code polishing

modules/local/build_intervals.nf

@@ -1,19 +1,17 @@
 process BUILD_INTERVALS {
-    tag "${fastaFai}"
+    tag "${fai}"
 
     publishDir params.outdir, mode: params.publish_dir_mode,
     saveAs: {params.save_reference ? "reference_genome/${it}" : null }
 
     input:
-        path file(fastaFai) 
+        path fai
 
     output:
-        path file("${fastaFai.baseName}.bed")
-
-    //when: !(params.intervals) && !('annotate' in step) && !('controlfreec' in step) 
+        path "${fai.baseName}.bed"
 
     script:
     """
-    awk -v FS='\t' -v OFS='\t' '{ print \$1, \"0\", \$2 }' ${fastaFai} > ${fastaFai.baseName}.bed
+    awk -v FS='\t' -v OFS='\t' '{ print \$1, \"0\", \$2 }' ${fai} > ${fai.baseName}.bed
     """
 }

modules/local/create_intervals_bed.nf

@@ -1,4 +1,4 @@
-include { hasExtension } from './functions'
+include { has_extension } from './functions'
 
 process CREATE_INTERVALS_BED {
     tag "${intervals}"
@@ -7,13 +7,12 @@ process CREATE_INTERVALS_BED {
         path intervals
 
     output:
-        path ('*.bed')//mode flatten
-
+        path ('*.bed')
 
     script:
     // If the interval file is BED format, the fifth column is interpreted to
     // contain runtime estimates, which is then used to combine short-running jobs
-    if (hasExtension(intervals, "bed"))
+    if (has_extension(intervals, "bed"))
         """
         awk -vFS="\t" '{
           t = \$5  # runtime estimate
@@ -33,7 +32,7 @@ process CREATE_INTERVALS_BED {
           print \$0 > name
         }' ${intervals}
         """
-    else if (hasExtension(intervals, "interval_list"))
+    else if (has_extension(intervals, "interval_list"))
         """
         grep -v '^@' ${intervals} | awk -vFS="\t" '{
           name = sprintf("%s_%d-%d", \$1, \$2, \$3);

modules/local/gatk_dict.nf

@@ -8,7 +8,7 @@ process GATK_CREATE_SEQUENCE_DICTIONARY {
         path fasta
 
     output:
-        path ("${fasta.baseName}.dict")
+        path "${fasta.baseName}.dict"
 
     script:
     """

modules/local/get_software_versions.nf

@@ -9,7 +9,7 @@ process GET_SOFTWARE_VERSIONS {
                 }
 
     output:
-    path 'software_versions_mqc.yaml', emit: yml
+    path "software_versions_mqc.yaml", emit: yml
     path "software_versions.csv", emit: csv
 
     script:

modules/local/output_documentation.nf

@@ -5,14 +5,14 @@ process OUTPUT_DOCUMENTATION {
     publishDir "${params.outdir}/pipeline_info", mode: params.publish_dir_mode
 
     input:
-    path output_docs
-    path images
+        path output_docs
+        path images
 
     output:
-    path "results_description.html"
+        path "results_description.html"
 
     script:
     """
-    markdown_to_html.py $output_docs -o results_description.html
+    markdown_to_html.py ${output_docs} -o results_description.html
     """
 }

modules/local/trim_galore.nf

@@ -5,19 +5,18 @@ process TRIM_GALORE {
 
     publishDir "${params.outdir}/Reports/${idSample}/TrimGalore/${idSample}_${idRun}", mode: params.publish_dir_mode,
       saveAs: {filename ->
-        if (filename.indexOf("_fastqc") > 0) "FastQC/$filename"
-        else if (filename.indexOf("trimming_report.txt") > 0) "logs/$filename"
+        if (filename.indexOf("_fastqc") > 0) "FastQC/${filename}"
+        else if (filename.indexOf("trimming_report.txt") > 0) "logs/${filename}"
         else if (params.save_trimmed) filename
         else null
       }
 
     input:
-        tuple val(idPatient), val(idSample), val(idRun), file("${idSample}_${idRun}_R1.fastq.gz"), file("${idSample}_${idRun}_R2.fastq.gz")
+        tuple val(idPatient), val(idSample), val(idRun), path("${idSample}_${idRun}_R1.fastq.gz"), path("${idSample}_${idRun}_R2.fastq.gz")
 
     output:
-        path "*.{html,zip,txt}",  emit: report
-        tuple idPatient, idSample, idRun, file("${idSample}_${idRun}_R1_val_1.fq.gz"), file("${idSample}_${idRun}_R2_val_2.fq.gz") , emit: trimmed_reads
-
+        path "*.{html,zip,txt}", emit: report
+        tuple idPatient, idSample, idRun, path("${idSample}_${idRun}_R1_val_1.fq.gz"), path("${idSample}_${idRun}_R2_val_2.fq.gz"), emit: trimmed_reads
 
     script:
     // Calculate number of --cores for TrimGalore based on value of task.cpus

modules/nf-core/bwamem2_index.nf

@@ -8,7 +8,7 @@ process BWAMEM2_INDEX {
         path fasta
 
     output:
-        path("${fasta}.*")
+        path "${fasta}.*"
 
     script:
     """

modules/nf-core/fastqc.nf

@@ -1,18 +1,17 @@
 process FASTQC {
-    label 'FastQC'
+    label 'FASTQC'
     label 'cpus_2'
 
     tag "${idPatient}-${idRun}"
 
     publishDir "${params.outdir}/Reports/${idSample}/FastQC/${idSample}_${idRun}", mode: params.publish_dir_mode
 
     input:
-        tuple val(idPatient), val(idSample), val(idRun), file("${idSample}_${idRun}_R1.fastq.gz"), file("${idSample}_${idRun}_R2.fastq.gz")
-       
+        tuple val(idPatient), val(idSample), val(idRun), path("${idSample}_${idRun}_R1.fastq.gz"), path("${idSample}_${idRun}_R2.fastq.gz")
+
     output:
         path "*.{html,zip}"
 
-
     script:
     """
     fastqc -t 2 -q ${idSample}_${idRun}_R1.fastq.gz ${idSample}_${idRun}_R2.fastq.gz

modules/nf-core/htslib_tabix.nf

@@ -4,10 +4,10 @@ process HTSLIB_TABIX {
     container 'quay.io/biocontainers/tabix:0.2.6--ha92aebf_0'
 
     input:
-        path(vcf)
+        path vcf
 
     output:
-        path("${vcf}.tbi")
+        path "${vcf}.tbi"
 
     script:
     """

modules/nf-core/multiqc.nf

@@ -9,25 +9,24 @@ process MULTIQC {
     publishDir "${params.outdir}/multiqc", mode: params.publish_dir_mode
 
     input:
-    path multiqc_config
-    path mqc_custom_config
-    // TODO nf-core: Add in log files from your new processes for MultiQC to find!
-    path fastqc
-    path trim_galore
-    path software_versions
-    val workflow_summary
+        path fastqc
+        path multiqc_config
+        path multiqc_custom_config
+        path software_versions
+        path trim_galore
+        val workflow_summary
 
     output:
-    path "*multiqc_report.html"
-    path "*_data"
-    path "multiqc_plots"
+        path "*multiqc_report.html"
+        path "*_data"
+        path "multiqc_plots"
 
     script:
-    rtitle = custom_runName ? "--title \"$custom_runName\"" : ''
-    rfilename = custom_runName ? "--filename " + custom_runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" : ''
-    custom_config_file = params.multiqc_config ? "--config $mqc_custom_config" : ''
+    title = custom_runName ? "--title \"${custom_runName}\"" : ''
+    filename = custom_runName ? "--filename " + custom_runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" : ''
+    custom_config_file = params.multiqc_config ? "--config ${multiqc_custom_config}" : ''
     """
-    echo '$workflow_summary' > workflow_summary_mqc.yaml
-    multiqc -f $rtitle $rfilename $custom_config_file .
+    echo '${workflow_summary}' > workflow_summary_mqc.yaml
+    multiqc -f ${title} ${filename} ${custom_config_file} .
     """
 }

modules/nf-core/samtools_faidx.nf

@@ -8,7 +8,7 @@ process SAMTOOLS_FAIDX {
         path fasta
 
     output:
-        path ("${fasta}.fai")
+        path "${fasta}.fai"
 
     //when: !(params.fasta_fai) && params.fasta && !('annotate' in step)
 

modules/subworkflows/build_indices.nf

@@ -6,16 +6,16 @@
 
 // And then initialize channels based on params or indexes that were just built
 
-
-include { HTSLIB_TABIX as HTSLIB_TABIX_DBSNP } from '../nf-core/htslib_tabix'
-include { HTSLIB_TABIX as HTSLIB_TABIX_GERMLINE_RESOURCE } from '../nf-core/htslib_tabix'
-include { HTSLIB_TABIX as HTSLIB_TABIX_KNOWN_INDELS } from '../nf-core/htslib_tabix'
-include { HTSLIB_TABIX as HTSLIB_TABIX_PON } from '../nf-core/htslib_tabix'
+include { BUILD_INTERVALS } from '../local/build_intervals.nf'
 include { BWAMEM2_INDEX as BWAMEM2_INDEX } from '../nf-core/bwamem2_index.nf'
-include { SAMTOOLS_FAIDX as SAMTOOLS_FAIDX } from '../nf-core/samtools_faidx.nf'
 include { GATK_CREATE_SEQUENCE_DICTIONARY as GATK_CREATE_SEQUENCE_DICTIONARY } from '../local/gatk_dict.nf'
-include { BUILD_INTERVALS } from '../local/build_intervals.nf'
-
+include {
+    HTSLIB_TABIX as HTSLIB_TABIX_DBSNP;
+    HTSLIB_TABIX as HTSLIB_TABIX_GERMLINE_RESOURCE;
+    HTSLIB_TABIX as HTSLIB_TABIX_KNOWN_INDELS;
+    HTSLIB_TABIX as HTSLIB_TABIX_PON;
+} from '../nf-core/htslib_tabix'
+include { SAMTOOLS_FAIDX as SAMTOOLS_FAIDX } from '../nf-core/samtools_faidx.nf'
 
 workflow BUILD_INDICES{
     take:
@@ -49,19 +49,17 @@ workflow BUILD_INDICES{
     if (!(params.pon_index) && params.pon && ('tnscope' in tools || 'mutect2' in tools))
         HTSLIB_TABIX_PON(ch_pon)
 
-    if (!(params.intervals) && !('annotate' in step) && !('controlfreec' in step)){
-        ch_fai = params.fasta_fai ? Channel.value(file(params.fasta_fai)) : SAMTOOLS_FAIDX.out
-        ch_fai.dump(tag: 'ch_fai')
-        BUILD_INTERVALS(ch_fai)
+    if (!(params.intervals) && !('annotate' in step) && !('controlfreec' in step)) {
+        BUILD_INTERVALS(SAMTOOLS_FAIDX.out)
     }
 
     emit:
         bwa_built = BWAMEM2_INDEX.out 
+        dbsnp_tbi = HTSLIB_TABIX_DBSNP.out
         dictBuilt = GATK_CREATE_SEQUENCE_DICTIONARY.out
         fai_built = SAMTOOLS_FAIDX.out
-        dbsnp_tbi = HTSLIB_TABIX_DBSNP.out
         germline_resource_tbi = HTSLIB_TABIX_GERMLINE_RESOURCE.out
+        intervalBuilt = BUILD_INTERVALS.out
         known_indels_tbi = HTSLIB_TABIX_KNOWN_INDELS.out
         pon_tbi = HTSLIB_TABIX_PON.out
-        intervalBuilt = BUILD_INTERVALS.out
 }