58:37.679954"
+    },
+    "sarscov2_sample_singleend_fqgz": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled_test_1.fastq.gz:md5,e5f44fafd7351c5abb9925a075132941"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ],
+                "reads": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test.sampled_test_1.fastq.gz:md5,e5f44fafd7351c5abb9925a075132941"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0529f2d163df9e2cd2ae8254dfb63806"
+                ]
+            }
+        ],
+        "timestamp": "2024-02-22T15:58:29.474491"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/seqtk/sample/tests/standard.config b/modules/nf-core/seqtk/sample/tests/standard.config
new file mode 100644
index 00000000..b2dd4b9f
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/tests/standard.config
@@ -0,0 +1,6 @@
+process {
+    withName: SEQTK_SAMPLE {
+        ext.args = '-s100'
+        ext.prefix = { "${meta.id}.sampled" }
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/seqtk/sample/tests/tags.yml b/modules/nf-core/seqtk/sample/tests/tags.yml
new file mode 100644
index 00000000..e5d113b8
--- /dev/null
+++ b/modules/nf-core/seqtk/sample/tests/tags.yml
@@ -0,0 +1,2 @@
+seqtk/sample:
+  - "modules/nf-core/seqtk/sample/**"
diff --git a/nextflow.config b/nextflow.config
index 50c1ecbb..10bcb897 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -12,7 +12,7 @@ params {
     // TODO nf-core: Specify your pipeline's command line flags
     // Input options
     input                      = null
-
+    sample_size                = null
     // References
     genome                     = null
     fasta                      = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 88fd607b..f87e525f 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -23,8 +23,15 @@
                     "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/seqinspector/usage#samplesheet-input).",
                     "fa_icon": "fas fa-file-csv"
                 },
+                "sample_size": {
+                    "type": "integer",
+                    "default": null,
+                    "description": "Subset this number of reads.",
+                    "help_text": "Samples will be subsetted to this number of reads. If null, no subsampling will be performed."
+                },
                 "outdir": {
                     "type": "string",
+                    "default": null,
                     "format": "directory-path",
                     "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                     "fa_icon": "fas fa-folder-open"
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ea628117..70b89679 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -3,6 +3,8 @@
     IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
+
+include { SEQTK_SAMPLE                  } from '../modules/nf-core/seqtk/sample/main'
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
@@ -30,11 +32,24 @@ workflow SEQINSPECTOR {
     ch_multiqc_extra_files = Channel.empty()
     ch_multiqc_reports     = Channel.empty()
 
+    //
+    // MODULE: Run Seqkit sample to perform subsampling
+    //
+    if (params.sample_size) {
+        ch_sample_sized = SEQTK_SAMPLE(ch_samplesheet.map {
+            meta, reads -> [meta, reads, params.sample_size]
+        }).reads
+        ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
+    } else {
+        // No do subsample
+        ch_sample_sized = ch_samplesheet
+    }
+
     //
     // MODULE: Run FastQC
     //
     FASTQC (
-        ch_samplesheet
+        ch_sample_sized
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())

From dbd64bfa4f311a9001f48a89df56a84581193d20 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 14:03:06 +0000
Subject: [PATCH 058/172] add subsampling nf-test

---
 tests/NovaSeq6000.main_subsample.nf.test      | 50 +++++++++++++++++++
 .../NovaSeq6000.main_subsample.nf.test.config |  8 +++
 2 files changed, 58 insertions(+)
 create mode 100644 tests/NovaSeq6000.main_subsample.nf.test
 create mode 100644 tests/NovaSeq6000.main_subsample.nf.test.config

diff --git a/tests/NovaSeq6000.main_subsample.nf.test b/tests/NovaSeq6000.main_subsample.nf.test
new file mode 100644
index 00000000..0919bc23
--- /dev/null
+++ b/tests/NovaSeq6000.main_subsample.nf.test
@@ -0,0 +1,50 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on NovaSeq6000 data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("NovaSeq6000 data test") {
+
+        when {
+            config "./NovaSeq6000.main_subsample.nf.test.config"
+            params {
+                outdir = "$outputDir"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_software_versions.txt"),
+
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_software_versions.txt"),
+                    ).match()
+                },
+            )
+        }
+    }
+}
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.config b/tests/NovaSeq6000.main_subsample.nf.test.config
new file mode 100644
index 00000000..acda74dd
--- /dev/null
+++ b/tests/NovaSeq6000.main_subsample.nf.test.config
@@ -0,0 +1,8 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
+    sample_size = 90
+}

From 44fb55455961c1d1cc56f04341a7d2a382dfbc42 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 14:09:57 +0000
Subject: [PATCH 059/172] add snapshots

---
 tests/NovaSeq6000.main_subsample.nf.test.snap | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 tests/NovaSeq6000.main_subsample.nf.test.snap

diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
new file mode 100644
index 00000000..d1dbe4a7
--- /dev/null
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -0,0 +1,31 @@
+{
+    "NovaSeq6000 data test": {
+        "content": [
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
+            "multiqc_general_stats.txt:md5,c4f40f2313aadc38619e7487226e8d93",
+            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
+            "multiqc_general_stats.txt:md5,d5d73d2888cd9895e5f116e5b869e73c",
+            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
+            "multiqc_general_stats.txt:md5,d01ec30a262b69bc5749b0ed108a950a",
+            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
+            "multiqc_general_stats.txt:md5,4dffc0d1169c49adde819d4467ffb775",
+            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
+            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
+            "multiqc_general_stats.txt:md5,05f8dfeea9fca7f4c16ba9d553af4c69",
+            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686"
+        ],
+        "meta": {
+            "nf-test": "0.9.1",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-28T14:05:44.868455454"
+    }
+}
\ No newline at end of file

From d781db1c98312bafc9419955aa43a26faa9dd076 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 14:20:03 +0000
Subject: [PATCH 060/172] better name

---
 tests/NovaSeq6000.main_subsample.nf.test | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/NovaSeq6000.main_subsample.nf.test b/tests/NovaSeq6000.main_subsample.nf.test
index 0919bc23..72851f91 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test
+++ b/tests/NovaSeq6000.main_subsample.nf.test
@@ -1,11 +1,11 @@
 nextflow_pipeline {
 
-    name "Test Workflow main.nf on NovaSeq6000 data"
+    name "Test Workflow main.nf on NovaSeq6000 data sample size 90"
     script "../main.nf"
     tag "seqinspector"
     tag "PIPELINE"
 
-    test("NovaSeq6000 data test") {
+    test("NovaSeq6000 data test sample size") {
 
         when {
             config "./NovaSeq6000.main_subsample.nf.test.config"

From ab30119cb07a2df13f5c6606747485796116434c Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 14:52:09 +0000
Subject: [PATCH 061/172] update docs

---
 docs/output.md  | 13 +++++++++++++
 docs/usage.md   |  5 +++++
 nextflow.config |  2 +-
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/docs/output.md b/docs/output.md
index e14c3ad6..a8257513 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -10,10 +10,23 @@ The directories listed below will be created in the results directory after the
 
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
+- [seqkit](#seqkit) - Subsample a specific number of reads per sample
 - [FastQC](#fastqc) - Raw read QC
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
+### Seqkit
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `seqtk/`
+  - `*_fastq`: FastQ file after being subsampled to the sample_size value.
+
+</details>
+
+[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [FastQC help pages](https://bioinf.shenwei.me/seqkit/usage/#sample).
+
 ### FastQC
 
 <details markdown="1">
diff --git a/docs/usage.md b/docs/usage.md
index d75e0fbd..c11b270f 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -93,6 +93,11 @@ genome: 'GRCh37'
 
 You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch).
 
+Optionally, the `sample_size` parameter allows you to subset a random number of reads to be analysed.
+```bash
+nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 90 -profile docker
+```
+
 ### Updating the pipeline
 
 When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:
diff --git a/nextflow.config b/nextflow.config
index 10bcb897..38eb3127 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -12,7 +12,7 @@ params {
     // TODO nf-core: Specify your pipeline's command line flags
     // Input options
     input                      = null
-    sample_size                = null
+    sample_size                = 0
     // References
     genome                     = null
     fasta                      = null

From b8befe4b35f94132418c81640af710ab4af486fb Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 14:52:21 +0000
Subject: [PATCH 062/172] change default to 0

---
 nextflow_schema.json      | 4 ++--
 workflows/seqinspector.nf | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index f87e525f..edb18ea0 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -25,9 +25,9 @@
                 },
                 "sample_size": {
                     "type": "integer",
-                    "default": null,
+                    "default": 0,
                     "description": "Subset this number of reads.",
-                    "help_text": "Samples will be subsetted to this number of reads. If null, no subsampling will be performed."
+                    "help_text": "Samples will be subsetted to this number of reads. If 0 (default), no subsampling will be performed."
                 },
                 "outdir": {
                     "type": "string",
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 70b89679..91a699da 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -35,7 +35,7 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run Seqkit sample to perform subsampling
     //
-    if (params.sample_size) {
+    if (params.sample_size > 0 ) {
         ch_sample_sized = SEQTK_SAMPLE(ch_samplesheet.map {
             meta, reads -> [meta, reads, params.sample_size]
         }).reads

From b2e7be55427d0bc063373d45e505d0c6b5509ed2 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 14:56:37 +0000
Subject: [PATCH 063/172] Fran's draft

---
 modules.json                                  |  5 ++
 .../fastqscreen/fastqscreen/environment.yml   |  9 ++
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 54 ++++++++++++
 .../nf-core/fastqscreen/fastqscreen/meta.yml  | 44 ++++++++++
 .../fastqscreen/tests/main.nf.test            | 87 +++++++++++++++++++
 .../fastqscreen/tests/main.nf.test.snap       | 81 +++++++++++++++++
 .../fastqscreen/fastqscreen/tests/tags.yml    |  2 +
 nextflow.config                               |  1 +
 nextflow_schema.json                          |  5 ++
 workflows/seqinspector.nf                     | 12 +++
 10 files changed, 300 insertions(+)
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/environment.yml
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/main.nf
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/meta.yml
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml

diff --git a/modules.json b/modules.json
index 8e632d50..cb726e0d 100644
--- a/modules.json
+++ b/modules.json
@@ -10,6 +10,11 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "fastqscreen/fastqscreen": {
+                        "branch": "master",
+                        "git_sha": "e1316cdcbef318b9cdfd35586423f8337c3d45f0",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
diff --git a/modules/nf-core/fastqscreen/fastqscreen/environment.yml b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
new file mode 100644
index 00000000..5097f091
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "fastqscreen_fastqscreen"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::fastq-screen=0.15.3"
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
new file mode 100644
index 00000000..8686f200
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -0,0 +1,54 @@
+process FASTQSCREEN_FASTQSCREEN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
+        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
+
+    input:
+    tuple val(meta), path(reads)  // .fastq files
+    path database
+
+    output:
+    tuple val(meta), path("*.txt") , emit: txt
+    tuple val(meta), path("*.png") , emit: png
+    tuple val(meta), path("*.html"), emit: html
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def args = task.ext.args ?: ""
+
+    """
+    fastq_screen --threads ${task.cpus} \\
+        --aligner bowtie2 \\
+        --conf ${database}/fastq_screen.conf \\
+        $reads \\
+        $args \\
+        --outdir .
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch test_1_screen.html
+    touch test_1_screen.png
+    touch test_1_screen.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/nf-core/fastqscreen/fastqscreen/meta.yml b/modules/nf-core/fastqscreen/fastqscreen/meta.yml
new file mode 100644
index 00000000..623dacf7
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/meta.yml
@@ -0,0 +1,44 @@
+name: fastqscreen_fastqscreen
+description: Align reads to multiple reference genomes using fastq-screen
+keywords:
+  - align
+  - map
+  - fasta
+  - fastq
+  - genome
+  - reference
+tools:
+  - "fastqscreen":
+      description: "FastQ Screen allows you to screen a library of sequences in FastQ format against a set of sequence databases so you can see if the composition of the library matches with what you expect."
+      homepage: "https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/"
+      documentation: "https://stevenwingett.github.io/FastQ-Screen/"
+      tool_dev_url: "https://github.com/StevenWingett/FastQ-Screen/archive/refs/tags/v0.15.3.zip"
+      doi: "10.5281/zenodo.5838377"
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - database:
+      type: directory
+      description: fastq screen database folder containing config file and index folders
+      pattern: "FastQ_Screen_Genomes"
+output:
+  - fastq_screen:
+      type: directory
+      description: Output fastq_screen file containing alignment statistics
+      pattern: "*.{_fq_screen}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@snesic"
+  - "@JPejovicApis"
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
new file mode 100644
index 00000000..6d858a4d
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
@@ -0,0 +1,87 @@
+nextflow_process {
+
+    name "Test Process FASTQSCREEN_FASTQSCREEN"
+    script "../main.nf"
+    process "FASTQSCREEN_FASTQSCREEN"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "bowtie2/build"
+    tag "fastqscreen"
+    tag "fastqscreen/buildfromindex"
+    tag "fastqscreen/fastqscreen"
+
+    setup {
+
+        run("BOWTIE2_BUILD") {
+            script "../../../bowtie2/build/main.nf"
+            process {
+                """
+                input[0] =  Channel.from([
+                                    [[id: "sarscov2"], file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)],
+                                    [[id: "human"]   , file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)]
+                            ])
+                """
+            }
+        }
+
+        run("FASTQSCREEN_BUILDFROMINDEX") {
+            script "../../../fastqscreen/buildfromindex/main.nf"
+            process {
+                """
+                input[0] = BOWTIE2_BUILD.out.index.map{meta, index -> meta.id}.collect()
+                input[1] = BOWTIE2_BUILD.out.index.map{meta, index -> index}.collect()
+                """
+            }
+        }
+    }
+
+    test("sarscov2 - human") {
+
+        when {
+            process {
+                """
+                input[0] =  [[ id:'test', single_end:true ],
+                             [file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+                            ]
+                input[1] = FASTQSCREEN_BUILDFROMINDEX.out.database
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.version).match("version") },
+                { assert file(process.out.txt.get(0).get(1)).exists() },
+                { assert file(process.out.png.get(0).get(1)).exists() },
+                { assert file(process.out.html.get(0).get(1)).exists() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - human - stub") {
+
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] =  [[ id:'test', single_end:true ],
+                             [file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+                            ]
+                input[1] = FASTQSCREEN_BUILDFROMINDEX.out.database
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
new file mode 100644
index 00000000..b2450191
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
@@ -0,0 +1,81 @@
+{
+    "version": {
+        "content": null,
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-30T14:22:56.541922683"
+    },
+    "sarscov2 - human - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "3": [
+                    "versions.yml:md5,8ac0239b5103352958d9a9e562b23103"
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "png": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "txt": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true
+                        },
+                        "test_1_screen.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,8ac0239b5103352958d9a9e562b23103"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-30T14:23:12.70922619"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml b/modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml
new file mode 100644
index 00000000..b03bfb45
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml
@@ -0,0 +1,2 @@
+fastqscreen/fastqscreen:
+  - "modules/nf-core/fastqscreen/fastqscreen/**"
diff --git a/nextflow.config b/nextflow.config
index 50c1ecbb..210f03ef 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -17,6 +17,7 @@ params {
     genome                     = null
     fasta                      = null
     igenomes_base              = 's3://ngi-igenomes/igenomes/'
+    config_fastq_screen        = "${projectDir}/modules/nf-core/fastqscreen/references"
     igenomes_ignore            = false
 
     // MultiQC options
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 88fd607b..f18a5f19 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -65,6 +65,11 @@
                     "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
                     "fa_icon": "far fa-file-code"
                 },
+                "config_fastq_screen": {
+                    "type": "string",
+                    "description": "path to directory with fastq_screen config (fastq_screen.conf)",
+                    "fa_icon": "fas fa-braille"
+                },
                 "igenomes_ignore": {
                     "type": "boolean",
                     "description": "Do not load the iGenomes reference config.",
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ea628117..6ec9ca9f 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -4,6 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
+include { FASTQSCREEN_FASTQSCREEN       } from '../modules/nf-core/fastqscreen/fastqscreen/main'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
@@ -39,6 +40,17 @@ workflow SEQINSPECTOR {
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
+    //
+    // MODULE: Run FastQ Screen
+    //
+
+    FASTQSCREEN_FASTQSCREEN (
+        ch_samplesheet,
+        Channel.fromPath(params.config_fastq_screen)
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
+    ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
+
     //
     // Collate and save software versions
     //

From d833d913c5f0da94eeee1c9eaf44fd14c5fdb2fa Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 15:02:08 +0000
Subject: [PATCH 064/172] nf-core modules update --> fastqscreen

---
 modules.json                                  |  2 +-
 .../fastqscreen/fastqscreen/environment.yml   |  3 +-
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 10 +--
 .../nf-core/fastqscreen/fastqscreen/meta.yml  | 78 +++++++++++++------
 .../fastqscreen/tests/main.nf.test            | 32 +++++++-
 .../fastqscreen/tests/main.nf.test.snap       | 65 ++++++++++++++--
 .../fastqscreen/tests/nextflow.config         |  5 ++
 7 files changed, 157 insertions(+), 38 deletions(-)
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config

diff --git a/modules.json b/modules.json
index cb726e0d..f8b48550 100644
--- a/modules.json
+++ b/modules.json
@@ -12,7 +12,7 @@
                     },
                     "fastqscreen/fastqscreen": {
                         "branch": "master",
-                        "git_sha": "e1316cdcbef318b9cdfd35586423f8337c3d45f0",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
diff --git a/modules/nf-core/fastqscreen/fastqscreen/environment.yml b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
index 5097f091..c63c61e2 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/environment.yml
+++ b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
@@ -1,9 +1,8 @@
 ---
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
-name: "fastqscreen_fastqscreen"
 channels:
   - conda-forge
   - bioconda
-  - defaults
 dependencies:
   - "bioconda::fastq-screen=0.15.3"
+  - bioconda::perl-gdgraph=1.54
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 8686f200..88c4e5c5 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -12,10 +12,11 @@ process FASTQSCREEN_FASTQSCREEN {
     path database
 
     output:
-    tuple val(meta), path("*.txt") , emit: txt
-    tuple val(meta), path("*.png") , emit: png
-    tuple val(meta), path("*.html"), emit: html
-    path "versions.yml"            , emit: versions
+    tuple val(meta), path("*.txt")     , emit: txt
+    tuple val(meta), path("*.png")     , emit: png  , optional: true
+    tuple val(meta), path("*.html")    , emit: html
+    tuple val(meta), path("*.fastq.gz"), emit: fastq, optional: true
+    path "versions.yml"                , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -30,7 +31,6 @@ process FASTQSCREEN_FASTQSCREEN {
         --conf ${database}/fastq_screen.conf \\
         $reads \\
         $args \\
-        --outdir .
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/nf-core/fastqscreen/fastqscreen/meta.yml b/modules/nf-core/fastqscreen/fastqscreen/meta.yml
index 623dacf7..39c86b4f 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/meta.yml
+++ b/modules/nf-core/fastqscreen/fastqscreen/meta.yml
@@ -9,36 +9,70 @@ keywords:
   - reference
 tools:
   - "fastqscreen":
-      description: "FastQ Screen allows you to screen a library of sequences in FastQ format against a set of sequence databases so you can see if the composition of the library matches with what you expect."
+      description: "FastQ Screen allows you to screen a library of sequences in FastQ
+        format against a set of sequence databases so you can see if the composition
+        of the library matches with what you expect."
       homepage: "https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/"
       documentation: "https://stevenwingett.github.io/FastQ-Screen/"
       tool_dev_url: "https://github.com/StevenWingett/FastQ-Screen/archive/refs/tags/v0.15.3.zip"
       doi: "10.5281/zenodo.5838377"
       licence: ["GPL-3.0-or-later"]
+      identifier: ""
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - database:
-      type: directory
-      description: fastq screen database folder containing config file and index folders
-      pattern: "FastQ_Screen_Genomes"
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+          List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+          respectively.
+  - - database:
+        type: directory
+        description: fastq screen database folder containing config file and index folders
+        pattern: "FastQ_Screen_Genomes"
 output:
-  - fastq_screen:
-      type: directory
-      description: Output fastq_screen file containing alignment statistics
-      pattern: "*.{_fq_screen}"
+  - txt:
+      - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.txt":
+          type: file
+          description: TXT file containing alignment statistics
+          pattern: "*.txt"
+  - png:
+      - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.png":
+          type: file
+          description: PNG file with graphical representation of alignments
+          pattern: "*.png"
+  - html:
+      - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.html":
+          type: file
+          description: HTML file containing mapping results as a table and graphical representation
+          pattern: "*.html"
+  - fastq:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.fastq.gz":
+          type: file
+          description: FastQ file containing reads that did not align to any database (optional)
+          pattern: "*.fastq.gz"
   - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@snesic"
   - "@JPejovicApis"
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
index 6d858a4d..71230a22 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test
@@ -10,6 +10,8 @@ nextflow_process {
     tag "fastqscreen"
     tag "fastqscreen/buildfromindex"
     tag "fastqscreen/fastqscreen"
+    tag "buildfromindex"
+    tag "modules_fastqscreen"
 
     setup {
 
@@ -52,7 +54,7 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.version).match("version") },
+                { assert snapshot(process.out.version).match() },
                 { assert file(process.out.txt.get(0).get(1)).exists() },
                 { assert file(process.out.png.get(0).get(1)).exists() },
                 { assert file(process.out.html.get(0).get(1)).exists() }
@@ -61,6 +63,34 @@ nextflow_process {
 
     }
 
+    test("sarscov2 - human - tags") {
+        config './nextflow.config'
+        when {
+            process {
+                """
+                input[0] =  [[ id:'test', single_end:false ],
+                             [file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
+                            ]
+                input[1] = FASTQSCREEN_BUILDFROMINDEX.out.database
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.version,
+                    process.out.txt,
+                    process.out.fastq,
+                    path(process.out.html.get(0).get(1)).readLines()[0..10],
+                    path(process.out.png.get(0).get(1)).exists()
+                    ).match() }
+            )
+        }
+
+    }
+
     test("sarscov2 - human - stub") {
 
         options "-stub"
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
index b2450191..2afffdea 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap
@@ -1,11 +1,56 @@
 {
-    "version": {
+    "sarscov2 - human": {
         "content": null,
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-04-30T14:22:56.541922683"
+        "timestamp": "2024-08-31T05:42:29.972454812"
+    },
+    "sarscov2 - human - tags": {
+        "content": [
+            null,
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test_1_screen.txt:md5,b0b0ea58bc26ebaa4d573a85e7898f25"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    [
+                        "test_1.tagged.fastq.gz:md5,f742b162c43ce28f80b89608d5c47f3d",
+                        "test_1.tagged_filter.fastq.gz:md5,28527a76bb0bb3fce0ee76afe01e90aa"
+                    ]
+                ]
+            ],
+            [
+                "<!DOCTYPE html>",
+                "<html>",
+                "",
+                "",
+                "<!-- Style, and Plotly code -->",
+                "<head>",
+                "\t<meta http-equiv=\"content-type\" content=\"text/html; charset=UTF-8\">",
+                "\t<title>FastQ Screen Processing Report - test_1.fastq.gz</title>",
+                "\t<style type=\"text/css\">",
+                "\t\tbody {",
+                "\t\t\tfont-family: Arial, sans-serif;"
+            ],
+            true
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-08-31T06:23:02.73675229"
     },
     "sarscov2 - human - stub": {
         "content": [
@@ -38,7 +83,13 @@
                     ]
                 ],
                 "3": [
+                    
+                ],
+                "4": [
                     "versions.yml:md5,8ac0239b5103352958d9a9e562b23103"
+                ],
+                "fastq": [
+                    
                 ],
                 "html": [
                     [
@@ -73,9 +124,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-04-30T14:23:12.70922619"
+        "timestamp": "2024-08-31T05:45:54.845041829"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config b/modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config
new file mode 100644
index 00000000..ccf580b7
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: FASTQSCREEN_FASTQSCREEN {
+        ext.args = "--tag --filter 10"
+    }
+}

From 135d6a35c15f0338a77dad2eaf5a7b3c9a144daa Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 15:15:17 +0000
Subject: [PATCH 065/172] update snapshot

---
 tests/MiSeq.main.nf.test.snap                 |  8 ++++----
 tests/NovaSeq6000.main.nf.test.snap           | 16 ++++++++--------
 tests/NovaSeq6000.main_subsample.nf.test.snap | 14 +++++++-------
 tests/PromethION.main.nf.test.snap            |  8 ++++----
 4 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 4613d525..d60f627d 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
             "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.1",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-28T13:18:10.3675973"
+        "timestamp": "2024-10-28T15:06:30.86052858"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index ee3c22b7..5ac1e09d 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,28 +4,28 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
             "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.1",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-28T13:19:13.226135825"
+        "timestamp": "2024-10-28T15:07:59.897711748"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index d1dbe4a7..c37e51cc 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -1,31 +1,31 @@
 {
-    "NovaSeq6000 data test": {
+    "NovaSeq6000 data test sample size": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
-            "multiqc_general_stats.txt:md5,c4f40f2313aadc38619e7487226e8d93",
+            "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
-            "multiqc_general_stats.txt:md5,d5d73d2888cd9895e5f116e5b869e73c",
+            "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
-            "multiqc_general_stats.txt:md5,d01ec30a262b69bc5749b0ed108a950a",
+            "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
-            "multiqc_general_stats.txt:md5,4dffc0d1169c49adde819d4467ffb775",
+            "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
-            "multiqc_general_stats.txt:md5,05f8dfeea9fca7f4c16ba9d553af4c69",
+            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686"
         ],
         "meta": {
             "nf-test": "0.9.1",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-28T14:05:44.868455454"
+        "timestamp": "2024-10-28T15:09:41.503580136"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 026a8cd2..1232678d 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
             "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_software_versions.txt:md5,49e3596d49ee49d967d3b6c363b486d5"
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.1",
+            "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-28T13:19:57.261730412"
+        "timestamp": "2024-10-28T15:10:20.186073387"
     }
 }
\ No newline at end of file

From 285a4b396885f85bb4f966d9220e3c884616a379 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 28 Oct 2024 15:15:37 +0000
Subject: [PATCH 066/172] add fastq_screen.conf

---
 conf/fastq_screen.conf | 64 ++++++++++++++++++++++++++++++++++++++++++
 nextflow.config        |  2 +-
 2 files changed, 65 insertions(+), 1 deletion(-)
 create mode 100644 conf/fastq_screen.conf

diff --git a/conf/fastq_screen.conf b/conf/fastq_screen.conf
new file mode 100644
index 00000000..aaa19641
--- /dev/null
+++ b/conf/fastq_screen.conf
@@ -0,0 +1,64 @@
+# This is a configuration file for fastq_screen
+
+###########
+## Bowtie #
+###########
+## If the bowtie binary is not in your PATH then you can
+## set this value to tell the program where to find it.
+## Uncomment the line below and set the appropriate location
+##
+
+#BOWTIE2 /sw/data/uppnex/reference/sw/mf/bioinfo-tools/pipelines/bowtie2/2.1.0/bowtie2
+
+############
+## Threads #
+############
+## Bowtie can be made to run across multiple CPU cores to
+## speed up your searches. Set this value to the number
+## of cores you want to use for your searches.
+
+#THREADS                16
+
+##############
+## Databases #
+##############
+## This section allows you to configure multiple databases
+## to search against in your screen.  For each database
+## you need to provide a database name (which can't contain
+## spaces) and the location of the bowtie indices which
+## you created for that database.
+##
+## The default entries shown below are only suggested examples
+## you can add as many DATABASE sections as you like, and you
+## can comment out or remove as many of the existing entries
+## as you like.
+##
+## Either the original bowtie or bowtie 2 may be used for the
+## mapping. Specify the aligner to use with the command line
+## flag --aligner with arguments 'bowtie' (default) or
+## 'bowtie2'.
+##
+## The configuration file may list paths to both bowtie and
+## bowtie2 indices, which are specified with either 'BOWTIE'
+## or 'BOWTIE2' after the path (leaving unspecified will
+## default to bowtie). While the configuration file may list
+## paths to both bowtie and bowtie2 indices, only one aligner
+## will be used for the mapping, as specified by the --aligner
+## flag.
+##
+## For example:
+## DATABASE     Human_Bowtie    /data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37 BOWTIE
+## DATABASE     Human_Bowtie    /data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37
+## DATABASE     Human_Bowtie2   /data/public/Genomes/Human_Bowtie2/GRCh37/Homo_sapiens.GRCh37 BOWTIE2
+
+## E. coli (igenomes/Escherichia_coli_K_12_DH10B/Ensembl/EB1)
+DATABASE    Ecoli   ../../../modules/nf-core/fastqscreen/references/genome_ecoli/genome BOWTIE2
+
+## M. tuberculosis (igenomes/Mycobacterium_tuberculosis_H37RV/Ensembl/H37Rv.EB1)
+DATABASE    Tuberculosis   ../../../modules/nf-core/fastqscreen/references/genome_tuberculosis/genome BOWTIE2
+
+## PhiX (/igenomes/PhiX/Illumina/RTA)
+DATABASE    PhiX   ../../../modules/nf-core/fastqscreen/references/genome_phix/genome BOWTIE2
+
+##S. cerevisiae (igenomes/Saccharomyces_cerevisiae/Ensembl/EF4)
+DATABASE    Scerevisiae   ../../../modules/nf-core/fastqscreen/references/genome_cerevisiae/genome BOWTIE2
diff --git a/nextflow.config b/nextflow.config
index 210f03ef..1600a70b 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -17,7 +17,7 @@ params {
     genome                     = null
     fasta                      = null
     igenomes_base              = 's3://ngi-igenomes/igenomes/'
-    config_fastq_screen        = "${projectDir}/modules/nf-core/fastqscreen/references"
+    config_fastq_screen        = "${projectDir}/conf"
     igenomes_ignore            = false
 
     // MultiQC options

From 36d80d33da43045c2175ed376bf32d79906ec3ae Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 15:43:30 +0000
Subject: [PATCH 067/172] prettify docs

---
 docs/usage.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/usage.md b/docs/usage.md
index c11b270f..0cbd8f5d 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -94,6 +94,7 @@ genome: 'GRCh37'
 You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch).
 
 Optionally, the `sample_size` parameter allows you to subset a random number of reads to be analysed.
+
 ```bash
 nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 90 -profile docker
 ```

From 96dc9f73b55dd448ec35cb16765d0a06034b7343 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 15:53:19 +0000
Subject: [PATCH 068/172] update changelog

---
 CHANGELOG.md   | 1 +
 docs/output.md | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b0b12de1..bad5a09b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#50](https://github.com/nf-core/seqinspector/pull/50) Add an optional subsampling step.
 
 ### `Fixed`
 
diff --git a/docs/output.md b/docs/output.md
index a8257513..aef433b2 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -25,7 +25,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 </details>
 
-[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [FastQC help pages](https://bioinf.shenwei.me/seqkit/usage/#sample).
+[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [Sekit sample](https://bioinf.shenwei.me/seqkit/usage/#sample).
 
 ### FastQC
 

From 0fd6a95e677dd8beac4805875a12b2a0b464221d Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Mon, 28 Oct 2024 15:54:54 +0000
Subject: [PATCH 069/172] typo

---
 docs/output.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/output.md b/docs/output.md
index aef433b2..f2048f07 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -25,7 +25,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 </details>
 
-[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [Sekit sample](https://bioinf.shenwei.me/seqkit/usage/#sample).
+[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [Seqkit sample](https://bioinf.shenwei.me/seqkit/usage/#sample).
 
 ### FastQC
 

From a417ad39a0b972e5aec2c8b57570ddaa235f4bdb Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 08:47:48 +0000
Subject: [PATCH 070/172] suggestions

---
 docs/output.md       | 6 +++---
 docs/usage.md        | 4 ++--
 nextflow_schema.json | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/docs/output.md b/docs/output.md
index f2048f07..2d4efb02 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -10,12 +10,12 @@ The directories listed below will be created in the results directory after the
 
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
-- [seqkit](#seqkit) - Subsample a specific number of reads per sample
+- [Seqtk](#seqtk) - Subsample a specific number of reads per sample
 - [FastQC](#fastqc) - Raw read QC
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
-### Seqkit
+### Seqtk
 
 <details markdown="1">
 <summary>Output files</summary>
@@ -25,7 +25,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 </details>
 
-[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [Seqkit sample](https://bioinf.shenwei.me/seqkit/usage/#sample).
+[Seqtk](https://github.com/lh3/seqtk) samples sequences by number.
 
 ### FastQC
 
diff --git a/docs/usage.md b/docs/usage.md
index 0cbd8f5d..31ab91ef 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -93,10 +93,10 @@ genome: 'GRCh37'
 
 You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch).
 
-Optionally, the `sample_size` parameter allows you to subset a random number of reads to be analysed.
+Optionally, the `sample_size` parameter allows you to subset a random number of reads to be analysed. Note that it refers to an absolute number.
 
 ```bash
-nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 90 -profile docker
+nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 1000000 -profile docker
 ```
 
 ### Updating the pipeline
diff --git a/nextflow_schema.json b/nextflow_schema.json
index edb18ea0..49742b28 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -26,8 +26,8 @@
                 "sample_size": {
                     "type": "integer",
                     "default": 0,
-                    "description": "Subset this number of reads.",
-                    "help_text": "Samples will be subsetted to this number of reads. If 0 (default), no subsampling will be performed."
+                    "description": "Take this number of reads as a subset.",
+                    "help_text": "Choose the size of the subset or 0, if no subsampling shall be performed. Note that it refers to an absolute number."
                 },
                 "outdir": {
                     "type": "string",

From a0815635ea42aca9b42488ad5163ba96f9c75267 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 09:57:43 +0100
Subject: [PATCH 071/172] hack out some ideas

---
 workflows/seqinspector.nf | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 6ec9ca9f..a0e9d900 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -44,6 +44,14 @@ workflow SEQINSPECTOR {
     // MODULE: Run FastQ Screen
     //
 
+    Channel.fromPath(params.config_fastq_screen)
+        .splitText()
+    .filter // TODO anything that doesn't have "database"
+        .collect()
+
+    file(list_of_configs)
+    // TODO write configs to text file?
+
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,
         Channel.fromPath(params.config_fastq_screen)

From 801220f5f936a4be2a9fb6391e7e4cffa7c63b57 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 09:14:24 +0000
Subject: [PATCH 072/172] switch to original reads for fastqc

---
 workflows/seqinspector.nf | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 91a699da..a89bd5c5 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -36,20 +36,28 @@ workflow SEQINSPECTOR {
     // MODULE: Run Seqkit sample to perform subsampling
     //
     if (params.sample_size > 0 ) {
-        ch_sample_sized = SEQTK_SAMPLE(ch_samplesheet.map {
-            meta, reads -> [meta, reads, params.sample_size]
-        }).reads
+        ch_sample_sized = ch_samplesheet.join(
+            SEQTK_SAMPLE(
+                ch_samplesheet.map {
+                    meta, reads -> [meta, reads, params.sample_size]
+                }
+            ).reads, by: [0]
+        )
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
     } else {
         // No do subsample
-        ch_sample_sized = ch_samplesheet
+        ch_sample_sized = ch_samplesheet.map {
+            meta, reads -> [meta, reads, []]
+        }
     }
 
     //
     // MODULE: Run FastQC
     //
     FASTQC (
-        ch_sample_sized
+        ch_sample_sized.map {
+            meta, reads, subsampled -> [meta, reads]
+        }
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())

From e9ae94cb797751ca97f3f86a199fa19bfe74d3f0 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 09:15:38 +0000
Subject: [PATCH 073/172] update snapshot

---
 tests/NovaSeq6000.main_subsample.nf.test.snap | 22 +++++++++----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index c37e51cc..ee118c94 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -2,30 +2,30 @@
     "NovaSeq6000 data test sample size": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
-            "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
+            "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
+            "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
-            "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
+            "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
+            "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
-            "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
+            "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
+            "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
-            "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
+            "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
+            "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
-            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
+            "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
+            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686"
         ],
         "meta": {
             "nf-test": "0.9.1",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-28T15:09:41.503580136"
+        "timestamp": "2024-10-29T09:15:03.224117679"
     }
 }
\ No newline at end of file

From 7a4dccd0bf9b5abe66e66af52e8c196b8e8d232d Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 10:33:48 +0100
Subject: [PATCH 074/172] test: Update path for database

---
 conf/fastq_screen.conf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/conf/fastq_screen.conf b/conf/fastq_screen.conf
index aaa19641..f170f285 100644
--- a/conf/fastq_screen.conf
+++ b/conf/fastq_screen.conf
@@ -52,10 +52,10 @@
 ## DATABASE     Human_Bowtie2   /data/public/Genomes/Human_Bowtie2/GRCh37/Homo_sapiens.GRCh37 BOWTIE2
 
 ## E. coli (igenomes/Escherichia_coli_K_12_DH10B/Ensembl/EB1)
-DATABASE    Ecoli   ../../../modules/nf-core/fastqscreen/references/genome_ecoli/genome BOWTIE2
+DATABASE    Ecoli   ./database/EB1 BOWTIE2
 
 ## M. tuberculosis (igenomes/Mycobacterium_tuberculosis_H37RV/Ensembl/H37Rv.EB1)
-DATABASE    Tuberculosis   ../../../modules/nf-core/fastqscreen/references/genome_tuberculosis/genome BOWTIE2
+DATABASE    Tuberculosis   ./references/genome_tuberculosis/genome BOWTIE2
 
 ## PhiX (/igenomes/PhiX/Illumina/RTA)
 DATABASE    PhiX   ../../../modules/nf-core/fastqscreen/references/genome_phix/genome BOWTIE2

From 0f7ff12c15b816b5ccd5c842c2ad001ac2e1ab8c Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 10:51:33 +0100
Subject: [PATCH 075/172] Add CI config for parallellized and economical
 nf-test runs, ripped from nf-test docs

---
 .github/workflows/nf-test.yml | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 .github/workflows/nf-test.yml

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
new file mode 100644
index 00000000..cf8def06
--- /dev/null
+++ b/.github/workflows/nf-test.yml
@@ -0,0 +1,34 @@
+name: nf-test
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        shard: [1, 2, 3, 4]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up JDK 11
+        uses: actions/setup-java@v2
+        with:
+          java-version: '11'
+          distribution: 'adopt'
+
+      - name: Setup Nextflow latest-edge
+        uses: nf-core/setup-nextflow@v1
+        with:
+          version: "latest-edge"
+
+      - name: Install nf-test
+        run: |
+          wget -qO- https://get.nf-test.com | bash
+          sudo mv nf-test /usr/local/bin/
+
+      - name: Run Tests (Shard ${{ matrix.shard }}/${{ strategy.job-total }})
+        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }} --changed-since HEAD^

From 389c50b615846b7ba5133ef93e27ce04009ba83d Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 10:53:07 +0100
Subject: [PATCH 076/172] Add nf-test config to trigger full test on changes to
 critical files

---
 .nf-test.config | 5 +++++
 1 file changed, 5 insertions(+)
 create mode 100644 .nf-test.config

diff --git a/.nf-test.config b/.nf-test.config
new file mode 100644
index 00000000..359a8b5f
--- /dev/null
+++ b/.nf-test.config
@@ -0,0 +1,5 @@
+config {
+    ...
+    triggers 'nextflow.config', 'nf-test.config', 'test-data/**/*'
+    ...
+}

From 38b0e4564aba0f3f2817e26a0edf721bbbce38d5 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 10:57:02 +0100
Subject: [PATCH 077/172] prettier lint

---
 .github/workflows/nf-test.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
index cf8def06..d7e81844 100644
--- a/.github/workflows/nf-test.yml
+++ b/.github/workflows/nf-test.yml
@@ -17,8 +17,8 @@ jobs:
       - name: Set up JDK 11
         uses: actions/setup-java@v2
         with:
-          java-version: '11'
-          distribution: 'adopt'
+          java-version: "11"
+          distribution: "adopt"
 
       - name: Setup Nextflow latest-edge
         uses: nf-core/setup-nextflow@v1

From b452763ce87231b509300193cb4911ab2ad2f9aa Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 11:00:58 +0100
Subject: [PATCH 078/172] Bump changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b0b12de1..c682d313 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 
 ### `Fixed`
 

From f0b23a78de7ac4df475a28c0af2aad8030ef67c4 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 11:14:00 +0100
Subject: [PATCH 079/172] Hack ideas

---
 workflows/seqinspector.nf | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index a0e9d900..20bec7a8 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -46,15 +46,23 @@ workflow SEQINSPECTOR {
 
     Channel.fromPath(params.config_fastq_screen)
         .splitText()
-    .filter // TODO anything that doesn't have "database"
+        .filter(!it.contains('database')) // TODO anything that doesn't have "database"
         .collect()
+        .view()
 
-    file(list_of_configs)
-    // TODO write configs to text file?
+    if(params.database_tar.endsWith('.tar.gz')) {
+        UNTAR (
+            params.database_tar,
+        )
+        ch_database = UNTAR.out.untar
+    } else {
+        ch_database = params.database_tar
+    }
 
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,
-        Channel.fromPath(params.config_fastq_screen)
+        Channel.fromPath(params.config_fastq_screen),
+        ch_database,
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())

From 89ca390fb2a947d0cffe25215b4ec49125a6f347 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 10:34:45 +0000
Subject: [PATCH 080/172] Add modules testdata base path to test config and
 trim out resource limits

---
 tests/nextflow.config | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/tests/nextflow.config b/tests/nextflow.config
index 8d9ef461..1e56f44d 100644
--- a/tests/nextflow.config
+++ b/tests/nextflow.config
@@ -8,14 +8,8 @@ params {
     config_profile_name        = 'nf-test profile'
     config_profile_description = 'Configuration profile to use for nf-test.'
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '3.GB'
-    max_time   = '2.h'
-
     pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
+    modules_testdata_base_path   = 's3://ngi-igenomes/testdata/nf-core/modules/'
 
     validationSchemaIgnoreParams = 'genomes,igenomes_base,pipelines_testdata_base_path'
-
-
 }

From 3ea8d8b73e97f8e38ee5ae500ef8cc3c2f53567d Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 11:36:11 +0100
Subject: [PATCH 081/172] Initial datasheet example

---
 assets/databasesheet.csv | 9 +++++++++
 1 file changed, 9 insertions(+)
 create mode 100644 assets/databasesheet.csv

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
new file mode 100644
index 00000000..9923e8d8
--- /dev/null
+++ b/assets/databasesheet.csv
@@ -0,0 +1,9 @@
+name,index,aligner
+Ecoli,./database/EB1,BOWTIE2
+Ecoli,s3://ngi-igenomes/database/EB1,BOWTIE2
+## M. tuberculosis (igenomes/Mycobacterium_tuberculosis_H37RV/Ensembl/H37Rv.EB1)
+Tuberculosis,./references/genome_tuberculosis/genome,BOWTIE2
+## PhiX (/igenomes/PhiX/Illumina/RTA)
+PhiX,../../../modules/nf-core/fastqscreen/references/genome_phix/genome,BOWTIE2
+##S. cerevisiae (igenomes/Saccharomyces_cerevisiae/Ensembl/EF4)
+Scerevisiae,../../../modules/nf-core/fastqscreen/references/genome_cerevisiae/genome,BOWTIE2

From fea850fff822a6baa47d6ad62137c6d28ccd769e Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 11:44:19 +0100
Subject: [PATCH 082/172] refactor: Rework fastqscreen with new ideas

---
 assets/databasesheet.csv                      |  9 +----
 assets/schema_database.json                   | 32 +++++++++++++++
 conf/test.config                              |  1 +
 main.nf                                       |  7 +++-
 modules.json                                  |  3 +-
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 40 +++++++++++++++++++
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 13 +++---
 workflows/seqinspector.nf                     | 23 ++++-------
 8 files changed, 96 insertions(+), 32 deletions(-)
 create mode 100644 assets/schema_database.json
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index 9923e8d8..f300a046 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,9 +1,2 @@
 name,index,aligner
-Ecoli,./database/EB1,BOWTIE2
-Ecoli,s3://ngi-igenomes/database/EB1,BOWTIE2
-## M. tuberculosis (igenomes/Mycobacterium_tuberculosis_H37RV/Ensembl/H37Rv.EB1)
-Tuberculosis,./references/genome_tuberculosis/genome,BOWTIE2
-## PhiX (/igenomes/PhiX/Illumina/RTA)
-PhiX,../../../modules/nf-core/fastqscreen/references/genome_phix/genome,BOWTIE2
-##S. cerevisiae (igenomes/Saccharomyces_cerevisiae/Ensembl/EF4)
-Scerevisiae,../../../modules/nf-core/fastqscreen/references/genome_cerevisiae/genome,BOWTIE2
+PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,BOWTIE2
diff --git a/assets/schema_database.json b/assets/schema_database.json
new file mode 100644
index 00000000..df54284e
--- /dev/null
+++ b/assets/schema_database.json
@@ -0,0 +1,32 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/seqinspector/master/assets/schema_database.json",
+    "title": "nf-core/seqinspector pipeline - params.databasesheet schema",
+    "description": "Schema for the file provided with params.databasesheet",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "name": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "The database name for fastq screen",
+                "meta": ["database_name"]
+            },
+            "index": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+$",
+                "errorMessage": "Path to the aligner index"
+            },
+            "aligner": {
+                "type": "string",
+                "enum": ["BOWTIE", "BOWTIE2", "BWA", "MINIMAP2"],
+                "errorMessage": "Specify the aligner to use for the mapping. Valid arguments are 'bowtie', bowtie2' (default), 'bwa' or 'minimap2'.",
+                "meta": ["database_notes"]
+            }
+        },
+        "required": ["name", "index", "aligner"]
+    }
+}
diff --git a/conf/test.config b/conf/test.config
index 76a7ad03..c0324318 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -26,6 +26,7 @@ params {
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
+    database_sheet = "${projectDir}/assets/databasesheet.csv"
 
     // Genome references
     genome = 'R64-1-1'
diff --git a/main.nf b/main.nf
index 85027a4b..79e8a33d 100644
--- a/main.nf
+++ b/main.nf
@@ -44,6 +44,7 @@ workflow NFCORE_SEQINSPECTOR {
 
     take:
     samplesheet // channel: samplesheet read in from --input
+    database_sheet
 
     main:
 
@@ -51,7 +52,8 @@ workflow NFCORE_SEQINSPECTOR {
     // WORKFLOW: Run pipeline
     //
     SEQINSPECTOR (
-        samplesheet
+        samplesheet,
+        database_sheet,
     )
     emit:
     global_report   = SEQINSPECTOR.out.global_report    // channel: /path/to/multiqc_report.html
@@ -83,7 +85,8 @@ workflow {
     // WORKFLOW: Run main workflow
     //
     NFCORE_SEQINSPECTOR (
-        PIPELINE_INITIALISATION.out.samplesheet
+        PIPELINE_INITIALISATION.out.samplesheet,
+        params.database_sheet,
     )
     //
     // SUBWORKFLOW: Run completion tasks
diff --git a/modules.json b/modules.json
index f8b48550..cb48bc3d 100644
--- a/modules.json
+++ b/modules.json
@@ -13,7 +13,8 @@
                     "fastqscreen/fastqscreen": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff"
                     },
                     "multiqc": {
                         "branch": "master",
diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
new file mode 100644
index 00000000..e8ff52e0
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -0,0 +1,40 @@
+Changes in module 'nf-core/fastqscreen/fastqscreen'
+'modules/nf-core/fastqscreen/fastqscreen/environment.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
+Changes in 'fastqscreen/fastqscreen/main.nf':
+--- modules/nf-core/fastqscreen/fastqscreen/main.nf
++++ modules/nf-core/fastqscreen/fastqscreen/main.nf
+@@ -9,7 +9,7 @@
+ 
+     input:
+     tuple val(meta), path(reads)  // .fastq files
+-    path database
++    tuple val(meta), path(database) // [[database_name,  database_notes], database_path]
+ 
+     output:
+     tuple val(meta), path("*.txt")     , emit: txt
+@@ -24,11 +24,14 @@
+     script:
+     def prefix = task.ext.prefix ?: "${meta.id}"
+     def args = task.ext.args ?: ""
++    // 'Database name','Genome path and basename','Notes'
++    """
++    fastq_screen --add_genome \\
++        '$meta.database_name','$database_path','$meta.database_notes'
+ 
+-    """
+-    fastq_screen --threads ${task.cpus} \\
+-        --aligner bowtie2 \\
+-        --conf ${database}/fastq_screen.conf \\
++    fastq_screen
++        --conf fastq_screen.conf \\
++        --threads ${task.cpus} \\
+         $reads \\
+         $args \\
+ 
+
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
+************************************************************
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 88c4e5c5..0106e6e8 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -9,7 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     tuple val(meta), path(reads)  // .fastq files
-    path database
+    tuple val(meta), path(database) // [[database_name,  database_notes], database_path]
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -24,11 +24,14 @@ process FASTQSCREEN_FASTQSCREEN {
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
-
+    // 'Database name','Genome path and basename','Notes'
     """
-    fastq_screen --threads ${task.cpus} \\
-        --aligner bowtie2 \\
-        --conf ${database}/fastq_screen.conf \\
+    fastq_screen --add_genome \\
+        '$meta.database_name','$database_path','$meta.database_notes'
+
+    fastq_screen
+        --conf fastq_screen.conf \\
+        --threads ${task.cpus} \\
         $reads \\
         $args \\
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 20bec7a8..d283c2ac 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -1,3 +1,5 @@
+include { samplesheetToList } from 'plugin/nf-schema'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS
@@ -24,6 +26,8 @@ workflow SEQINSPECTOR {
 
     take:
     ch_samplesheet // channel: samplesheet read in from --input
+    ch_databasesheet // channel: database sheet read in from --database_sheet
+
     main:
 
     ch_versions            = Channel.empty()
@@ -43,26 +47,13 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run FastQ Screen
     //
-
-    Channel.fromPath(params.config_fastq_screen)
-        .splitText()
-        .filter(!it.contains('database')) // TODO anything that doesn't have "database"
-        .collect()
+    ch_databases = Channel
+        .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
         .view()
 
-    if(params.database_tar.endsWith('.tar.gz')) {
-        UNTAR (
-            params.database_tar,
-        )
-        ch_database = UNTAR.out.untar
-    } else {
-        ch_database = params.database_tar
-    }
-
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,
-        Channel.fromPath(params.config_fastq_screen),
-        ch_database,
+        ch_databases,
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())

From afb2a61fc15b1f0cbefb3aa72b3e58f25b18b6f8 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 11:14:12 +0000
Subject: [PATCH 083/172] back to the past

---
 workflows/seqinspector.nf | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index a89bd5c5..972b2f31 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -36,18 +36,16 @@ workflow SEQINSPECTOR {
     // MODULE: Run Seqkit sample to perform subsampling
     //
     if (params.sample_size > 0 ) {
-        ch_sample_sized = ch_samplesheet.join(
-            SEQTK_SAMPLE(
-                ch_samplesheet.map {
-                    meta, reads -> [meta, reads, params.sample_size]
-                }
-            ).reads, by: [0]
-        )
+        ch_sample_sized = SEQTK_SAMPLE(
+            ch_samplesheet.map {
+                meta, reads -> [meta, reads, params.sample_size]
+            }
+        ).reads
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
     } else {
         // No do subsample
         ch_sample_sized = ch_samplesheet.map {
-            meta, reads -> [meta, reads, []]
+            meta, reads -> [meta, reads]
         }
     }
 
@@ -56,7 +54,7 @@ workflow SEQINSPECTOR {
     //
     FASTQC (
         ch_sample_sized.map {
-            meta, reads, subsampled -> [meta, reads]
+            meta, subsampled -> [meta, subsampled]
         }
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)

From 600c2fb4d8e6150fe6111f55f5f9321d9fde4f26 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 12:20:59 +0100
Subject: [PATCH 084/172] chore: Bump fastq-screen

---
 modules/nf-core/fastqscreen/fastqscreen/environment.yml | 8 +++++++-
 modules/nf-core/fastqscreen/fastqscreen/main.nf         | 4 ++--
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/environment.yml b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
index c63c61e2..7d4c8922 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/environment.yml
+++ b/modules/nf-core/fastqscreen/fastqscreen/environment.yml
@@ -4,5 +4,11 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::fastq-screen=0.15.3"
+  - bioconda::fastq-screen=0.16.0
   - bioconda::perl-gdgraph=1.54
+  # - gzip
+  # - SAMtools
+  # - bowtie
+  # - bowtie2
+  # - bwa
+  # - bismark
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 0106e6e8..c792707e 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -4,8 +4,8 @@ process FASTQSCREEN_FASTQSCREEN {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
-        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/fc/fc53eee7ca23c32220a9662fbb63c67769756544b6d74a1ee85cf439ea79a7ee/data' :
+        'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
 
     input:
     tuple val(meta), path(reads)  // .fastq files

From 89e67fa7534c2654e4a43e81953e1ba611c17df9 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 13:00:00 +0100
Subject: [PATCH 085/172] fix: Give up on fastq_screen writing it's own config

---
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 12 +++++++-----
 workflows/seqinspector.nf                       |  1 -
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index c792707e..771c6acf 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -1,5 +1,5 @@
 process FASTQSCREEN_FASTQSCREEN {
-    tag "$meta.id"
+    tag "$meta.id | $meta2.database_name"
     label 'process_medium'
 
     conda "${moduleDir}/environment.yml"
@@ -9,7 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     tuple val(meta), path(reads)  // .fastq files
-    tuple val(meta), path(database) // [[database_name,  database_notes], database_path]
+    tuple val(meta2), path(database) // [[database_name,  database_notes], database_path]
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -26,12 +26,14 @@ process FASTQSCREEN_FASTQSCREEN {
     def args = task.ext.args ?: ""
     // 'Database name','Genome path and basename','Notes'
     """
-    fastq_screen --add_genome \\
-        '$meta.database_name','$database_path','$meta.database_notes'
+    echo "Writing config"
+    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
+    echo "Wrote config"
 
-    fastq_screen
+    fastq_screen \\
         --conf fastq_screen.conf \\
         --threads ${task.cpus} \\
+        --aligner ${meta2.database_notes.toLowerCase()} \\
         $reads \\
         $args \\
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index d283c2ac..ad6dc2cb 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -49,7 +49,6 @@ workflow SEQINSPECTOR {
     //
     ch_databases = Channel
         .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
-        .view()
 
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,

From 80e49aa4ca09ea17483a7df007e6416fe868c13c Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 13:35:36 +0000
Subject: [PATCH 086/172] update README

---
 README.md                 | 5 +++--
 workflows/seqinspector.nf | 6 ++----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index f647af08..6cf36dcc 100644
--- a/README.md
+++ b/README.md
@@ -31,8 +31,9 @@
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Subsample reads ([`Seqtk`](https://github.com/lh3/seqtk))
+2. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
+3. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## Usage
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 972b2f31..2fbb2348 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -33,7 +33,7 @@ workflow SEQINSPECTOR {
     ch_multiqc_reports     = Channel.empty()
 
     //
-    // MODULE: Run Seqkit sample to perform subsampling
+    // MODULE: Run Seqtk sample to perform subsampling
     //
     if (params.sample_size > 0 ) {
         ch_sample_sized = SEQTK_SAMPLE(
@@ -44,9 +44,7 @@ workflow SEQINSPECTOR {
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
     } else {
         // No do subsample
-        ch_sample_sized = ch_samplesheet.map {
-            meta, reads -> [meta, reads]
-        }
+        ch_sample_sized = ch_samplesheet
     }
 
     //

From a6565f78155c4fae14031af4a9d2a6afe72b111b Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 13:05:42 +0100
Subject: [PATCH 087/172] test: Update databases

---
 assets/databasesheet.csv                        | 2 ++
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index f300a046..150f8318 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,2 +1,4 @@
 name,index,aligner
+Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,BOWTIE2
 PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,BOWTIE2
+Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,BOWTIE2
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 771c6acf..eab5afb1 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -35,7 +35,7 @@ process FASTQSCREEN_FASTQSCREEN {
         --threads ${task.cpus} \\
         --aligner ${meta2.database_notes.toLowerCase()} \\
         $reads \\
-        $args \\
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

From 4af6dd4bf344612bc92ffa7ae34a8952740ed46e Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 14:32:09 +0100
Subject: [PATCH 088/172] fix: Run every sample and every DB

---
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 4 ++--
 workflows/seqinspector.nf                       | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index eab5afb1..5037db6a 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -8,8 +8,8 @@ process FASTQSCREEN_FASTQSCREEN {
         'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
 
     input:
-    tuple val(meta), path(reads)  // .fastq files
-    tuple val(meta2), path(database) // [[database_name,  database_notes], database_path]
+    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
+    tuple val(meta), path(reads), val(meta2), path(database)
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ad6dc2cb..75ea2d6c 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -51,8 +51,7 @@ workflow SEQINSPECTOR {
         .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
 
     FASTQSCREEN_FASTQSCREEN (
-        ch_samplesheet,
-        ch_databases,
+        ch_samplesheet.combine(ch_databases)
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())

From 34437348868aa0f4f7aa18424f35738903987a94 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 13:39:41 +0000
Subject: [PATCH 089/172] nf-core subworkflows update to apply fix

---
 modules.json                                           |  4 ++--
 .../tests/main.workflow.nf.test                        | 10 ++++++----
 .../nf-core/utils_nfschema_plugin/tests/main.nf.test   |  4 ++--
 workflows/seqinspector.nf                              |  4 ++--
 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/modules.json b/modules.json
index 8e632d50..a27c7506 100644
--- a/modules.json
+++ b/modules.json
@@ -21,7 +21,7 @@
                 "nf-core": {
                     "utils_nextflow_pipeline": {
                         "branch": "master",
-                        "git_sha": "3aa0aec1d52d492fe241919f0c6100ebf0074082",
+                        "git_sha": "56372688d8979092cafbe0c5c3895b491166ca1c",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nfcore_pipeline": {
@@ -31,7 +31,7 @@
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
-                        "git_sha": "bbd5a41f4535a8defafe6080e00ea74c45f4f96c",
+                        "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
                         "installed_by": ["subworkflows"]
                     }
                 }
diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
index ca964ce8..02dbf094 100644
--- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
+++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test
@@ -52,10 +52,12 @@ nextflow_workflow {
         }
 
         then {
-            assertAll(
-                { assert workflow.success },
-                { assert workflow.stdout.contains("nextflow_workflow v9.9.9") }
-            )
+            expect {
+                with(workflow) {
+                    assert success
+                    assert "nextflow_workflow v9.9.9" in stdout
+                }
+            }
         }
     }
 
diff --git a/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
index 842dc432..8fb30164 100644
--- a/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
+++ b/subworkflows/nf-core/utils_nfschema_plugin/tests/main.nf.test
@@ -42,7 +42,7 @@ nextflow_workflow {
 
             params {
                 test_data   = ''
-                outdir      = 1
+                outdir      = null
             }
 
             workflow {
@@ -94,7 +94,7 @@ nextflow_workflow {
 
             params {
                 test_data   = ''
-                outdir      = 1
+                outdir      = null
             }
 
             workflow {
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ea628117..d1fb2891 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -138,9 +138,9 @@ workflow SEQINSPECTOR {
     )
 
     emit:
-    global_report = MULTIQC_GLOBAL.out.report.toList()      // channel: /path/to/multiqc_report.html
+    global_report   = MULTIQC_GLOBAL.out.report.toList()    // channel: /path/to/multiqc_report.html
     grouped_reports = MULTIQC_PER_TAG.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
-    versions       = ch_versions                            // channel: [ path(versions.yml) ]
+    versions        = ch_versions                           // channel: [ path(versions.yml) ]
 }
 
 /*

From ee42aa9b0a5de78419451666b571e8d3575c2498 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 13:43:56 +0000
Subject: [PATCH 090/172] simplify CI, always run

---
 .github/workflows/nf-test.yml | 4 +---
 .nf-test.config               | 5 -----
 2 files changed, 1 insertion(+), 8 deletions(-)
 delete mode 100644 .nf-test.config

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
index d7e81844..b6276bfd 100644
--- a/.github/workflows/nf-test.yml
+++ b/.github/workflows/nf-test.yml
@@ -11,8 +11,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Set up JDK 11
         uses: actions/setup-java@v2
@@ -31,4 +29,4 @@ jobs:
           sudo mv nf-test /usr/local/bin/
 
       - name: Run Tests (Shard ${{ matrix.shard }}/${{ strategy.job-total }})
-        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }} --changed-since HEAD^
+        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }}
diff --git a/.nf-test.config b/.nf-test.config
deleted file mode 100644
index 359a8b5f..00000000
--- a/.nf-test.config
+++ /dev/null
@@ -1,5 +0,0 @@
-config {
-    ...
-    triggers 'nextflow.config', 'nf-test.config', 'test-data/**/*'
-    ...
-}

From 47053765d465c663e4e90c7d2dff8f745a54cd28 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 13:48:10 +0000
Subject: [PATCH 091/172] try specifying cwd as arg in nf-test command

---
 .github/workflows/nf-test.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
index b6276bfd..b0d7b8e8 100644
--- a/.github/workflows/nf-test.yml
+++ b/.github/workflows/nf-test.yml
@@ -29,4 +29,4 @@ jobs:
           sudo mv nf-test /usr/local/bin/
 
       - name: Run Tests (Shard ${{ matrix.shard }}/${{ strategy.job-total }})
-        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }}
+        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }} .

From 3b2949609c67489610ebbfce498529ccb8842cdc Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Tue, 29 Oct 2024 14:09:35 +0000
Subject: [PATCH 092/172] add module config

---
 conf/modules.config                           |  4 ++++
 tests/NovaSeq6000.main_subsample.nf.test.snap | 22 +++++++++----------
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index c8838224..d3c597b3 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -18,6 +18,10 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    withName: SEQTK_SAMPLE {
+        ext.args = '-s100'
+    }
+
     withName: FASTQC {
         ext.args = '--quiet'
     }
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index ee118c94..27277ff0 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -2,30 +2,30 @@
     "NovaSeq6000 data test sample size": {
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
-            "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
+            "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
+            "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
-            "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
+            "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
+            "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
-            "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
+            "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
+            "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
-            "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
+            "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
+            "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
-            "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
-            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
+            "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
+            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
             "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686"
         ],
         "meta": {
             "nf-test": "0.9.1",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-29T09:15:03.224117679"
+        "timestamp": "2024-10-29T13:44:43.105472321"
     }
 }
\ No newline at end of file

From a5cb4c4abbec27fa27f10da79f7e3e224b97fddb Mon Sep 17 00:00:00 2001
From: ctuni <c.tuni.dominguez@gmail.com>
Date: Tue, 29 Oct 2024 15:23:39 +0100
Subject: [PATCH 093/172] added seqfu stats

---
 modules.json                                  |  5 ++
 modules/nf-core/seqfu/stats/environment.yml   |  7 ++
 modules/nf-core/seqfu/stats/main.nf           | 51 +++++++++++++
 modules/nf-core/seqfu/stats/meta.yml          | 60 +++++++++++++++
 .../nf-core/seqfu/stats/tests/main.nf.test    | 75 +++++++++++++++++++
 .../seqfu/stats/tests/main.nf.test.snap       | 56 ++++++++++++++
 modules/nf-core/seqfu/stats/tests/tags.yml    |  2 +
 workflows/seqinspector.nf                     | 11 +++
 8 files changed, 267 insertions(+)
 create mode 100644 modules/nf-core/seqfu/stats/environment.yml
 create mode 100644 modules/nf-core/seqfu/stats/main.nf
 create mode 100644 modules/nf-core/seqfu/stats/meta.yml
 create mode 100644 modules/nf-core/seqfu/stats/tests/main.nf.test
 create mode 100644 modules/nf-core/seqfu/stats/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/seqfu/stats/tests/tags.yml

diff --git a/modules.json b/modules.json
index 8e632d50..ae745d1d 100644
--- a/modules.json
+++ b/modules.json
@@ -14,6 +14,11 @@
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
                         "installed_by": ["modules"]
+                    },
+                    "seqfu/stats": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
                     }
                 }
             },
diff --git a/modules/nf-core/seqfu/stats/environment.yml b/modules/nf-core/seqfu/stats/environment.yml
new file mode 100644
index 00000000..8fa07dfc
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::seqfu=1.20.3"
diff --git a/modules/nf-core/seqfu/stats/main.nf b/modules/nf-core/seqfu/stats/main.nf
new file mode 100644
index 00000000..0f8bb3e2
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/main.nf
@@ -0,0 +1,51 @@
+process SEQFU_STATS {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqfu:1.20.3--h1eb128b_0':
+        'biocontainers/seqfu:1.20.3--h1eb128b_0' }"
+
+
+    input:
+    // stats can get one or more fasta or fastq files
+    tuple val(meta), path(files)
+
+    output:
+    tuple val(meta), path("*.tsv")    ,  emit: stats
+    tuple val(meta), path("*_mqc.txt"), emit: multiqc
+    path "versions.yml"               ,  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    seqfu \\
+        stats \\
+        $args \\
+        --multiqc ${prefix}_mqc.txt \\
+        $files > ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqfu: \$(seqfu version)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_mqc.txt
+    seqfu stats ${prefix}_mqc.txt > ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqfu: \$(samtools --version |& sed '1!d ; s/samtools //')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/seqfu/stats/meta.yml b/modules/nf-core/seqfu/stats/meta.yml
new file mode 100644
index 00000000..f534a3f5
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/meta.yml
@@ -0,0 +1,60 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "seqfu_stats"
+description: Statistics for FASTA or FASTQ files
+keywords:
+  - seqfu
+  - stats
+  - n50
+tools:
+  - "seqfu":
+      description: "Cross-platform compiled suite of tools to manipulate and inspect
+        FASTA and FASTQ files"
+      homepage: "https://telatin.github.io/seqfu2/"
+      documentation: "https://telatin.github.io/seqfu2/"
+      tool_dev_url: "https://github.com/telatin/seqfu2"
+      doi: "10.3390/bioengineering8050059"
+      licence: ["GPL v3"]
+      identifier: biotools:seqfu
+
+input:
+  # Only when we have meta
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - files:
+        type: file
+        description: One or more FASTA or FASTQ files
+        pattern: "*.{fasta,fastq,fasta.gz,fastq.gz,fq,fq.gz}"
+output:
+  #Only when we have meta
+  - stats:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.tsv":
+          type: file
+          description: Tab-separated output file with basic sequence statistics.
+          pattern: "*.{tsv}"
+  - multiqc:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*_mqc.txt":
+          type: file
+          description: MultiQC ready table
+          pattern: "*.{_mqc.txt}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@telatin"
+maintainers:
+  - "@telatin"
diff --git a/modules/nf-core/seqfu/stats/tests/main.nf.test b/modules/nf-core/seqfu/stats/tests/main.nf.test
new file mode 100644
index 00000000..b889b2bb
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/tests/main.nf.test
@@ -0,0 +1,75 @@
+nextflow_process {
+
+    name "Test Process SEQFU_STATS"
+    script "../main.nf"
+    process "SEQFU_STATS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "seqfu"
+    tag "seqfu/stats"
+
+    
+    test("seqfu stats - faa") {
+        // test with 1 FAA file (with  multiple sequences of different length)
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], 
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.stats },
+                { assert process.out.multiqc },
+                { assert process.out.stats.size() == 1 },
+                { assert snapshot(process.out.versions).match("versions-single") },
+                { assert snapshot(process.out.stats).match("stats-single") },
+                { assert path(process.out.stats.get(0).get(1)).md5 == "26141ef87ad8a6f59a6f283cc0a06fda" }
+            )
+        }
+
+    }
+
+    test("seqfu stats - multiple files") {
+        // test feeding a mix of files including compressed
+        when {
+            process {
+                """
+                input[0] = [
+                            [ id:'test' ],
+                            [
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true),
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.gz', checkIfExists: true),
+                                file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                            ]
+                        ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.stats },
+                { assert process.out.multiqc },
+                { assert process.out.stats.size() == 1 },
+                { assert path(process.out.versions[0]).readLines()[1].contains('.') },
+                { assert snapshot(process.out.stats).match("stats-multi") },
+                { assert snapshot(process.out.stats).md5().match("multi-lines") },
+                { assert path(process.out.stats[0][1]).readLines()[0] ==  'File\t#Seq\tTotal bp\tAvg\tN50\tN75\tN90\tauN\tMin\tMax' },
+                { assert path(process.out.multiqc[0][1]).readLines().join('\n').contains('genome.fasta') },
+                { assert path(process.out.multiqc[0][1]).readLines().join('\n').contains('proteome.fasta') }              
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/seqfu/stats/tests/main.nf.test.snap b/modules/nf-core/seqfu/stats/tests/main.nf.test.snap
new file mode 100644
index 00000000..8049c827
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/tests/main.nf.test.snap
@@ -0,0 +1,56 @@
+{
+    "versions-single": {
+        "content": [
+            [
+                "versions.yml:md5,fd11b4665f68f22e7ad4c646ad3c56cd"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-19T20:21:50.896221522"
+    },
+    "multi-lines": {
+        "content": "d5ab14ce74939f856edc64c6a8d250d3",
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-19T20:22:03.775940585"
+    },
+    "stats-single": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.tsv:md5,26141ef87ad8a6f59a6f283cc0a06fda"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-19T20:21:50.937732021"
+    },
+    "stats-multi": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.tsv:md5,98102573ecf7e3b9e53db1c6e0f02b06"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-19T20:22:03.681146614"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/seqfu/stats/tests/tags.yml b/modules/nf-core/seqfu/stats/tests/tags.yml
new file mode 100644
index 00000000..2685ed43
--- /dev/null
+++ b/modules/nf-core/seqfu/stats/tests/tags.yml
@@ -0,0 +1,2 @@
+seqfu/stats:
+  - "modules/nf-core/seqfu/stats/**"
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ea628117..53ceb0d0 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -4,6 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
+include { SEQFU_STATS                   } from '../modules/nf-core/seqfu/stats'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
@@ -39,6 +40,16 @@ workflow SEQINSPECTOR {
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
+
+    //
+    // Module: Run SeqFu stats
+    //
+    SEQFU_STATS (
+        ch_samplesheet
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
+    ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+
     //
     // Collate and save software versions
     //

From 222a986914543fde7cdedf891c20bfe85320f787 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 14:34:32 +0000
Subject: [PATCH 094/172] harmonize syntax and correct comment

---
 workflows/seqinspector.nf | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index d1fb2891..ab6cda41 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -87,10 +87,10 @@ workflow SEQINSPECTOR {
             .mix(ch_multiqc_extra_files)
             .collect(),
         ch_multiqc_config.toList(),
-        Channel.empty().toList(),
+        [],
         ch_multiqc_logo.toList(),
-        Channel.empty().toList(),
-        Channel.empty().toList()
+        [],
+        []
     )
 
     ch_tags = ch_multiqc_files
@@ -138,7 +138,7 @@ workflow SEQINSPECTOR {
     )
 
     emit:
-    global_report   = MULTIQC_GLOBAL.out.report.toList()    // channel: /path/to/multiqc_report.html
+    global_report   = MULTIQC_GLOBAL.out.report.toList()    // channel: [ /path/to/multiqc_report.html ]
     grouped_reports = MULTIQC_PER_TAG.out.report.toList()   // channel: [ /path/to/multiqc_report.html ]
     versions        = ch_versions                           // channel: [ path(versions.yml) ]
 }

From 69825df5aa0763953398bcca78fe9ba86699ff3f Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 29 Oct 2024 14:42:03 +0000
Subject: [PATCH 095/172] remove multiqc versions file from snapshot assertion,
 will fail if tests run on different nextflow versions

---
 tests/MiSeq.main.nf.test            | 1 -
 tests/MiSeq.main.nf.test.snap       | 5 ++---
 tests/NovaSeq6000.main.nf.test      | 5 -----
 tests/NovaSeq6000.main.nf.test.snap | 9 ++-------
 tests/PromethION.main.nf.test       | 1 -
 tests/PromethION.main.nf.test.snap  | 5 ++---
 6 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index 8fbff4a3..246a05a5 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -21,7 +21,6 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 }
             )
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 4613d525..0742b5a8 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -3,8 +3,7 @@
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
-            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf"
         ],
         "meta": {
             "nf-test": "0.9.0",
@@ -12,4 +11,4 @@
         },
         "timestamp": "2024-10-28T13:18:10.3675973"
     }
-}
\ No newline at end of file
+}
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index d050399e..e24637cd 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -21,27 +21,22 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 },
             )
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index ee3c22b7..fc38ac52 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,23 +4,18 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
-            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a"
         ],
         "meta": {
             "nf-test": "0.9.0",
@@ -28,4 +23,4 @@
         },
         "timestamp": "2024-10-28T13:19:13.226135825"
     }
-}
\ No newline at end of file
+}
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index 8fec8b33..ad6fe6d0 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -21,7 +21,6 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 },
             )
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 026a8cd2..875673c0 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -3,8 +3,7 @@
         "content": [
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
-            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
-            "multiqc_software_versions.txt:md5,a3698a2d32e8695c38d50e3d17de5fe3"
+            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32"
         ],
         "meta": {
             "nf-test": "0.9.0",
@@ -12,4 +11,4 @@
         },
         "timestamp": "2024-10-28T13:19:57.261730412"
     }
-}
\ No newline at end of file
+}

From dfbb354dc0c0f9aeef8046f5a52c3129a2a04bbe Mon Sep 17 00:00:00 2001
From: ctuni <c.tuni.dominguez@gmail.com>
Date: Tue, 29 Oct 2024 15:43:59 +0100
Subject: [PATCH 096/172] citations, usage, output, etc

---
 CHANGELOG.md   |  1 +
 CITATIONS.md   |  4 ++++
 docs/output.md | 14 ++++++++++++++
 3 files changed, 19 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b0b12de1..fb229c2b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#56](https://github.com/nf-core/seqinspector/pull/56) Added SeqFu stats module.
 
 ### `Fixed`
 
diff --git a/CITATIONS.md b/CITATIONS.md
index ecbfb16e..b5b796eb 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -14,6 +14,10 @@
 
 > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
+- [SeqFu](https://telatin.github.io/seqfu2/)
+
+> Telatin A, Fariselli P, Birolo G. SeqFu: A Suite of Utilities for the Robust and Reproducible Manipulation of Sequence Files. Bioengineering 2021, 8, 59. doi.org/10.3390/bioengineering8050059
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
diff --git a/docs/output.md b/docs/output.md
index e14c3ad6..1937c179 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -11,6 +11,7 @@ The directories listed below will be created in the results directory after the
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
 - [FastQC](#fastqc) - Raw read QC
+- [SeqFu Stats](#seqfu_stats) - Statistics for FASTA or FASTQ files
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -27,6 +28,19 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
+#### SeqFu Stats
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `seqfu/`
+  - `*.tsv`: Tab-separated file containing quality metrics.
+  - `*_mqc.txt`: File containing the same quality metrics as the TSV file, ready to be read by MultiQC.
+
+</details>
+
+[SeqFu](https://telatin.github.io/seqfu2/) is general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files. Includes functions to interleave and de-interleave FASTQ files, to rename sequences and to count and print statistics on sequence lengths. In this pipeline, the `seqfu stats` module is used to produce general quality metrics statistics.
+
 ### MultiQC
 
 nf-core/seqinspector will generate the following MultiQC reports:

From 46805e871bcd352f949d49df7f8eeaab1475d291 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 13:00:00 +0100
Subject: [PATCH 097/172] fix: Give up on fastq_screen writing it's own config

---
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 51 +++++++++++++++----
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 14 ++---
 workflows/seqinspector.nf                     |  1 -
 3 files changed, 50 insertions(+), 16 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index e8ff52e0..e2f8a54d 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -1,37 +1,70 @@
 Changes in module 'nf-core/fastqscreen/fastqscreen'
-'modules/nf-core/fastqscreen/fastqscreen/environment.yml' is unchanged
+Changes in 'fastqscreen/fastqscreen/environment.yml':
+--- modules/nf-core/fastqscreen/fastqscreen/environment.yml
++++ modules/nf-core/fastqscreen/fastqscreen/environment.yml
+@@ -4,5 +4,11 @@
+   - conda-forge
+   - bioconda
+ dependencies:
+-  - "bioconda::fastq-screen=0.15.3"
++  - bioconda::fastq-screen=0.16.0
+   - bioconda::perl-gdgraph=1.54
++  # - gzip
++  # - SAMtools
++  # - bowtie
++  # - bowtie2
++  # - bwa
++  # - bismark
+
 'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
 Changes in 'fastqscreen/fastqscreen/main.nf':
 --- modules/nf-core/fastqscreen/fastqscreen/main.nf
 +++ modules/nf-core/fastqscreen/fastqscreen/main.nf
-@@ -9,7 +9,7 @@
+@@ -1,15 +1,15 @@
+ process FASTQSCREEN_FASTQSCREEN {
+-    tag "$meta.id"
++    tag "$meta.id | $meta2.database_name"
+     label 'process_medium'
+ 
+     conda "${moduleDir}/environment.yml"
+     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+-        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
+-        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
++        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/fc/fc53eee7ca23c32220a9662fbb63c67769756544b6d74a1ee85cf439ea79a7ee/data' :
++        'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
  
      input:
-     tuple val(meta), path(reads)  // .fastq files
+-    tuple val(meta), path(reads)  // .fastq files
 -    path database
-+    tuple val(meta), path(database) // [[database_name,  database_notes], database_path]
++    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
++    tuple val(meta), path(reads), val(meta2), path(database)
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,11 +24,14 @@
+@@ -24,13 +24,18 @@
      script:
      def prefix = task.ext.prefix ?: "${meta.id}"
      def args = task.ext.args ?: ""
 +    // 'Database name','Genome path and basename','Notes'
 +    """
-+    fastq_screen --add_genome \\
-+        '$meta.database_name','$database_path','$meta.database_notes'
++    echo "Writing config"
++    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
++    echo "Wrote config"
  
 -    """
 -    fastq_screen --threads ${task.cpus} \\
 -        --aligner bowtie2 \\
 -        --conf ${database}/fastq_screen.conf \\
-+    fastq_screen
++    fastq_screen \\
 +        --conf fastq_screen.conf \\
 +        --threads ${task.cpus} \\
++        --aligner ${meta2.database_notes.toLowerCase()} \\
          $reads \\
-         $args \\
+-        $args \\
++        $args
  
+     cat <<-END_VERSIONS > versions.yml
+     "${task.process}":
 
 'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index c792707e..eab5afb1 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -1,5 +1,5 @@
 process FASTQSCREEN_FASTQSCREEN {
-    tag "$meta.id"
+    tag "$meta.id | $meta2.database_name"
     label 'process_medium'
 
     conda "${moduleDir}/environment.yml"
@@ -9,7 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     tuple val(meta), path(reads)  // .fastq files
-    tuple val(meta), path(database) // [[database_name,  database_notes], database_path]
+    tuple val(meta2), path(database) // [[database_name,  database_notes], database_path]
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -26,14 +26,16 @@ process FASTQSCREEN_FASTQSCREEN {
     def args = task.ext.args ?: ""
     // 'Database name','Genome path and basename','Notes'
     """
-    fastq_screen --add_genome \\
-        '$meta.database_name','$database_path','$meta.database_notes'
+    echo "Writing config"
+    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
+    echo "Wrote config"
 
-    fastq_screen
+    fastq_screen \\
         --conf fastq_screen.conf \\
         --threads ${task.cpus} \\
+        --aligner ${meta2.database_notes.toLowerCase()} \\
         $reads \\
-        $args \\
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index d283c2ac..ad6dc2cb 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -49,7 +49,6 @@ workflow SEQINSPECTOR {
     //
     ch_databases = Channel
         .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
-        .view()
 
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,

From 4001a50caae62121dc8778cc88dc7a596d8a2242 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 13:05:42 +0100
Subject: [PATCH 098/172] test: Update databases

---
 assets/databasesheet.csv | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index f300a046..150f8318 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,2 +1,4 @@
 name,index,aligner
+Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,BOWTIE2
 PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,BOWTIE2
+Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,BOWTIE2

From 7ebb6c144666ae62c2071a3e4c56ef7a4f70004b Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Tue, 29 Oct 2024 14:32:09 +0100
Subject: [PATCH 099/172] fix: Run every sample and every DB

---
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 4 ++--
 workflows/seqinspector.nf                       | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index eab5afb1..5037db6a 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -8,8 +8,8 @@ process FASTQSCREEN_FASTQSCREEN {
         'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
 
     input:
-    tuple val(meta), path(reads)  // .fastq files
-    tuple val(meta2), path(database) // [[database_name,  database_notes], database_path]
+    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
+    tuple val(meta), path(reads), val(meta2), path(database)
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ad6dc2cb..75ea2d6c 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -51,8 +51,7 @@ workflow SEQINSPECTOR {
         .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
 
     FASTQSCREEN_FASTQSCREEN (
-        ch_samplesheet,
-        ch_databases,
+        ch_samplesheet.combine(ch_databases)
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())

From 0445a9e6854be9fd13032d1cfd33091c2c55a828 Mon Sep 17 00:00:00 2001
From: matrulda <matilda.aslin@medsci.uu.se>
Date: Wed, 30 Oct 2024 08:15:54 +0100
Subject: [PATCH 100/172] Update CONTRIBUTION regarding displaying tool results

---
 .github/CONTRIBUTING.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
index 4bcb559a..ed49905d 100644
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -82,6 +82,12 @@ If you wish to contribute a new step, please use the following coding standards:
 9. Update MultiQC config `assets/multiqc_config.yml` so relevant suffixes, file name clean up and module plots are in the appropriate order. If applicable, add a [MultiQC](https://https://multiqc.info/) module.
 10. Add a description of the output files and if relevant any appropriate images from the MultiQC report to `docs/output.md`.
 
+### Things to consider regarding displaying results for a new tool
+
+- If a MultiQC module exist for the tool, use the standard settings for it to start with.
+- If no Multiqc module exists, the results of the tool should be made available in the results directory.
+- If a tool doesn’t produce output files, the stdout should be channeled into a output file that can be accessible from the outdir of the pipeline.
+
 ### Default values
 
 Parameters should be initialised / defined with default values in `nextflow.config` under the `params` scope.

From 1e0530409ea728223d9d34b32047e2d360e2d862 Mon Sep 17 00:00:00 2001
From: matrulda <matilda.aslin@medsci.uu.se>
Date: Wed, 30 Oct 2024 08:25:32 +0100
Subject: [PATCH 101/172] Updated Changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index c682d313..73a4af01 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -13,6 +13,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
+- [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools
 
 ### `Fixed`
 

From 1dadfaa7b445f0b65a08ca0ebe583b12e8e99d97 Mon Sep 17 00:00:00 2001
From: matrulda <matilda.aslin@medsci.uu.se>
Date: Wed, 30 Oct 2024 09:59:43 +0100
Subject: [PATCH 102/172] Ignore files_unchanged for CONTRIBUTION.md

---
 .nf-core.yml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.nf-core.yml b/.nf-core.yml
index fb856008..3765b89d 100644
--- a/.nf-core.yml
+++ b/.nf-core.yml
@@ -1,5 +1,7 @@
 bump_version: null
-lint: null
+lint:
+  files_unchanged:
+    - .github/CONTRIBUTING.md
 nf_core_version: 3.0.2
 org_path: null
 repository_type: pipeline

From 88fa0dcedfe8d5411a01a54c5e9a093aa2d52048 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Wed, 30 Oct 2024 09:26:52 +0000
Subject: [PATCH 103/172] fix test

---
 tests/NovaSeq6000.main_subsample.nf.test      | 1 -
 tests/NovaSeq6000.main_subsample.nf.test.snap | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/tests/NovaSeq6000.main_subsample.nf.test b/tests/NovaSeq6000.main_subsample.nf.test
index 72851f91..efdc574f 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test
+++ b/tests/NovaSeq6000.main_subsample.nf.test
@@ -21,7 +21,6 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index fdb7c8c4..8e9ada04 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -4,7 +4,6 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
             "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
-            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
@@ -26,6 +25,6 @@
             "nf-test": "0.9.1",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-30T09:11:23.734754433"
+        "timestamp": "2024-10-30T09:25:16.689719475"
     }
 }
\ No newline at end of file

From 5079047a7adf95729591a3f52b3771ff7c01a1e3 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Wed, 30 Oct 2024 09:38:34 +0000
Subject: [PATCH 104/172] add citation

---
 CITATIONS.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/CITATIONS.md b/CITATIONS.md
index ecbfb16e..8a4e350b 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -18,6 +18,8 @@
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [Seqtk](https://github.com/lh3/seqtk)
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

From 5a0a3e8c2e5d565f4d0b8ec1200d2f5ede017e67 Mon Sep 17 00:00:00 2001
From: ngarcia <natalia.garcia@nanoporetech.com>
Date: Wed, 30 Oct 2024 09:38:51 +0000
Subject: [PATCH 105/172] fix test

---
 tests/NovaSeq6000.main_subsample.nf.test      | 4 ----
 tests/NovaSeq6000.main_subsample.nf.test.snap | 8 ++------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/tests/NovaSeq6000.main_subsample.nf.test b/tests/NovaSeq6000.main_subsample.nf.test
index efdc574f..fe2b0685 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test
+++ b/tests/NovaSeq6000.main_subsample.nf.test
@@ -25,22 +25,18 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_software_versions.txt"),
 
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_software_versions.txt"),
                     ).match()
                 },
             )
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index 8e9ada04..651973b1 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -7,24 +7,20 @@
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
-            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
             "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
-            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
             "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
-            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686",
             "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
-            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
-            "multiqc_software_versions.txt:md5,b7d1ca14785a9361f0a39ce1b6a02686"
+            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012"
         ],
         "meta": {
             "nf-test": "0.9.1",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-30T09:25:16.689719475"
+        "timestamp": "2024-10-30T09:37:46.182191597"
     }
 }
\ No newline at end of file

From ad3d278412e2b101f8bd7f78106c4588968ceb66 Mon Sep 17 00:00:00 2001
From: ctuni <c.tuni.dominguez@gmail.com>
Date: Wed, 30 Oct 2024 11:20:57 +0100
Subject: [PATCH 106/172] added seqfu config

---
 conf/modules.config | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/conf/modules.config b/conf/modules.config
index c8838224..e1f0350b 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -22,6 +22,15 @@ process {
         ext.args = '--quiet'
     }
 
+    withName: 'SEQFU_STATS' {
+        ext.args   = ''
+        publishDir = [
+            path: { "${params.outdir}/seqfu_stats" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

From e56018190e120c3d39acc3c255ee5039b3db0f6e Mon Sep 17 00:00:00 2001
From: FranBonath <franziska.bonath@scilifelab.se>
Date: Wed, 30 Oct 2024 12:02:01 +0100
Subject: [PATCH 107/172] adding fastqscreen database parameter, updating docs

---
 CHANGELOG.md                |  1 +
 CITATIONS.md                |  4 ++++
 assets/schema_database.json |  4 ++--
 docs/output.md              | 17 +++++++++++++++++
 main.nf                     |  2 +-
 nextflow.config             |  3 +++
 nextflow_schema.json        |  9 ++++++++-
 workflows/seqinspector.nf   |  4 ++--
 8 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b0b12de1..e396512f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#53](https://github.com/nf-core/seqinspector/pull/53) Add FastQ-Screen database multiplexing
 
 ### `Fixed`
 
diff --git a/CITATIONS.md b/CITATIONS.md
index ecbfb16e..9cbd9f80 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -14,6 +14,10 @@
 
 > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
+- [Fastqscreen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/)
+
+> Wingett SW and Andrews S. FastQ Screen: A tool for multi-genome mapping and quality control [version 2; referees: 4 approved]. F1000Research 2018, 7:1338 (https://doi.org/10.12688/f1000research.15931.2)
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
diff --git a/assets/schema_database.json b/assets/schema_database.json
index df54284e..e735ea42 100644
--- a/assets/schema_database.json
+++ b/assets/schema_database.json
@@ -1,8 +1,8 @@
 {
     "$schema": "https://json-schema.org/draft/2020-12/schema",
     "$id": "https://raw.githubusercontent.com/nf-core/seqinspector/master/assets/schema_database.json",
-    "title": "nf-core/seqinspector pipeline - params.databasesheet schema",
-    "description": "Schema for the file provided with params.databasesheet",
+    "title": "nf-core/seqinspector pipeline - params.fastqscreen_databasesheet schema",
+    "description": "Schema for the file provided with params.fastq_screen_databasesheet",
     "type": "array",
     "items": {
         "type": "object",
diff --git a/docs/output.md b/docs/output.md
index e14c3ad6..337037d2 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -11,6 +11,7 @@ The directories listed below will be created in the results directory after the
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
 - [FastQC](#fastqc) - Raw read QC
+- [Fastqscreen](#fastqscreen) - mapping against a set of references for basic contamination QC
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -27,6 +28,22 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
+### FASTQSCREEN
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `fastqc/`
+  - `*_screen.html`: Interactive graphical fastqscreen report which summaries the mapping of your sequences against each of your libraries.
+  - `*_screen.pdf`: Static graphical fastqscreen report which summaries the mapping of your sequences against each of your libraries.
+  - `*_screen.txt` : text based fastqscreen report which summaries the mapping of your sequences against each of your libraries.
+
+</details>
+
+[Fastqscreen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/) allows you to set up a standard set of libraries against which all of your sequences can be searched. Your search libraries might contain the genomes of all of the organisms you work on, along with PhiX, Vectors or other contaminants commonly seen in sequencing experiments.
+
+It requires the supply of referenced (databases) in a config file. In order to parallelize the mapping of the different samples, in seqinspector, this a fastqscreen config file is generated for every sample/reference combination.
+
 ### MultiQC
 
 nf-core/seqinspector will generate the following MultiQC reports:
diff --git a/main.nf b/main.nf
index 79e8a33d..cd4af962 100644
--- a/main.nf
+++ b/main.nf
@@ -86,7 +86,7 @@ workflow {
     //
     NFCORE_SEQINSPECTOR (
         PIPELINE_INITIALISATION.out.samplesheet,
-        params.database_sheet,
+        params.fastqscreen_database_sheet,
     )
     //
     // SUBWORKFLOW: Run completion tasks
diff --git a/nextflow.config b/nextflow.config
index 1600a70b..42372b9e 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -20,6 +20,9 @@ params {
     config_fastq_screen        = "${projectDir}/conf"
     igenomes_ignore            = false
 
+    // Fastqscreen options
+    fastqscreen_database_sheet = './assets/databasesheet.csv'
+
     // MultiQC options
     multiqc_config             = null
     multiqc_title              = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index f18a5f19..8331a2e4 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -68,7 +68,8 @@
                 "config_fastq_screen": {
                     "type": "string",
                     "description": "path to directory with fastq_screen config (fastq_screen.conf)",
-                    "fa_icon": "fas fa-braille"
+                    "fa_icon": "fas fa-braille",
+                    "default": "/Users/franziska.franziska/workspace/seqinspector/conf"
                 },
                 "igenomes_ignore": {
                     "type": "boolean",
@@ -84,6 +85,12 @@
                     "fa_icon": "fas fa-ban",
                     "hidden": true,
                     "default": "s3://ngi-igenomes/igenomes/"
+                },
+                "fastqscreen_database_sheet": {
+                    "type": "string",
+                    "default": "./assets/databasesheet.csv",
+                    "fa_icon": "fas fa-search",
+                    "description": "list of reference genomes (databases) to be mapped against in fastqscreen"
                 }
             }
         },
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 75ea2d6c..535448dd 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -26,7 +26,7 @@ workflow SEQINSPECTOR {
 
     take:
     ch_samplesheet // channel: samplesheet read in from --input
-    ch_databasesheet // channel: database sheet read in from --database_sheet
+    ch_fastqscreen_databasesheet // channel: database sheet read in from --fastqscreen_database_sheet
 
     main:
 
@@ -48,7 +48,7 @@ workflow SEQINSPECTOR {
     // MODULE: Run FastQ Screen
     //
     ch_databases = Channel
-        .fromList(samplesheetToList(ch_databasesheet, "${projectDir}/assets/schema_database.json"))
+        .fromList(samplesheetToList(ch_fastqscreen_databasesheet, "${projectDir}/assets/schema_database.json"))
 
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet.combine(ch_databases)

From effa9c9d1b886f1b3e79e2ad8cff4c79b8ce4f16 Mon Sep 17 00:00:00 2001
From: Franziska Bonath <41994400+FranBonath@users.noreply.github.com>
Date: Thu, 7 Nov 2024 10:43:32 +0100
Subject: [PATCH 108/172] remove absolute path of fastqscreen config

---
 nextflow_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 8331a2e4..ba1304e5 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -69,7 +69,7 @@
                     "type": "string",
                     "description": "path to directory with fastq_screen config (fastq_screen.conf)",
                     "fa_icon": "fas fa-braille",
-                    "default": "/Users/franziska.franziska/workspace/seqinspector/conf"
+                    "default": "./conf"
                 },
                 "igenomes_ignore": {
                     "type": "boolean",

From a2f2dfc50c4952ea5a67b4399f751203a7db12dc Mon Sep 17 00:00:00 2001
From: Franziska Bonath <41994400+FranBonath@users.noreply.github.com>
Date: Thu, 7 Nov 2024 10:47:53 +0100
Subject: [PATCH 109/172] remove "projectDir" from path for fastqscreen config
 in nextflow.config

---
 nextflow.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow.config b/nextflow.config
index 42372b9e..791764c5 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -17,7 +17,7 @@ params {
     genome                     = null
     fasta                      = null
     igenomes_base              = 's3://ngi-igenomes/igenomes/'
-    config_fastq_screen        = "${projectDir}/conf"
+    config_fastq_screen        = "./conf"
     igenomes_ignore            = false
 
     // Fastqscreen options

From 2c4432061c578b90b42db70b253fb115e3114437 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:03:05 +0000
Subject: [PATCH 110/172] remove conf/fastq_screen.conf and it's references, as
 the file is built by the process on the fly

---
 conf/fastq_screen.conf | 64 ------------------------------------------
 nextflow.config        |  1 -
 nextflow_schema.json   |  6 ----
 3 files changed, 71 deletions(-)
 delete mode 100644 conf/fastq_screen.conf

diff --git a/conf/fastq_screen.conf b/conf/fastq_screen.conf
deleted file mode 100644
index f170f285..00000000
--- a/conf/fastq_screen.conf
+++ /dev/null
@@ -1,64 +0,0 @@
-# This is a configuration file for fastq_screen
-
-###########
-## Bowtie #
-###########
-## If the bowtie binary is not in your PATH then you can
-## set this value to tell the program where to find it.
-## Uncomment the line below and set the appropriate location
-##
-
-#BOWTIE2 /sw/data/uppnex/reference/sw/mf/bioinfo-tools/pipelines/bowtie2/2.1.0/bowtie2
-
-############
-## Threads #
-############
-## Bowtie can be made to run across multiple CPU cores to
-## speed up your searches. Set this value to the number
-## of cores you want to use for your searches.
-
-#THREADS                16
-
-##############
-## Databases #
-##############
-## This section allows you to configure multiple databases
-## to search against in your screen.  For each database
-## you need to provide a database name (which can't contain
-## spaces) and the location of the bowtie indices which
-## you created for that database.
-##
-## The default entries shown below are only suggested examples
-## you can add as many DATABASE sections as you like, and you
-## can comment out or remove as many of the existing entries
-## as you like.
-##
-## Either the original bowtie or bowtie 2 may be used for the
-## mapping. Specify the aligner to use with the command line
-## flag --aligner with arguments 'bowtie' (default) or
-## 'bowtie2'.
-##
-## The configuration file may list paths to both bowtie and
-## bowtie2 indices, which are specified with either 'BOWTIE'
-## or 'BOWTIE2' after the path (leaving unspecified will
-## default to bowtie). While the configuration file may list
-## paths to both bowtie and bowtie2 indices, only one aligner
-## will be used for the mapping, as specified by the --aligner
-## flag.
-##
-## For example:
-## DATABASE     Human_Bowtie    /data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37 BOWTIE
-## DATABASE     Human_Bowtie    /data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37
-## DATABASE     Human_Bowtie2   /data/public/Genomes/Human_Bowtie2/GRCh37/Homo_sapiens.GRCh37 BOWTIE2
-
-## E. coli (igenomes/Escherichia_coli_K_12_DH10B/Ensembl/EB1)
-DATABASE    Ecoli   ./database/EB1 BOWTIE2
-
-## M. tuberculosis (igenomes/Mycobacterium_tuberculosis_H37RV/Ensembl/H37Rv.EB1)
-DATABASE    Tuberculosis   ./references/genome_tuberculosis/genome BOWTIE2
-
-## PhiX (/igenomes/PhiX/Illumina/RTA)
-DATABASE    PhiX   ../../../modules/nf-core/fastqscreen/references/genome_phix/genome BOWTIE2
-
-##S. cerevisiae (igenomes/Saccharomyces_cerevisiae/Ensembl/EF4)
-DATABASE    Scerevisiae   ../../../modules/nf-core/fastqscreen/references/genome_cerevisiae/genome BOWTIE2
diff --git a/nextflow.config b/nextflow.config
index 0c7668c9..9b9a8bd4 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -17,7 +17,6 @@ params {
     genome                     = null
     fasta                      = null
     igenomes_base              = 's3://ngi-igenomes/igenomes/'
-    config_fastq_screen        = "./conf"
     igenomes_ignore            = false
 
     // Fastqscreen options
diff --git a/nextflow_schema.json b/nextflow_schema.json
index b464e2a6..b320d2be 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -72,12 +72,6 @@
                     "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
                     "fa_icon": "far fa-file-code"
                 },
-                "config_fastq_screen": {
-                    "type": "string",
-                    "description": "path to directory with fastq_screen config (fastq_screen.conf)",
-                    "fa_icon": "fas fa-braille",
-                    "default": "./conf"
-                },
                 "igenomes_ignore": {
                     "type": "boolean",
                     "description": "Do not load the iGenomes reference config.",

From fedeab2f55efaa5fc01687e398d6f43f84818977 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:03:40 +0000
Subject: [PATCH 111/172] remove diff dump, I don't see why it should be here

---
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 73 -------------------
 1 file changed, 73 deletions(-)
 delete mode 100644 modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
deleted file mode 100644
index e2f8a54d..00000000
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ /dev/null
@@ -1,73 +0,0 @@
-Changes in module 'nf-core/fastqscreen/fastqscreen'
-Changes in 'fastqscreen/fastqscreen/environment.yml':
---- modules/nf-core/fastqscreen/fastqscreen/environment.yml
-+++ modules/nf-core/fastqscreen/fastqscreen/environment.yml
-@@ -4,5 +4,11 @@
-   - conda-forge
-   - bioconda
- dependencies:
--  - "bioconda::fastq-screen=0.15.3"
-+  - bioconda::fastq-screen=0.16.0
-   - bioconda::perl-gdgraph=1.54
-+  # - gzip
-+  # - SAMtools
-+  # - bowtie
-+  # - bowtie2
-+  # - bwa
-+  # - bismark
-
-'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
-Changes in 'fastqscreen/fastqscreen/main.nf':
---- modules/nf-core/fastqscreen/fastqscreen/main.nf
-+++ modules/nf-core/fastqscreen/fastqscreen/main.nf
-@@ -1,15 +1,15 @@
- process FASTQSCREEN_FASTQSCREEN {
--    tag "$meta.id"
-+    tag "$meta.id | $meta2.database_name"
-     label 'process_medium'
- 
-     conda "${moduleDir}/environment.yml"
-     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
--        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
--        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
-+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/fc/fc53eee7ca23c32220a9662fbb63c67769756544b6d74a1ee85cf439ea79a7ee/data' :
-+        'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
- 
-     input:
--    tuple val(meta), path(reads)  // .fastq files
--    path database
-+    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
-+    tuple val(meta), path(reads), val(meta2), path(database)
- 
-     output:
-     tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,13 +24,18 @@
-     script:
-     def prefix = task.ext.prefix ?: "${meta.id}"
-     def args = task.ext.args ?: ""
-+    // 'Database name','Genome path and basename','Notes'
-+    """
-+    echo "Writing config"
-+    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
-+    echo "Wrote config"
- 
--    """
--    fastq_screen --threads ${task.cpus} \\
--        --aligner bowtie2 \\
--        --conf ${database}/fastq_screen.conf \\
-+    fastq_screen \\
-+        --conf fastq_screen.conf \\
-+        --threads ${task.cpus} \\
-+        --aligner ${meta2.database_notes.toLowerCase()} \\
-         $reads \\
--        $args \\
-+        $args
- 
-     cat <<-END_VERSIONS > versions.yml
-     "${task.process}":
-
-'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
-************************************************************

From 588ad1d41dfd8d42d09b05123c805605d6dd9521 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:05:16 +0000
Subject: [PATCH 112/172] spacing

---
 workflows/seqinspector.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 54974dc7..fe8e99df 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -27,7 +27,7 @@ include { methodsDescriptionText        } from '../subworkflows/local/utils_nfco
 workflow SEQINSPECTOR {
 
     take:
-    ch_samplesheet // channel: samplesheet read in from --input
+    ch_samplesheet               // channel: samplesheet read in from --input
     ch_fastqscreen_databasesheet // channel: database sheet read in from --fastqscreen_database_sheet
 
     main:

From 2001ccdda102520266db3c991ed0b5d247bce0f6 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:21:06 +0000
Subject: [PATCH 113/172] Revert remove diff dump, now I see why it should be
 here :)

---
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 73 +++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100644 modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
new file mode 100644
index 00000000..e2f8a54d
--- /dev/null
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -0,0 +1,73 @@
+Changes in module 'nf-core/fastqscreen/fastqscreen'
+Changes in 'fastqscreen/fastqscreen/environment.yml':
+--- modules/nf-core/fastqscreen/fastqscreen/environment.yml
++++ modules/nf-core/fastqscreen/fastqscreen/environment.yml
+@@ -4,5 +4,11 @@
+   - conda-forge
+   - bioconda
+ dependencies:
+-  - "bioconda::fastq-screen=0.15.3"
++  - bioconda::fastq-screen=0.16.0
+   - bioconda::perl-gdgraph=1.54
++  # - gzip
++  # - SAMtools
++  # - bowtie
++  # - bowtie2
++  # - bwa
++  # - bismark
+
+'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
+Changes in 'fastqscreen/fastqscreen/main.nf':
+--- modules/nf-core/fastqscreen/fastqscreen/main.nf
++++ modules/nf-core/fastqscreen/fastqscreen/main.nf
+@@ -1,15 +1,15 @@
+ process FASTQSCREEN_FASTQSCREEN {
+-    tag "$meta.id"
++    tag "$meta.id | $meta2.database_name"
+     label 'process_medium'
+ 
+     conda "${moduleDir}/environment.yml"
+     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+-        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
+-        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
++        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/fc/fc53eee7ca23c32220a9662fbb63c67769756544b6d74a1ee85cf439ea79a7ee/data' :
++        'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
+ 
+     input:
+-    tuple val(meta), path(reads)  // .fastq files
+-    path database
++    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
++    tuple val(meta), path(reads), val(meta2), path(database)
+ 
+     output:
+     tuple val(meta), path("*.txt")     , emit: txt
+@@ -24,13 +24,18 @@
+     script:
+     def prefix = task.ext.prefix ?: "${meta.id}"
+     def args = task.ext.args ?: ""
++    // 'Database name','Genome path and basename','Notes'
++    """
++    echo "Writing config"
++    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
++    echo "Wrote config"
+ 
+-    """
+-    fastq_screen --threads ${task.cpus} \\
+-        --aligner bowtie2 \\
+-        --conf ${database}/fastq_screen.conf \\
++    fastq_screen \\
++        --conf fastq_screen.conf \\
++        --threads ${task.cpus} \\
++        --aligner ${meta2.database_notes.toLowerCase()} \\
+         $reads \\
+-        $args \\
++        $args
+ 
+     cat <<-END_VERSIONS > versions.yml
+     "${task.process}":
+
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
+************************************************************

From 5bb8dfdead84a2a7f471b40ae1a2a8dd17dc039a Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:31:04 +0000
Subject: [PATCH 114/172] fix faulty params var name in test config

---
 conf/test.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/conf/test.config b/conf/test.config
index c0324318..1a6f84b4 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -26,7 +26,7 @@ params {
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
-    database_sheet = "${projectDir}/assets/databasesheet.csv"
+    fastqscreen_database_sheet = "${projectDir}/assets/databasesheet.csv"
 
     // Genome references
     genome = 'R64-1-1'

From 3baa7fc7d1ff871bc71612c28c0a30a2f140a004 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:37:41 +0000
Subject: [PATCH 115/172] update snapshots for new multiqc citations

---
 tests/MiSeq.main.nf.test.snap                 |  8 ++++----
 tests/NovaSeq6000.main.nf.test.snap           | 16 ++++++++--------
 tests/NovaSeq6000.main_subsample.nf.test.snap | 16 ++++++++--------
 tests/PromethION.main.nf.test.snap            |  8 ++++----
 4 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index de0afa29..1dc646e5 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -1,14 +1,14 @@
 {
     "MiSeq data test": {
         "content": [
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
             "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf"
         ],
         "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-10-30T09:08:29.692511055"
+        "timestamp": "2024-11-07T12:32:20.523618752"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 62ccd4aa..823926fb 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -1,26 +1,26 @@
 {
     "NovaSeq6000 data test": {
         "content": [
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
             "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a"
         ],
         "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-10-30T09:09:57.158871165"
+        "timestamp": "2024-11-07T12:33:47.150820885"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index 651973b1..024fa662 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -1,26 +1,26 @@
 {
     "NovaSeq6000 data test sample size": {
         "content": [
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
             "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
             "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
             "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
             "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012"
         ],
         "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-10-30T09:37:46.182191597"
+        "timestamp": "2024-11-07T12:35:00.745830145"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index dfa4eb6f..24a77664 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -1,14 +1,14 @@
 {
     "PromethION data test": {
         "content": [
-            "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
             "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32"
         ],
         "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.0"
         },
-        "timestamp": "2024-10-30T09:12:03.048502046"
+        "timestamp": "2024-11-07T12:35:46.010641114"
     }
 }
\ No newline at end of file

From 843e2c62a6a1429797c80b72b73e4075400138bb Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 12:53:19 +0000
Subject: [PATCH 116/172] module tests of fastqscreen are dependent on
 non-installed modules, so try to limit the scope of nf-test to the tests/ dir

---
 .github/workflows/nf-test.yml | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
index b0d7b8e8..3a2abcbd 100644
--- a/.github/workflows/nf-test.yml
+++ b/.github/workflows/nf-test.yml
@@ -5,9 +5,7 @@ on: [push, pull_request]
 jobs:
   test:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        shard: [1, 2, 3, 4]
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -28,5 +26,5 @@ jobs:
           wget -qO- https://get.nf-test.com | bash
           sudo mv nf-test /usr/local/bin/
 
-      - name: Run Tests (Shard ${{ matrix.shard }}/${{ strategy.job-total }})
-        run: nf-test test --ci --shard ${{ matrix.shard }}/${{ strategy.job-total }} .
+      - name: Run Tests
+        run: nf-test test --ci tests

From 66d08ad14e2d5f8d4eb085fb0300727eda6c7d94 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 13:34:52 +0000
Subject: [PATCH 117/172] Append changelog entry

---
 CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 299e0305..01d94016 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -15,7 +15,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#50](https://github.com/nf-core/seqinspector/pull/50) Add an optional subsampling step.
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 - [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools
-- [#53](https://github.com/nf-core/seqinspector/pull/53) Add FastQ-Screen database multiplexing
+- [#53](https://github.com/nf-core/seqinspector/pull/53) Add FastQ-Screen database multiplexing and limit scope of nf-test in CI.
 
 ### `Fixed`
 

From 9567f475929d83b6b6d8b1fe4b02309d973c300f Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 13:38:26 +0000
Subject: [PATCH 118/172] Check for fastQ Screen files in multiqc report in
 pipeline tests and update snapshots accordingly

---
 tests/MiSeq.main.nf.test                      | 1 +
 tests/MiSeq.main.nf.test.snap                 | 5 +++--
 tests/NovaSeq6000.main.nf.test                | 7 ++++++-
 tests/NovaSeq6000.main.nf.test.snap           | 9 +++++++--
 tests/NovaSeq6000.main_subsample.nf.test      | 5 +++++
 tests/NovaSeq6000.main_subsample.nf.test.snap | 9 +++++++--
 tests/PromethION.main.nf.test                 | 1 +
 tests/PromethION.main.nf.test.snap            | 5 +++--
 8 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index 246a05a5..a1badfac 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -21,6 +21,7 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
                     ).match()
                 }
             )
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 1dc646e5..0e8fec2e 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -3,12 +3,13 @@
         "content": [
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
-            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf"
+            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
+            "multiqc_fastq_screen.txt:md5,88473b5190a4ff3bbe5a1b5b92da2601"
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T12:32:20.523618752"
+        "timestamp": "2024-11-07T13:33:59.180570696"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index e24637cd..06a5cb14 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -21,23 +21,28 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
-                    ).match()
+                                        path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt"),
+                                        ).match()
                 },
             )
         }
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 823926fb..c22361f9 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,23 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
+            "multiqc_fastq_screen.txt:md5,836b01175da79f0de458df899b9751e1",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
+            "multiqc_fastq_screen.txt:md5,fd72aaf00fd4fac3da4ef222608e0c32",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
+            "multiqc_fastq_screen.txt:md5,301fe12a6c6ccd09904c4f759008d416",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
+            "multiqc_fastq_screen.txt:md5,045f5b7623f6abb99b7075734fdb0cf4",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
-            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a"
+            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
+            "multiqc_fastq_screen.txt:md5,ee786f054e356ee005ca33c7558866dc"
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T12:33:47.150820885"
+        "timestamp": "2024-11-07T13:35:28.998292704"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main_subsample.nf.test b/tests/NovaSeq6000.main_subsample.nf.test
index fe2b0685..d006de37 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test
+++ b/tests/NovaSeq6000.main_subsample.nf.test
@@ -21,22 +21,27 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastq_screen.txt"),
 
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt"),
                     ).match()
                 },
             )
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index 024fa662..b3407e2e 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -4,23 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
             "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
+            "multiqc_fastq_screen.txt:md5,2730834c61a9e1349b357ef6a729ddd9",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
+            "multiqc_fastq_screen.txt:md5,a2b7469ab6b81d2872214eeba32933f5",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
             "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
+            "multiqc_fastq_screen.txt:md5,956cb8876c334293186ea213c4c39c6e",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
             "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
+            "multiqc_fastq_screen.txt:md5,81cedab716aa382d7b4db2e42b681cb2",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
-            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012"
+            "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
+            "multiqc_fastq_screen.txt:md5,8bbb1968587dbf3139bac07991a225cb"
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T12:35:00.745830145"
+        "timestamp": "2024-11-07T13:36:43.785887669"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index ad6fe6d0..126a58c1 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -21,6 +21,7 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
                     ).match()
                 },
             )
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 24a77664..17178fdd 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -3,12 +3,13 @@
         "content": [
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
-            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32"
+            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
+            "multiqc_fastq_screen.txt:md5,37efa56cefb899abf506cf7a7fba0d54"
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T12:35:46.010641114"
+        "timestamp": "2024-11-07T13:37:39.008847194"
     }
 }
\ No newline at end of file

From 5248fad891a8687679f8147eaf4041b3d6416109 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 7 Nov 2024 13:54:40 +0000
Subject: [PATCH 119/172] fix indent

---
 tests/NovaSeq6000.main.nf.test | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index 06a5cb14..e70a191c 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -41,8 +41,8 @@ nextflow_pipeline {
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
                     path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
-                                        path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt"),
-                                        ).match()
+                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt"),
+                    ).match()
                 },
             )
         }

From e2a290c25d09b9d4d3871a4cdf57d5fb6385a9e5 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Thu, 14 Nov 2024 11:14:57 -0600
Subject: [PATCH 120/172] fix: Rename fastqscreen files so they're unique

---
 .../fastqscreen/fastqscreen-fastqscreen.diff       |  6 +++++-
 modules/nf-core/fastqscreen/fastqscreen/main.nf    |  4 ++++
 tests/MiSeq.main.nf.test.snap                      |  6 +++---
 tests/NovaSeq6000.main.nf.test.snap                | 14 +++++++-------
 tests/NovaSeq6000.main_subsample.nf.test.snap      | 14 +++++++-------
 tests/PromethION.main.nf.test.snap                 |  6 +++---
 6 files changed, 29 insertions(+), 21 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index e2f8a54d..ad5b6fe0 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -41,7 +41,7 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,13 +24,18 @@
+@@ -24,13 +24,22 @@
      script:
      def prefix = task.ext.prefix ?: "${meta.id}"
      def args = task.ext.args ?: ""
@@ -62,6 +62,10 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
          $reads \\
 -        $args \\
 +        $args
++
++    mv *_screen.txt ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.txt
++    mv *_screen.html ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.html
++    mv *_screen.png ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.png
  
      cat <<-END_VERSIONS > versions.yml
      "${task.process}":
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 5037db6a..c0f98b9e 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -37,6 +37,10 @@ process FASTQSCREEN_FASTQSCREEN {
         $reads \\
         $args
 
+    mv *_screen.txt ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.txt
+    mv *_screen.html ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.html
+    mv *_screen.png ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.png
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 0e8fec2e..9207f882 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
             "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
-            "multiqc_fastq_screen.txt:md5,88473b5190a4ff3bbe5a1b5b92da2601"
+            "multiqc_fastq_screen.txt:md5,435d8c1ac6e237448c9ce38e853ac82e"
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T13:33:59.180570696"
+        "timestamp": "2024-11-14T11:21:34.348023"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index c22361f9..8b0f1366 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,28 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_fastq_screen.txt:md5,836b01175da79f0de458df899b9751e1",
+            "multiqc_fastq_screen.txt:md5,c7b24e20fd157128924384e52eb3405d",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_fastq_screen.txt:md5,fd72aaf00fd4fac3da4ef222608e0c32",
+            "multiqc_fastq_screen.txt:md5,a1e15006994d06a47634ccf07a08df0f",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_fastq_screen.txt:md5,301fe12a6c6ccd09904c4f759008d416",
+            "multiqc_fastq_screen.txt:md5,d4f1cc5396c4f719b1fcaab2470e7d7c",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_fastq_screen.txt:md5,045f5b7623f6abb99b7075734fdb0cf4",
+            "multiqc_fastq_screen.txt:md5,02246ddb4bf5373b157b45eab698cdc8",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
             "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
-            "multiqc_fastq_screen.txt:md5,ee786f054e356ee005ca33c7558866dc"
+            "multiqc_fastq_screen.txt:md5,483995ed26ba25b3217650840b2d82fa"
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T13:35:28.998292704"
+        "timestamp": "2024-11-14T11:22:20.902938"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index b3407e2e..da7ba9a4 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -4,28 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
             "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
-            "multiqc_fastq_screen.txt:md5,2730834c61a9e1349b357ef6a729ddd9",
+            "multiqc_fastq_screen.txt:md5,c7b24e20fd157128924384e52eb3405d",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
-            "multiqc_fastq_screen.txt:md5,a2b7469ab6b81d2872214eeba32933f5",
+            "multiqc_fastq_screen.txt:md5,a1e15006994d06a47634ccf07a08df0f",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
             "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
-            "multiqc_fastq_screen.txt:md5,956cb8876c334293186ea213c4c39c6e",
+            "multiqc_fastq_screen.txt:md5,d4f1cc5396c4f719b1fcaab2470e7d7c",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
             "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
-            "multiqc_fastq_screen.txt:md5,81cedab716aa382d7b4db2e42b681cb2",
+            "multiqc_fastq_screen.txt:md5,02246ddb4bf5373b157b45eab698cdc8",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
             "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
-            "multiqc_fastq_screen.txt:md5,8bbb1968587dbf3139bac07991a225cb"
+            "multiqc_fastq_screen.txt:md5,483995ed26ba25b3217650840b2d82fa"
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T13:36:43.785887669"
+        "timestamp": "2024-11-14T11:23:19.55095"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 17178fdd..74c12f5d 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
             "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
-            "multiqc_fastq_screen.txt:md5,37efa56cefb899abf506cf7a7fba0d54"
+            "multiqc_fastq_screen.txt:md5,2931dcec302d74c378b69a0831363224"
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.0"
         },
-        "timestamp": "2024-11-07T13:37:39.008847194"
+        "timestamp": "2024-11-14T11:23:42.382002"
     }
 }
\ No newline at end of file

From 46d1bfd93a2a622c091bfea1ea908c360919ebbf Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Thu, 14 Nov 2024 12:05:44 -0600
Subject: [PATCH 121/172] fix: collectFile fastqscreen rough draft

---
 workflows/seqinspector.nf | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 307b163f..d9996829 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -83,7 +83,29 @@ workflow SEQINSPECTOR {
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet.combine(ch_databases)
     )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
+    // Group by sample
+    FASTQSCREEN_FASTQSCREEN.out.txt
+        .groupTuple(by: [0])
+        .collectFile(
+            keepHeader: true,
+            skip: 1,
+            newLine: false,
+            storeDir: "${params.outdir}/fastqscreen/",
+        )
+        { meta, file ->
+            filename = "${meta.id}_screen.txt"
+            [filename, file.text]
+        }
+        // TODO Add % Not hit
+        .map { path ->
+            meta = [
+                id:path.getSimpleName(),
+            ]
+            [meta, file(path)]
+        }
+        .set { ch_fastqscreen_clean }
+
+    ch_multiqc_files = ch_multiqc_files.mix(ch_fastqscreen_clean)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
 
     //

From b8c363c9fed1b28cf14738eb0ad675f8d63383d1 Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Thu, 14 Nov 2024 12:10:07 -0600
Subject: [PATCH 122/172] chore: Lock down arity in fastqscreen

---
 .../fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff        | 2 +-
 modules/nf-core/fastqscreen/fastqscreen/main.nf                 | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index ad5b6fe0..df84f5ad 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -37,7 +37,7 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
 -    tuple val(meta), path(reads)  // .fastq files
 -    path database
 +    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
-+    tuple val(meta), path(reads), val(meta2), path(database)
++    tuple val(meta), path(reads, arity: '1..2'), val(meta2), path(database, arity: '1')
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index c0f98b9e..fff1414b 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -9,7 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
-    tuple val(meta), path(reads), val(meta2), path(database)
+    tuple val(meta), path(reads, arity: '1..2'), val(meta2), path(database, arity: '1')
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt

From d021ed012a20107c97103d029159c49e7d5548dc Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Thu, 14 Nov 2024 13:16:41 -0600
Subject: [PATCH 123/172] feat: Getting close to making the config on the head
 node

---
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 20 +++++-----
 workflows/seqinspector.nf                     | 37 +++++++------------
 2 files changed, 23 insertions(+), 34 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index fff1414b..4f2bdf9a 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -1,5 +1,5 @@
 process FASTQSCREEN_FASTQSCREEN {
-    tag "$meta.id | $meta2.database_name"
+    tag "$meta.id"
     label 'process_medium'
 
     conda "${moduleDir}/environment.yml"
@@ -8,8 +8,10 @@ process FASTQSCREEN_FASTQSCREEN {
         'community.wave.seqera.io/library/fastq-screen_perl-gdgraph:5c1786a5d5bc1309'}"
 
     input:
-    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
-    tuple val(meta), path(reads, arity: '1..2'), val(meta2), path(database, arity: '1')
+    tuple val(meta), path(reads, arity: '1..2')
+    path('fastq_screen.conf', arity: '1')
+    path(database, arity:'1..*', name: '*/*')
+
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -25,21 +27,17 @@ process FASTQSCREEN_FASTQSCREEN {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
     // 'Database name','Genome path and basename','Notes'
+    // FIXME? --aligner ${meta2.database_notes.toLowerCase()} \\
     """
-    echo "Writing config"
-    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
-    echo "Wrote config"
-
     fastq_screen \\
         --conf fastq_screen.conf \\
         --threads ${task.cpus} \\
-        --aligner ${meta2.database_notes.toLowerCase()} \\
         $reads \\
         $args
 
-    mv *_screen.txt ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.txt
-    mv *_screen.html ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.html
-    mv *_screen.png ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.png
+    mv *_screen.txt ${prefix}_screen.txt
+    mv *_screen.html ${prefix}_screen.html
+    mv *_screen.png ${prefix}_screen.png
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index d9996829..059bda7a 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -79,33 +79,24 @@ workflow SEQINSPECTOR {
     //
     ch_databases = Channel
         .fromList(samplesheetToList(ch_fastqscreen_databasesheet, "${projectDir}/assets/schema_database.json"))
-
-    FASTQSCREEN_FASTQSCREEN (
-        ch_samplesheet.combine(ch_databases)
-    )
-    // Group by sample
-    FASTQSCREEN_FASTQSCREEN.out.txt
-        .groupTuple(by: [0])
+    ch_fastqscreen_config = ch_databases
         .collectFile(
-            keepHeader: true,
-            skip: 1,
-            newLine: false,
+            newLine: true,
+            name: 'fastq_screen.conf',
             storeDir: "${params.outdir}/fastqscreen/",
         )
-        { meta, file ->
-            filename = "${meta.id}_screen.txt"
-            [filename, file.text]
-        }
-        // TODO Add % Not hit
-        .map { path ->
-            meta = [
-                id:path.getSimpleName(),
-            ]
-            [meta, file(path)]
-        }
-        .set { ch_fastqscreen_clean }
+    {
+        meta, db ->
+        "DATABASE    ${meta.database_name}    ./${db}/genome    ${meta.database_notes}"
+    }
+    ch_database_files = ch_databases.collect { meta, db -> db}
 
-    ch_multiqc_files = ch_multiqc_files.mix(ch_fastqscreen_clean)
+    FASTQSCREEN_FASTQSCREEN (
+        ch_samplesheet,
+        ch_fastqscreen_config,
+        ch_database_files,
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
 
     //

From 4b278bf946476a951c40244722266cb4d21d171e Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 11:57:04 +0000
Subject: [PATCH 124/172] make functional :')

---
 assets/databasesheet.csv                      |  6 ++--
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 31 +++++++++----------
 workflows/seqinspector.nf                     | 26 +++++++---------
 3 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index 150f8318..16d1a3e7 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,4 +1,4 @@
 name,index,aligner
-Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,BOWTIE2
-PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,BOWTIE2
-Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,BOWTIE2
+Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,Bowtie2
+PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,Bowtie2
+Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,Bowtie2
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 4f2bdf9a..6b0a04d4 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -9,9 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     tuple val(meta), path(reads, arity: '1..2')
-    path('fastq_screen.conf', arity: '1')
-    path(database, arity:'1..*', name: '*/*')
-
+    tuple val(ref_names), path(ref_paths, name:"ref*"), val(ref_aligners)
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -26,9 +24,10 @@ process FASTQSCREEN_FASTQSCREEN {
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
-    // 'Database name','Genome path and basename','Notes'
-    // FIXME? --aligner ${meta2.database_notes.toLowerCase()} \\
+    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_paths[i]}/genome ${ref_aligners[i]}" }.join('\n')
     """
+    echo '${config_content}' > fastq_screen.conf
+
     fastq_screen \\
         --conf fastq_screen.conf \\
         --threads ${task.cpus} \\
@@ -39,23 +38,21 @@ process FASTQSCREEN_FASTQSCREEN {
     mv *_screen.html ${prefix}_screen.html
     mv *_screen.png ${prefix}_screen.png
 
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
-    END_VERSIONS
+    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    echo "\\\"${task.process}\\\":" > versions.yml
+    echo "    fastqscreen: \$fastq_screen_version" >> versions.yml
     """
 
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch test_1_screen.html
-    touch test_1_screen.png
-    touch test_1_screen.txt
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
-    END_VERSIONS
+    touch ${prefix}_screen.html
+    touch ${prefix}_screen.png
+    touch ${prefix}_screen.txt
+
+    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    echo "\\\"${task.process}\\\":" > versions.yml
+    echo "    fastqscreen: \$fastq_screen_version" >> versions.yml
     """
 
 }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 059bda7a..a66beced 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -77,24 +77,20 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run FastQ Screen
     //
-    ch_databases = Channel
-        .fromList(samplesheetToList(ch_fastqscreen_databasesheet, "${projectDir}/assets/schema_database.json"))
-    ch_fastqscreen_config = ch_databases
-        .collectFile(
-            newLine: true,
-            name: 'fastq_screen.conf',
-            storeDir: "${params.outdir}/fastqscreen/",
-        )
-    {
-        meta, db ->
-        "DATABASE    ${meta.database_name}    ./${db}/genome    ${meta.database_notes}"
-    }
-    ch_database_files = ch_databases.collect { meta, db -> db}
+
+    // Parse the reference info needed to create a FastQ Screen config file
+    // and transpose it into a tuple containing lists of names, index paths and aligners
+    ch_fastqscreen_refs = Channel
+        .fromPath("${projectDir}/assets/databasesheet.csv")
+        .splitCsv(header: true)
+        .map { row -> tuple(row.name, row.index, row.aligner) }
+        .toList()
+        .transpose()
+        .toList()
 
     FASTQSCREEN_FASTQSCREEN (
         ch_samplesheet,
-        ch_fastqscreen_config,
-        ch_database_files,
+        ch_fastqscreen_refs
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
     ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())

From 63ebd6737455d384065092dda52747a08fbc565e Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 13:46:38 +0000
Subject: [PATCH 125/172] make input mounting more flexible by separating
 mounted dir path from basename of reference / index files therein

---
 assets/databasesheet.csv                        | 8 ++++----
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 4 ++--
 workflows/seqinspector.nf                       | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index 16d1a3e7..31f93a16 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,4 +1,4 @@
-name,index,aligner
-Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,Bowtie2
-PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,Bowtie2
-Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,Bowtie2
+name,dir,basename,aligner
+Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,genome,Bowtie2
+PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,genome,Bowtie2
+Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,genome,Bowtie2
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 6b0a04d4..2eba8390 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -9,7 +9,7 @@ process FASTQSCREEN_FASTQSCREEN {
 
     input:
     tuple val(meta), path(reads, arity: '1..2')
-    tuple val(ref_names), path(ref_paths, name:"ref*"), val(ref_aligners)
+    tuple val(ref_names), path(ref_dirs, name:"ref*"), val(ref_basenames), val(ref_aligners)
 
     output:
     tuple val(meta), path("*.txt")     , emit: txt
@@ -24,7 +24,7 @@ process FASTQSCREEN_FASTQSCREEN {
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
-    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_paths[i]}/genome ${ref_aligners[i]}" }.join('\n')
+    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
     """
     echo '${config_content}' > fastq_screen.conf
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index a66beced..8536a877 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -83,7 +83,7 @@ workflow SEQINSPECTOR {
     ch_fastqscreen_refs = Channel
         .fromPath("${projectDir}/assets/databasesheet.csv")
         .splitCsv(header: true)
-        .map { row -> tuple(row.name, row.index, row.aligner) }
+        .map { row -> tuple(row.name, row.dir, row.basename, row.aligner) }
         .toList()
         .transpose()
         .toList()

From 2608088905388fe77c6a4272a1872219f72d5726 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 14:31:55 +0000
Subject: [PATCH 126/172] successfully use schema validation for fastqscreen
 reference .csv

---
 assets/databasesheet.csv    |  6 +++---
 assets/schema_database.json | 19 +++++++++++--------
 workflows/seqinspector.nf   |  8 +++++---
 3 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/assets/databasesheet.csv b/assets/databasesheet.csv
index 31f93a16..59f0cdf6 100644
--- a/assets/databasesheet.csv
+++ b/assets/databasesheet.csv
@@ -1,4 +1,4 @@
 name,dir,basename,aligner
-Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,genome,Bowtie2
-PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,genome,Bowtie2
-Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,genome,Bowtie2
+Ecoli,s3://ngi-igenomes/igenomes/Escherichia_coli_K_12_MG1655/NCBI/2001-10-15/Sequence/Bowtie2Index/,genome,bowtie2
+PhiX,s3://ngi-igenomes/igenomes/PhiX/Illumina/RTA/Sequence/Bowtie2Index/,genome,bowtie2
+Scerevisiae,s3://ngi-igenomes/igenomes/Saccharomyces_cerevisiae/NCBI/build3.1/Sequence/Bowtie2Index/,genome,bowtie2
diff --git a/assets/schema_database.json b/assets/schema_database.json
index e735ea42..4a796bbc 100644
--- a/assets/schema_database.json
+++ b/assets/schema_database.json
@@ -10,23 +10,26 @@
             "name": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "The database name for fastq screen",
-                "meta": ["database_name"]
+                "errorMessage": "The reference name as referred to by FastQ Screen."
             },
-            "index": {
+            "dir": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
                 "pattern": "^\\S+$",
-                "errorMessage": "Path to the aligner index"
+                "errorMessage": "Path to the dir containing the aligner reference and index. Can be remote."
+            },
+            "basename": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "The shared basename of the reference and index files contained in the dir."
             },
             "aligner": {
                 "type": "string",
-                "enum": ["BOWTIE", "BOWTIE2", "BWA", "MINIMAP2"],
-                "errorMessage": "Specify the aligner to use for the mapping. Valid arguments are 'bowtie', bowtie2' (default), 'bwa' or 'minimap2'.",
-                "meta": ["database_notes"]
+                "enum": ["bowtie", "bowtie2", "bwa", "minimap2"],
+                "errorMessage": "Specify the aligner to use for the mapping. Valid arguments are 'bowtie', bowtie2' (default), 'bwa' or 'minimap2'."
             }
         },
-        "required": ["name", "index", "aligner"]
+        "required": ["name", "dir", "basename", "aligner"]
     }
 }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 8536a877..0d622cc3 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -81,9 +81,11 @@ workflow SEQINSPECTOR {
     // Parse the reference info needed to create a FastQ Screen config file
     // and transpose it into a tuple containing lists of names, index paths and aligners
     ch_fastqscreen_refs = Channel
-        .fromPath("${projectDir}/assets/databasesheet.csv")
-        .splitCsv(header: true)
-        .map { row -> tuple(row.name, row.dir, row.basename, row.aligner) }
+        .fromList(samplesheetToList(
+            "${projectDir}/assets/databasesheet.csv",
+            "${projectDir}/assets/schema_database.json"
+        ))
+        .map { row -> tuple(row[0], row[1], row[2], row[3]) }
         .toList()
         .transpose()
         .toList()

From 4f743e243c571c8d79a2018cf80682a882fea89a Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 14:42:57 +0000
Subject: [PATCH 127/172] remove redundant operator

---
 workflows/seqinspector.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 0d622cc3..4c745f71 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -85,7 +85,6 @@ workflow SEQINSPECTOR {
             "${projectDir}/assets/databasesheet.csv",
             "${projectDir}/assets/schema_database.json"
         ))
-        .map { row -> tuple(row[0], row[1], row[2], row[3]) }
         .toList()
         .transpose()
         .toList()

From 5aeb8d18da74781bfd2b97c3727b95e21cd52336 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 14:46:05 +0000
Subject: [PATCH 128/172] update comment

---
 workflows/seqinspector.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 4c745f71..b2b7f672 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -79,7 +79,7 @@ workflow SEQINSPECTOR {
     //
 
     // Parse the reference info needed to create a FastQ Screen config file
-    // and transpose it into a tuple containing lists of names, index paths and aligners
+    // and transpose it into a tuple containing lists for each property
     ch_fastqscreen_refs = Channel
         .fromList(samplesheetToList(
             "${projectDir}/assets/databasesheet.csv",

From a31a392c209fd302f1aee575feebc0751a9649ff Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 14:59:48 +0000
Subject: [PATCH 129/172] switch to cleaner file and variable names, remove
 fastqscreen .csv as main workflow input

---
 ...tabasesheet.csv => example_fastq_screen_references.csv} | 0
 ...a_database.json => schema_fastq_screen_references.json} | 6 +++---
 conf/test.config                                           | 2 +-
 main.nf                                                    | 7 ++-----
 nextflow.config                                            | 2 +-
 nextflow_schema.json                                       | 6 +++---
 workflows/seqinspector.nf                                  | 6 +++---
 7 files changed, 13 insertions(+), 16 deletions(-)
 rename assets/{databasesheet.csv => example_fastq_screen_references.csv} (100%)
 rename assets/{schema_database.json => schema_fastq_screen_references.json} (89%)

diff --git a/assets/databasesheet.csv b/assets/example_fastq_screen_references.csv
similarity index 100%
rename from assets/databasesheet.csv
rename to assets/example_fastq_screen_references.csv
diff --git a/assets/schema_database.json b/assets/schema_fastq_screen_references.json
similarity index 89%
rename from assets/schema_database.json
rename to assets/schema_fastq_screen_references.json
index 4a796bbc..9a938d99 100644
--- a/assets/schema_database.json
+++ b/assets/schema_fastq_screen_references.json
@@ -1,8 +1,8 @@
 {
     "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "$id": "https://raw.githubusercontent.com/nf-core/seqinspector/master/assets/schema_database.json",
-    "title": "nf-core/seqinspector pipeline - params.fastqscreen_databasesheet schema",
-    "description": "Schema for the file provided with params.fastq_screen_databasesheet",
+    "$id": "https://raw.githubusercontent.com/nf-core/seqinspector/master/assets/schema_fastq_screen_references.json",
+    "title": "nf-core/seqinspector pipeline - params.fastq_screen_references schema",
+    "description": "Schema for the file provided with params.fastq_screen_references",
     "type": "array",
     "items": {
         "type": "object",
diff --git a/conf/test.config b/conf/test.config
index 1a6f84b4..0ebc405a 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -26,7 +26,7 @@ params {
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
-    fastqscreen_database_sheet = "${projectDir}/assets/databasesheet.csv"
+    fastq_screen_references = "${projectDir}/assets/example_fastq_screen_references.csv"
 
     // Genome references
     genome = 'R64-1-1'
diff --git a/main.nf b/main.nf
index cd4af962..85027a4b 100644
--- a/main.nf
+++ b/main.nf
@@ -44,7 +44,6 @@ workflow NFCORE_SEQINSPECTOR {
 
     take:
     samplesheet // channel: samplesheet read in from --input
-    database_sheet
 
     main:
 
@@ -52,8 +51,7 @@ workflow NFCORE_SEQINSPECTOR {
     // WORKFLOW: Run pipeline
     //
     SEQINSPECTOR (
-        samplesheet,
-        database_sheet,
+        samplesheet
     )
     emit:
     global_report   = SEQINSPECTOR.out.global_report    // channel: /path/to/multiqc_report.html
@@ -85,8 +83,7 @@ workflow {
     // WORKFLOW: Run main workflow
     //
     NFCORE_SEQINSPECTOR (
-        PIPELINE_INITIALISATION.out.samplesheet,
-        params.fastqscreen_database_sheet,
+        PIPELINE_INITIALISATION.out.samplesheet
     )
     //
     // SUBWORKFLOW: Run completion tasks
diff --git a/nextflow.config b/nextflow.config
index 9b9a8bd4..5b835a8b 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -20,7 +20,7 @@ params {
     igenomes_ignore            = false
 
     // Fastqscreen options
-    fastqscreen_database_sheet = './assets/databasesheet.csv'
+    fastq_screen_references    = './assets/example_fastq_screen_references.csv'
 
     // MultiQC options
     multiqc_config             = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index b320d2be..722d80bf 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -87,11 +87,11 @@
                     "hidden": true,
                     "default": "s3://ngi-igenomes/igenomes/"
                 },
-                "fastqscreen_database_sheet": {
+                "fastq_screen_references": {
                     "type": "string",
-                    "default": "./assets/databasesheet.csv",
+                    "default": "./assets/example_fastq_screen_references.csv",
                     "fa_icon": "fas fa-search",
-                    "description": "list of reference genomes (databases) to be mapped against in fastqscreen"
+                    "description": "A .csv of reference genomes to be mapped against by FastQ Screen"
                 }
             }
         },
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index b2b7f672..4afff158 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -29,7 +29,6 @@ workflow SEQINSPECTOR {
 
     take:
     ch_samplesheet               // channel: samplesheet read in from --input
-    ch_fastqscreen_databasesheet // channel: database sheet read in from --fastqscreen_database_sheet
 
     main:
 
@@ -80,10 +79,11 @@ workflow SEQINSPECTOR {
 
     // Parse the reference info needed to create a FastQ Screen config file
     // and transpose it into a tuple containing lists for each property
+
     ch_fastqscreen_refs = Channel
         .fromList(samplesheetToList(
-            "${projectDir}/assets/databasesheet.csv",
-            "${projectDir}/assets/schema_database.json"
+            "${projectDir}/assets/example_fastq_screen_references.csv",
+            "${projectDir}/assets/schema_fastq_screen_references.json"
         ))
         .toList()
         .transpose()

From 7396d4ccfd26d573269f32a1592ac20137ccf833 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 15:11:32 +0000
Subject: [PATCH 130/172] update docs

---
 docs/output.md | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/docs/output.md b/docs/output.md
index a2706a8f..dc26159f 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -56,7 +56,16 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [Fastqscreen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/) allows you to set up a standard set of libraries against which all of your sequences can be searched. Your search libraries might contain the genomes of all of the organisms you work on, along with PhiX, Vectors or other contaminants commonly seen in sequencing experiments.
 
-It requires the supply of referenced (databases) in a config file. In order to parallelize the mapping of the different samples, in seqinspector, this a fastqscreen config file is generated for every sample/reference combination.
+It requires a `.csv` detailing:
+
+- the working name of the reference
+- the name of the aligner used to generate its index (which is also the aligner and index used by the tool)
+- the file basename of the reference and its index (e.g. the reference `genoma.fa` and its index `genome.bt2` have the basename `genome`)
+- the path to a dir where the reference and index files both reside.
+
+See `assets/example_fastq_screen_references.csv` for example.
+
+The `.csv` is provided as a pipeline parameter `fastq_screen_references`. The `.csv` is used to construct a `FastQ Screen` configuration file within the context of the process work directory in order to properly mount the references.
 
 ### SeqFu Stats
 

From e3a88624ed49d21a8176079e20b370e9e9207c6a Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 15:20:51 +0000
Subject: [PATCH 131/172] update snapshots

---
 tests/MiSeq.main.nf.test.snap                 |  8 ++++----
 tests/NovaSeq6000.main.nf.test.snap           | 16 ++++++++--------
 tests/NovaSeq6000.main_subsample.nf.test.snap | 16 ++++++++--------
 tests/PromethION.main.nf.test.snap            |  8 ++++----
 4 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 9207f882..af7022dd 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
             "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
-            "multiqc_fastq_screen.txt:md5,435d8c1ac6e237448c9ce38e853ac82e"
+            "multiqc_fastq_screen.txt:md5,bd50a8641c6481cc497fc6e3e9af2607"
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-11-14T11:21:34.348023"
+        "timestamp": "2024-12-05T15:15:09.227024034"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 8b0f1366..9b3826a5 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -4,28 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
             "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_fastq_screen.txt:md5,c7b24e20fd157128924384e52eb3405d",
+            "multiqc_fastq_screen.txt:md5,2ff2485b1f197cb6228dd4350d1bd638",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
             "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_fastq_screen.txt:md5,a1e15006994d06a47634ccf07a08df0f",
+            "multiqc_fastq_screen.txt:md5,c54d863ed3e68ee8bcb51c9ad85de9bc",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
             "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_fastq_screen.txt:md5,d4f1cc5396c4f719b1fcaab2470e7d7c",
+            "multiqc_fastq_screen.txt:md5,737dc47e74e5b2f2c590652788831eff",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
             "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_fastq_screen.txt:md5,02246ddb4bf5373b157b45eab698cdc8",
+            "multiqc_fastq_screen.txt:md5,568f6b6d14562d01b5aaeb1a39e1cf3d",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
             "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
-            "multiqc_fastq_screen.txt:md5,483995ed26ba25b3217650840b2d82fa"
+            "multiqc_fastq_screen.txt:md5,a4dca31413036d35899a35ba14b17ea5"
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-11-14T11:22:20.902938"
+        "timestamp": "2024-12-05T15:16:34.893751981"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main_subsample.nf.test.snap b/tests/NovaSeq6000.main_subsample.nf.test.snap
index da7ba9a4..3ba50465 100644
--- a/tests/NovaSeq6000.main_subsample.nf.test.snap
+++ b/tests/NovaSeq6000.main_subsample.nf.test.snap
@@ -4,28 +4,28 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aba942d1e6996b579f19798e5673f514",
             "multiqc_general_stats.txt:md5,ad1ec9c64cbdb1131a26aeb6de51e31c",
-            "multiqc_fastq_screen.txt:md5,c7b24e20fd157128924384e52eb3405d",
+            "multiqc_fastq_screen.txt:md5,2ff2485b1f197cb6228dd4350d1bd638",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,aa1b8d6adae86005ea7a8b2e901099b8",
             "multiqc_general_stats.txt:md5,c73c8d10568a56f6534d280fff701e60",
-            "multiqc_fastq_screen.txt:md5,a1e15006994d06a47634ccf07a08df0f",
+            "multiqc_fastq_screen.txt:md5,c54d863ed3e68ee8bcb51c9ad85de9bc",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ff996e1d3dc4a46e0c9535e54d51ccab",
             "multiqc_general_stats.txt:md5,834e1868b887171cfda72029bbbe2d3f",
-            "multiqc_fastq_screen.txt:md5,d4f1cc5396c4f719b1fcaab2470e7d7c",
+            "multiqc_fastq_screen.txt:md5,737dc47e74e5b2f2c590652788831eff",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,3df36ecfe76b25b0c22dcda84bce2b3b",
             "multiqc_general_stats.txt:md5,274a001b007521970f14d68bd176e5be",
-            "multiqc_fastq_screen.txt:md5,02246ddb4bf5373b157b45eab698cdc8",
+            "multiqc_fastq_screen.txt:md5,568f6b6d14562d01b5aaeb1a39e1cf3d",
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,ce61b4ce4b1d76ec3f20de3bf0c9ec7f",
             "multiqc_general_stats.txt:md5,d476ad59458a035a329605d5284b6012",
-            "multiqc_fastq_screen.txt:md5,483995ed26ba25b3217650840b2d82fa"
+            "multiqc_fastq_screen.txt:md5,a4dca31413036d35899a35ba14b17ea5"
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-11-14T11:23:19.55095"
+        "timestamp": "2024-12-05T15:17:50.525033752"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 74c12f5d..7d0a6bfe 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -4,12 +4,12 @@
             "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
             "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
             "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
-            "multiqc_fastq_screen.txt:md5,2931dcec302d74c378b69a0831363224"
+            "multiqc_fastq_screen.txt:md5,7c5d711e27c53d13c81644a1f2468dba"
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-11-14T11:23:42.382002"
+        "timestamp": "2024-12-05T15:18:25.176791779"
     }
 }
\ No newline at end of file

From 586ac9bb757ae40020332ed46da21185d4c37af5 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 15:28:25 +0000
Subject: [PATCH 132/172] re-generate module patch

---
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 62 ++++++++++++-------
 1 file changed, 41 insertions(+), 21 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index df84f5ad..2fbd94b3 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -16,15 +16,10 @@ Changes in 'fastqscreen/fastqscreen/environment.yml':
 +  # - bwa
 +  # - bismark
 
-'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
 Changes in 'fastqscreen/fastqscreen/main.nf':
 --- modules/nf-core/fastqscreen/fastqscreen/main.nf
 +++ modules/nf-core/fastqscreen/fastqscreen/main.nf
-@@ -1,15 +1,15 @@
- process FASTQSCREEN_FASTQSCREEN {
--    tag "$meta.id"
-+    tag "$meta.id | $meta2.database_name"
-     label 'process_medium'
+@@ -4,12 +4,12 @@
  
      conda "${moduleDir}/environment.yml"
      container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
@@ -36,20 +31,18 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
      input:
 -    tuple val(meta), path(reads)  // .fastq files
 -    path database
-+    // NOTE for meta 2 and database [[database_name,  database_notes], database_path]
-+    tuple val(meta), path(reads, arity: '1..2'), val(meta2), path(database, arity: '1')
++    tuple val(meta), path(reads, arity: '1..2')
++    tuple val(ref_names), path(ref_dirs, name:"ref*"), val(ref_basenames), val(ref_aligners)
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,13 +24,22 @@
+@@ -24,31 +24,35 @@
      script:
      def prefix = task.ext.prefix ?: "${meta.id}"
      def args = task.ext.args ?: ""
-+    // 'Database name','Genome path and basename','Notes'
++    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
 +    """
-+    echo "Writing config"
-+    echo "DATABASE    ${meta2.database_name}    ./${database}/genome    ${meta2.database_notes}" > fastq_screen.conf
-+    echo "Wrote config"
++    echo '${config_content}' > fastq_screen.conf
  
 -    """
 -    fastq_screen --threads ${task.cpus} \\
@@ -58,20 +51,47 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
 +    fastq_screen \\
 +        --conf fastq_screen.conf \\
 +        --threads ${task.cpus} \\
-+        --aligner ${meta2.database_notes.toLowerCase()} \\
          $reads \\
 -        $args \\
 +        $args
+ 
+-    cat <<-END_VERSIONS > versions.yml
+-    "${task.process}":
+-        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+-    END_VERSIONS
++    mv *_screen.txt ${prefix}_screen.txt
++    mv *_screen.html ${prefix}_screen.html
++    mv *_screen.png ${prefix}_screen.png
 +
-+    mv *_screen.txt ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.txt
-+    mv *_screen.html ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.html
-+    mv *_screen.png ${prefix}_${meta2.database_name}_${meta2.database_notes}_screen.png
++    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
++    echo "\\\"${task.process}\\\":" > versions.yml
++    echo "    fastqscreen: \$fastq_screen_version" >> versions.yml
+     """
+ 
+     stub:
+     def prefix = task.ext.prefix ?: "${meta.id}"
+     """
+-    touch test_1_screen.html
+-    touch test_1_screen.png
+-    touch test_1_screen.txt
++    touch ${prefix}_screen.html
++    touch ${prefix}_screen.png
++    touch ${prefix}_screen.txt
+ 
+-    cat <<-END_VERSIONS > versions.yml
+-    "${task.process}":
+-        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+-    END_VERSIONS
++    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
++    echo "\\\"${task.process}\\\":" > versions.yml
++    echo "    fastqscreen: \$fastq_screen_version" >> versions.yml
+     """
  
-     cat <<-END_VERSIONS > versions.yml
-     "${task.process}":
+ }
 
+'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
 ************************************************************

From 7b6c18bdc55f74f32edb9397b1a6411b400688b9 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 5 Dec 2024 15:50:17 +0000
Subject: [PATCH 133/172] try gha update

---
 .github/workflows/nf-test.yml | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/.github/workflows/nf-test.yml b/.github/workflows/nf-test.yml
index 3a2abcbd..233897ed 100644
--- a/.github/workflows/nf-test.yml
+++ b/.github/workflows/nf-test.yml
@@ -10,14 +10,8 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up JDK 11
-        uses: actions/setup-java@v2
-        with:
-          java-version: "11"
-          distribution: "adopt"
-
       - name: Setup Nextflow latest-edge
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
         with:
           version: "latest-edge"
 

From c61d90f2e33d8e0fc5c38de46834662a62f91bf7 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 12:30:18 +0100
Subject: [PATCH 134/172] Fix pre-commit

---
 subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index 93d640e4..70994073 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -144,7 +144,7 @@ workflow PIPELINE_COMPLETION {
     main:
     summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json")
     def multiqc_reports = multiqc_report.toList()
-    
+
     //
     // Completion email and summary
     //

From 7a105c59cba1952315e181e075c00217a9dbc3f9 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 12:57:06 +0100
Subject: [PATCH 135/172] Fix warning messages

---
 modules.json                                  | 10 +++
 modules/nf-core/bowtie2/build/environment.yml |  5 ++
 modules/nf-core/bowtie2/build/main.nf         | 42 +++++++++++
 modules/nf-core/bowtie2/build/meta.yml        | 49 +++++++++++++
 .../nf-core/bowtie2/build/tests/main.nf.test  | 31 ++++++++
 .../bowtie2/build/tests/main.nf.test.snap     | 45 ++++++++++++
 modules/nf-core/bowtie2/build/tests/tags.yml  |  2 +
 .../buildfromindex/environment.yml            |  7 ++
 .../fastqscreen/buildfromindex/main.nf        | 69 ++++++++++++++++++
 .../fastqscreen/buildfromindex/meta.yml       | 39 ++++++++++
 .../buildfromindex/tests/main.nf.test         | 71 +++++++++++++++++++
 .../buildfromindex/tests/main.nf.test.snap    | 71 +++++++++++++++++++
 .../fastqscreen/buildfromindex/tests/tags.yml |  2 +
 13 files changed, 443 insertions(+)
 create mode 100644 modules/nf-core/bowtie2/build/environment.yml
 create mode 100644 modules/nf-core/bowtie2/build/main.nf
 create mode 100644 modules/nf-core/bowtie2/build/meta.yml
 create mode 100644 modules/nf-core/bowtie2/build/tests/main.nf.test
 create mode 100644 modules/nf-core/bowtie2/build/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/bowtie2/build/tests/tags.yml
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/environment.yml
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/main.nf
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/meta.yml
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/fastqscreen/buildfromindex/tests/tags.yml

diff --git a/modules.json b/modules.json
index 9864725e..01ae9110 100644
--- a/modules.json
+++ b/modules.json
@@ -5,11 +5,21 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "bowtie2/build": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
                         "installed_by": ["modules"]
                     },
+                    "fastqscreen/buildfromindex": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "fastqscreen/fastqscreen": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
diff --git a/modules/nf-core/bowtie2/build/environment.yml b/modules/nf-core/bowtie2/build/environment.yml
new file mode 100644
index 00000000..e590f7ce
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::bowtie2=2.5.2
diff --git a/modules/nf-core/bowtie2/build/main.nf b/modules/nf-core/bowtie2/build/main.nf
new file mode 100644
index 00000000..9e2e0e5e
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/main.nf
@@ -0,0 +1,42 @@
+process BOWTIE2_BUILD {
+    tag "$fasta"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bowtie2:2.5.2--py39h6fed5c7_0' :
+        'biocontainers/bowtie2:2.5.2--py39h6fed5c7_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path('bowtie2')    , emit: index
+    path "versions.yml"                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    mkdir bowtie2
+    bowtie2-build $args --threads $task.cpus $fasta bowtie2/${fasta.baseName}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    mkdir bowtie2
+    touch bowtie2/${fasta.baseName}.{1..4}.bt2
+    touch bowtie2/${fasta.baseName}.rev.{1,2}.bt2
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/bowtie2/build/meta.yml b/modules/nf-core/bowtie2/build/meta.yml
new file mode 100644
index 00000000..2729a92e
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/meta.yml
@@ -0,0 +1,49 @@
+name: bowtie2_build
+description: Builds bowtie index for reference genome
+keywords:
+  - build
+  - index
+  - fasta
+  - genome
+  - reference
+tools:
+  - bowtie2:
+      description: |
+        Bowtie 2 is an ultrafast and memory-efficient tool for aligning
+        sequencing reads to long reference sequences.
+      homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
+      documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
+      doi: 10.1038/nmeth.1923
+      licence: ["GPL-3.0-or-later"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing reference information
+          e.g. [ id:'test', single_end:false ]
+    - fasta:
+        type: file
+        description: Input genome fasta file
+output:
+  - index:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing reference information
+            e.g. [ id:'test', single_end:false ]
+      - bowtie2:
+          type: file
+          description: Bowtie2 genome index files
+          pattern: "*.bt2"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"
+maintainers:
+  - "@joseespinosa"
+  - "@drpatelh"
diff --git a/modules/nf-core/bowtie2/build/tests/main.nf.test b/modules/nf-core/bowtie2/build/tests/main.nf.test
new file mode 100644
index 00000000..16376025
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/tests/main.nf.test
@@ -0,0 +1,31 @@
+nextflow_process {
+
+    name "Test Process BOWTIE2_BUILD"
+    script "modules/nf-core/bowtie2/build/main.nf"
+    process "BOWTIE2_BUILD"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "bowtie2"
+    tag "bowtie2/build"
+
+    test("Should run without failures") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assert snapshot(process.out).match()
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/bowtie2/build/tests/main.nf.test.snap b/modules/nf-core/bowtie2/build/tests/main.nf.test.snap
new file mode 100644
index 00000000..6875e021
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/tests/main.nf.test.snap
@@ -0,0 +1,45 @@
+{
+    "Should run without failures": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "genome.1.bt2:md5,cbe3d0bbea55bc57c99b4bfa25b5fbdf",
+                            "genome.2.bt2:md5,47b153cd1319abc88dda532462651fcf",
+                            "genome.3.bt2:md5,4ed93abba181d8dfab2e303e33114777",
+                            "genome.4.bt2:md5,c25be5f8b0378abf7a58c8a880b87626",
+                            "genome.rev.1.bt2:md5,52be6950579598a990570fbcf5372184",
+                            "genome.rev.2.bt2:md5,e3b4ef343dea4dd571642010a7d09597"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,1df11e9b82891527271c889c880d3974"
+                ],
+                "index": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "genome.1.bt2:md5,cbe3d0bbea55bc57c99b4bfa25b5fbdf",
+                            "genome.2.bt2:md5,47b153cd1319abc88dda532462651fcf",
+                            "genome.3.bt2:md5,4ed93abba181d8dfab2e303e33114777",
+                            "genome.4.bt2:md5,c25be5f8b0378abf7a58c8a880b87626",
+                            "genome.rev.1.bt2:md5,52be6950579598a990570fbcf5372184",
+                            "genome.rev.2.bt2:md5,e3b4ef343dea4dd571642010a7d09597"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,1df11e9b82891527271c889c880d3974"
+                ]
+            }
+        ],
+        "timestamp": "2023-11-23T11:51:01.107681997"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/bowtie2/build/tests/tags.yml b/modules/nf-core/bowtie2/build/tests/tags.yml
new file mode 100644
index 00000000..81aa61da
--- /dev/null
+++ b/modules/nf-core/bowtie2/build/tests/tags.yml
@@ -0,0 +1,2 @@
+bowtie2/build:
+  - modules/nf-core/bowtie2/build/**
diff --git a/modules/nf-core/fastqscreen/buildfromindex/environment.yml b/modules/nf-core/fastqscreen/buildfromindex/environment.yml
new file mode 100644
index 00000000..85764e0d
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::fastq-screen=0.15.3"
diff --git a/modules/nf-core/fastqscreen/buildfromindex/main.nf b/modules/nf-core/fastqscreen/buildfromindex/main.nf
new file mode 100644
index 00000000..33840120
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/main.nf
@@ -0,0 +1,69 @@
+process FASTQSCREEN_BUILDFROMINDEX {
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastq-screen:0.15.3--pl5321hdfd78af_0':
+        'biocontainers/fastq-screen:0.15.3--pl5321hdfd78af_0'}"
+
+    input:
+    val(genome_names)
+    path(indexes), stageAs: "dir*"
+
+    output:
+    path("FastQ_Screen_Genomes"), emit: database
+    path "versions.yml"         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    dir = "FastQ_Screen_Genomes"
+    folder = indexes.collect { it.toString() }
+    database = [genome_names, folder].transpose()
+    copy_indexes = folder.collect { "cp -r ${it} $dir/${it}"}.join(" && ")
+
+    // Folder name and index (within folder) name could be different - use bash to look for index name
+    config = database
+        .collect { "########## ${it[0]} \nDATABASE ${it[0]} $dir/${it[1]}/${it[1] + '_to_be_replaced'}" }
+        .join("\n\n")
+        .replace("\n", "\\n")
+
+    """
+    mkdir $dir
+    $copy_indexes
+
+    echo "$config" > fastq_screen.conf
+    sed 's/\\\\n/\\n/g' fastq_screen.conf > $dir/fastq_screen.conf
+    echo "Replace folder name real index name"
+
+    for f in ${folder.join(' ')}
+    do
+        TO_REPLACE=\${f}_to_be_replaced
+
+        REPLACE_WITH=(\$f"/*.rev.1.bt2")
+        REPLACE_WITH=\$(basename \$REPLACE_WITH)
+        REPLACE_WITH=\${REPLACE_WITH%%.rev.1.bt2}
+
+        sed "s/\$TO_REPLACE/\$REPLACE_WITH/g" $dir/fastq_screen.conf > new_conf.conf
+        mv new_conf.conf $dir/fastq_screen.conf
+    done
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    dir = "FastQ_Screen_Genomes"
+    """
+    mkdir $dir
+    touch $dir/fastq_screen.conf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/fastqscreen/buildfromindex/meta.yml b/modules/nf-core/fastqscreen/buildfromindex/meta.yml
new file mode 100644
index 00000000..d92817fc
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/meta.yml
@@ -0,0 +1,39 @@
+name: "fastqscreen_buildfromindex"
+description: Build fastq screen config file from bowtie index files
+keywords:
+  - build
+  - index
+  - genome
+  - reference
+tools:
+  - "fastqscreen":
+      description: "FastQ Screen allows you to screen a library of sequences in FastQ
+        format against a set of sequence databases so you can see if the composition
+        of the library matches with what you expect."
+      homepage: "https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/"
+      documentation: "https://stevenwingett.github.io/FastQ-Screen/"
+      tool_dev_url: "https://github.com/StevenWingett/FastQ-Screen/archive/refs/tags/v0.15.3.zip"
+      doi: "10.5281/zenodo.5838377"
+      licence: ["GPL-3.0-or-later"]
+      identifier: ""
+input:
+  - - genome_names:
+        type: string
+        description: List of names for each index
+  - - indexes:
+        type: directory
+        description: Bowtie2 genome directories containing index files
+output:
+  - database:
+      - FastQ_Screen_Genomes:
+          type: directory
+          description: fastq screen database folder containing config file and index folders
+          pattern: "FastQ_Screen_Genomes"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@snesic"
+  - "@JPejovicApis"
diff --git a/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test b/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test
new file mode 100644
index 00000000..5357712a
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test
@@ -0,0 +1,71 @@
+nextflow_process {
+
+    name "Test Process FASTQSCREEN_BUILDFROMINDEX"
+    script "../main.nf"
+    process "FASTQSCREEN_BUILDFROMINDEX"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "fastqscreen"
+    tag "fastqscreen/buildfromindex"
+    tag "bowtie2/build"
+
+    setup {
+
+        run("BOWTIE2_BUILD") {
+            script "../../../bowtie2/build/main.nf"
+            process {
+                """
+                input[0] =  Channel.from([
+                                    [[id: "sarscov2"], file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)],
+                                    [[id: "human"]   , file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)]
+                            ])
+                """
+            }
+        }
+
+    }
+
+    test("sarscov2 - human") {
+
+        when {
+            process {
+                """
+                input[0] = BOWTIE2_BUILD.out.index.map{meta, index -> meta.id}.collect()
+                input[1] = BOWTIE2_BUILD.out.index.map{meta, index -> index}.collect()
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.database, process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - human - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = BOWTIE2_BUILD.out.index.map{meta, index -> meta.id}.collect()
+                input[1] = BOWTIE2_BUILD.out.index.map{meta, index -> index}.collect()
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test.snap b/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test.snap
new file mode 100644
index 00000000..0fe7d7d1
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/tests/main.nf.test.snap
@@ -0,0 +1,71 @@
+{
+    "database": {
+        "content": [
+            [
+                [
+                    [
+                        "genome.1.bt2:md5,cbe3d0bbea55bc57c99b4bfa25b5fbdf",
+                        "genome.2.bt2:md5,47b153cd1319abc88dda532462651fcf",
+                        "genome.3.bt2:md5,4ed93abba181d8dfab2e303e33114777",
+                        "genome.4.bt2:md5,c25be5f8b0378abf7a58c8a880b87626",
+                        "genome.rev.1.bt2:md5,52be6950579598a990570fbcf5372184",
+                        "genome.rev.2.bt2:md5,e3b4ef343dea4dd571642010a7d09597"
+                    ],
+                    [
+                        "genome.1.bt2:md5,2fbc8eeaf480f03b3a2362a782fa5755",
+                        "genome.2.bt2:md5,a5300e3cf590d4cd8bd5521cac6337d6",
+                        "genome.3.bt2:md5,d2a7a0e1c9891e847a15781c0695b84e",
+                        "genome.4.bt2:md5,a55dc4b09e3e00586de6963800c95b9a",
+                        "genome.rev.1.bt2:md5,93c07f7d04e5da6bf1322ad5f46ac806",
+                        "genome.rev.2.bt2:md5,c3fa30132c0c9b9bc7868059e8e23466"
+                    ],
+                    "fastq_screen.conf:md5,ca56e866c7006a46bdfe4e751e787265"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-01T20:37:34.647221"
+    },
+    "versions": {
+        "content": [
+            [
+                "versions.yml:md5,c2bcf85b00046c72d5dccd2dba8ac35c"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-01T20:37:35.126085"
+    },
+    "sarscov2 - human - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        "fastq_screen.conf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,c2bcf85b00046c72d5dccd2dba8ac35c"
+                ],
+                "database": [
+                    [
+                        "fastq_screen.conf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,c2bcf85b00046c72d5dccd2dba8ac35c"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-01T20:39:14.913696"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/fastqscreen/buildfromindex/tests/tags.yml b/modules/nf-core/fastqscreen/buildfromindex/tests/tags.yml
new file mode 100644
index 00000000..9c98e870
--- /dev/null
+++ b/modules/nf-core/fastqscreen/buildfromindex/tests/tags.yml
@@ -0,0 +1,2 @@
+fastqscreen/buildfromindex:
+  - "modules/nf-core/fastqscreen/buildfromindex/**"

From 9aa2ea0b95869e2ab698614ee0cee56cd8b1b4e8 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 13:12:05 +0100
Subject: [PATCH 136/172] Fix contributor field

---
 nextflow.config | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/nextflow.config b/nextflow.config
index 46144693..bac5d198 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -230,15 +230,13 @@ dag {
 
 manifest {
     name            = 'nf-core/seqinspector'
-    author          = """Adrien Coulier""" // The author field is deprecated from Nextflow version 24.10.0, use contributors instead
     contributors    = [
-        // TODO nf-core: Update the field with the details of the contributors to your pipeline. New with Nextflow version 24.10.0
         [
-            name: 'Adrien Coulier',
+            name: 'National Genomics Infrastructure',
             affiliation: '',
             email: '',
-            github: '',
-            contribution: [], // List of contribution types ('author', 'maintainer' or 'contributor')
+            github: 'https://github.com/NationalGenomicsInfrastructure/',
+            contribution: ['author'], // List of contribution types ('author', 'maintainer' or 'contributor')
             orcid: ''
         ],
     ]

From 0e9db9f93482aea21fd3cd39d84a5ac6527a4392 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 16:06:26 +0100
Subject: [PATCH 137/172] Include conf/modules.config again

---
 nextflow.config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/nextflow.config b/nextflow.config
index bac5d198..9ab822e8 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -57,6 +57,7 @@ params {
 
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
+includeConfig 'conf/modules.config'
 
 profiles {
     debug {

From 5e399e9c5c54fd2f7702f2f54ded005affc2a16e Mon Sep 17 00:00:00 2001
From: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Date: Tue, 17 Dec 2024 16:24:12 +0000
Subject: [PATCH 138/172] Patch fastqscreen to handle multiple input FASTQ
 files

---
 modules.json                                  |  5 ++++
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 24 +++++++++++++------
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 16 ++++++++++---
 3 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/modules.json b/modules.json
index 566d84ec..8f0fd8d5 100644
--- a/modules.json
+++ b/modules.json
@@ -16,6 +16,11 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff"
                     },
+                    "fq/lint": {
+                        "branch": "master",
+                        "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index 2fbd94b3..beef4a99 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -16,6 +16,7 @@ Changes in 'fastqscreen/fastqscreen/environment.yml':
 +  # - bwa
 +  # - bismark
 
+'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
 Changes in 'fastqscreen/fastqscreen/main.nf':
 --- modules/nf-core/fastqscreen/fastqscreen/main.nf
 +++ modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -36,11 +37,21 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,31 +24,35 @@
+@@ -24,31 +24,45 @@
      script:
      def prefix = task.ext.prefix ?: "${meta.id}"
      def args = task.ext.args ?: ""
 +    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
++    def num_reads     = reads instanceof List  ? reads.size() : 1
++    def mv_txt_cmd    = (num_reads == 1) ? 
++            "mv ${reads[0].simpleName}_screen.txt ${prefix}_screen.txt" : 
++            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
++    def mv_html_cmd   = (num_reads == 1) ? 
++            "mv ${reads[0].simpleName}_screen.html ${prefix}_1_screen.html" : 
++            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
++    def mv_png_cmd    = (num_reads == 1) ? 
++            "mv ${reads[0].simpleName}_screen.png ${prefix}_1_screen.png" : 
++            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
 +    """
 +    echo '${config_content}' > fastq_screen.conf
  
@@ -59,9 +70,9 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
 -    "${task.process}":
 -        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
 -    END_VERSIONS
-+    mv *_screen.txt ${prefix}_screen.txt
-+    mv *_screen.html ${prefix}_screen.html
-+    mv *_screen.png ${prefix}_screen.png
++    $mv_txt_cmd
++    $mv_html_cmd
++    $mv_png_cmd
 +
 +    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
 +    echo "\\\"${task.process}\\\":" > versions.yml
@@ -89,9 +100,8 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
  
  }
 
-'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
 ************************************************************
diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 2eba8390..9df8e27c 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -25,6 +25,16 @@ process FASTQSCREEN_FASTQSCREEN {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
     def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
+    def num_reads     = reads instanceof List  ? reads.size() : 1
+    def mv_txt_cmd    = (num_reads == 1) ? 
+            "mv ${reads[0].simpleName}_screen.txt ${prefix}_screen.txt" : 
+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
+    def mv_html_cmd   = (num_reads == 1) ? 
+            "mv ${reads[0].simpleName}_screen.html ${prefix}_1_screen.html" : 
+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
+    def mv_png_cmd    = (num_reads == 1) ? 
+            "mv ${reads[0].simpleName}_screen.png ${prefix}_1_screen.png" : 
+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
     """
     echo '${config_content}' > fastq_screen.conf
 
@@ -34,9 +44,9 @@ process FASTQSCREEN_FASTQSCREEN {
         $reads \\
         $args
 
-    mv *_screen.txt ${prefix}_screen.txt
-    mv *_screen.html ${prefix}_screen.html
-    mv *_screen.png ${prefix}_screen.png
+    $mv_txt_cmd
+    $mv_html_cmd
+    $mv_png_cmd
 
     fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
     echo "\\\"${task.process}\\\":" > versions.yml

From 25805d7c18c95f792b6da2ff241ae2f38185a450 Mon Sep 17 00:00:00 2001
From: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Date: Tue, 17 Dec 2024 16:43:39 +0000
Subject: [PATCH 139/172] docs: CHANGELOG

---
 CHANGELOG.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a4b5e286..91ee0b7f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Fixed`
 
+- [#71](https://github.com/nf-core/seqinspector/pull/71) FASTQSCREEN does not fail when multiple reads are provided.
+
 ### `Dependencies`
 
 ### `Deprecated`

From 126d1e398485fc127d2502b7e8ead8d779c694b9 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Wed, 18 Dec 2024 14:10:30 +0100
Subject: [PATCH 140/172] Bugfix

The file extensions were a bit wonky. Likely due to hasty copy-pasty :)
---
 modules/nf-core/fastqscreen/fastqscreen/main.nf | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index 9df8e27c..ee6eeb2b 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -30,11 +30,11 @@ process FASTQSCREEN_FASTQSCREEN {
             "mv ${reads[0].simpleName}_screen.txt ${prefix}_screen.txt" : 
             reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
     def mv_html_cmd   = (num_reads == 1) ? 
-            "mv ${reads[0].simpleName}_screen.html ${prefix}_1_screen.html" : 
-            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
+            "mv ${reads[0].simpleName}_screen.html ${prefix}_screen.html" : 
+            reads.collect { "mv ${it.simpleName}_screen.html ${prefix}_${it.simpleName}_screen.html" }.join(' && ')
     def mv_png_cmd    = (num_reads == 1) ? 
-            "mv ${reads[0].simpleName}_screen.png ${prefix}_1_screen.png" : 
-            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
+            "mv ${reads[0].simpleName}_screen.png ${prefix}_screen.png" : 
+            reads.collect { "mv ${it.simpleName}_screen.png ${prefix}_${it.simpleName}_screen.png" }.join(' && ')
     """
     echo '${config_content}' > fastq_screen.conf
 

From bd8735ed24a484ba8046bd9fe07c10677a3e3108 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <89784800+kedhammar@users.noreply.github.com>
Date: Wed, 18 Dec 2024 16:04:42 +0100
Subject: [PATCH 141/172] Use <meta.id>(_1|2)?_screen filenames and make DRYer

---
 .../nf-core/fastqscreen/fastqscreen/main.nf   | 23 ++++++++-----------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/main.nf b/modules/nf-core/fastqscreen/fastqscreen/main.nf
index ee6eeb2b..21012c1f 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/main.nf
+++ b/modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -25,16 +25,15 @@ process FASTQSCREEN_FASTQSCREEN {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ""
     def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
-    def num_reads     = reads instanceof List  ? reads.size() : 1
-    def mv_txt_cmd    = (num_reads == 1) ? 
-            "mv ${reads[0].simpleName}_screen.txt ${prefix}_screen.txt" : 
-            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
-    def mv_html_cmd   = (num_reads == 1) ? 
-            "mv ${reads[0].simpleName}_screen.html ${prefix}_screen.html" : 
-            reads.collect { "mv ${it.simpleName}_screen.html ${prefix}_${it.simpleName}_screen.html" }.join(' && ')
-    def mv_png_cmd    = (num_reads == 1) ? 
-            "mv ${reads[0].simpleName}_screen.png ${prefix}_screen.png" : 
-            reads.collect { "mv ${it.simpleName}_screen.png ${prefix}_${it.simpleName}_screen.png" }.join(' && ')
+
+    // Build mv commands to rename the output files. Dual reads will be appended with '_1' and '_2'
+    def num_reads = reads instanceof List  ? reads.size() : 1
+    def file_extensions = ['txt', 'html', 'png']
+    def mv_cmd = file_extensions.collect { ext ->
+        reads.withIndex().collect { read, i ->
+            "mv ${read.simpleName}_screen.${ext} ${prefix}${num_reads > 1 ? "_${i+1}" : ''}_screen.${ext}"
+        }.join(' && ')
+    }.join(' && ')
     """
     echo '${config_content}' > fastq_screen.conf
 
@@ -44,9 +43,7 @@ process FASTQSCREEN_FASTQSCREEN {
         $reads \\
         $args
 
-    $mv_txt_cmd
-    $mv_html_cmd
-    $mv_png_cmd
+    $mv_cmd
 
     fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
     echo "\\\"${task.process}\\\":" > versions.yml

From b6d7f0d41d09b5539e28c40ec285b8fd7dad4a27 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 19 Dec 2024 10:02:43 +0000
Subject: [PATCH 142/172] bump docs

---
 docs/output.md | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/docs/output.md b/docs/output.md
index dc26159f..3d3c3497 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -13,7 +13,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [Seqtk](#seqtk) - Subsample a specific number of reads per sample
 - [FastQC](#fastqc) - Raw read QC
 - [SeqFu Stats](#seqfu_stats) - Statistics for FASTA or FASTQ files
-- [Fastqscreen](#fastqscreen) - mapping against a set of references for basic contamination QC
+- [FastQ Screen](#fastqscreen) - Mapping against a set of references for basic contamination QC
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -42,21 +42,21 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
-### FASTQSCREEN
+### FastQ Screen
 
 <details markdown="1">
 <summary>Output files</summary>
 
 - `fastqscreen/`
-  - `*_screen.html`: Interactive graphical fastqscreen report which summaries the mapping of your sequences against each of your libraries.
-  - `*_screen.pdf`: Static graphical fastqscreen report which summaries the mapping of your sequences against each of your libraries.
-  - `*_screen.txt` : text based fastqscreen report which summaries the mapping of your sequences against each of your libraries.
+  - `*_screen.html`: Interactive graphical report.
+  - `*_screen.pdf`: Static graphical report.
+  - `*_screen.txt` : Text-based report.
 
 </details>
 
-[Fastqscreen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/) allows you to set up a standard set of libraries against which all of your sequences can be searched. Your search libraries might contain the genomes of all of the organisms you work on, along with PhiX, Vectors or other contaminants commonly seen in sequencing experiments.
+[FastQ Screen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/) allows you to set up a standard set of references against which all of your samples can be mapped. Your references might contain the genomes of all of the organisms you work on, along with PhiX, vectors or other contaminants commonly seen in sequencing experiments.
 
-It requires a `.csv` detailing:
+To use FastQ Screen, this pipeline requires a `.csv` detailing:
 
 - the working name of the reference
 - the name of the aligner used to generate its index (which is also the aligner and index used by the tool)
@@ -65,7 +65,7 @@ It requires a `.csv` detailing:
 
 See `assets/example_fastq_screen_references.csv` for example.
 
-The `.csv` is provided as a pipeline parameter `fastq_screen_references`. The `.csv` is used to construct a `FastQ Screen` configuration file within the context of the process work directory in order to properly mount the references.
+The `.csv` is provided as a pipeline parameter `fastq_screen_references` and is used to construct a `FastQ Screen` configuration file within the context of the process work directory in order to properly mount the references.
 
 ### SeqFu Stats
 

From 841ea902528376d36f94ee9d7d9a10b15fbaf9a1 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 19 Dec 2024 10:11:53 +0000
Subject: [PATCH 143/172] bump module patch

---
 .../fastqscreen/fastqscreen-fastqscreen.diff  | 38 +++++++++----------
 1 file changed, 17 insertions(+), 21 deletions(-)

diff --git a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
index beef4a99..658d149b 100644
--- a/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
+++ b/modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff
@@ -1,4 +1,4 @@
-Changes in module 'nf-core/fastqscreen/fastqscreen'
+Changes in component 'nf-core/fastqscreen/fastqscreen'
 Changes in 'fastqscreen/fastqscreen/environment.yml':
 --- modules/nf-core/fastqscreen/fastqscreen/environment.yml
 +++ modules/nf-core/fastqscreen/fastqscreen/environment.yml
@@ -16,7 +16,6 @@ Changes in 'fastqscreen/fastqscreen/environment.yml':
 +  # - bwa
 +  # - bismark
 
-'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
 Changes in 'fastqscreen/fastqscreen/main.nf':
 --- modules/nf-core/fastqscreen/fastqscreen/main.nf
 +++ modules/nf-core/fastqscreen/fastqscreen/main.nf
@@ -37,28 +36,26 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
  
      output:
      tuple val(meta), path("*.txt")     , emit: txt
-@@ -24,31 +24,45 @@
+@@ -24,31 +24,42 @@
      script:
      def prefix = task.ext.prefix ?: "${meta.id}"
      def args = task.ext.args ?: ""
 +    def config_content = ref_names.withIndex().collect { name, i -> "DATABASE ${name} ./${ref_dirs[i]}/${ref_basenames[i]} ${ref_aligners[i]}" }.join('\n')
-+    def num_reads     = reads instanceof List  ? reads.size() : 1
-+    def mv_txt_cmd    = (num_reads == 1) ? 
-+            "mv ${reads[0].simpleName}_screen.txt ${prefix}_screen.txt" : 
-+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
-+    def mv_html_cmd   = (num_reads == 1) ? 
-+            "mv ${reads[0].simpleName}_screen.html ${prefix}_1_screen.html" : 
-+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
-+    def mv_png_cmd    = (num_reads == 1) ? 
-+            "mv ${reads[0].simpleName}_screen.png ${prefix}_1_screen.png" : 
-+            reads.collect { "mv ${it.simpleName}_screen.txt ${prefix}_${it.simpleName}_screen.txt" }.join(' && ')
-+    """
-+    echo '${config_content}' > fastq_screen.conf
  
--    """
++    // Build mv commands to rename the output files. Dual reads will be appended with '_1' and '_2'
++    def num_reads = reads instanceof List  ? reads.size() : 1
++    def file_extensions = ['txt', 'html', 'png']
++    def mv_cmd = file_extensions.collect { ext ->
++        reads.withIndex().collect { read, i ->
++            "mv ${read.simpleName}_screen.${ext} ${prefix}${num_reads > 1 ? "_${i+1}" : ''}_screen.${ext}"
++        }.join(' && ')
++    }.join(' && ')
+     """
 -    fastq_screen --threads ${task.cpus} \\
 -        --aligner bowtie2 \\
 -        --conf ${database}/fastq_screen.conf \\
++    echo '${config_content}' > fastq_screen.conf
++
 +    fastq_screen \\
 +        --conf fastq_screen.conf \\
 +        --threads ${task.cpus} \\
@@ -70,9 +67,7 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
 -    "${task.process}":
 -        fastqscreen: \$(echo \$(fastq_screen --version 2>&1) | sed 's/^.*FastQ Screen v//; s/ .*\$//')
 -    END_VERSIONS
-+    $mv_txt_cmd
-+    $mv_html_cmd
-+    $mv_png_cmd
++    $mv_cmd
 +
 +    fastq_screen_version=\$(fastq_screen --version 2>&1 | sed 's/^.*FastQ Screen v//; s/ .*\$//')
 +    echo "\\\"${task.process}\\\":" > versions.yml
@@ -100,8 +95,9 @@ Changes in 'fastqscreen/fastqscreen/main.nf':
  
  }
 
+'modules/nf-core/fastqscreen/fastqscreen/meta.yml' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test.snap' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
 'modules/nf-core/fastqscreen/fastqscreen/tests/nextflow.config' is unchanged
-'modules/nf-core/fastqscreen/fastqscreen/tests/main.nf.test' is unchanged
+'modules/nf-core/fastqscreen/fastqscreen/tests/tags.yml' is unchanged
 ************************************************************

From 5d9122abc4db039242ce5c621f0abcda2bb6c7f1 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 19 Dec 2024 10:20:39 +0000
Subject: [PATCH 144/172] nf-core tools lint autofixes

---
 .github/workflows/branch.yml          | 18 ++++++++++--------
 .github/workflows/linting.yml         | 10 +++++-----
 .github/workflows/linting_comment.yml |  2 +-
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml
index 5a2fffda..ffe93094 100644
--- a/.github/workflows/branch.yml
+++ b/.github/workflows/branch.yml
@@ -1,15 +1,17 @@
 name: nf-core branch protection
-# This workflow is triggered on PRs to master branch on the repository
-# It fails when someone tries to make a PR against the nf-core `master` branch instead of `dev`
+# This workflow is triggered on PRs to `main`/`master` branch on the repository
+# It fails when someone tries to make a PR against the nf-core `main`/`master` branch instead of `dev`
 on:
   pull_request_target:
-    branches: [master]
+    branches:
+      - main
+      - master
 
 jobs:
   test:
     runs-on: ubuntu-latest
     steps:
-      # PRs to the nf-core repo master branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
+      # PRs to the nf-core repo main/master branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
       - name: Check PRs
         if: github.repository == 'nf-core/seqinspector'
         run: |
@@ -22,7 +24,7 @@ jobs:
         uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2
         with:
           message: |
-            ## This PR is against the `master` branch :x:
+            ## This PR is against the `${{github.event.pull_request.base.ref}}` branch :x:
 
             * Do not close this PR
             * Click _Edit_ and change the `base` to `dev`
@@ -32,9 +34,9 @@ jobs:
 
             Hi @${{ github.event.pull_request.user.login }},
 
-            It looks like this pull-request is has been made against the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `master` branch.
-            The `master` branch on nf-core repositories should always contain code from the latest release.
-            Because of this, PRs to `master` are only allowed if they come from the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `dev` branch.
+            It looks like this pull-request is has been made against the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) ${{github.event.pull_request.base.ref}} branch.
+            The ${{github.event.pull_request.base.ref}} branch on nf-core repositories should always contain code from the latest release.
+            Because of this, PRs to ${{github.event.pull_request.base.ref}} are only allowed if they come from the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `dev` branch.
 
             You do not need to close this PR, you can change the target branch to `dev` by clicking the _"Edit"_ button at the top of this page.
             Note that even after this, the test will continue to show as failing until you push a new commit.
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
index a502573c..dbd52d5a 100644
--- a/.github/workflows/linting.yml
+++ b/.github/workflows/linting.yml
@@ -14,10 +14,10 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
 
       - name: Set up Python 3.12
-        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
+        uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
         with:
           python-version: "3.12"
 
@@ -31,12 +31,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
+      - uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
         with:
           python-version: "3.12"
           architecture: "x64"
@@ -74,7 +74,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4
         with:
           name: linting-logs
           path: |
diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
index 42e519bf..0bed96d3 100644
--- a/.github/workflows/linting_comment.yml
+++ b/.github/workflows/linting_comment.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@bf251b5aa9c2f7eeb574a96ee720e24f801b7c11 # v6
+        uses: dawidd6/action-download-artifact@80620a5d27ce0ae443b965134db88467fc607b43 # v7
         with:
           workflow: linting.yml
           workflow_conclusion: completed

From e2d54eac2cc8a1cd8298f5b88932ac8e97bcc786 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Thu, 19 Dec 2024 11:13:08 +0000
Subject: [PATCH 145/172] remove fq/lint from modules.json, handled in separate
 PR

---
 modules.json | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/modules.json b/modules.json
index 82514096..01ae9110 100644
--- a/modules.json
+++ b/modules.json
@@ -26,11 +26,6 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff"
                     },
-                    "fq/lint": {
-                        "branch": "master",
-                        "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
-                        "installed_by": ["modules"]
-                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",

From 7072d598ca2b600aa9603bb14bc3228b2e17e531 Mon Sep 17 00:00:00 2001
From: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Date: Sat, 2 Nov 2024 12:26:01 +0000
Subject: [PATCH 146/172] Adds fq/lint for early validation of FASTQs

Validation of FASTQS early prevents running the pipeline on invalid FASTQ files which will make the pipeline more efficient at achieving it's ultimate objective of checking FASTQ validity.

It adds 3 more parameters:
 - `--skip_linting` which enables the linting of FASTQs
 - `--fq_lint_args` which is a string of arguments to pass to the linting tool
 - `--continue_with_lint_fail` which is a boolean to determine whether to continue if the linting fails

Between these three options the user has a high degree of control over how the pipeline lints which should handle most use cases.

Closes #31
---
 CHANGELOG.md                                  |  1 +
 CITATIONS.md                                  |  2 +
 README.md                                     |  5 +-
 conf/modules.config                           |  9 ++
 modules.json                                  | 49 ++++++++---
 modules/nf-core/fq/lint/environment.yml       |  5 ++
 modules/nf-core/fq/lint/main.nf               | 33 +++++++
 modules/nf-core/fq/lint/meta.yml              | 43 +++++++++
 modules/nf-core/fq/lint/tests/main.nf.test    | 63 ++++++++++++++
 .../nf-core/fq/lint/tests/main.nf.test.snap   | 25 ++++++
 modules/nf-core/fq/lint/tests/tags.yml        |  2 +
 nextflow.config                               |  7 ++
 nextflow_schema.json                          | 28 +++++-
 tests/rnaseq.main.nf.test                     | 87 +++++++++++++++++++
 tests/rnaseq.main.nf.test.config              |  8 ++
 workflows/seqinspector.nf                     | 19 ++++
 16 files changed, 372 insertions(+), 14 deletions(-)
 create mode 100644 modules/nf-core/fq/lint/environment.yml
 create mode 100644 modules/nf-core/fq/lint/main.nf
 create mode 100644 modules/nf-core/fq/lint/meta.yml
 create mode 100644 modules/nf-core/fq/lint/tests/main.nf.test
 create mode 100644 modules/nf-core/fq/lint/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/fq/lint/tests/tags.yml
 create mode 100644 tests/rnaseq.main.nf.test
 create mode 100644 tests/rnaseq.main.nf.test.config

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 91ee0b7f..ea20eb3a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -17,6 +17,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 - [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools
 - [#53](https://github.com/nf-core/seqinspector/pull/53) Add FastQ-Screen database multiplexing and limit scope of nf-test in CI.
+- [#67](https://github.com/nf-core/seqinspector/pull/67) Add FASTQ linting for early validation
 
 ### `Fixed`
 
diff --git a/CITATIONS.md b/CITATIONS.md
index 208cfa1e..e1811c78 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -10,6 +10,8 @@
 
 ## Pipeline tools
 
+- [FQ](https://github.com/stjude-rust-labs/fq)
+
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
 > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
diff --git a/README.md b/README.md
index 6cf36dcc..6f25df40 100644
--- a/README.md
+++ b/README.md
@@ -31,9 +31,10 @@
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
+1. Lint FASTQs with ([`fq`](https://github.com/stjude-rust-labs/fq))
 1. Subsample reads ([`Seqtk`](https://github.com/lh3/seqtk))
-2. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-3. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
+1. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## Usage
 
diff --git a/conf/modules.config b/conf/modules.config
index 4a653ed0..4e4f33f3 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -18,6 +18,15 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    withName: 'FQ_LINT' {
+        ext.args      = { params.fq_lint_args }
+        errorStrategy = {
+                            task.exitStatus in ((130..145) + 104) ? 'retry'  :
+                            params.continue_with_lint_fail        ? 'ignore' :
+                            'finish'
+                        }
+    }
+
     withName: SEQTK_SAMPLE {
         ext.args = '-s100'
     }
diff --git a/modules.json b/modules.json
index 01ae9110..00a9f11f 100644
--- a/modules.json
+++ b/modules.json
@@ -8,38 +8,59 @@
                     "bowtie2/build": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "fastqscreen/buildfromindex": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "fastqscreen/fastqscreen": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"],
+                        "installed_by": [
+                            "modules"
+                        ],
                         "patch": "modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff"
                     },
+                    "fq/lint": {
+                        "branch": "master",
+                        "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
+                        "installed_by": [
+                            "modules"
+                        ]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "seqfu/stats": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     },
                     "seqtk/sample": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": ["modules"]
+                        "installed_by": [
+                            "modules"
+                        ]
                     }
                 }
             },
@@ -48,20 +69,26 @@
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "c2b22d85f30a706a3073387f30380704fcae013b",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
                         "git_sha": "51ae5406a030d4da1e49e4dab49756844fdd6c7a",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
                         "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
-                        "installed_by": ["subworkflows"]
+                        "installed_by": [
+                            "subworkflows"
+                        ]
                     }
                 }
             }
         }
     }
-}
+}
\ No newline at end of file
diff --git a/modules/nf-core/fq/lint/environment.yml b/modules/nf-core/fq/lint/environment.yml
new file mode 100644
index 00000000..74b14608
--- /dev/null
+++ b/modules/nf-core/fq/lint/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::fq=0.12.0
diff --git a/modules/nf-core/fq/lint/main.nf b/modules/nf-core/fq/lint/main.nf
new file mode 100644
index 00000000..943314c8
--- /dev/null
+++ b/modules/nf-core/fq/lint/main.nf
@@ -0,0 +1,33 @@
+process FQ_LINT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fq:0.12.0--h9ee0642_0':
+        'biocontainers/fq:0.12.0--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(fastq)
+
+    output:
+    tuple val(meta), path("*.fq_lint.txt"), emit: lint
+    path "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args   = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    fq lint \\
+        $args \\
+        $fastq > ${prefix}.fq_lint.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fq: \$(echo \$(fq lint --version | sed 's/fq-lint //g'))
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/fq/lint/meta.yml b/modules/nf-core/fq/lint/meta.yml
new file mode 100644
index 00000000..7240fb57
--- /dev/null
+++ b/modules/nf-core/fq/lint/meta.yml
@@ -0,0 +1,43 @@
+name: "fq_lint"
+description: fq lint is a FASTQ file pair validator.
+keywords:
+  - lint
+  - fastq
+  - validate
+tools:
+  - "fq":
+      description: "fq is a library to generate and validate FASTQ file pairs."
+      homepage: "https://github.com/stjude-rust-labs/fq"
+      documentation: "https://github.com/stjude-rust-labs/fq"
+      tool_dev_url: "https://github.com/stjude-rust-labs/fq"
+      licence: ["MIT"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - fastq:
+        type: file
+        description: FASTQ file list
+        pattern: "*.fastq{,.gz}"
+output:
+  - lint:
+      - meta:
+          type: file
+          description: Lint output
+          pattern: "*.fq_lint.txt"
+      - "*.fq_lint.txt":
+          type: file
+          description: Lint output
+          pattern: "*.fq_lint.txt"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@adamrtalbot"
+maintainers:
+  - "@adamrtalbot"
diff --git a/modules/nf-core/fq/lint/tests/main.nf.test b/modules/nf-core/fq/lint/tests/main.nf.test
new file mode 100644
index 00000000..ec2eaf8b
--- /dev/null
+++ b/modules/nf-core/fq/lint/tests/main.nf.test
@@ -0,0 +1,63 @@
+nextflow_process {
+
+    name "Test Process FQ_LINT"
+    script "../main.nf"
+    process "FQ_LINT"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "fq"
+    tag "fq/lint"
+
+    test("test_fq_lint_success") {
+        when {
+            params {
+                outdir   = "$outputDir"
+            }
+            process {
+                """
+                input[0] = [ [ id:'test', single_end:false ], // meta map
+                             [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                               file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ]
+                           ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert process.out.lint.get(0).get(1) ==~ ".*/test.fq_lint.txt" },
+                { assert path(process.out.lint.get(0).get(1)).getText().contains("fq-lint start") },
+                { assert path(process.out.lint.get(0).get(1)).getText().contains("read 100 records") },
+                { assert path(process.out.lint.get(0).get(1)).getText().contains("fq-lint end") },
+            )
+        }
+
+    }
+
+    test("test_fq_lint_fail") {
+        when {
+            params {
+                outdir   = "$outputDir"
+            }
+            process {
+                """
+                input[0] = [ [ id:'test', single_end:false ], // meta map
+                             [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                               file(params.modules_testdata_base_path + 'genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ]
+                           ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert !process.success },
+                { assert snapshot(process.out).match() },
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/fq/lint/tests/main.nf.test.snap b/modules/nf-core/fq/lint/tests/main.nf.test.snap
new file mode 100644
index 00000000..fec8e524
--- /dev/null
+++ b/modules/nf-core/fq/lint/tests/main.nf.test.snap
@@ -0,0 +1,25 @@
+{
+    "test_fq_lint_fail": {
+        "content": [
+            {
+                "0": [
+                    
+                ],
+                "1": [
+                    
+                ],
+                "lint": [
+                    
+                ],
+                "versions": [
+                    
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-19T16:37:02.133847389"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/fq/lint/tests/tags.yml b/modules/nf-core/fq/lint/tests/tags.yml
new file mode 100644
index 00000000..9c9c323f
--- /dev/null
+++ b/modules/nf-core/fq/lint/tests/tags.yml
@@ -0,0 +1,2 @@
+fq/lint:
+  - modules/nf-core/fq/lint/**
diff --git a/nextflow.config b/nextflow.config
index 9ab822e8..a9b27a67 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -13,6 +13,13 @@ params {
     // Input options
     input                      = null
     sample_size                = 0
+
+    // Options
+    skip_linting               = false
+    fq_lint_args               = ""
+    continue_with_lint_fail    = false
+
+
     // References
     genome                     = null
     fasta                      = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 3f84164a..77af3b5e 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -31,7 +31,6 @@
                 },
                 "outdir": {
                     "type": "string",
-                    "default": null,
                     "format": "directory-path",
                     "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                     "fa_icon": "fas fa-folder-open"
@@ -50,6 +49,30 @@
                 }
             }
         },
+        "validation_options": {
+            "title": "Validation options",
+            "type": "object",
+            "description": "Options for validating and screening FASTQ files.",
+            "default": "",
+            "properties": {
+                "skip_linting": {
+                    "type": "boolean",
+                    "default": false,
+                    "description": "Whether to lint the FASTQs before performing QC on the sequences",
+                    "help_text": "FASTQ files will be linted with FQ early in the pipeline. If they fail validation, the pipeline will terminate preventing expensive quality control steps being performed on the other samples. If ignoring FQ is enabled, quality control will be performed on the remaining samples."
+                },
+                "fq_lint_args": {
+                    "type": "string",
+                    "description": "Arguments to pass to FQ lint",
+                    "help_text": "Arguments to pass to FQ lint. This can be used to disable overly strict linting. See https://github.com/stjude-rust-labs/fq?tab=readme-ov-file#lint for more information."
+                },
+                "continue_with_lint_fail": {
+                    "type": "boolean",
+                    "description": "Whether to continue with the pipeline if linting fails for a single sample.",
+                    "help_text": "If set to true, the pipeline will continue with the remaining samples if linting fails for a single sample. If set to false, the pipeline will terminate if linting fails for a single sample."
+                }
+            }
+        },
         "reference_genome_options": {
             "title": "Reference genome options",
             "type": "object",
@@ -245,6 +268,9 @@
         {
             "$ref": "#/$defs/input_output_options"
         },
+        {
+            "$ref": "#/$defs/validation_options"
+        },
         {
             "$ref": "#/$defs/reference_genome_options"
         },
diff --git a/tests/rnaseq.main.nf.test b/tests/rnaseq.main.nf.test
new file mode 100644
index 00000000..411e58c5
--- /dev/null
+++ b/tests/rnaseq.main.nf.test
@@ -0,0 +1,87 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on NovaSeq6000 data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("rnaseq data test fail linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+            }
+        }
+
+        then {
+            assertAll(
+                // Linting should fail!
+                { assert workflow.failed }
+            )
+        }
+    }
+
+    test("rnaseq data test skip linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                skip_linting = true
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success }
+            )
+        }
+    }
+
+    test("rnaseq data test ignore linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                continue_with_lint_fail = true
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt")
+                    )
+                },
+            )
+        }
+    }
+
+    test("rnaseq data test add args to fq/lint") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                fq_lint_args = "--disable-validator P001"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt")
+                    )
+                },
+            )
+        }
+    }
+}
diff --git a/tests/rnaseq.main.nf.test.config b/tests/rnaseq.main.nf.test.config
new file mode 100644
index 00000000..f85acb50
--- /dev/null
+++ b/tests/rnaseq.main.nf.test.config
@@ -0,0 +1,8 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + '626c8fab639062eade4b10747e919341cbf9b41a/samplesheet/v3.10/samplesheet_test.csv'
+
+}
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index edce5425..f8775169 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -7,6 +7,7 @@ include { samplesheetToList } from 'plugin/nf-schema'
 */
 
 include { SEQTK_SAMPLE                  } from '../modules/nf-core/seqtk/sample/main'
+include { FQ_LINT                       } from '../modules/nf-core/fq/lint/main'
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 include { SEQFU_STATS                   } from '../modules/nf-core/seqfu/stats'
 include { FASTQSCREEN_FASTQSCREEN       } from '../modules/nf-core/fastqscreen/fastqscreen/main'
@@ -37,6 +38,24 @@ workflow SEQINSPECTOR {
     ch_multiqc_extra_files = Channel.empty()
     ch_multiqc_reports     = Channel.empty()
 
+    //
+    // MODULE: Run FQ_LINT to catch early errors
+    //
+    if ( !params.skip_linting ) {
+        FQ_LINT (
+            ch_samplesheet
+        )
+        ch_versions = ch_versions.mix(FQ_LINT.out.versions.first())
+        // This catches all FASTQs that pass linting
+        // If you use an error strategy that allows FQ_LINT to fail,
+        // only valid FASTQ files will be passed to the next module
+        ch_samplesheet = FQ_LINT.out.lint
+                            .join(ch_samplesheet)
+                            .map { meta, fq_lint, reads ->
+                                [meta, reads]
+                            }
+    }
+
     //
     // MODULE: Run Seqtk sample to perform subsampling
     //

From a8f6944f7fe1c11e9712d31d5bc7a30535dfb2c5 Mon Sep 17 00:00:00 2001
From: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Date: Thu, 19 Dec 2024 11:25:05 +0000
Subject: [PATCH 147/172] prettier

---
 modules.json | 46 ++++++++++++----------------------------------
 1 file changed, 12 insertions(+), 34 deletions(-)

diff --git a/modules.json b/modules.json
index 00a9f11f..82514096 100644
--- a/modules.json
+++ b/modules.json
@@ -8,59 +8,43 @@
                     "bowtie2/build": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "fastqscreen/buildfromindex": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "fastqscreen/fastqscreen": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ],
+                        "installed_by": ["modules"],
                         "patch": "modules/nf-core/fastqscreen/fastqscreen/fastqscreen-fastqscreen.diff"
                     },
                     "fq/lint": {
                         "branch": "master",
                         "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "seqfu/stats": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     },
                     "seqtk/sample": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-                        "installed_by": [
-                            "modules"
-                        ]
+                        "installed_by": ["modules"]
                     }
                 }
             },
@@ -69,26 +53,20 @@
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "c2b22d85f30a706a3073387f30380704fcae013b",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
                         "git_sha": "51ae5406a030d4da1e49e4dab49756844fdd6c7a",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
                         "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
-                        "installed_by": [
-                            "subworkflows"
-                        ]
+                        "installed_by": ["subworkflows"]
                     }
                 }
             }
         }
     }
-}
\ No newline at end of file
+}

From 4e30ba80afe899f78116af1e92d52d509d1fdeae Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 29 Oct 2024 10:11:24 +0100
Subject: [PATCH 148/172] Add skip tools parameter

---
 nextflow.config           |  1 +
 nextflow_schema.json      |  5 +++++
 workflows/seqinspector.nf | 29 +++++++++++++++++------------
 3 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/nextflow.config b/nextflow.config
index 9ab822e8..924274c1 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -13,6 +13,7 @@ params {
     // Input options
     input                      = null
     sample_size                = 0
+    skip_tools                 = ''
     // References
     genome                     = null
     fasta                      = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 3f84164a..465b2a23 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -47,6 +47,11 @@
                     "type": "string",
                     "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
                     "fa_icon": "fas fa-file-signature"
+                },
+                "skip_tools": {
+                    "type": "string",
+                    "description": "Comma-separated string of tools to skip",
+                    "pattern": "^(fastqc|seqfu_stats)(,(fastqc|seqfu_stats))*$$"
                 }
             }
         },
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index edce5425..0888270e 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -31,6 +31,7 @@ workflow SEQINSPECTOR {
     ch_samplesheet               // channel: samplesheet read in from --input
 
     main:
+    skip_tools = params.skip_tools ? params.skip_tools.split(',') : []
 
     ch_versions            = Channel.empty()
     ch_multiqc_files       = Channel.empty()
@@ -55,23 +56,27 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run FastQC
     //
-    FASTQC (
-        ch_sample_sized.map {
-            meta, subsampled -> [meta, subsampled]
-        }
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
-    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    if (!("fastqc" in skip_tools)) {
+        FASTQC (
+            ch_sample_sized.map {
+                meta, subsampled -> [meta, subsampled]
+            }
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
+        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    }
 
 
     //
     // Module: Run SeqFu stats
     //
-    SEQFU_STATS (
-        ch_samplesheet
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
-    ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+    if (!("seqfu_stats" in skip_tools)) {
+        SEQFU_STATS (
+            ch_samplesheet
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
+        ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+    }
 
     //
     // MODULE: Run FastQ Screen

From 503794916196e645b4fe5ff2327743cbdf14e1e9 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 22 Nov 2024 13:32:10 +0100
Subject: [PATCH 149/172] Add tests for skip_tools

---
 tests/MiSeq.main.nf.test      | 23 +++++++++++++++++++++++
 tests/MiSeq.main.nf.test.snap | 12 +++++++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index a1badfac..d5851898 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -27,4 +27,27 @@ nextflow_pipeline {
             )
         }
     }
+
+    test("Miseq data test (skip fastqc)") {
+        when {
+            config "./MiSeq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                skip_tools = "fastqc"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    ).match()
+                },
+                {
+                  assert !path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt").exists()
+                }
+            )
+        }
+    }
 }
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index af7022dd..9d8026d0 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -10,6 +10,16 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-05T15:15:09.227024034"
+        "timestamp": "2024-12-13T16:10:21.816261"
+    },
+    "Miseq data test (skip fastqc)": {
+        "content": [
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a"
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-13T16:10:53.718831"
     }
 }
\ No newline at end of file

From e48d5b71c4bb4a10e355b7c3b66401eeafc2929a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 22 Nov 2024 13:52:03 +0100
Subject: [PATCH 150/172] Update docs

---
 docs/usage.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/docs/usage.md b/docs/usage.md
index 01211f28..c82131e1 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -98,6 +98,12 @@ Optionally, the `sample_size` parameter allows you to subset a random number of
 nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 1000000 -profile docker
 ```
 
+### Skipping tools
+
+Some tools might not be compatible with your data. In this case it might be desired to skip some of them. This can be done easily by providing a comma-separated list of tools to be skipped with the `--skip_tools` parameter.
+
+In case you want to make this more permanent, it is recommended to specify this in a params file, or even in your own nextflow configuration file. The nextflow configuration file can also be use to customise tool arguments. See official [nexflow](https://www.nextflow.io/docs/latest/config.html) and [nf-core](https://nf-co.re/docs/usage/configuration) documentation for further details.
+
 ### Updating the pipeline
 
 When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:

From e75d68477bc762ba00efb8ced2830471e07d5736 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 22 Nov 2024 14:19:48 +0100
Subject: [PATCH 151/172] Update CHANGELOG

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 91ee0b7f..6086d786 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#68](https://github.com/nf-core/seqinspector/pull/68) Add tool selector
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.

From af55550218f9cb1a0d25a4c66718bfe1aa5652d0 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 22 Nov 2024 14:21:45 +0100
Subject: [PATCH 152/172] Fixed linting

---
 tests/MiSeq.main.nf.test | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index d5851898..0b584453 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -45,7 +45,7 @@ nextflow_pipeline {
                     ).match()
                 },
                 {
-                  assert !path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt").exists()
+                    assert !path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt").exists()
                 }
             )
         }

From 868f8c20f9dc94c1bdac962acd06f30544468c07 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 16:16:17 +0100
Subject: [PATCH 153/172] Improve `skip_tools` regex pattern

---
 nextflow_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 465b2a23..a0cbf942 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -51,7 +51,7 @@
                 "skip_tools": {
                     "type": "string",
                     "description": "Comma-separated string of tools to skip",
-                    "pattern": "^(fastqc|seqfu_stats)(,(fastqc|seqfu_stats))*$$"
+                    "pattern": "^((fastqc|fastqscreen|seqfu_stats|seqtk_sample)?,?)*(?<!,)$"
                 }
             }
         },

From 439d747e465e7eceadd98acce17472abbb296d0a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 16:16:52 +0100
Subject: [PATCH 154/172] Add option to skip fastqscreen and subsampling

---
 nextflow_schema.json      |  4 ++--
 workflows/seqinspector.nf | 36 +++++++++++++++++++-----------------
 2 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index a0cbf942..248660b7 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -25,9 +25,9 @@
                 },
                 "sample_size": {
                     "type": "integer",
-                    "default": 0,
                     "description": "Take this number of reads as a subset.",
-                    "help_text": "Choose the size of the subset or 0, if no subsampling shall be performed. Note that it refers to an absolute number."
+                    "help_text": "Choose the size of the subset or 0, if no subsampling shall be performed. Note that it refers to an absolute number.",
+                    "default": 0
                 },
                 "outdir": {
                     "type": "string",
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 0888270e..fc9b8f7f 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -41,7 +41,7 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run Seqtk sample to perform subsampling
     //
-    if (params.sample_size > 0 ) {
+    if (!("seqtk_sample" in skip_tools) && params.sample_size > 0) {
         ch_sample_sized = SEQTK_SAMPLE(
             ch_samplesheet.map {
                 meta, reads -> [meta, reads, params.sample_size]
@@ -49,7 +49,7 @@ workflow SEQINSPECTOR {
         ).reads
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
     } else {
-        // No do subsample
+        // No subsampling
         ch_sample_sized = ch_samplesheet
     }
 
@@ -85,21 +85,23 @@ workflow SEQINSPECTOR {
     // Parse the reference info needed to create a FastQ Screen config file
     // and transpose it into a tuple containing lists for each property
 
-    ch_fastqscreen_refs = Channel
-        .fromList(samplesheetToList(
-            "${projectDir}/assets/example_fastq_screen_references.csv",
-            "${projectDir}/assets/schema_fastq_screen_references.json"
-        ))
-        .toList()
-        .transpose()
-        .toList()
-
-    FASTQSCREEN_FASTQSCREEN (
-        ch_samplesheet,
-        ch_fastqscreen_refs
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
-    ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
+    if (!("fastqscreen" in skip_tools)) {
+        ch_fastqscreen_refs = Channel
+            .fromList(samplesheetToList(
+                "${projectDir}/assets/example_fastq_screen_references.csv",
+                "${projectDir}/assets/schema_fastq_screen_references.json"
+            ))
+            .toList()
+            .transpose()
+            .toList()
+
+        FASTQSCREEN_FASTQSCREEN (
+            ch_samplesheet,
+            ch_fastqscreen_refs
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
+        ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
+    }
 
     //
     // Collate and save software versions

From ad6a2c4a3da72d28b888c54634650be600bb911e Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 13 Dec 2024 16:19:30 +0100
Subject: [PATCH 155/172] Fix link to nf-core docs

---
 docs/usage.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/usage.md b/docs/usage.md
index c82131e1..2d84000e 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -102,7 +102,7 @@ nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results -
 
 Some tools might not be compatible with your data. In this case it might be desired to skip some of them. This can be done easily by providing a comma-separated list of tools to be skipped with the `--skip_tools` parameter.
 
-In case you want to make this more permanent, it is recommended to specify this in a params file, or even in your own nextflow configuration file. The nextflow configuration file can also be use to customise tool arguments. See official [nexflow](https://www.nextflow.io/docs/latest/config.html) and [nf-core](https://nf-co.re/docs/usage/configuration) documentation for further details.
+In case you want to make this more permanent, it is recommended to specify this in a params file, or even in your own nextflow configuration file. The nextflow configuration file can also be use to customise tool arguments. See official [nexflow](https://www.nextflow.io/docs/latest/config.html) and [nf-core](https://nf-co.re/docs/usage/configuration#customising-tool-arguments) documentation for further details.
 
 ### Updating the pipeline
 

From e3c10e393e55c77e3973b67fec1b43a1b6d28c45 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Wed, 15 Jan 2025 15:32:11 +0100
Subject: [PATCH 156/172] Set nf_core version to 3.1.1

---
 .nf-core.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.nf-core.yml b/.nf-core.yml
index 7c9cb078..4bf81e71 100644
--- a/.nf-core.yml
+++ b/.nf-core.yml
@@ -1,7 +1,7 @@
 lint:
   files_unchanged:
     - .github/CONTRIBUTING.md
-nf_core_version: 3.1.2.dev0
+nf_core_version: 3.1.1
 repository_type: pipeline
 template:
   author: Adrien Coulier

From 2ab4fa0a1c72ba0d8ce145ef32d01da9b387937c Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Wed, 15 Jan 2025 15:39:22 +0100
Subject: [PATCH 157/172] Remove double include of modules.config

---
 nextflow.config | 1 -
 1 file changed, 1 deletion(-)

diff --git a/nextflow.config b/nextflow.config
index 2703524a..3f726e02 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -57,7 +57,6 @@ params {
 
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
-includeConfig 'conf/modules.config'
 
 profiles {
     debug {

From 78edd609d58af9aaadee44b2ded0934ec3e18637 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 17 Jan 2025 13:47:28 +0100
Subject: [PATCH 158/172] Update CITATIONS.md
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: Júlia Mir Pedrol <mirp.julia@gmail.com>
---
 CITATIONS.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/CITATIONS.md b/CITATIONS.md
index b1c06043..a8aaa88e 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -12,7 +12,9 @@
 
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+
+- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 - [SeqFu](https://telatin.github.io/seqfu2/)
 

From 59490988c5d5ed60a2142a815f18b86390990f44 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 17 Jan 2025 13:47:42 +0100
Subject: [PATCH 159/172] Update README.md
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: Júlia Mir Pedrol <mirp.julia@gmail.com>
---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 238dc163..e884871d 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,8 @@
     <source media="(prefers-color-scheme: dark)" srcset="docs/images/nf-core-seqinspector_logo_dark.png">
     <img alt="nf-core/seqinspector" src="docs/images/nf-core-seqinspector_logo_light.png">
   </picture>
-</h1>[![GitHub Actions CI Status](https://github.com/nf-core/seqinspector/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/seqinspector/actions/workflows/ci.yml)
+</h1>
+[![GitHub Actions CI Status](https://github.com/nf-core/seqinspector/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/seqinspector/actions/workflows/ci.yml)
 [![GitHub Actions Linting Status](https://github.com/nf-core/seqinspector/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/seqinspector/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/seqinspector/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 

From 0a9958847b35bd77bec48eea95dd787cc007d1ec Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 17 Jan 2025 13:48:33 +0100
Subject: [PATCH 160/172] Update README.md
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: Júlia Mir Pedrol <mirp.julia@gmail.com>
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index e884871d..c60b7dfa 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,7 @@
 ## Usage
 
 > [!NOTE]
-> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow.Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
+> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
 First, prepare a samplesheet with your input data that looks as follows:
 

From 84e15b0e45d74bad9d3c31ca8f2a1561d3ab4359 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Fri, 17 Jan 2025 13:48:58 +0100
Subject: [PATCH 161/172] Update docs/output.md
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: Júlia Mir Pedrol <mirp.julia@gmail.com>
---
 docs/output.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docs/output.md b/docs/output.md
index a9f505fb..3d3c3497 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -110,7 +110,9 @@ nf-core/seqinspector will generate the following MultiQC reports:
 
 [MultiQC](http://multiqc.info) is a visualization tool that generates a single HTML report summarising all samples in your project. Most of the pipeline QC results are visualised in the report and further statistics are available in the report data directory.
 
-Results generated by MultiQC collate pipeline QC from supported tools e.g. FastQC. The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. For more information about how to use MultiQC reports, see <http://multiqc.info>.### Pipeline information
+Results generated by MultiQC collate pipeline QC from supported tools e.g. FastQC. The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. For more information about how to use MultiQC reports, see <http://multiqc.info>.
+
+### Pipeline information
 
 <details markdown="1">
 <summary>Output files</summary>

From 734a412da526e69a89dcb2ac9595025a68ba110a Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 7 Jan 2025 16:55:07 +0100
Subject: [PATCH 162/172] Set up nft-utils in tests

---
 nf-test.config                      |   3 +
 tests/.nftignore                    |  12 +
 tests/MiSeq.main.nf.test            |  90 +++-
 tests/MiSeq.main.nf.test.snap       | 225 +++++++++-
 tests/NovaSeq6000.main.nf.test      |  47 +--
 tests/NovaSeq6000.main.nf.test.snap | 610 +++++++++++++++++++++++++++-
 tests/PromethION.main.nf.test       |  27 +-
 tests/PromethION.main.nf.test.snap  | 141 ++++++-
 8 files changed, 1070 insertions(+), 85 deletions(-)
 create mode 100644 tests/.nftignore

diff --git a/nf-test.config b/nf-test.config
index 6969c085..d4d15358 100644
--- a/nf-test.config
+++ b/nf-test.config
@@ -5,4 +5,7 @@ config {
     configFile "tests/nextflow.config"
     profile "test,docker"
 
+    plugins {
+        load "nft-utils@0.0.3"
+    }
 }
diff --git a/tests/.nftignore b/tests/.nftignore
new file mode 100644
index 00000000..504be1c6
--- /dev/null
+++ b/tests/.nftignore
@@ -0,0 +1,12 @@
+.DS_Store
+multiqc/{global_report,group_reports/*}/multiqc_data/multiqc.log
+multiqc/{global_report,group_reports/*}/multiqc_data/multiqc_data.json
+multiqc/{global_report,group_reports/*}/multiqc_data/multiqc_general_stats.txt
+multiqc/{global_report,group_reports/*}/multiqc_data/multiqc_software_versions.txt
+multiqc/{global_report,group_reports/*}/multiqc_data/multiqc_sources.txt
+multiqc/{global_report,group_reports/*}/multiqc_data/fastqc_top_overrepresented_sequences_table.txt
+multiqc/{global_report,group_reports/*}/multiqc_plots/{svg,pdf,png}/*.{svg,pdf,png}
+multiqc/{global_report,group_reports/*}/multiqc_report.html
+pipeline_info/*.{html,json,txt,yml}
+fastqscreen/*_screen.html
+fastqc/*_fastqc.zip
diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
index 0b584453..0ed7052a 100644
--- a/tests/MiSeq.main.nf.test
+++ b/tests/MiSeq.main.nf.test
@@ -15,15 +15,28 @@ nextflow_pipeline {
         }
 
         then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(
+                params.outdir,
+                relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']
+            )
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(
+                params.outdir,
+                ignoreFile: 'tests/.nftignore'
+            )
             assertAll(
-                { assert workflow.success },
+                { assert workflow.success},
                 { assert snapshot(
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
-                    ).match()
-                }
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"),
+                    // All stable path names, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
             )
         }
     }
@@ -38,15 +51,64 @@ nextflow_pipeline {
         }
 
         then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(
+                params.outdir,
+                relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']
+            )
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(
+                params.outdir,
+                ignoreFile: 'tests/.nftignore'
+            )
+            assertAll(
+                { assert workflow.success},
+                { assert snapshot(
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"),
+                    // All stable path names, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
+            )
+        }
+    }
+
+    test("Miseq data test (skip all tools)") {
+        when {
+            config "./MiSeq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                skip_tools = "fastqc,fastqscreen,seqfu_stats,seqtk_sample"
+            }
+        }
+
+        then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(
+                params.outdir,
+                relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']
+            )
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(
+                params.outdir,
+                ignoreFile: 'tests/.nftignore'
+            )
             assertAll(
-                { assert workflow.success },
+                { assert workflow.success},
                 { assert snapshot(
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
-                    ).match()
-                },
-                {
-                    assert !path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt").exists()
-                }
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"),
+                    // All stable path names, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
             )
         }
     }
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 9d8026d0..66996292 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -1,25 +1,232 @@
 {
     "MiSeq data test": {
         "content": [
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
-            "multiqc_general_stats.txt:md5,5b28a83b14cb2fe88d084d08900ebdbf",
-            "multiqc_fastq_screen.txt:md5,bd50a8641c6481cc497fc6e3e9af2607"
+            4,
+            {
+                "FASTQC": {
+                    "fastqc": "0.12.1"
+                },
+                "FASTQSCREEN_FASTQSCREEN": {
+                    "fastqscreen": "0.16.0"
+                },
+                "SEQFU_STATS": {
+                    "seqfu": "1.20.3"
+                },
+                "Workflow": {
+                    "nf-core/seqinspector": "v1.0dev"
+                }
+            },
+            [
+                "fastqc",
+                "fastqc/SAMPLE_SINGLE_END_1_fastqc.html",
+                "fastqc/SAMPLE_SINGLE_END_1_fastqc.zip",
+                "fastqscreen",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.html",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.png",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.txt",
+                "multiqc",
+                "multiqc/global_report",
+                "multiqc/global_report/multiqc_data",
+                "multiqc/global_report/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/global_report/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/global_report/multiqc_data/multiqc.log",
+                "multiqc/global_report/multiqc_data/multiqc_SAMPLE_SINGLE_END_1.txt",
+                "multiqc/global_report/multiqc_data/multiqc_citations.txt",
+                "multiqc/global_report/multiqc_data/multiqc_data.json",
+                "multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/global_report/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/global_report/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/global_report/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sources.txt",
+                "multiqc/global_report/multiqc_plots",
+                "multiqc/global_report/multiqc_plots/pdf",
+                "multiqc/global_report/multiqc_plots/pdf/SAMPLE_SINGLE_END_1.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/global_report/multiqc_plots/png",
+                "multiqc/global_report/multiqc_plots/png/SAMPLE_SINGLE_END_1.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/global_report/multiqc_plots/png/general_stats_table.png",
+                "multiqc/global_report/multiqc_plots/svg",
+                "multiqc/global_report/multiqc_plots/svg/SAMPLE_SINGLE_END_1.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/global_report/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/global_report/multiqc_report.html",
+                "pipeline_info",
+                "pipeline_info/nf_core_seqinspector_software_mqc_versions.yml",
+                "seqfu_stats",
+                "seqfu_stats/SAMPLE_SINGLE_END_1.tsv",
+                "seqfu_stats/SAMPLE_SINGLE_END_1_mqc.txt"
+            ],
+            [
+                "SAMPLE_SINGLE_END_1_fastqc.html:md5,a299e4a9a0b5aa289d6a325b71f915ce",
+                "SAMPLE_SINGLE_END_1_screen.png:md5,ad98ae0f39335aede67e0a233cf16616",
+                "SAMPLE_SINGLE_END_1_screen.txt:md5,588b1b1f2d307fae7272ab0819e4bac5",
+                "fastq_screen_plot.txt:md5,8393eabda6ebac90ff00533f9562271f",
+                "fastqc-status-check-heatmap.txt:md5,8f98652c377741c974e485652a19f37f",
+                "fastqc_overrepresented_sequences_plot.txt:md5,cdc7479933cae03e0043ae794f81c304",
+                "fastqc_per_base_n_content_plot.txt:md5,dd8d6976dc5ea8cf67d9fa2c3be9e24b",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,5f9a98d3068aab17f26731ae0615f41a",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,1de1333bb959189dcf8230706f60dbfc",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,62f140bfa52d462c9c499dfdabc35476",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,5fda43eb9b7c60cf6b4348f734a94b26",
+                "fastqc_sequence_counts_plot.txt:md5,00cd6842465f7aa9ae75434e175946a6",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,c3befe0812d2f1c23d5e75e6fccf0622",
+                "multiqc_SAMPLE_SINGLE_END_1.txt:md5,8e6989a2392f599a09a5c3edf8119702",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,bd50a8641c6481cc497fc6e3e9af2607",
+                "multiqc_fastqc.txt:md5,7b1b7fd457b60404768045b148d4c0a8",
+                "SAMPLE_SINGLE_END_1.tsv:md5,f65c868e562291647d539090698ba5eb",
+                "SAMPLE_SINGLE_END_1_mqc.txt:md5,1de529f1e2cbd4df0945cb08a24d6d39"
+            ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.10.2"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-13T16:10:21.816261"
+        "timestamp": "2025-02-03T16:39:35.285693"
+    },
+    "Miseq data test (skip all tools)": {
+        "content": [
+            1,
+            {
+                "Workflow": {
+                    "nf-core/seqinspector": "v1.0dev"
+                }
+            },
+            [
+                "multiqc",
+                "multiqc/global_report",
+                "multiqc/global_report/multiqc_data",
+                "multiqc/global_report/multiqc_data/multiqc.log",
+                "multiqc/global_report/multiqc_data/multiqc_citations.txt",
+                "multiqc/global_report/multiqc_data/multiqc_data.json",
+                "multiqc/global_report/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sources.txt",
+                "multiqc/global_report/multiqc_report.html",
+                "pipeline_info",
+                "pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"
+            ],
+            [
+                "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.3"
+        },
+        "timestamp": "2025-01-07T13:49:22.707398"
     },
     "Miseq data test (skip fastqc)": {
         "content": [
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a"
+            3,
+            {
+                "FASTQSCREEN_FASTQSCREEN": {
+                    "fastqscreen": "0.16.0"
+                },
+                "SEQFU_STATS": {
+                    "seqfu": "1.20.3"
+                },
+                "Workflow": {
+                    "nf-core/seqinspector": "v1.0dev"
+                }
+            },
+            [
+                "fastqscreen",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.html",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.png",
+                "fastqscreen/SAMPLE_SINGLE_END_1_screen.txt",
+                "multiqc",
+                "multiqc/global_report",
+                "multiqc/global_report/multiqc_data",
+                "multiqc/global_report/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/global_report/multiqc_data/multiqc.log",
+                "multiqc/global_report/multiqc_data/multiqc_SAMPLE_SINGLE_END_1.txt",
+                "multiqc/global_report/multiqc_data/multiqc_citations.txt",
+                "multiqc/global_report/multiqc_data/multiqc_data.json",
+                "multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/global_report/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sources.txt",
+                "multiqc/global_report/multiqc_plots",
+                "multiqc/global_report/multiqc_plots/pdf",
+                "multiqc/global_report/multiqc_plots/pdf/SAMPLE_SINGLE_END_1.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/png",
+                "multiqc/global_report/multiqc_plots/png/SAMPLE_SINGLE_END_1.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/svg",
+                "multiqc/global_report/multiqc_plots/svg/SAMPLE_SINGLE_END_1.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/global_report/multiqc_report.html",
+                "pipeline_info",
+                "pipeline_info/nf_core_seqinspector_software_mqc_versions.yml",
+                "seqfu_stats",
+                "seqfu_stats/SAMPLE_SINGLE_END_1.tsv",
+                "seqfu_stats/SAMPLE_SINGLE_END_1_mqc.txt"
+            ],
+            [
+                "SAMPLE_SINGLE_END_1_screen.png:md5,ad98ae0f39335aede67e0a233cf16616",
+                "SAMPLE_SINGLE_END_1_screen.txt:md5,588b1b1f2d307fae7272ab0819e4bac5",
+                "fastq_screen_plot.txt:md5,8393eabda6ebac90ff00533f9562271f",
+                "multiqc_SAMPLE_SINGLE_END_1.txt:md5,8e6989a2392f599a09a5c3edf8119702",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,bd50a8641c6481cc497fc6e3e9af2607",
+                "SAMPLE_SINGLE_END_1.tsv:md5,f65c868e562291647d539090698ba5eb",
+                "SAMPLE_SINGLE_END_1_mqc.txt:md5,1de529f1e2cbd4df0945cb08a24d6d39"
+            ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.10.2"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-13T16:10:53.718831"
+        "timestamp": "2025-02-03T16:40:27.8664"
     }
 }
\ No newline at end of file
diff --git a/tests/NovaSeq6000.main.nf.test b/tests/NovaSeq6000.main.nf.test
index e70a191c..8eea81f7 100644
--- a/tests/NovaSeq6000.main.nf.test
+++ b/tests/NovaSeq6000.main.nf.test
@@ -15,35 +15,28 @@ nextflow_pipeline {
         }
 
         then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(
+                params.outdir,
+                relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']
+            )
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(
+                params.outdir,
+                ignoreFile: 'tests/.nftignore'
+            )
             assertAll(
-                { assert workflow.success },
+                { assert workflow.success},
                 { assert snapshot(
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
-
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/lane1/multiqc_data/multiqc_fastq_screen.txt"),
-
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group1/multiqc_data/multiqc_fastq_screen.txt"),
-
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/group2/multiqc_data/multiqc_fastq_screen.txt"),
-
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt"),
-                    ).match()
-                },
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"),
+                    // All stable path names, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
             )
         }
     }
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 9b3826a5..0a9ab878 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -1,31 +1,597 @@
 {
     "NovaSeq6000 data test": {
         "content": [
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
-            "multiqc_general_stats.txt:md5,25abe0f6a35eb4a3b056fc3cf5c13732",
-            "multiqc_fastq_screen.txt:md5,2ff2485b1f197cb6228dd4350d1bd638",
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
-            "multiqc_general_stats.txt:md5,90ee35137492b80aab36ef67f72d8921",
-            "multiqc_fastq_screen.txt:md5,c54d863ed3e68ee8bcb51c9ad85de9bc",
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
-            "multiqc_general_stats.txt:md5,d62a2fc39e674d98783d408791803148",
-            "multiqc_fastq_screen.txt:md5,737dc47e74e5b2f2c590652788831eff",
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
-            "multiqc_general_stats.txt:md5,2f09b8f199ac40cf67ba50843cebd29c",
-            "multiqc_fastq_screen.txt:md5,568f6b6d14562d01b5aaeb1a39e1cf3d",
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
-            "multiqc_general_stats.txt:md5,6a1c16f068d7ba3a9225a17eb570ed9a",
-            "multiqc_fastq_screen.txt:md5,a4dca31413036d35899a35ba14b17ea5"
+            20,
+            {
+                "FASTQC": {
+                    "fastqc": "0.12.1"
+                },
+                "FASTQSCREEN_FASTQSCREEN": {
+                    "fastqscreen": "0.16.0"
+                },
+                "SEQFU_STATS": {
+                    "seqfu": "1.20.3"
+                },
+                "Workflow": {
+                    "nf-core/seqinspector": "v1.0dev"
+                }
+            },
+            [
+                "fastqc",
+                "fastqc/Sample1_1_fastqc.html",
+                "fastqc/Sample1_1_fastqc.zip",
+                "fastqc/Sample23_3_fastqc.html",
+                "fastqc/Sample23_3_fastqc.zip",
+                "fastqc/SampleA_2_fastqc.html",
+                "fastqc/SampleA_2_fastqc.zip",
+                "fastqc/Undetermined_5_fastqc.html",
+                "fastqc/Undetermined_5_fastqc.zip",
+                "fastqc/sampletest_4_fastqc.html",
+                "fastqc/sampletest_4_fastqc.zip",
+                "fastqscreen",
+                "fastqscreen/Sample1_1_screen.html",
+                "fastqscreen/Sample1_1_screen.png",
+                "fastqscreen/Sample1_1_screen.txt",
+                "fastqscreen/Sample23_3_screen.html",
+                "fastqscreen/Sample23_3_screen.png",
+                "fastqscreen/Sample23_3_screen.txt",
+                "fastqscreen/SampleA_2_screen.html",
+                "fastqscreen/SampleA_2_screen.png",
+                "fastqscreen/SampleA_2_screen.txt",
+                "fastqscreen/Undetermined_5_screen.html",
+                "fastqscreen/Undetermined_5_screen.png",
+                "fastqscreen/Undetermined_5_screen.txt",
+                "fastqscreen/sampletest_4_screen.html",
+                "fastqscreen/sampletest_4_screen.png",
+                "fastqscreen/sampletest_4_screen.txt",
+                "multiqc",
+                "multiqc/global_report",
+                "multiqc/global_report/multiqc_data",
+                "multiqc/global_report/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/global_report/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/global_report/multiqc_data/multiqc.log",
+                "multiqc/global_report/multiqc_data/multiqc_Sample1_1.txt",
+                "multiqc/global_report/multiqc_data/multiqc_Sample23_3.txt",
+                "multiqc/global_report/multiqc_data/multiqc_SampleA_2.txt",
+                "multiqc/global_report/multiqc_data/multiqc_Undetermined_5.txt",
+                "multiqc/global_report/multiqc_data/multiqc_citations.txt",
+                "multiqc/global_report/multiqc_data/multiqc_data.json",
+                "multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/global_report/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/global_report/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sampletest_4.txt",
+                "multiqc/global_report/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sources.txt",
+                "multiqc/global_report/multiqc_plots",
+                "multiqc/global_report/multiqc_plots/pdf",
+                "multiqc/global_report/multiqc_plots/pdf/Sample1_1.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/Sample23_3.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/SampleA_2.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/Undetermined_5.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/sampletest_4.pdf",
+                "multiqc/global_report/multiqc_plots/png",
+                "multiqc/global_report/multiqc_plots/png/Sample1_1.png",
+                "multiqc/global_report/multiqc_plots/png/Sample23_3.png",
+                "multiqc/global_report/multiqc_plots/png/SampleA_2.png",
+                "multiqc/global_report/multiqc_plots/png/Undetermined_5.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/global_report/multiqc_plots/png/general_stats_table.png",
+                "multiqc/global_report/multiqc_plots/png/sampletest_4.png",
+                "multiqc/global_report/multiqc_plots/svg",
+                "multiqc/global_report/multiqc_plots/svg/Sample1_1.svg",
+                "multiqc/global_report/multiqc_plots/svg/Sample23_3.svg",
+                "multiqc/global_report/multiqc_plots/svg/SampleA_2.svg",
+                "multiqc/global_report/multiqc_plots/svg/Undetermined_5.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/global_report/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/global_report/multiqc_plots/svg/sampletest_4.svg",
+                "multiqc/global_report/multiqc_report.html",
+                "multiqc/group_reports",
+                "multiqc/group_reports/group1",
+                "multiqc/group_reports/group1/multiqc_data",
+                "multiqc/group_reports/group1/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/group_reports/group1/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc.log",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_Sample1_1.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_SampleA_2.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_citations.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_data.json",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/group_reports/group1/multiqc_data/multiqc_sources.txt",
+                "multiqc/group_reports/group1/multiqc_plots",
+                "multiqc/group_reports/group1/multiqc_plots/pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/Sample1_1.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/SampleA_2.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/group_reports/group1/multiqc_plots/png",
+                "multiqc/group_reports/group1/multiqc_plots/png/Sample1_1.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/SampleA_2.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/group_reports/group1/multiqc_plots/png/general_stats_table.png",
+                "multiqc/group_reports/group1/multiqc_plots/svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/Sample1_1.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/SampleA_2.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/group_reports/group1/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/group_reports/group1/multiqc_report.html",
+                "multiqc/group_reports/group2",
+                "multiqc/group_reports/group2/multiqc_data",
+                "multiqc/group_reports/group2/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/group_reports/group2/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc.log",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_Sample23_3.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_citations.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_data.json",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/group_reports/group2/multiqc_data/multiqc_sources.txt",
+                "multiqc/group_reports/group2/multiqc_plots",
+                "multiqc/group_reports/group2/multiqc_plots/pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/Sample23_3.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/group_reports/group2/multiqc_plots/png",
+                "multiqc/group_reports/group2/multiqc_plots/png/Sample23_3.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/group_reports/group2/multiqc_plots/png/general_stats_table.png",
+                "multiqc/group_reports/group2/multiqc_plots/svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/Sample23_3.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/group_reports/group2/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/group_reports/group2/multiqc_report.html",
+                "multiqc/group_reports/lane1",
+                "multiqc/group_reports/lane1/multiqc_data",
+                "multiqc/group_reports/lane1/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/group_reports/lane1/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc.log",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_Sample1_1.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_Sample23_3.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_SampleA_2.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_citations.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_data.json",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/group_reports/lane1/multiqc_data/multiqc_sources.txt",
+                "multiqc/group_reports/lane1/multiqc_plots",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/Sample1_1.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/Sample23_3.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/SampleA_2.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/group_reports/lane1/multiqc_plots/png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/Sample1_1.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/Sample23_3.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/SampleA_2.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/group_reports/lane1/multiqc_plots/png/general_stats_table.png",
+                "multiqc/group_reports/lane1/multiqc_plots/svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/Sample1_1.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/Sample23_3.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/SampleA_2.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/group_reports/lane1/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/group_reports/lane1/multiqc_report.html",
+                "multiqc/group_reports/test",
+                "multiqc/group_reports/test/multiqc_data",
+                "multiqc/group_reports/test/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/group_reports/test/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc.log",
+                "multiqc/group_reports/test/multiqc_data/multiqc_Sample23_3.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_Undetermined_5.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_citations.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_data.json",
+                "multiqc/group_reports/test/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_sampletest_4.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/group_reports/test/multiqc_data/multiqc_sources.txt",
+                "multiqc/group_reports/test/multiqc_plots",
+                "multiqc/group_reports/test/multiqc_plots/pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/Sample23_3.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/Undetermined_5.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/group_reports/test/multiqc_plots/pdf/sampletest_4.pdf",
+                "multiqc/group_reports/test/multiqc_plots/png",
+                "multiqc/group_reports/test/multiqc_plots/png/Sample23_3.png",
+                "multiqc/group_reports/test/multiqc_plots/png/Undetermined_5.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/group_reports/test/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/group_reports/test/multiqc_plots/png/general_stats_table.png",
+                "multiqc/group_reports/test/multiqc_plots/png/sampletest_4.png",
+                "multiqc/group_reports/test/multiqc_plots/svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/Sample23_3.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/Undetermined_5.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/group_reports/test/multiqc_plots/svg/sampletest_4.svg",
+                "multiqc/group_reports/test/multiqc_report.html",
+                "pipeline_info",
+                "pipeline_info/nf_core_seqinspector_software_mqc_versions.yml",
+                "seqfu_stats",
+                "seqfu_stats/Sample1_1.tsv",
+                "seqfu_stats/Sample1_1_mqc.txt",
+                "seqfu_stats/Sample23_3.tsv",
+                "seqfu_stats/Sample23_3_mqc.txt",
+                "seqfu_stats/SampleA_2.tsv",
+                "seqfu_stats/SampleA_2_mqc.txt",
+                "seqfu_stats/Undetermined_5.tsv",
+                "seqfu_stats/Undetermined_5_mqc.txt",
+                "seqfu_stats/sampletest_4.tsv",
+                "seqfu_stats/sampletest_4_mqc.txt"
+            ],
+            [
+                "Sample1_1_fastqc.html:md5,358c1d6e7ea23b531312d88b51f525fa",
+                "Sample23_3_fastqc.html:md5,5b2b55815c667515184d1591fc57249b",
+                "SampleA_2_fastqc.html:md5,ecc7ab9529216dac84acc864bde7c839",
+                "Undetermined_5_fastqc.html:md5,ec71c3ad29df3c70411777b0bcbddd61",
+                "sampletest_4_fastqc.html:md5,62fc1e99df0da04e3dd5e17fa608a763",
+                "Sample1_1_screen.png:md5,562256290643b51e4374c2225a15f463",
+                "Sample1_1_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
+                "Sample23_3_screen.png:md5,6bb2caf67b9b2ed25d3d5f32c343e9ab",
+                "Sample23_3_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
+                "SampleA_2_screen.png:md5,b2c3e95e034f5c038754bf108537de0e",
+                "SampleA_2_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
+                "Undetermined_5_screen.png:md5,fc5d53f8876dfae3d1a781fa512ea1db",
+                "Undetermined_5_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
+                "sampletest_4_screen.png:md5,1fb60070e8f4b70de0c1b3786b54f27e",
+                "sampletest_4_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
+                "fastq_screen_plot.txt:md5,562b783630f698c3220c951b73b87027",
+                "fastqc-status-check-heatmap.txt:md5,6cd55dc80642c78b5e0d71821b83fe2e",
+                "fastqc_overrepresented_sequences_plot.txt:md5,37fd53c396d047467fbd38c5c4a0c4ba",
+                "fastqc_per_base_n_content_plot.txt:md5,75aee7627205c6513389d7a52e7a383b",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,2a60a8518caad855e842cf70a8037dad",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,1325b4b3971f7d4d544d9e252abf47b9",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,ef663c12746dfb88f7297b891756fadd",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,5a224c4e837ba42c16b724289bb1bf32",
+                "fastqc_sequence_counts_plot.txt:md5,20364b3b979bc99ae375a2dffcaf1cc1",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,7f33f3d0e2eb3405eb6456acbd18dfd4",
+                "fastqc_sequence_length_distribution_plot.txt:md5,9472fb38f57150d55fb9e4995aaeeb90",
+                "multiqc_Sample1_1.txt:md5,000ff826a01fcae9fe0bf43fa11df1dc",
+                "multiqc_Sample23_3.txt:md5,b5434520fa5be5c98be5ed164a464d23",
+                "multiqc_SampleA_2.txt:md5,3ce1aacaff46ea0df3fbbb07da9dba6a",
+                "multiqc_Undetermined_5.txt:md5,9dffb6858b809b9bb97ca450158abb6c",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,2ff2485b1f197cb6228dd4350d1bd638",
+                "multiqc_fastqc.txt:md5,3730f9046b20ac5c17a86db0a33f8d5d",
+                "multiqc_sampletest_4.txt:md5,ded2705a3247b72dffb5367bcb5f95b8",
+                "fastq_screen_plot.txt:md5,c25d34568f10f131156294d31fbfa994",
+                "fastqc-status-check-heatmap.txt:md5,67afbf7ec626c4fc7a28b4922352bc84",
+                "fastqc_overrepresented_sequences_plot.txt:md5,0356d007eaf807f7b63714b438b11289",
+                "fastqc_per_base_n_content_plot.txt:md5,4c5bfb1594b391f3e36a9e1223b43a94",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,6251cde1646484446499252bd15c58a2",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,f645e38916efafd07d4c2c3d5c7cd051",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,a9d3152a43988e39fae4a75faa3a5aa4",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,aef487a8b267a14a92be64b0b01d9b5c",
+                "fastqc_sequence_counts_plot.txt:md5,5021496dd00366d08064804bbb5192e3",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,e37e8e4584f0157a5fa0d53b4834e836",
+                "fastqc_sequence_length_distribution_plot.txt:md5,393cc090200a5151561efb1ed5280b89",
+                "multiqc_Sample1_1.txt:md5,000ff826a01fcae9fe0bf43fa11df1dc",
+                "multiqc_SampleA_2.txt:md5,3ce1aacaff46ea0df3fbbb07da9dba6a",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,737dc47e74e5b2f2c590652788831eff",
+                "multiqc_fastqc.txt:md5,f38ffdc112c73af3a41ed15848a3761f",
+                "fastq_screen_plot.txt:md5,44fca6453b0a3d0590271bd7a31cc740",
+                "fastqc-status-check-heatmap.txt:md5,b6872d9dbaa3cce396d48dc137076e53",
+                "fastqc_overrepresented_sequences_plot.txt:md5,eac8d0fd31c614d8d0f56bd54ee8c78c",
+                "fastqc_per_base_n_content_plot.txt:md5,b7b249afe807ca2321e6dd839961795c",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,3bca5f0121d27b0777a40a4ab44e2abc",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,ee29af5517a8c6f872adbaccea4ff2f8",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,3eaf12f9267c10e4e457a2bb9bdc70ea",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,1818e0b917e45a583740f2cbb0638f8d",
+                "fastqc_sequence_counts_plot.txt:md5,0c4863a5475a2444cd00b053eb8941b1",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,a7a050f827a4f821117efd8d25668c51",
+                "fastqc_sequence_length_distribution_plot.txt:md5,9c0761008be04d8ccf4c0e16acc6348c",
+                "multiqc_Sample23_3.txt:md5,b5434520fa5be5c98be5ed164a464d23",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,568f6b6d14562d01b5aaeb1a39e1cf3d",
+                "multiqc_fastqc.txt:md5,7ff71ceb8ecdf086331047f8860c3347",
+                "fastq_screen_plot.txt:md5,5f748d33a7a396547fe8c260b728aa06",
+                "fastqc-status-check-heatmap.txt:md5,08228a8f3d6f11b174b98626bb22bda1",
+                "fastqc_overrepresented_sequences_plot.txt:md5,3434dfb79f150e2e584e85866983ba01",
+                "fastqc_per_base_n_content_plot.txt:md5,e371981072ec99d11c6adb5a4034808c",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,bf83d019eaaeb1ca659ff28cfb2bdfea",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,3f40b8ee69d3eaefe657cc5ed622cc8b",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,86b61d09437a96448e1325e6be834048",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,9f7307469b112bd054f8ee0cc2cf4d65",
+                "fastqc_sequence_counts_plot.txt:md5,f0c693cc281a6e61ba219bab04f59a47",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,8c2aa91358fd4a2e946cbcc1f312f9b6",
+                "fastqc_sequence_length_distribution_plot.txt:md5,875ebcd6726bb9d36ffa64265e5071d0",
+                "multiqc_Sample1_1.txt:md5,000ff826a01fcae9fe0bf43fa11df1dc",
+                "multiqc_Sample23_3.txt:md5,b5434520fa5be5c98be5ed164a464d23",
+                "multiqc_SampleA_2.txt:md5,3ce1aacaff46ea0df3fbbb07da9dba6a",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,c54d863ed3e68ee8bcb51c9ad85de9bc",
+                "multiqc_fastqc.txt:md5,8284e25ccc21041cf3b5a32eb6a51e78",
+                "fastq_screen_plot.txt:md5,8622e1dbd0fe62520af6096207b9775d",
+                "fastqc-status-check-heatmap.txt:md5,2a66f5d61b9eb579555905cd5954b04c",
+                "fastqc_overrepresented_sequences_plot.txt:md5,e0b5bfc4b64d37611b51c939e61196fa",
+                "fastqc_per_base_n_content_plot.txt:md5,1380831484d1b069a2fd4a20437118bf",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,12585cf6b03db684a5ebd959f51e77e7",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,a1464399e84711454499d27e98ed942b",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,026d11e7b49a49ac7bac85f376760305",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,4d646b20970d09d846947b87961efe7e",
+                "fastqc_sequence_counts_plot.txt:md5,057fb961863b325fe875d3a7879cb888",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,3b86c9d8625c439376102f3286c7bba7",
+                "fastqc_sequence_length_distribution_plot.txt:md5,6296c9ddbf8ba8e12053149d057fd7b2",
+                "multiqc_Sample23_3.txt:md5,b5434520fa5be5c98be5ed164a464d23",
+                "multiqc_Undetermined_5.txt:md5,9dffb6858b809b9bb97ca450158abb6c",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,a4dca31413036d35899a35ba14b17ea5",
+                "multiqc_fastqc.txt:md5,519ff344a896ac369bba4d5c5b8be7b5",
+                "multiqc_sampletest_4.txt:md5,ded2705a3247b72dffb5367bcb5f95b8",
+                "Sample1_1.tsv:md5,269fabf8435defcd327aa69a050b7869",
+                "Sample1_1_mqc.txt:md5,a354b0ed16b9cf84aa88f501d7740fd6",
+                "Sample23_3.tsv:md5,6fdadbeeefccbf957f880d6852bf9676",
+                "Sample23_3_mqc.txt:md5,e94269e3efc8b8192d7ac9c15ea2aa99",
+                "SampleA_2.tsv:md5,b980ed694a05825fcf7c8b5b73888eb3",
+                "SampleA_2_mqc.txt:md5,1d4b0e918644cf553108b7ccf77b4a01",
+                "Undetermined_5.tsv:md5,b4458d41df4dee9321da03f4d4672aae",
+                "Undetermined_5_mqc.txt:md5,0c869488cb61d2f87758c621bded212b",
+                "sampletest_4.tsv:md5,db3179b0c41a09e6317a5a5c0852f476",
+                "sampletest_4_mqc.txt:md5,590b97cc48268629204f59007bae7ad7"
+            ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.10.2"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-05T15:16:34.893751981"
+        "timestamp": "2025-02-03T16:42:55.549005"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test b/tests/PromethION.main.nf.test
index 126a58c1..5cb291ef 100644
--- a/tests/PromethION.main.nf.test
+++ b/tests/PromethION.main.nf.test
@@ -15,15 +15,28 @@ nextflow_pipeline {
         }
 
         then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(
+                params.outdir,
+                relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}']
+            )
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(
+                params.outdir,
+                ignoreFile: 'tests/.nftignore'
+            )
             assertAll(
-                { assert workflow.success },
+                { assert workflow.success},
                 { assert snapshot(
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt"),
-                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt"),
-                    ).match()
-                },
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_seqinspector_software_mqc_versions.yml"),
+                    // All stable path names, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
             )
         }
     }
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 7d0a6bfe..6e3f39c1 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -1,15 +1,144 @@
 {
     "PromethION data test": {
         "content": [
-            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
-            "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
-            "multiqc_general_stats.txt:md5,409cefc7f17f95d176ced6032bf8fb32",
-            "multiqc_fastq_screen.txt:md5,7c5d711e27c53d13c81644a1f2468dba"
+            4,
+            {
+                "FASTQC": {
+                    "fastqc": "0.12.1"
+                },
+                "FASTQSCREEN_FASTQSCREEN": {
+                    "fastqscreen": "0.16.0"
+                },
+                "SEQFU_STATS": {
+                    "seqfu": "1.20.3"
+                },
+                "Workflow": {
+                    "nf-core/seqinspector": "v1.0dev"
+                }
+            },
+            [
+                "fastqc",
+                "fastqc/hg001_1_fastqc.html",
+                "fastqc/hg001_1_fastqc.zip",
+                "fastqscreen",
+                "fastqscreen/hg001_1_screen.html",
+                "fastqscreen/hg001_1_screen.png",
+                "fastqscreen/hg001_1_screen.txt",
+                "multiqc",
+                "multiqc/global_report",
+                "multiqc/global_report/multiqc_data",
+                "multiqc/global_report/multiqc_data/fastq_screen_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc-status-check-heatmap.txt",
+                "multiqc/global_report/multiqc_data/fastqc_adapter_content_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_overrepresented_sequences_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_n_content_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_base_sequence_quality_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt",
+                "multiqc/global_report/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_counts_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_duplication_levels_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_sequence_length_distribution_plot.txt",
+                "multiqc/global_report/multiqc_data/fastqc_top_overrepresented_sequences_table.txt",
+                "multiqc/global_report/multiqc_data/multiqc.log",
+                "multiqc/global_report/multiqc_data/multiqc_citations.txt",
+                "multiqc/global_report/multiqc_data/multiqc_data.json",
+                "multiqc/global_report/multiqc_data/multiqc_fastq_screen.txt",
+                "multiqc/global_report/multiqc_data/multiqc_fastqc.txt",
+                "multiqc/global_report/multiqc_data/multiqc_general_stats.txt",
+                "multiqc/global_report/multiqc_data/multiqc_hg001_1.txt",
+                "multiqc/global_report/multiqc_data/multiqc_software_versions.txt",
+                "multiqc/global_report/multiqc_data/multiqc_sources.txt",
+                "multiqc/global_report/multiqc_plots",
+                "multiqc/global_report/multiqc_plots/pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastq_screen_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc-status-check-heatmap.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_adapter_content_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_overrepresented_sequences_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_n_content_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_base_sequence_quality_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Counts.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_gc_content_plot_Percentages.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_per_sequence_quality_scores_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-cnt.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_counts_plot-pct.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_duplication_levels_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_sequence_length_distribution_plot.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/fastqc_top_overrepresented_sequences_table.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/general_stats_table.pdf",
+                "multiqc/global_report/multiqc_plots/pdf/hg001_1.pdf",
+                "multiqc/global_report/multiqc_plots/png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastq_screen_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc-status-check-heatmap.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_adapter_content_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_overrepresented_sequences_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_n_content_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_base_sequence_quality_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Counts.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_gc_content_plot_Percentages.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_per_sequence_quality_scores_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-cnt.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_counts_plot-pct.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_duplication_levels_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_sequence_length_distribution_plot.png",
+                "multiqc/global_report/multiqc_plots/png/fastqc_top_overrepresented_sequences_table.png",
+                "multiqc/global_report/multiqc_plots/png/general_stats_table.png",
+                "multiqc/global_report/multiqc_plots/png/hg001_1.png",
+                "multiqc/global_report/multiqc_plots/svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastq_screen_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc-status-check-heatmap.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_adapter_content_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_overrepresented_sequences_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_n_content_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_base_sequence_quality_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Counts.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_gc_content_plot_Percentages.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_per_sequence_quality_scores_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-cnt.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_counts_plot-pct.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_duplication_levels_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_sequence_length_distribution_plot.svg",
+                "multiqc/global_report/multiqc_plots/svg/fastqc_top_overrepresented_sequences_table.svg",
+                "multiqc/global_report/multiqc_plots/svg/general_stats_table.svg",
+                "multiqc/global_report/multiqc_plots/svg/hg001_1.svg",
+                "multiqc/global_report/multiqc_report.html",
+                "pipeline_info",
+                "pipeline_info/nf_core_seqinspector_software_mqc_versions.yml",
+                "seqfu_stats",
+                "seqfu_stats/hg001_1.tsv",
+                "seqfu_stats/hg001_1_mqc.txt"
+            ],
+            [
+                "hg001_1_fastqc.html:md5,e1c944e38d02d26a2220fdb0ead48114",
+                "hg001_1_screen.png:md5,b9c58e388f18ad11f4c2e29e9b573a5e",
+                "hg001_1_screen.txt:md5,8e53ea043d658a130f4b8ca455e2ba9b",
+                "fastq_screen_plot.txt:md5,3023b86477fecf6d46d8fc60d82cc53a",
+                "fastqc-status-check-heatmap.txt:md5,825668e94de27356f0a112beb758e416",
+                "fastqc_adapter_content_plot.txt:md5,1fa991080c20755e5e729a5eeab960e5",
+                "fastqc_overrepresented_sequences_plot.txt:md5,e810a3d3eba0ba83b122763505f511a7",
+                "fastqc_per_base_n_content_plot.txt:md5,cbdb64298ff839665e8c8c8e89896e87",
+                "fastqc_per_base_sequence_quality_plot.txt:md5,4962950bc3ce77169ac510d64cb769c6",
+                "fastqc_per_sequence_gc_content_plot_Counts.txt:md5,e62273533304be59dab5f13afef93b3e",
+                "fastqc_per_sequence_gc_content_plot_Percentages.txt:md5,3d49290a15406cb5dac1460c02729f0f",
+                "fastqc_per_sequence_quality_scores_plot.txt:md5,7cc10d1bc92ca09431a506c38d911228",
+                "fastqc_sequence_counts_plot.txt:md5,0425d7298c24df6158d5bf7aca1d4190",
+                "fastqc_sequence_duplication_levels_plot.txt:md5,9111d942c7eed5af0e9ccb8c42db8505",
+                "fastqc_sequence_length_distribution_plot.txt:md5,04adfcd0125ebcc3e3bb631f1956c812",
+                "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a",
+                "multiqc_fastq_screen.txt:md5,7c5d711e27c53d13c81644a1f2468dba",
+                "multiqc_fastqc.txt:md5,1a4b472e13cadc770832b0e20d1de7b0",
+                "multiqc_hg001_1.txt:md5,9595d608ff5709f2bdec8cb1016416c0",
+                "hg001_1.tsv:md5,b133752c897afbb4d8721b911fa117d4",
+                "hg001_1_mqc.txt:md5,6285f582c03faa70e8dcb3503e5db728"
+            ]
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.10.2"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-05T15:18:25.176791779"
+        "timestamp": "2025-02-03T16:45:47.047432"
     }
 }
\ No newline at end of file

From 50530983806cc4baeec97e4b2551da1a47111249 Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 4 Feb 2025 10:13:05 +0100
Subject: [PATCH 163/172] Exclude fastqc/*_fastqc.html files

---
 tests/.nftignore                    | 2 +-
 tests/MiSeq.main.nf.test.snap       | 3 +--
 tests/NovaSeq6000.main.nf.test.snap | 7 +------
 tests/PromethION.main.nf.test.snap  | 3 +--
 4 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/tests/.nftignore b/tests/.nftignore
index 504be1c6..ded3eac7 100644
--- a/tests/.nftignore
+++ b/tests/.nftignore
@@ -9,4 +9,4 @@ multiqc/{global_report,group_reports/*}/multiqc_plots/{svg,pdf,png}/*.{svg,pdf,p
 multiqc/{global_report,group_reports/*}/multiqc_report.html
 pipeline_info/*.{html,json,txt,yml}
 fastqscreen/*_screen.html
-fastqc/*_fastqc.zip
+fastqc/*_fastqc.{html,zip}
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
index 66996292..71bf40cc 100644
--- a/tests/MiSeq.main.nf.test.snap
+++ b/tests/MiSeq.main.nf.test.snap
@@ -104,7 +104,6 @@
                 "seqfu_stats/SAMPLE_SINGLE_END_1_mqc.txt"
             ],
             [
-                "SAMPLE_SINGLE_END_1_fastqc.html:md5,a299e4a9a0b5aa289d6a325b71f915ce",
                 "SAMPLE_SINGLE_END_1_screen.png:md5,ad98ae0f39335aede67e0a233cf16616",
                 "SAMPLE_SINGLE_END_1_screen.txt:md5,588b1b1f2d307fae7272ab0819e4bac5",
                 "fastq_screen_plot.txt:md5,8393eabda6ebac90ff00533f9562271f",
@@ -129,7 +128,7 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-02-03T16:39:35.285693"
+        "timestamp": "2025-02-04T10:07:47.514983"
     },
     "Miseq data test (skip all tools)": {
         "content": [
diff --git a/tests/NovaSeq6000.main.nf.test.snap b/tests/NovaSeq6000.main.nf.test.snap
index 0a9ab878..6838297d 100644
--- a/tests/NovaSeq6000.main.nf.test.snap
+++ b/tests/NovaSeq6000.main.nf.test.snap
@@ -477,11 +477,6 @@
                 "seqfu_stats/sampletest_4_mqc.txt"
             ],
             [
-                "Sample1_1_fastqc.html:md5,358c1d6e7ea23b531312d88b51f525fa",
-                "Sample23_3_fastqc.html:md5,5b2b55815c667515184d1591fc57249b",
-                "SampleA_2_fastqc.html:md5,ecc7ab9529216dac84acc864bde7c839",
-                "Undetermined_5_fastqc.html:md5,ec71c3ad29df3c70411777b0bcbddd61",
-                "sampletest_4_fastqc.html:md5,62fc1e99df0da04e3dd5e17fa608a763",
                 "Sample1_1_screen.png:md5,562256290643b51e4374c2225a15f463",
                 "Sample1_1_screen.txt:md5,3b184ef10eeb99043a85826534a4ee28",
                 "Sample23_3_screen.png:md5,6bb2caf67b9b2ed25d3d5f32c343e9ab",
@@ -592,6 +587,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-02-03T16:42:55.549005"
+        "timestamp": "2025-02-04T10:10:13.268943"
     }
 }
\ No newline at end of file
diff --git a/tests/PromethION.main.nf.test.snap b/tests/PromethION.main.nf.test.snap
index 6e3f39c1..c256a372 100644
--- a/tests/PromethION.main.nf.test.snap
+++ b/tests/PromethION.main.nf.test.snap
@@ -112,7 +112,6 @@
                 "seqfu_stats/hg001_1_mqc.txt"
             ],
             [
-                "hg001_1_fastqc.html:md5,e1c944e38d02d26a2220fdb0ead48114",
                 "hg001_1_screen.png:md5,b9c58e388f18ad11f4c2e29e9b573a5e",
                 "hg001_1_screen.txt:md5,8e53ea043d658a130f4b8ca455e2ba9b",
                 "fastq_screen_plot.txt:md5,3023b86477fecf6d46d8fc60d82cc53a",
@@ -139,6 +138,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-02-03T16:45:47.047432"
+        "timestamp": "2025-02-04T10:12:21.446251"
     }
 }
\ No newline at end of file

From 0372247f0a3cc62b616d3c844351f7052a21b0ae Mon Sep 17 00:00:00 2001
From: Adrien Coulier <adrien.coulier@medsci.uu.se>
Date: Tue, 4 Feb 2025 10:42:25 +0100
Subject: [PATCH 164/172] Update changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6086d786..3ea1be05 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#75](https://github.com/nf-core/seqinspector/pull/75) Set up nft-utils
 - [#68](https://github.com/nf-core/seqinspector/pull/68) Add tool selector
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.

From f79897c85fdbaf8b61482dd0985da2c7652c88ed Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 17 Mar 2025 17:09:51 +0100
Subject: [PATCH 165/172] use parameter-supplied fastqscreen reference instead
 of hardcoded example

---
 workflows/seqinspector.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 4afff158..910ac3c7 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -82,7 +82,7 @@ workflow SEQINSPECTOR {
 
     ch_fastqscreen_refs = Channel
         .fromList(samplesheetToList(
-            "${projectDir}/assets/example_fastq_screen_references.csv",
+            params.fastq_screen_references,
             "${projectDir}/assets/schema_fastq_screen_references.json"
         ))
         .toList()

From 4bcca1529249f08eac2cae0feb69baac7c4a0de1 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 17 Mar 2025 17:15:42 +0100
Subject: [PATCH 166/172] typo

---
 workflows/seqinspector.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 1a6b6dc0..9488cea0 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -88,7 +88,7 @@ workflow SEQINSPECTOR {
     if (!("fastqscreen" in skip_tools)) {
         ch_fastqscreen_refs = Channel
             .fromList(samplesheetToList(
-                params.fastq_screen_references.csv,
+                params.fastq_screen_references,
                 "${projectDir}/assets/schema_fastq_screen_references.json"
             ))
             .toList()

From 0ba165203724f077c859f6f27bf0b8c101250670 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 18 Mar 2025 11:26:25 +0100
Subject: [PATCH 167/172] add assertions

---
 workflows/seqinspector.nf | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 9488cea0..45c77681 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -86,6 +86,10 @@ workflow SEQINSPECTOR {
     // and transpose it into a tuple containing lists for each property
 
     if (!("fastqscreen" in skip_tools)) {
+
+        assert params.fastq_screen_references; "params.fastq_screen_references is not defined, either supply it or skip running FastQ Screen"
+        assert file(params.fastq_screen_references).exists(); "params.fastq_screen_references does not exist, either supply it or skip running FastQ Screen"
+
         ch_fastqscreen_refs = Channel
             .fromList(samplesheetToList(
                 params.fastq_screen_references,

From 2fd5f7c4aec5873d3d383abb0ebdf069c6703bec Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 18 Mar 2025 11:34:02 +0100
Subject: [PATCH 168/172] Revert "add assertions"

This reverts commit 0ba165203724f077c859f6f27bf0b8c101250670.
---
 workflows/seqinspector.nf | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 45c77681..9488cea0 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -86,10 +86,6 @@ workflow SEQINSPECTOR {
     // and transpose it into a tuple containing lists for each property
 
     if (!("fastqscreen" in skip_tools)) {
-
-        assert params.fastq_screen_references; "params.fastq_screen_references is not defined, either supply it or skip running FastQ Screen"
-        assert file(params.fastq_screen_references).exists(); "params.fastq_screen_references does not exist, either supply it or skip running FastQ Screen"
-
         ch_fastqscreen_refs = Channel
             .fromList(samplesheetToList(
                 params.fastq_screen_references,

From a99d0d6e458d0e4a32eeb45865f2fae367401dae Mon Sep 17 00:00:00 2001
From: Mac <mac@employee-17-200.eduroam.muni.cz>
Date: Mon, 24 Mar 2025 16:06:42 +0100
Subject: [PATCH 169/172] Added missing citations to citation tool

---
 .../main.nf                                   | 32 +++++++++----------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index 70994073..31405ac2 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -229,27 +229,27 @@ def genomeExistsError() {
 // Generate methods description for MultiQC
 //
 def toolCitationText() {
-    // TODO nf-core: Optionally add in-text citation tools to this list.
-    // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "",
-    // Uncomment function in methodsDescriptionText to render in MultiQC report
     def citation_text = [
-            "Tools used in the workflow included:",
-            "FastQC (Andrews 2010),",
-            "MultiQC (Ewels et al. 2016)",
-            "."
-        ].join(' ').trim()
+        "Tools used in the workflow included:",
+        "FastQC (Andrews 2010),",
+        "MultiQC (Ewels et al. 2016),",
+        "FastQ Screen (Wingett & Andrews 2018)",
+        params.sample_size > 0 ? "Seqtk (Li 2021)," : "",
+        "SeqFu (Telatin et al. 2021),",
+        "."
+    ].join(' ').trim()
 
     return citation_text
 }
 
 def toolBibliographyText() {
-    // TODO nf-core: Optionally add bibliographic entries to this list.
-    // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "<li>Author (2023) Pub name, Journal, DOI</li>" : "",
-    // Uncomment function in methodsDescriptionText to render in MultiQC report
     def reference_text = [
-            "<li>Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).</li>",
-            "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"
-        ].join(' ').trim()
+        "<li>Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/.</li>",
+        "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics, 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>",
+        "<li>Wingett SW, Andrews S. FastQ Screen: A tool for multi-genome mapping and quality control. F1000Res. 2018 Aug 24 [revised 2018 Jan 1];7:1338. doi: 10.12688/f1000research.15931.2. eCollection</li>",
+        params.sample_size > 0 ? "<li>Li, H. SeqTk. Available online: https://github.com/lh3/seqtk (accessed on 6 May 2021)</li>" : "",
+        "<li>Telatin, A.; Fariselli, P.; Birolo, G. SeqFu: A Suite of Utilities for the Robust and Reproducible Manipulation of Sequence Files. Bioengineering 2021, 8, 59. https://doi.org/10.3390/bioengineering8050059</li>"
+    ].join(' ').trim()
 
     return reference_text
 }
@@ -279,8 +279,8 @@ def methodsDescriptionText(mqc_methods_yaml) {
     meta["tool_bibliography"] = ""
 
     // TODO nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled!
-    // meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".")
-    // meta["tool_bibliography"] = toolBibliographyText()
+    meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".")
+    meta["tool_bibliography"] = toolBibliographyText()
 
 
     def methods_text = mqc_methods_yaml.text

From 6c4bcde42088fb68b82d73eab57599489951d89c Mon Sep 17 00:00:00 2001
From: Patricie34 <patricie.johnova@email.cz>
Date: Tue, 25 Mar 2025 09:34:38 +0100
Subject: [PATCH 170/172] TODOs removed

---
 .../local/utils_nfcore_seqinspector_pipeline/main.nf         | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
index 31405ac2..708d73fb 100644
--- a/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf
@@ -275,14 +275,9 @@ def methodsDescriptionText(mqc_methods_yaml) {
     meta["nodoi_text"] = meta.manifest_map.doi ? "" : "<li>If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used. </li>"
 
     // Tool references
-    meta["tool_citations"] = ""
-    meta["tool_bibliography"] = ""
-
-    // TODO nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled!
     meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".")
     meta["tool_bibliography"] = toolBibliographyText()
 
-
     def methods_text = mqc_methods_yaml.text
 
     def engine =  new groovy.text.SimpleTemplateEngine()

From 7ca405338d89621c66a08d9aaadcdc98d9748209 Mon Sep 17 00:00:00 2001
From: Patricie34 <patricie.johnova@email.cz>
Date: Tue, 25 Mar 2025 09:59:45 +0100
Subject: [PATCH 171/172] CHANGELOG.md updated

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3ea1be05..530200b3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -19,6 +19,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 - [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools
 - [#53](https://github.com/nf-core/seqinspector/pull/53) Add FastQ-Screen database multiplexing and limit scope of nf-test in CI.
+- [#96](https://github.com/nf-core/seqinspector/pull/96) Added missing citations to citation tool
 
 ### `Fixed`
 

From ad0817d7205c7398d6ee32f52d39c517e0b4d221 Mon Sep 17 00:00:00 2001
From: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Date: Tue, 25 Mar 2025 12:27:16 +0000
Subject: [PATCH 172/172] Update syntax of fq skipping to use the skip_tools
 parameter

---
 nextflow.config           | 4 +---
 nextflow_schema.json      | 8 +-------
 tests/rnaseq.main.nf.test | 2 +-
 workflows/seqinspector.nf | 2 +-
 4 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/nextflow.config b/nextflow.config
index e5eef360..a220f599 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -15,12 +15,10 @@ params {
     sample_size                = 0
 
     // Options
-    skip_linting               = false
     fq_lint_args               = ""
     continue_with_lint_fail    = false
-
-
     skip_tools                 = ''
+
     // References
     genome                     = null
     fasta                      = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index cb70a4b2..e5760c7e 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -50,7 +50,7 @@
                 "skip_tools": {
                     "type": "string",
                     "description": "Comma-separated string of tools to skip",
-                    "pattern": "^((fastqc|fastqscreen|seqfu_stats|seqtk_sample)?,?)*(?<!,)$"
+                    "pattern": "^((fq|fastqc|fastqscreen|seqfu_stats|seqtk_sample)?,?)*(?<!,)$"
                 }
             }
         },
@@ -60,12 +60,6 @@
             "description": "Options for validating and screening FASTQ files.",
             "default": "",
             "properties": {
-                "skip_linting": {
-                    "type": "boolean",
-                    "default": false,
-                    "description": "Whether to lint the FASTQs before performing QC on the sequences",
-                    "help_text": "FASTQ files will be linted with FQ early in the pipeline. If they fail validation, the pipeline will terminate preventing expensive quality control steps being performed on the other samples. If ignoring FQ is enabled, quality control will be performed on the remaining samples."
-                },
                 "fq_lint_args": {
                     "type": "string",
                     "description": "Arguments to pass to FQ lint",
diff --git a/tests/rnaseq.main.nf.test b/tests/rnaseq.main.nf.test
index 411e58c5..9225dd54 100644
--- a/tests/rnaseq.main.nf.test
+++ b/tests/rnaseq.main.nf.test
@@ -28,7 +28,7 @@ nextflow_pipeline {
             config "./rnaseq.main.nf.test.config"
             params {
                 outdir = "$outputDir"
-                skip_linting = true
+                skip_tools = "fq"
             }
         }
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 56004c45..69fc29bd 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -42,7 +42,7 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run FQ_LINT to catch early errors
     //
-    if ( !params.skip_linting ) {
+    if ( !("fq" in skip_tools) ) {
         FQ_LINT (
             ch_samplesheet
         )