299 add qc for nanopore data

CHANGELOG.md

@@ -19,6 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added ska filepath to yaml
 - Added optional read downsampling using seqtk
 - Added `tbGradingRulesBed` to IGV track
+- Added module NanoPlot to check quality of raw reads from ONT
 
 ### Fixed
 
@@ -51,6 +52,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added `samplelist_nanopore.csv` for running long-read test data
 - Added location of documentation to `README` 
 - Added `cdmDir` to config
+- Added NanoPlot module
 - Added process for adding IGV annotation tracks with PRP.
 - Updated how `mycobacterium_tuberculosis` workflow adds IGV annotation tracks.
 

configs/nextflow.base.config

@@ -260,6 +260,11 @@ process {
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/mykrobe", mode: 'copy', overwrite: true ]
 		ext.args = "--species tb --format csv"
 	}
+	withName: nanoplot {
+		container = "${params.containerDir}/nanoplot.sif"
+		publishDir = [ path: "${params.outdir}/${params.speciesDir}/nanoplot", mode: 'copy', overwrite: true ]
+		ext.args = "-t 8"
+	}
 	withName: post_align_qc {
 		memory = '2 GB'
 		container = "${params.containerDir}/bonsai-prp.sif"

configs/nextflow.ci.config

@@ -232,6 +232,11 @@ process {
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/mykrobe", mode: 'copy', overwrite: true ]
 		ext.args = "--species tb --format csv"
 	}
+	withName: nanoplot {
+		container = "${params.containerDir}/nanoplot.sif"
+		publishDir = [ path: "${params.outdir}/${params.speciesDir}/nanoplot", mode: 'copy', overwrite: true ]
+		ext.args = "-t 8"
+	}
 	withName: post_align_qc {
 		memory = '2 GB'
 		container = "${params.containerDir}/bonsai-prp.sif"

configs/nextflow.dev.config

@@ -246,6 +246,11 @@ process {
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/mykrobe", mode: 'copy', overwrite: true ]
 		ext.args = "--species tb --format csv"
 	}
+	withName: nanoplot {
+		container = "https://depot.galaxyproject.org/singularity/nanoplot:1.43.0--pyhdfd78af_1"
+		publishDir = [ path: "${params.outdir}/${params.speciesDir}/nanoplot", mode: 'copy', overwrite: true ]
+		ext.args = "-t 8"
+	}
 	withName: post_align_qc {
 		memory = '2 GB'
 		container = "${params.containerDir}/bonsai-prp.sif"

configs/nextflow.hopper.config

@@ -262,6 +262,11 @@ process {
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/mykrobe", mode: 'copy', overwrite: true ]
 		ext.args = "--species tb --format csv"
 	}
+	withName: nanoplot {
+		container = "https://depot.galaxyproject.org/singularity/nanoplot:1.43.0--pyhdfd78af_1"
+		publishDir = [ path: "${params.outdir}/${params.speciesDir}/nanoplot", mode: 'copy', overwrite: true ]
+		ext.args = "-t 8"
+	}
 	withName: post_align_qc {
 		memory = '2 GB'
 		container = "docker://clinicalgenomicslund/bonsai-prp:0.11.1"

configs/nextflow.ngp.config

@@ -259,6 +259,11 @@ process {
 		publishDir = [ path: "${params.outdir}/${params.speciesDir}/mykrobe", mode: 'copy', overwrite: true ]
 		ext.args = "--species tb --format csv"
 	}
+	withName: nanoplot {
+		container = "${params.containerDir}/nanoplot.sif"
+		publishDir = [ path: "${params.outdir}/${params.speciesDir}/nanoplot", mode: 'copy', overwrite: true ]
+		ext.args = "-t 8"
+	}
 	withName: post_align_qc {
 		cpus = params.cpus_medium
 		memory = params.mem_small

container/Makefile

@@ -27,6 +27,7 @@ remote_containers := ncbi-amrfinderplus.sif \
 					freebayes.sif \
 					kraken2.sif \
 					medaka.sif \
+					nanoplot.sif \
 					mlst.sif \
 					mykrobe.sif \
 					perl-json.sif \
@@ -60,6 +61,7 @@ URL_kraken2 := https://depot.galaxyproject.org/singularity/kraken2:2.1.2--pl5321
 URL_medaka := https://depot.galaxyproject.org/singularity/medaka:1.11.3--py39h05d5c5e_0
 URL_mlst := https://depot.galaxyproject.org/singularity/mlst:2.23.0--hdfd78af_1
 URL_mykrobe := https://depot.galaxyproject.org/singularity/mykrobe:0.12.2--py39h70e0db4_0
+URL_nanoplot := https://depot.galaxyproject.org/singularity/nanoplot:1.43.0--pyhdfd78af_1
 URL_perl-json := https://depot.galaxyproject.org/singularity/perl-json:4.10--pl5321hdfd78af_0
 URL_quast := https://depot.galaxyproject.org/singularity/quast:5.2.0--py310pl5321hc8f18ef_2
 URL_resfinder := https://depot.galaxyproject.org/singularity/resfinder:4.4.2--pyhdfd78af_1

nextflow-modules/modules/nanoplot/main.nf

@@ -0,0 +1,41 @@
+process nanoplot {
+  tag "${sampleID}"
+  scratch params.scratch
+
+  input:
+    tuple val(sampleID), path(reads), val(platform) 
+
+  output:
+    tuple val(sampleID), path(output), emit: html
+    path "*versions.yml"             , emit: versions
+
+  when:
+    platform == "nanopore"
+
+  script:
+    def args = task.ext.args ?: ''
+    output = "${sampleID}_NanoPlot-report.html"
+    """
+    NanoPlot $args --prefix ${sampleID}_ --fastq $reads
+
+    cat <<-END_VERSIONS > ${sampleID}_${task.process}_versions.yml
+    ${task.process}:
+     nanoplot:
+      version: \$(echo \$(NanoPlot --version 2>&1))
+      container: ${task.container}
+    END_VERSIONS
+    """
+
+  stub:
+    output = "${sampleID}_NanoPlot-report.html"
+    """
+    touch $output
+
+    cat <<-END_VERSIONS > ${sampleID}_${task.process}_versions.yml
+    ${task.process}:
+     nanoplot:
+      version: \$(echo \$(NanoPlot --version 2>&1))
+      container: ${task.container}
+    END_VERSIONS
+    """
+}

workflows/bacterial_base.nf

@@ -9,6 +9,7 @@ include { assembly_trim_clean                   } from '../nextflow-modules/modu
 include { bwa_mem as bwa_mem_ref                } from '../nextflow-modules/modules/bwa/main.nf'
 include { flye                                  } from '../nextflow-modules/modules/flye/main.nf'
 include { medaka                                } from '../nextflow-modules/modules/medaka/main.nf'
+include { nanoplot                              } from '../nextflow-modules/modules/nanoplot/main.nf'
 include { post_align_qc                         } from '../nextflow-modules/modules/prp/main.nf'
 include { quast                                 } from '../nextflow-modules/modules/quast/main.nf'
 include { samtools_index as samtools_index_ref  } from '../nextflow-modules/modules/samtools/main.nf'
@@ -90,13 +91,16 @@ workflow CALL_BACTERIAL_BASE {
 
         post_align_qc(bwa_mem_ref.out.bam, referenceGenome, coreLociBed)
 
+        nanoplot(ch_reads_w_meta)
+
         sourmash(ch_assembly)
 
         ska_build(ch_reads)
 
         ch_versions = ch_versions.mix(bwa_mem_ref.out.versions)
         ch_versions = ch_versions.mix(flye.out.versions)
         ch_versions = ch_versions.mix(medaka.out.versions)
+        ch_versions = ch_versions.mix(nanoplot.out.versions)
         ch_versions = ch_versions.mix(quast.out.versions)
         ch_versions = ch_versions.mix(samtools_index_ref.out.versions)
         ch_versions = ch_versions.mix(skesa.out.versions)
@@ -112,6 +116,7 @@ workflow CALL_BACTERIAL_BASE {
         bai             = samtools_index_ref.out.bai        // channel: [ val(meta), path(bai)]
         metadata        = save_analysis_metadata.out.meta   // channel: [ val(meta), path(json)]
         qc              = post_align_qc.out.qc              // channel: [ val(meta), path(fasta)]
+        qc_nano         = nanoplot.out.html                 // channel: [ val(meta), path(html)]
         quast           = quast.out.qc                      // channel: [ val(meta), path(qc)]
         reads           = ch_reads                          // channel: [ val(meta), path(json)]
         ska_build       = ska_build.out.skf                 // channel: [ val(meta), path(skf)]