Merge pull request #235 from nf-core/skipqc-fix

Skipqc fix and group samples by adapter for mirtrace

Author: drpatelh

CHANGELOG.md

@@ -3,14 +3,16 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [v2.2.0](https://github.com/nf-core/smrnaseq/releases/tag/2.2.0) - 2023-04-25
+## [v2.2.0](https://github.com/nf-core/smrnaseq/releases/tag/2.2.0) - 2023-04-26
 
 - [[#220](https://github.com/nf-core/smrnaseq/issues/220)] - Fixed an issue where miRTrace reports fastq basename instead of sample ID
 - [[#208](https://github.com/nf-core/smrnaseq/issues/208)] - Fixed usability of `--skip_qc` parameter
 - Updated FASTP module to allow direct addition of adapter_fasta file to it
 - [[#205](https://github.com/nf-core/smrnaseq/issues/205)] - Fix mirTrace Report to be a single report again instead of per sample reports
 - [[#206](https://github.com/nf-core/smrnaseq/issues/206)] - Use % as separator in sed commands to enable conda working properly on OSX and Linux
 - [[#207](https://github.com/nf-core/smrnaseq/issues/224)] - Fix Samplesheet print error
+- Group samples by adapter sequence before running mirtrace
+- Remove `--skip_qc` parameter
 
 ## [v2.1.0](https://github.com/nf-core/smrnaseq/releases/tag/2.1.0) - 2022-10-20 Maroon Tin Dalmatian
 

conf/modules.config

@@ -87,7 +87,7 @@ process {
     }
 }
 
-if (!(params.skip_fastqc || params.skip_qc)) {
+if (!(params.skip_fastqc)) {
     process {
         withName: '.*:FASTQC_FASTP:FASTQC_.*' {
             ext.args = '--quiet'

modules/local/mirtrace.nf

@@ -7,7 +7,7 @@ process MIRTRACE_RUN {
         'quay.io/biocontainers/mirtrace:1.0.1--hdfd78af_1' }"
 
     input:
-    tuple val(meta), path(reads)
+    tuple val(adapter), val(ids), path(reads)
 
     output:
     path "mirtrace/*"  , emit: mirtrace
@@ -18,22 +18,20 @@ process MIRTRACE_RUN {
 
     script:
     // mirtrace protocol defaults to 'params.protocol' if not set
-    def primer = meta.adapter ? "--adapter ${meta.adapter}" : ""
+    def primer = adapter ? "--adapter ${adapter}" : ""
     def protocol = params.protocol == 'custom' ? '' : "--protocol $params.protocol"
     def java_mem = ''
-    def prefix = "${meta.id}"
     if(task.memory){
         tmem = task.memory.toBytes()
         java_mem = "-Xms${tmem} -Xmx${tmem}"
     }
+    def config_lines = [ids,reads]
+    .transpose()
+    .collect({ id, path -> "echo '${path},${id}' >> mirtrace_config" })
     """
     export mirtracejar=\$(dirname \$(which mirtrace))
-    for i in $reads
-    do
-        path=\$(realpath \${i})
-        prefix=$prefix
-        echo \$path","\$prefix
-    done > mirtrace_config
+
+    ${config_lines.join("\n    ")}
 
     java $java_mem -jar \$mirtracejar/mirtrace.jar --mirtrace-wrapper-name mirtrace qc  \\
         --species $params.mirtrace_species \\

nextflow.config

@@ -36,7 +36,6 @@ params {
     fastp_min_length            = 17
     fastp_known_mirna_adapters  = "$projectDir/assets/known_adapters.fa"
     save_trimmed_fail           = false
-    skip_qc                     = false
     skip_fastqc                 = false
     skip_multiqc                = false
     skip_mirdeep                = false

nextflow_schema.json

@@ -249,11 +249,6 @@
             "description": "Switches to skip specific pipeline steps, if desired.",
             "fa_icon": "fas fa-fast-forward",
             "properties": {
-                "skip_qc": {
-                    "type": "boolean",
-                    "fa_icon": "fas fa-fast-forward",
-                    "description": "Skip all QC steps"
-                },
                 "skip_fastqc": {
                     "type": "boolean",
                     "fa_icon": "fas fa-fast-forward",

subworkflows/nf-core/fastqc_fastp.nf renamed to subworkflows/local/fastqc_fastp.nf

@@ -35,10 +35,10 @@ workflow FASTQC_FASTP {
 
     main:
 
-    ch_versions = Channel.empty()
-
+    ch_versions     = Channel.empty()
     fastqc_raw_html = Channel.empty()
     fastqc_raw_zip  = Channel.empty()
+    adapterseq      = reads.map { meta, _ -> [meta, null] }
     if (!params.skip_fastqc) {
         FASTQC_RAW (
             reads

subworkflows/local/mirtrace.nf

@@ -6,10 +6,11 @@ include { MIRTRACE_RUN } from '../../modules/local/mirtrace'
 
 workflow MIRTRACE {
     take:
-    reads      // channel: [ val(meta), [ reads ] ]
+    reads      // channel: [ val(adapterseq), [ val(ids) ], [ path(reads) ] ]
 
     main:
     reads
+    | map { adapterseq, ids, read_collection -> [adapterseq, ids, read_collection*.first()]}
     | MIRTRACE_RUN
 
     emit:

workflows/smrnaseq.nf

@@ -59,7 +59,7 @@ if (!params.mirgenedb) {
 }
 
 include { INPUT_CHECK        } from '../subworkflows/local/input_check'
-include { FASTQC_FASTP       } from '../subworkflows/nf-core/fastqc_fastp'
+include { FASTQC_FASTP       } from '../subworkflows/local/fastqc_fastp'
 include { CONTAMINANT_FILTER } from '../subworkflows/local/contaminant_filter'
 include { MIRNA_QUANT        } from '../subworkflows/local/mirna_quant'
 include { GENOME_QUANT       } from '../subworkflows/local/genome_quant'
@@ -125,36 +125,26 @@ workflow SMRNASEQ {
     // SUBWORKFLOW: Read QC and trim adapters
     //
 
-    if(!params.skip_qc){
     FASTQC_FASTP (
         ch_cat_fastq,
         ch_fastp_adapters,
         false,
         false
     )
     ch_versions = ch_versions.mix(FASTQC_FASTP.out.versions)
-    reads_for_mirna = FASTQC_FASTP.out.reads
-
 
     //
     // SUBWORKFLOW: mirtrace QC
     //
-    ch_outputs_for_mirtrace = FASTQC_FASTP.out.adapterseq
+    FASTQC_FASTP.out.adapterseq
     .join( ch_cat_fastq )
-    .map { meta, adapterseq, fastq -> [meta + [adapter:adapterseq], fastq] }
-    .collect()
-
-    MIRTRACE(ch_outputs_for_mirtrace)
+    .map { meta, adapterseq, fastq -> [adapterseq, meta.id, fastq] }
+    .groupTuple()
+    .set { ch_mitrace_inputs }
 
+    MIRTRACE(ch_mitrace_inputs)
     ch_versions = ch_versions.mix(MIRTRACE.out.versions.ifEmpty(null))
 
-    } else{
-        //TODO - rob? :-)
-
-    }
-
-
-
 
     //
     // SUBWORKFLOW: remove contaminants from reads
@@ -172,18 +162,16 @@ workflow SMRNASEQ {
             FASTQC_FASTP.out.reads
         )
 
-        reads_for_mirna = CONTAMINANT_FILTER.out.filtered_reads
+        contamination_stats = CONTAMINANT_FILTER.out.filter_stats
         ch_versions = ch_versions.mix(CONTAMINANT_FILTER.out.versions)
-        CONTAMINANT_FILTER.out.filter_stats
-            .set { contamination_stats }
 
     }
 
     MIRNA_QUANT (
         reference_mature,
         reference_hairpin,
         mirna_gtf,
-        reads_for_mirna
+        contamination_stats
     )
     ch_versions = ch_versions.mix(MIRNA_QUANT.out.versions.ifEmpty(null))
 
@@ -192,10 +180,8 @@ workflow SMRNASEQ {
     //
     genome_stats = Channel.empty()
     if (params.fasta){
-        ch_fasta = file(params.fasta)
-        GENOME_QUANT ( ch_fasta, params.bowtie_index, MIRNA_QUANT.out.unmapped )
-        GENOME_QUANT.out.stats
-            .set { genome_stats }
+        GENOME_QUANT ( file(params.fasta), params.bowtie_index, MIRNA_QUANT.out.unmapped )
+        genome_stats = GENOME_QUANT.out.stats
         ch_versions = ch_versions.mix(GENOME_QUANT.out.versions)
 
         if (!params.skip_mirdeep) {
@@ -229,23 +215,22 @@ workflow SMRNASEQ {
         ch_multiqc_files = Channel.empty()
         ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
         ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-
-        ch_multiqc_files = ch_multiqc_files.mix(FASTQC_FASTP.out.fastqc_raw_zip.collect{it[1]}.ifEmpty([])),
-        ch_multiqc_files = ch_multiqc_files.mix(FASTQC_FASTP.out.trim_json.collect{it[1]}.ifEmpty([])),
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQC_FASTP.out.fastqc_raw_zip.collect{it[1]}.ifEmpty([]))
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQC_FASTP.out.trim_json.collect{it[1]}.ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(contamination_stats.collect().ifEmpty([]))
+        ch_multiqc_files = ch_multiqc_files.mix(genome_stats.collect({it[1]}).ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(MIRNA_QUANT.out.mature_stats.collect({it[1]}).ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(MIRNA_QUANT.out.hairpin_stats.collect({it[1]}).ifEmpty([]))
-        ch_multiqc_files = ch_multiqc_files.mix(genome_stats.collect({it[1]}).ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(MIRNA_QUANT.out.mirtop_logs.collect().ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(MIRTRACE.out.results.collect().ifEmpty([]))
 
-    MULTIQC (
-        ch_multiqc_files.collect(),
-        ch_multiqc_config.toList(),
-        ch_multiqc_custom_config.toList(),
-        ch_multiqc_logo.toList()
-    )
-    multiqc_report = MULTIQC.out.report.toList()
+        MULTIQC (
+            ch_multiqc_files.collect(),
+            ch_multiqc_config.toList(),
+            ch_multiqc_custom_config.toList(),
+            ch_multiqc_logo.toList()
+        )
+        multiqc_report = MULTIQC.out.report.toList()
     }
 }