src/nf_modules/RSEM/tests/tests.sh

-nextflow src/nf_modules/RSEM/tests/index.nf \
-  -c src/nf_modules/RSEM/rsem.config \
-  -profile docker \
-  --fasta "data/tiny_dataset/fasta/tiny_v2.fasta" \
-  --annotation "data/tiny_dataset/annot/tiny.gff"
-
-nextflow src/nf_modules/RSEM/tests/quantification_single.nf \
-  -c src/nf_modules/RSEM/rsem.config \
-  -profile docker \
-  --index "results/mapping/index/tiny_v2.index*" \
-  --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
-
-nextflow src/nf_modules/RSEM/tests/quantification_paired.nf \
-  -c src/nf_modules/RSEM/rsem.config \
-  -profile docker \
-  --index "results/mapping/index/tiny_v2.index*" \
-  --fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
-

src/nf_modules/SAMtools/samtools.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $sort_bam {
-        container = "samtools:1.7"
-      }
-      $index_bam {
-        container = "samtools:1.7"
-      }
-      $split_bam {
-        container = "samtools:1.7"
-      }
-      $filter_bam {
-        container = "samtools:1.7"
-      }
-    }
-  }
-  sge {
-    process{
-      $trimming {
-        beforeScript = "module purge; module load SAMtools/1.7"
-      }
-      $index_bam {
-        beforeScript = "module purge; module load SAMtools/1.7"
-      }
-      $split_bam {
-        beforeScript = "module purge; module load SAMtools/1.7"
-      }
-      $filter_bam {
-        beforeScript = "module purge; module load SAMtools/1.7"
-      }
-    }
-  }
-}

src/nf_modules/SAMtools/samtools.nf

-/*
-* SAMtools :
-* Imputs : bam files
-* Output : bam files
-*/
-
-/*                      bams sorting                                     */
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process sort_bam {
-  tag "$bam.baseName"
-  cpus 4
-
-  input:
-    file bam from bam_files
-
-  output:
-    file "*_sorted.bam" into sorted_bam_files
-
-  script:
-"""
-samtools sort -@ ${task.cpus} -O BAM -o ${bam.baseName}_sorted.bam ${bam}
-"""
-}
-
-/*                      bams indexing                                     */
-
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process index_bam {
-  tag "$bam.baseName"
-  input:
-    file bam from bam_files
-  output:
-    file "*bam*" into indexed_bam_file
-  script:
-"""
-samtools index ${bam}
-"""
-}
-
-
-/*                      bams spliting                                     */
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process split_bam {
-  tag "$bam.baseName"
-  cpus 2
-
-  input:
-    file bam from bam_files
-
-  output:
-    file "*_forward.bam*" into forward_bam_files
-    file "*_reverse.bam*" into reverse_bam_files
-  script:
-"""
-samtools view -hb -F 0x10 ${bam} > ${bam}_forward.bam &
-samtools view -hb -f 0x10 ${bam} > ${bam}_reverse.bam
-"""
-}
-
-
-/*                      bams filtering                                     */
-params.bam = "$baseDir/data/bam/*.bam"
-params.bed = "$baseDir/data/bam/*.bed"
-
-log.info "bams files : ${params.bam}"
-log.info "bed file : ${params.bed}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-Channel
-  .fromPath( params.bed )
-  .ifEmpty { error "Cannot find any bed file matching: ${params.bed}" }
-  .set { bed_files }
-
-process filter_bam {
-  tag "$bam.baseName"
-  cpus 4
-
-  input:
-    file bam from bam_files
-    file bed from bed_files
-
-  output:
-    file "*_filtered.bam*" into filtered_bam_files
-  script:
-"""
-samtools view -@ ${task.cpus} -hb ${bam} -L ${bed} > ${bam.baseName}_filtered.bam
-"""
-}
-
-

src/nf_modules/SAMtools/tests/filter_bams.nf

-params.bam = "$baseDir/data/bam/*.bam"
-params.bed = "$baseDir/data/bam/*.bed"
-
-log.info "bams files : ${params.bam}"
-log.info "bed file : ${params.bed}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-Channel
-  .fromPath( params.bed )
-  .ifEmpty { error "Cannot find any bed file matching: ${params.bed}" }
-  .set { bed_files }
-
-process filter_bam {
-  tag "$bam.baseName"
-  cpus 4
-
-  input:
-    file bam from bam_files
-    file bed from bed_files
-
-  output:
-    file "*_filtered.bam*" into filtered_bam_files
-  script:
-"""
-samtools view -@ ${task.cpus} -hb ${bam} -L ${bed} > ${bam.baseName}_filtered.bam
-"""
-}
-
-

src/nf_modules/SAMtools/tests/index_bams.nf

-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process index_bam {
-  tag "$bam.baseName"
-  input:
-    file bam from bam_files
-  output:
-    file "*bam*" into indexed_bam_file
-  script:
-"""
-samtools index ${bam}
-"""
-}
-

src/nf_modules/SAMtools/tests/sort_bams.nf

-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process sort_bam {
-  tag "$bams.baseName"
-  cpus 4
-
-  input:
-    file bam from bam_files
-
-  output:
-    file "*_sorted.bam" into sorted_bam_files
-
-  script:
-"""
-samtools sort -@ ${task.cpus} -O BAM -o ${bam.baseName}_sorted.bam ${bam}
-"""
-}
-

src/nf_modules/SAMtools/tests/split_bams.nf

-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
-  .set { bam_files }
-
-process split_bam {
-  tag "$bam.baseName"
-  cpus 2
-
-  input:
-    file bam from bam_files
-
-  output:
-    file "*_forward.bam*" into forward_bam_files
-    file "*_reverse.bam*" into reverse_bam_files
-  script:
-"""
-samtools view -hb -F 0x10 ${bam} > ${bam}_forward.bam &
-samtools view -hb -f 0x10 ${bam} > ${bam}_reverse.bam
-"""
-}
-

src/nf_modules/SAMtools/tests/tests.sh

-nextflow src/nf_modules/SAMtools/tests/sort_bams.nf \
-  -c src/nf_modules/SAMtools/samtools.config \
-  -profile docker \
-  --bam "data/tiny_dataset/map/tiny_v2.bam"
-
-nextflow src/nf_modules/SAMtools/tests/index_bams.nf \
-  -c src/nf_modules/SAMtools/samtools.config \
-  -profile docker \
-  --bam "data/tiny_dataset/map/tiny_v2.sort.bam"
-
-nextflow src/nf_modules/SAMtools/tests/split_bams.nf \
-  -c src/nf_modules/SAMtools/samtools.config \
-  -profile docker \
-  --bam "data/tiny_dataset/map/tiny_v2.bam"
-
-nextflow src/nf_modules/SAMtools/tests/filter_bams.nf \
-  -c src/nf_modules/SAMtools/samtools.config \
-  -profile docker \
-  --bam "data/tiny_dataset/map/tiny_v2.bam" \
-  --bed "data/tiny_dataset/OLD/2genes.bed"

src/nf_modules/SRAtoolkit/sratoolkit.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $fastq_dump {
-        container = "sratoolkit:2.8.2"
-      }
-    }
-  }
-  sge {
-    process{
-      $fastq_dump {
-        beforeScript = "module purge; module load SRAtoolkit/2.8.2"
-        executor = "sge"
-        cpus = 1
-        memory = "5GB"
-        time = "6h"
-        queueSize = 1000
-        pollInterval = '60sec'
-        queue = 'monointeldeb128'
-      }
-    }
-  }
-}

src/nf_modules/SRAtoolkit/sratoolkit.nf

-/*
-* sra-tools :
-
-*/
-
-/*                      fastq-dump
-* Imputs : srr list
-* Outputs : fastq files
-*/
-
-params.list_srr = "$baseDir/data/SRR/*.txt"
-
-log.info "downloading list srr : ${params.list_srr}"
-
-Channel
-  .fromPath( params.list_srr )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.list_srr}" }
-  .splitCsv(header: true)
-  .set { SRR }
-
-//run is the column name containing SRR ids
-
-process fastq_dump {
-  tag {"${x.run}"}
-  publishDir "results/download/fastq/${x.run}/", mode: 'copy'
-
-  input:
-    val x  from SRR
-
-  output:
-    file("*") into fastq
-
-  script:
-"""
-fastq-dump --split-files --defline-seq '@\$ac_\$si/\$ri' --defline-qual "+"  ${x.run}
-if [ -f ${x.run}_1.fastq ]
-then
-  true
-else
-  touch ${x.run}.fastq
-fi
-"""
-}

src/nf_modules/SRAtoolkit/tests/fastqdump.nf

-/*
-* sra-tools :
-
-*/
-
-/*                      fastq-dump
-* Imputs : srr list
-* Outputs : fastq files
-*/
-
-params.list_srr = "$baseDir/data/SRR/*.txt"
-
-log.info "downloading list srr : ${params.list_srr}"
-
-Channel
-  .fromPath( params.list_srr )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.list_srr}" }
-  .splitCsv(header: true)
-  .set { SRR }
-
-//run is the column name containing SRR ids
-
-process fastq_dump {
-  tag {"${x.run}"}
-  publishDir "results/download/fastq/${x.run}/", mode: 'copy'
-
-  input:
-    val x  from SRR
-
-  output:
-    file("*") into fastq
-
-  script:
-"""
-#for test only 10000  reads are downloading with the option -N 10000 -X 20000
-fastq-dump --split-files --defline-seq '@\$ac_\$si/\$ri' --defline-qual "+" -N 10000 -X 20000 ${x.run}
-if [ -f ${x.run}_1.fastq ]
-then
-  true
-else
-  touch ${x.run}.fastq
-fi
-"""
-}

src/nf_modules/SRAtoolkit/tests/tests.sh

-nextflow src/nf_modules/SRAtoolkit/tests/fastqdump.nf \
-  -c src/nf_modules/SRAtoolkit/sratoolkit.config \
-  -profile docker \
-  --list_srr "src/nf_modules/SRAtoolkit/tests/list-srr.txt"

src/nf_modules/UrQt/tests/tests.sh

-nextflow src/nf_modules/UrQt/tests/trimming_paired.nf \
-  -c src/nf_modules/UrQt/urqt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/UrQt/tests/trimming_single.nf \
-  -c src/nf_modules/UrQt/urqt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"

src/nf_modules/UrQt/tests/trimming_paired.nf

-log.info "fastq files : ${params.fastq}"
-
-Channel
-  .fromFilePairs( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-
-process trimming {
-  tag "${reads}"
-  cpus 4
-  publishDir "results/fastq/trimming/", mode: 'copy'
-
-  input:
-  set pair_id, file(reads) from fastq_files
-
-  output:
-  set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
-
-  script:
-"""
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads[0]} --inpair ${reads[1]} \
---out ${pair_id}_trim_R1.fastq.gz --outpair ${pair_id}_trim_R2.fastq.gz \
-> ${pair_id}_trimming_report.txt
-"""
-}
-

src/nf_modules/UrQt/tests/trimming_single.nf

-params.fastq = "$baseDir/data/fastq/*.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
-  .fromPath( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-
-process trimming {
-  tag "$reads.baseName"
-  cpus 4
-
-  input:
-  file reads from fastq_files
-
-  output:
-  file "*_trim.fastq.gz" into fastq_files_trim
-
-  script:
-  """
-  UrQt --t 20 --m ${task.cpus} --gz \
-  --in ${reads} \
-  --out ${reads.baseName}_trim.fastq.gz \
-  > ${reads.baseName}_trimming_report.txt
-  """
-}
-

src/nf_modules/UrQt/urqt.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $trimming {
-        container = "urqt:d62c1f8"
-      }
-    }
-  }
-  sge {
-    process{
-      $trimming {
-        beforeScript = "module purge; module load UrQt/d62c1f8"
-        executor = "sge"
-        cpus = 4
-        memory = "5GB"
-        time = "6h"
-        queueSize = 1000
-        pollInterval = '60sec'
-        queue = 'h6-E5-2667v4deb128'
-        penv = 'openmp8'
-      }
-    }
-  }
-}

src/nf_modules/UrQt/urqt.nf

-/*
-* urqt :
-* Imputs : fastq files
-* Output : fastq files
-*/
-/*                      quality trimming                                     */
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
-  .fromFilePairs( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-
-process trimming {
-  tag "${reads}"
-  cpus 4
-  publishDir "results/fastq/trimming/", mode: 'copy'
-
-  input:
-  set pair_id, file(reads) from fastq_files
-
-  output:
-  set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
-
-  script:
-"""
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads[0]} --inpair ${reads[1]} \
---out ${pair_id}_trim_R1.fastq.gz --outpair ${pair_id}_trim_R2.fastq.gz \
-> ${pair_id}_trimming_report.txt
-"""
-}
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
-  .fromPath( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-
-process trimming {
-  tag "$reads.baseName"
-  cpus 4
-  publishDir "results/fastq/trimming/", mode: 'copy'
-
-  input:
-  file reads from fastq_files
-
-  output:
-  file "*_trim.fastq.gz" into fastq_files_trim
-
-  script:
-"""
-
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads} \
---out ${reads.baseName}_trim.fastq.gz \
-> ${reads.baseName}_trimming_report.txt
-"""
-}
-

src/nf_modules/agat/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "0.8.0"
+container_url = "lbmc/agat:${version}"
+
+params.gff_to_bed = ""
+params.gff_to_bed_out = ""
+process gff_to_bed {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.gff_to_bed_out != "") {
+    publishDir "results/${params.gff_to_bed_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(gff)
+  output:
+    tuple val(file_id), path("*.bed"), emit: bed
+
+  script:
+"""
+zcat ${gff} > ${gff.baseName}.gff
+agat_convert_sp_gff2bed.pl ${params.gff_to_bed} --gff ${gff.baseName}.gff -o ${gff.simpleName}.bed
+"""
+}
+
+params.gff_to_gtf = ""
+params.gff_to_gtf_out = ""
+process gff_to_gtf {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.gff_to_gtf_out != "") {
+    publishDir "results/${params.gff_to_gtf_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(gff)
+  output:
+    tuple val(file_id), path("*.gtf"), emit: gtf
+
+  script:
+"""
+zcat ${gff} > ${gff.baseName}.gff
+agat_convert_sp_gff2gtf.pl ${params.gff_to_gtf} --gff ${gff.baseName}.gff -o ${gff.simpleName}.gtf
+"""
+}
\ No newline at end of file

src/nf_modules/alntools/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "dd96682"
+container_url = "lbmc/alntools:${version}"
+
+params.bam2ec = ""
+params.bam2ec_out = ""
+process bam2ec {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.bam2ec_out != "") {
+    publishDir "results/${params.bam2ec_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(bam), path(bam_idx)
+    tuple val(transcripts_lengths_id), path(transcripts_lengths)
+
+  output:
+    tuple val(file_id), path("${bam.simpleName}.bin"), emit: bin
+    tuple val(transcripts_lengths_id), path("${transcripts_lengths}"), emit: tsv
+    tuple val(file_id), path("${bam.simpleName}_bam2ec_report.txt"), emit: report
+
+  script:
+"""
+mkdir tmp
+alntools bam2ec \
+  -c 1 ${params.bam2ec} \
+  -d ./tmp \
+  -t ${transcripts_lengths} \
+  -v \
+  ${bam} ${bam.simpleName}.bin &> \
+  ${bam.simpleName}_bam2ec_report.txt
+"""
+}
+
+params.gtf_to_transcripts_lengths = ""
+params.gtf_to_transcripts_lengths_out = ""
+process gtf_to_transcripts_lengths {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.gtf_to_transcripts_lengths != "") {
+    publishDir "results/${params.gtf_to_transcripts_lengths}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(gtf)
+
+  output:
+    tuple val(file_id), path("${gtf.simpleName}_transcripts_lengths.tsv"), emit: tsv
+
+  script:
+"""
+awk -F"[\\t;]" '
+\$3=="exon" {
+        ID=gensub(/transcript_id \\"(.*)\\"/, "\\\\1", "g", \$11); 
+        LEN[ID]+=\$5-\$4+1;
+    } 
+END{
+    for(i in LEN)
+        {print i"\\t"LEN[i]}
+    }
+' ${gtf} > ${gtf.simpleName}_transcripts_lengths.tsv
+"""
+}

src/nf_modules/beagle/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "5.1_24Aug19.3e8--hdfd78af_1"
+container_url = "quay.io/biocontainers/beagle::${version}"
+
+params.phasing = ""
+process phasing {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+  tag "$file_id"
+
+  input:
+    tuple val(file_id), path(vcf)
+    tuple val(ref_id), path(ref_vcf)
+
+  output:
+    tuple val(file_id), path("*.bam*"), emit: bam
+
+  script:
+"""
+beagle nthread=${task.cpus} \
+  gtgl=${vcf} \
+  ref=${ref_vcf}
+"""
+}