From 566f67a9c982a705d15794401eb98b5ecaf0436c Mon Sep 17 00:00:00 2001
From: Fernando Duarte <123090819+FernandoDuarteF@users.noreply.github.com>
Date: Tue, 13 May 2025 19:31:22 +0000
Subject: [PATCH 1/4] Input declaration and added plink/vcf

---
 assets/samplesheet.csv                        |   5 +-
 assets/schema_input.json                      |  16 +-
 modules.json                                  |   5 +
 modules/nf-core/plink/vcf/environment.yml     |   7 +
 modules/nf-core/plink/vcf/main.nf             |  54 +++++++
 modules/nf-core/plink/vcf/meta.yml            |  68 +++++++++
 modules/nf-core/plink/vcf/tests/main.nf.test  |  57 +++++++
 .../nf-core/plink/vcf/tests/main.nf.test.snap | 144 ++++++++++++++++++
 .../nf-core/plink/vcf/tests/nextflow.config   |   5 +
 .../local/utils_nfcore_gwas_pipeline/main.nf  |  23 +--
 workflows/gwas.nf                             |  15 ++
 11 files changed, 369 insertions(+), 30 deletions(-)
 create mode 100644 modules/nf-core/plink/vcf/environment.yml
 create mode 100644 modules/nf-core/plink/vcf/main.nf
 create mode 100644 modules/nf-core/plink/vcf/meta.yml
 create mode 100644 modules/nf-core/plink/vcf/tests/main.nf.test
 create mode 100644 modules/nf-core/plink/vcf/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/plink/vcf/tests/nextflow.config

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index 5f653ab..7cac86e 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,3 +1,2 @@
-sample,fastq_1,fastq_2
-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
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+id,vcf,pheno,cov
+test,https://github.com/nf-core/test-datasets/blob/gwas/data/data_shrink_combined_4500/chr1_to_22_and_X.vcf.bgz,https://github.com/nf-core/test-datasets/blob/gwas/data/data_phenotypes_and_covariates/example1.pheno,https://github.com/nf-core/test-datasets/blob/gwas/data/data_phenotypes_and_covariates/example1.covar
diff --git a/assets/schema_input.json b/assets/schema_input.json
index 6011b20..0e2b67e 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -7,27 +7,31 @@
     "items": {
         "type": "object",
         "properties": {
-            "sample": {
+            "id": {
                 "type": "string",
                 "pattern": "^\\S+$",
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["id"]
             },
-            "fastq_1": {
+            "vcf": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
-            "fastq_2": {
+            "pheno": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+            },
+            "cov": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["id", "vcf", "pheno"]
     }
 }
diff --git a/modules.json b/modules.json
index 5ea2d55..9d3d943 100644
--- a/modules.json
+++ b/modules.json
@@ -9,6 +9,11 @@
                         "branch": "master",
                         "git_sha": "f0719ae309075ae4a291533883847c3f7c441dad",
                         "installed_by": ["modules"]
+                    },
+                    "plink/vcf": {
+                        "branch": "master",
+                        "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
+                        "installed_by": ["modules"]
                     }
                 }
             },
diff --git a/modules/nf-core/plink/vcf/environment.yml b/modules/nf-core/plink/vcf/environment.yml
new file mode 100644
index 0000000..fe7bb86
--- /dev/null
+++ b/modules/nf-core/plink/vcf/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::plink=1.90b6.21
diff --git a/modules/nf-core/plink/vcf/main.nf b/modules/nf-core/plink/vcf/main.nf
new file mode 100644
index 0000000..8419be1
--- /dev/null
+++ b/modules/nf-core/plink/vcf/main.nf
@@ -0,0 +1,54 @@
+process PLINK_VCF {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/plink:1.90b6.21--h779adbc_1' :
+        'biocontainers/plink:1.90b6.21--h779adbc_1' }"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed, optional: true
+    tuple val(meta), path("*.bim"), emit: bim, optional: true
+    tuple val(meta), path("*.fam"), emit: fam, optional: true
+
+    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}"
+
+    """
+    plink \\
+        --vcf ${vcf} \\
+        $args \\
+        --threads $task.cpus \\
+        --out ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(echo \$(plink --version 2>&1) | sed 's/^PLINK v//' | sed 's/..-bit.*//' )
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}.bed
+    touch ${prefix}.bim
+    touch ${prefix}.fam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(echo \$(plink --version 2>&1) | sed 's/^PLINK v//' | sed 's/..-bit.*//' )
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/plink/vcf/meta.yml b/modules/nf-core/plink/vcf/meta.yml
new file mode 100644
index 0000000..d6eefd9
--- /dev/null
+++ b/modules/nf-core/plink/vcf/meta.yml
@@ -0,0 +1,68 @@
+name: plink_vcf
+description: Analyses variant calling files using plink
+keywords:
+  - plink
+  - vcf
+  - variant
+  - call
+tools:
+  - plink:
+      description: |
+        Whole genome association analysis toolset, designed to perform a range
+        of basic, large-scale analyses in a computationally efficient manner
+      homepage: "https://www.cog-genomics.org/plink"
+      tool_dev_url: "https://www.cog-genomics.org/plink/1.9/dev"
+      licence: ["GPL"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - vcf:
+        type: file
+        description: Variant calling file (vcf)
+        pattern: "*.{vcf}"
+output:
+  - bed:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.bed":
+          type: file
+          description: PLINK binary biallelic genotype table
+          pattern: "*.{bed}"
+  - bim:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.bim":
+          type: file
+          description: PLINK extended MAP file
+          pattern: "*.{bim}"
+  - fam:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.fam":
+          type: file
+          description: PLINK sample information file
+          pattern: "*.{fam}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@Mxrcon"
+  - "@abhi18av"
+maintainers:
+  - "@Mxrcon"
+  - "@abhi18av"
diff --git a/modules/nf-core/plink/vcf/tests/main.nf.test b/modules/nf-core/plink/vcf/tests/main.nf.test
new file mode 100644
index 0000000..f091ac3
--- /dev/null
+++ b/modules/nf-core/plink/vcf/tests/main.nf.test
@@ -0,0 +1,57 @@
+
+nextflow_process {
+
+    name "Test Process PLINK_VCF"
+    script "../main.nf"
+    process "PLINK_VCF"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "plink"
+    tag "plink/vcf"
+
+    test("test-plink-vcf") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+				    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf', checkIfExists: true) ]
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("test-plink-vcf-stub") {
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+				    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf', checkIfExists: true) ]
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+}
diff --git a/modules/nf-core/plink/vcf/tests/main.nf.test.snap b/modules/nf-core/plink/vcf/tests/main.nf.test.snap
new file mode 100644
index 0000000..bd25aad
--- /dev/null
+++ b/modules/nf-core/plink/vcf/tests/main.nf.test.snap
@@ -0,0 +1,144 @@
+{
+    "test-plink-vcf-stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bed:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bim:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "3": [
+                    "versions.yml:md5,e8954e602ae53e958694bbc72e67abca"
+                ],
+                "bed": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bed:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "bim": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bim:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "fam": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e8954e602ae53e958694bbc72e67abca"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-08-29T15:53:07.531154"
+    },
+    "test-plink-vcf": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bed:md5,55c3ab2636212911b5f952ef6f5d855c"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bim:md5,54164b6f103e152de05712c6bb317db8"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fam:md5,0c6d4ffd228a3c5248b5a73eef84b9cc"
+                    ]
+                ],
+                "3": [
+                    "versions.yml:md5,e8954e602ae53e958694bbc72e67abca"
+                ],
+                "bed": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bed:md5,55c3ab2636212911b5f952ef6f5d855c"
+                    ]
+                ],
+                "bim": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.bim:md5,54164b6f103e152de05712c6bb317db8"
+                    ]
+                ],
+                "fam": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.fam:md5,0c6d4ffd228a3c5248b5a73eef84b9cc"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e8954e602ae53e958694bbc72e67abca"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-08-29T15:53:02.837603"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/plink/vcf/tests/nextflow.config b/modules/nf-core/plink/vcf/tests/nextflow.config
new file mode 100644
index 0000000..bb80765
--- /dev/null
+++ b/modules/nf-core/plink/vcf/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: PLINK_VCF {
+        ext.args = ' --make-bed --biallelic-only strict --vcf-half-call missing --double-id --recode ped --id-delim \'=\' --allow-extra-chr'
+    }
+}
diff --git a/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf b/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
index 97f52c5..a72e36e 100644
--- a/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
@@ -69,22 +69,9 @@ workflow PIPELINE_INITIALISATION {
 
     Channel
         .fromList(samplesheetToList(params.input, "${projectDir}/assets/schema_input.json"))
-        .map {
-            meta, fastq_1, fastq_2 ->
-                if (!fastq_2) {
-                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-                } else {
-                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-                }
-        }
-        .groupTuple()
         .map { samplesheet ->
             validateInputSamplesheet(samplesheet)
         }
-        .map {
-            meta, fastqs ->
-                return [ meta, fastqs.flatten() ]
-        }
         .set { ch_samplesheet }
 
     emit:
@@ -150,15 +137,9 @@ workflow PIPELINE_COMPLETION {
 // Validate channels from input samplesheet
 //
 def validateInputSamplesheet(input) {
-    def (metas, fastqs) = input[1..2]
-
-    // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end
-    def endedness_ok = metas.collect{ meta -> meta.single_end }.unique().size == 1
-    if (!endedness_ok) {
-        error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}")
-    }
+    def (meta, vcf, pheno, cov) = input
 
-    return [ metas[0], fastqs ]
+    return [ meta, vcf, pheno, cov ]
 }
 //
 // Generate methods description for MultiQC
diff --git a/workflows/gwas.nf b/workflows/gwas.nf
index c35b58d..3651464 100644
--- a/workflows/gwas.nf
+++ b/workflows/gwas.nf
@@ -8,6 +8,7 @@ include { paramsSummaryMap       } from 'plugin/nf-schema'
 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_gwas_pipeline'
+include { PLINK_VCF              } from '../modules/nf-core/plink/vcf/main'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -24,6 +25,20 @@ workflow GWAS {
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
 
+    // Prob multiMap is not necessary but I'll use it in case
+    // it's helpful in the future
+    ch_inputs = ch_samplesheet
+              | multiMap {
+                    meta, vcf, pheno, cov ->
+                    vcf   : [ meta,vcf ]
+                    pheno : [ meta, pheno]
+                    cov   : cov ? [ meta,cov ] : null
+              }
+
+    PLINK_VCF (
+        ch_inputs.vcf
+    )
+
     //
     // Collate and save software versions
     //

From 8d846278c9b50127b3b35174f0dee96a071b518c Mon Sep 17 00:00:00 2001
From: Fernando Duarte <123090819+FernandoDuarteF@users.noreply.github.com>
Date: Tue, 13 May 2025 20:22:03 +0000
Subject: [PATCH 2/4] Module plink/vcf can be run

---
 assets/samplesheet.csv                                | 2 +-
 subworkflows/local/utils_nfcore_gwas_pipeline/main.nf | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index 7cac86e..efbba4d 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,2 +1,2 @@
 id,vcf,pheno,cov
-test,https://github.com/nf-core/test-datasets/blob/gwas/data/data_shrink_combined_4500/chr1_to_22_and_X.vcf.bgz,https://github.com/nf-core/test-datasets/blob/gwas/data/data_phenotypes_and_covariates/example1.pheno,https://github.com/nf-core/test-datasets/blob/gwas/data/data_phenotypes_and_covariates/example1.covar
+test,https://raw.githubusercontent.com/nf-core/test-datasets/gwas/data/data_shrink_combined_4500/chr1_to_22_and_X.vcf.bgz,https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/gwas/data/data_phenotypes_and_covariates/example1.pheno,https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/gwas/data/data_phenotypes_and_covariates/example1.covar
diff --git a/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf b/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
index a72e36e..82b1bb1 100644
--- a/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_gwas_pipeline/main.nf
@@ -138,7 +138,7 @@ workflow PIPELINE_COMPLETION {
 //
 def validateInputSamplesheet(input) {
     def (meta, vcf, pheno, cov) = input
-
+    
     return [ meta, vcf, pheno, cov ]
 }
 //

From 1b1e2c6bd844fd9db325460306d9fa798a68933e Mon Sep 17 00:00:00 2001
From: Fernando Duarte <123090819+FernandoDuarteF@users.noreply.github.com>
Date: Wed, 14 May 2025 16:39:11 +0000
Subject: [PATCH 3/4] Added plink association

---
 conf/modules.config                           |   7 +
 modules.json                                  |   5 +
 modules/nf-core/plink/gwas/environment.yml    |   7 +
 modules/nf-core/plink/gwas/main.nf            |  94 +++++++++
 modules/nf-core/plink/gwas/meta.yml           | 108 ++++++++++
 modules/nf-core/plink/gwas/tests/main.nf.test | 198 ++++++++++++++++++
 .../plink/gwas/tests/main.nf.test.snap        | 134 ++++++++++++
 .../nf-core/plink/gwas/tests/nextflow.config  |   7 +
 .../plink/gwas/tests/pheno_name.config        |   7 +
 modules/nf-core/plink/vcf/main.nf             |   5 +-
 workflows/gwas.nf                             |  28 ++-
 11 files changed, 596 insertions(+), 4 deletions(-)
 create mode 100644 modules/nf-core/plink/gwas/environment.yml
 create mode 100644 modules/nf-core/plink/gwas/main.nf
 create mode 100644 modules/nf-core/plink/gwas/meta.yml
 create mode 100644 modules/nf-core/plink/gwas/tests/main.nf.test
 create mode 100644 modules/nf-core/plink/gwas/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/plink/gwas/tests/nextflow.config
 create mode 100644 modules/nf-core/plink/gwas/tests/pheno_name.config

diff --git a/conf/modules.config b/conf/modules.config
index f0b0d55..dce24e0 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -27,4 +27,11 @@ process {
         ]
     }
 
+    withName: 'PLINK_GWAS' {
+        ext.args   = '--allow-no-sex --linear'
+        publishDir = [
+            path: { "${params.outdir}/plink_gwas" },
+            mode: params.publish_dir_mode
+        ]
+    }
 }
diff --git a/modules.json b/modules.json
index 9d3d943..f12b644 100644
--- a/modules.json
+++ b/modules.json
@@ -10,6 +10,11 @@
                         "git_sha": "f0719ae309075ae4a291533883847c3f7c441dad",
                         "installed_by": ["modules"]
                     },
+                    "plink/gwas": {
+                        "branch": "master",
+                        "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
+                        "installed_by": ["modules"]
+                    },
                     "plink/vcf": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
diff --git a/modules/nf-core/plink/gwas/environment.yml b/modules/nf-core/plink/gwas/environment.yml
new file mode 100644
index 0000000..fe7bb86
--- /dev/null
+++ b/modules/nf-core/plink/gwas/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::plink=1.90b6.21
diff --git a/modules/nf-core/plink/gwas/main.nf b/modules/nf-core/plink/gwas/main.nf
new file mode 100644
index 0000000..7e42cfe
--- /dev/null
+++ b/modules/nf-core/plink/gwas/main.nf
@@ -0,0 +1,94 @@
+process PLINK_GWAS {
+    tag "$meta.id"
+    label 'process_medium'
+
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/plink:1.90b6.21--h031d066_5':
+        'biocontainers/plink:1.90b6.21--h031d066_5' }"
+
+    input:
+    tuple val(meta),  path(bed), path(bim), path(fam)
+    tuple val(meta2), path(vcf)
+    tuple val(meta3), path(bcf)
+    tuple val(meta4), path(phe)
+
+    output:
+    tuple val(meta), path("*.assoc"),  emit: assoc, optional:true
+    tuple val(meta), path("*.qassoc"), emit: qassoc, optional:true
+    tuple val(meta), path("*.log")  ,  emit: log
+    tuple val(meta), path("*.nosex"),  emit: nosex   , optional:true
+    path "versions.yml"             ,  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = ""
+    // define input string based on provided input files
+    // in hierarchical order
+    def input_command = ""
+    def outmeta = ""
+    if (bed){
+        input_command = "--bed ${bed} --bim ${bim} --fam ${fam}"
+        prefix = task.ext.prefix ?: "${meta.id}"
+    } else if (vcf) {
+        input_command = "--vcf ${vcf} --pheno ${phe}"
+        prefix = task.ext.prefix ?: "${meta2.id}"
+        meta = meta2
+    } else if (bcf) {
+        input_command = "--bcf ${bcf} --pheno ${phe}"
+        prefix = task.ext.prefix ?: "${meta3.id}"
+        meta = meta3
+    } else {
+        log.error 'ERROR: the input should be either plink native binary format, VCF or BCF'
+    }
+
+    """
+    plink \\
+        $input_command \\
+        --threads $task.cpus \\
+        --assoc \\
+        $args \\
+        --out $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(echo \$(plink --version) | sed 's/^PLINK v//;s/64.*//')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = ""
+    // define input string based on provided input files
+    // in hierarchical order
+    def input_command = ""
+    def outmeta = ""
+    if (bed){
+        input_command = "--bed ${bed} --bim ${bim} --fam ${fam}"
+        prefix = task.ext.prefix ?: "${meta.id}"
+    } else if (vcf) {
+        input_command = "--vcf ${vcf}"
+        prefix = task.ext.prefix ?: "${meta2.id} --pheno ${phe}"
+        meta = meta2
+    } else if (bcf) {
+        input_command = "--bcf ${bcf} --pheno ${phe}"
+        prefix = task.ext.prefix ?: "${meta3.id}"
+        meta = meta3
+    } else {
+        log.error 'ERROR: the input should be either plink native binary format, VCF or BCF'
+    }
+    """
+    touch ${prefix}.assoc
+    touch ${prefix}.nosex
+    touch ${prefix}.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(echo \$(plink --version) | sed 's/^PLINK v//;s/64.*//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/plink/gwas/meta.yml b/modules/nf-core/plink/gwas/meta.yml
new file mode 100644
index 0000000..67a6272
--- /dev/null
+++ b/modules/nf-core/plink/gwas/meta.yml
@@ -0,0 +1,108 @@
+name: "plink_gwas"
+description: Generate GWAS association studies
+keywords:
+  - association
+  - GWAS
+  - case/control
+tools:
+  - "plink":
+      description: "Whole genome association analysis toolset, designed to perform a
+        range of basic, large-scale analyses in a computationally efficient manner."
+      homepage: "https://www.cog-genomics.org/plink"
+      documentation: "https://www.cog-genomics.org/plink/1.9/data#recode"
+      tool_dev_url: "https://www.cog-genomics.org/plink/1.9/dev"
+      licence: ["GPL"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+          meta is associated to the PLINK native file input
+    - bed:
+        type: file
+        description: PLINK binary biallelic genotype table file
+        pattern: "*.{bed}"
+    - bim:
+        type: file
+        description: PLINK extended MAP file
+        pattern: "*.{bim}"
+    - fam:
+        type: file
+        description: PLINK sample information file
+        pattern: "*.{fam}"
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information,
+          e.g. [ id:'test', single_end:false ]
+          meta2 is associated to VCF file input
+    - vcf:
+        type: file
+        description: Variant calling file (vcf)
+        pattern: "*.{vcf}"
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing sample information,
+          e.g. [ id:'test', single_end:false ]
+          meta3 is associated to BCF file input
+    - bcf:
+        type: file
+        description: PLINK variant information + sample ID + genotype call binary file
+        pattern: "*.{bcf}"
+  - - meta4:
+        type: map
+        description: |
+          Groovy Map containing sample information,
+          e.g. [ id:'test', single_end:false ]
+          meta4 is associated to phenotype file input
+    - phe:
+        type: file
+        description: PLINK file containing phenotype information. This phenotype information
+          can be read from the third column with the --pheno option or from a specific
+          column with the --pheno-name option
+        pattern: "*.{phe}"
+output:
+  - assoc:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.assoc":
+          type: file
+          description: PLINK GWAS association file
+          pattern: "*.{assoc}"
+  - log:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.log":
+          type: file
+          description: PLINK GWAS association log file
+          pattern: "*.{log}"
+  - nosex:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.nosex":
+          type: file
+          description: PLINK GWAS association file that retains phenotypes for samples
+            with ambiguous sex. Produced with the option --allow-no-sex
+          pattern: "*.{nosex}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@LorenzoS96"
+maintainers:
+  - "@LorenzoS96"
diff --git a/modules/nf-core/plink/gwas/tests/main.nf.test b/modules/nf-core/plink/gwas/tests/main.nf.test
new file mode 100644
index 0000000..38236e1
--- /dev/null
+++ b/modules/nf-core/plink/gwas/tests/main.nf.test
@@ -0,0 +1,198 @@
+nextflow_process {
+
+    name "test Plink GWAS function"
+    script "../main.nf"
+    process "PLINK_GWAS"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "plink"
+    tag "plink/gwas"
+
+    test("plink - VCF") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.vcf.gz', checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.phe', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" },
+                { assert snapshot(
+                    process.out.assoc,
+                    process.out.nosex,
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("plink - VCF with phenotype name") {
+
+        config "./pheno_name.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.vcf.gz', checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated_phenoname.phe', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" },
+                { assert snapshot(
+                    process.out.assoc,
+                    process.out.nosex,
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("plink - binary") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [
+                        [id:"test"],
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
+                ]
+                input[1] = [ [id:"null"], []]
+                input[2] = [ [id:"null"], []]
+                input[3] = [ [id:"null"], []]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" },
+                { assert snapshot(
+                    process.out.assoc,
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("plink - BCF") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [ [id:"null"], []]
+                input[2] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bcf.gz', checkIfExists: true)
+                ]
+                input[3] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.phe', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" },
+                { assert snapshot(
+                    process.out.assoc,
+                    process.out.nosex,
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("plink - BCF with phenotype name") {
+
+        config "./pheno_name.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.vcf.gz', checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated_phenoname.phe', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" },
+                { assert snapshot(
+                    process.out.assoc,
+                    process.out.nosex,
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/plink/gwas/tests/main.nf.test.snap b/modules/nf-core/plink/gwas/tests/main.nf.test.snap
new file mode 100644
index 0000000..3a0c750
--- /dev/null
+++ b/modules/nf-core/plink/gwas/tests/main.nf.test.snap
@@ -0,0 +1,134 @@
+{
+    "plink - BCF": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.assoc:md5,ab8f91519a605cd9f2b2f89e18c3df9b"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.nosex:md5,4f9aa36c44a417ff6d7caa9841e66ad9"
+                ]
+            ],
+            [
+                "versions.yml:md5,6201877470ebd48d6b5cb97ca0641641"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-30T18:03:08.363934"
+    },
+    "plink - BCF with phenotype name": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.assoc:md5,ab8f91519a605cd9f2b2f89e18c3df9b"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.nosex:md5,4f9aa36c44a417ff6d7caa9841e66ad9"
+                ]
+            ],
+            [
+                "versions.yml:md5,6201877470ebd48d6b5cb97ca0641641"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-30T18:01:33.223256"
+    },
+    "plink - VCF with phenotype name": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.assoc:md5,ab8f91519a605cd9f2b2f89e18c3df9b"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.nosex:md5,4f9aa36c44a417ff6d7caa9841e66ad9"
+                ]
+            ],
+            [
+                "versions.yml:md5,6201877470ebd48d6b5cb97ca0641641"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-30T18:01:15.485141"
+    },
+    "plink - binary": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.assoc:md5,ab8f91519a605cd9f2b2f89e18c3df9b"
+                ]
+            ],
+            [
+                "versions.yml:md5,6201877470ebd48d6b5cb97ca0641641"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-30T18:01:22.136918"
+    },
+    "plink - VCF": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.assoc:md5,ab8f91519a605cd9f2b2f89e18c3df9b"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.nosex:md5,4f9aa36c44a417ff6d7caa9841e66ad9"
+                ]
+            ],
+            [
+                "versions.yml:md5,6201877470ebd48d6b5cb97ca0641641"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-07-30T18:01:09.222434"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/plink/gwas/tests/nextflow.config b/modules/nf-core/plink/gwas/tests/nextflow.config
new file mode 100644
index 0000000..ed5ce1c
--- /dev/null
+++ b/modules/nf-core/plink/gwas/tests/nextflow.config
@@ -0,0 +1,7 @@
+process {
+
+    withName: PLINK_GWAS {
+        ext.args = '--1 --allow-no-sex'
+    }
+
+}
diff --git a/modules/nf-core/plink/gwas/tests/pheno_name.config b/modules/nf-core/plink/gwas/tests/pheno_name.config
new file mode 100644
index 0000000..5cf1d78
--- /dev/null
+++ b/modules/nf-core/plink/gwas/tests/pheno_name.config
@@ -0,0 +1,7 @@
+process {
+
+    withName: PLINK_GWAS {
+        ext.args = '--1 --pheno-name Phenotype --allow-no-sex'
+    }
+
+}
diff --git a/modules/nf-core/plink/vcf/main.nf b/modules/nf-core/plink/vcf/main.nf
index 8419be1..baff00c 100644
--- a/modules/nf-core/plink/vcf/main.nf
+++ b/modules/nf-core/plink/vcf/main.nf
@@ -1,6 +1,6 @@
 process PLINK_VCF {
     tag "$meta.id"
-    label 'process_medium'
+    label 'process_low'
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
@@ -9,6 +9,7 @@ process PLINK_VCF {
 
     input:
     tuple val(meta), path(vcf)
+    tuple val(meta2), path(pheno)
 
     output:
     tuple val(meta), path("*.bed"), emit: bed, optional: true
@@ -23,10 +24,12 @@ process PLINK_VCF {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def phenotype = pheno ? "--pheno ${pheno} --make-bed" : ''
 
     """
     plink \\
         --vcf ${vcf} \\
+        $phenotype \\
         $args \\
         --threads $task.cpus \\
         --out ${prefix}
diff --git a/workflows/gwas.nf b/workflows/gwas.nf
index 3651464..6f01928 100644
--- a/workflows/gwas.nf
+++ b/workflows/gwas.nf
@@ -9,6 +9,7 @@ include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pi
 include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline'
 include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_gwas_pipeline'
 include { PLINK_VCF              } from '../modules/nf-core/plink/vcf/main'
+include { PLINK_GWAS             } from '../modules/nf-core/plink/gwas/main'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -30,13 +31,34 @@ workflow GWAS {
     ch_inputs = ch_samplesheet
               | multiMap {
                     meta, vcf, pheno, cov ->
-                    vcf   : [ meta,vcf ]
+                    vcf   : [ meta, vcf ]
                     pheno : [ meta, pheno]
-                    cov   : cov ? [ meta,cov ] : null
+                    cov   : [ meta, cov ] // Might be worth adding ? : null
               }
 
     PLINK_VCF (
-        ch_inputs.vcf
+        ch_inputs.vcf,
+        ch_inputs.pheno
+    )
+
+    // Update input with plink binary coversion from vcf
+    new_ch_input = PLINK_VCF.out.bed
+                 | combine(PLINK_VCF.out.bim, by:0)
+                 | combine(PLINK_VCF.out.fam, by:0)
+                 | combine(ch_inputs.pheno, by:0)
+                 | combine(ch_inputs.cov, by:0)
+                 | multiMap {
+                        meta, bed, bim, fam, pheno, cov ->
+                        plink: [ meta, bed, bim, fam ]
+                        pheno: [ meta, pheno ]
+                        cov:   [ meta, cov ]
+                 }
+
+    PLINK_GWAS (
+        new_ch_input.plink,
+        [[],[]], // vcf if not converted to plink binary before
+        [[],[]], // bcf if not converted to plink birary before
+        [[],[]],
     )
 
     //

From b52cdb916f2e851fbb2b3a09d984292e42a52268 Mon Sep 17 00:00:00 2001
From: Fernando Duarte <123090819+FernandoDuarteF@users.noreply.github.com>
Date: Fri, 23 May 2025 11:12:41 +0100
Subject: [PATCH 4/4] Update README.md

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

diff --git a/README.md b/README.md
index 696459d..f423837 100644
--- a/README.md
+++ b/README.md
@@ -19,6 +19,8 @@
 
 ## Introduction
 
+REMOVE THIS LINE
+
 **nf-core/gwas** is a bioinformatics pipeline that ...
 
 <!-- TODO nf-core: