src/nf_modules/sratoolkit/list-srr.txt.license

+SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+
+SPDX-License-Identifier: CC-BY-SA-4.0

src/nf_modules/sratoolkit/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "3.0.0"
+container_url = "lbmc/sratoolkit:${version}"
+
+params.fastq_dump = ""
+params.fastq_dump_out = ""
+process fastq_dump {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$sra"
+  if (params.fastq_dump_out != "") {
+    publishDir "results/${params.fastq_dump_out}", mode: 'copy'
+  }
+
+  input:
+    val sra
+
+  output:
+    tuple val(sra), path("*.fastq"), emit: fastq
+
+  script:
+"""
+fastq-dump ${params.fastq_dump} --split-files --gzip ${sra}
+if [ -f ${sra}_1.fastq ]
+then
+  mv ${sra}_1.fastq ${sra}_R1.fastq
+fi
+if [ -f ${sra}_2.fastq ]
+then
+  mv ${sra}_2.fastq ${sra}_R2.fastq
+fi
+"""
+}

src/nf_modules/sratoolkit/tests.sh

-./nextflow src/nf_modules/sratoolkit/fastqdump.nf \
-  -c src/nf_modules/sratoolkit/fastqdump.config \
-  -profile docker \
-  --list_srr "src/nf_modules/sratoolkit/list-srr.txt" \
-  -resume
-
-if [ -x "$(command -v singularity)" ]; then
-./nextflow src/nf_modules/sratoolkit/fastqdump.nf \
-  -c src/nf_modules/sratoolkit/fastqdump.config \
-  -profile docker \
-  --list_srr "src/nf_modules/sratoolkit/list-srr.txt" \
-  -resume
-fi

src/nf_modules/star/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+// STAR is an ultrafast universal RNA-seq aligner
+// 
+// EXAMPLE:
+
+/*
+include {
+    index_with_gff as star_index_with_gff;
+    mapping_fastq as star_mapping_fastq
+ } from './nf_modules/star/main.nf'
+   addParams(
+    star_mapping_fastq_out: "star/"
+   )
+
+star_index_with_gff(
+  genome_file,
+  gff_file
+  )
+
+star_mapping_fastq(
+    star_index_with_gff.out.index,
+    reads
+)
+
+*/
+
+
+version = "2.7.3a"
+container_url = "lbmc/star:${version}"
+
+params.star_mapping_fastq_out = ""
+
+
+process gff3_2_gtf {
+  container = "dceoy/cufflinks"
+  label "small_mem_mono_cpus"
+
+    input:
+        tuple val(genome_id), path(gff3_file)
+    output:
+        path "${genome_id}.gtf", emit: gtf
+    script:
+"""
+gffread ${gff3_file} -T -o ${genome_id}.gtf
+"""
+}
+
+
+process index_with_gtf {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+
+  input:
+    tuple val(genome_id), path(genome_fasta)
+    path gtf_file
+
+  output:
+    tuple val(genome_id), path ("*"), emit: index
+
+  script:
+"""
+STAR --runThreadN ${task.cpus} --runMode genomeGenerate \
+--genomeDir ./ \
+--genomeFastaFiles ${genome_fasta}  \
+--sjdbGTFfile ${gtf_file} \
+--genomeSAindexNbases 13 # min(14, log2(GenomeLength)/2 - 1)
+"""
+}
+
+workflow index_with_gff {
+  take:
+    genome_fasta
+    gff_file
+  main:
+    gff3_2_gtf(gff_file)
+    index_with_gtf(genome_fasta,gff3_2_gtf.out.gtf)
+  emit:
+    report = index_with_gtf.out.index
+}
+
+
+process index_without_gff {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+
+  input:
+    tuple val(genome_id), path(genome_fasta)
+
+  output:
+    tuple val(genome_id), path ("*"), emit: index
+
+  script:
+"""
+STAR --runThreadN ${task.cpus} --runMode genomeGenerate \
+--genomeDir ./ \
+--genomeFastaFiles ${genome_fasta}  \
+--genomeSAindexNbases 13 # min(14, log2(GenomeLength)/2 - 1)
+"""
+}
+
+
+process mapping_fastq {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+  if (params.star_mapping_fastq_out != "") {
+    publishDir "results/${params.star_mapping_fastq_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(index_id), path(index)
+    tuple val(reads_id), path(reads) 
+
+  output:
+    path "*.Log.final.out", emit: report
+    tuple val(reads_id), path("*.bam"), emit: bam
+
+  script:
+if (reads_id instanceof List){
+    file_prefix = reads_id[0]
+  } else {
+    file_prefix = reads_id
+  }
+
+if (reads.size() == 2)
+"""
+mkdir -p index
+mv ${index} index/
+STAR --runThreadN ${task.cpus} \
+--genomeDir index/ \
+--readFilesCommand zcat \
+--readFilesIn ${reads[0]} ${reads[1]} \
+--outFileNamePrefix ${reads_id}. \
+--alignIntronMax 10000 \
+--outSAMtype BAM SortedByCoordinate \
+--outSAMstrandField intronMotif
+
+mv ${reads_id}.Aligned.sortedByCoord.out.bam ${reads_id}.bam
+"""
+else
+"""
+mkdir -p index
+mv ${index} index/
+STAR --runThreadN ${task.cpus} \
+--genomeDir index/ \
+--readFilesCommand zcat \
+--readFilesIn ${reads} \
+--outFileNamePrefix ${reads_id}. \
+--alignIntronMax 10000 \
+--outSAMtype BAM SortedByCoordinate \
+--outSAMstrandField intronMotif
+
+mv ${reads_id}.Aligned.sortedByCoord.out.bam ${reads_id}.bam
+"""
+}
\ No newline at end of file

src/nf_modules/stringtie2/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "2.1.1"
+container_url = "lbmc/stringtie2:${version}"
+
+process jcount {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+  tag "$file_id"
+  if (params.salmon_out != "") {
+    publishDir "results/${params.salmon_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(bam)
+
+  output:
+    tuple val(file_id), path("*.sf"), emit: quant
+  script:
+"""
+salmon quant -l A --noErrorModel -t XXXXXXXXXX -a ${bam} -p 4 -o ${params.salmon_out}
+"""
+}
\ No newline at end of file

src/nf_modules/subread/subread.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      withName: sort_bam {
-        container = "lbmc/samtools:1.7"
-        cpus = 1
-      }
-      withName: counting {
-        container = "lbmc/subread:1.6.4"
-        cpus = 1
-      }
-    }
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.cacheDir = "./bin/"
-    process {
-      withName: sort_bam {
-        container = "lbmc/samtools:1.7"
-        cpus = 1
-      }
-      withName: counting {
-        container = "lbmc/subread:1.6.4"
-        cpus = 1
-      }
-    }
-  }
-  psmn{
-    process{
-      withName: sort_bam {
-        beforeScript = "source $baseDir/.conda_psmn.sh"
-        conda = "$baseDir/.conda_envs/samtools_1.7"
-        executor = "sge"
-        clusterOptions = "-cwd -V"
-        cpus = 1
-        memory = "20GB"
-        time = "12h"
-        queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
-      }
-      withName: counting {
-        beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
-        module = "subread/1.6.4"
-        executor = "sge"
-        clusterOptions = "-cwd -V"
-        cpus = 1
-        memory = "20GB"
-        time = "12h"
-        queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
-      }
-    }
-  }
-  ccin2p3 {
-    singularity.enabled = true
-    singularity.cacheDir = "/sps/lbmc/common/singularity/"
-    singularity.runOptions = "--bind /pbs,/sps,/scratch"
-    process{
-      withName: sort_bam {
-        container = "lbmc/samtools:1.7"
-        scratch = true
-        stageInMode = "copy"
-        stageOutMode = "rsync"
-        executor = "sge"
-        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n\
-        "
-        cpus = 1
-        queue = 'huge'
-      }
-      withName: counting {
-        container = "lbmc/subread:1.6.4"
-        scratch = true
-        stageInMode = "copy"
-        stageOutMode = "rsync"
-        executor = "sge"
-        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n\
-        "
-        cpus = 1
-        queue = 'huge'
-      }
-    }
-  }
-}

src/nf_modules/subread/subread.nf

-params.bam = "$baseDir/data/bam/*.bam"
-params.gtf = "$baseDir/data/annotation/*.gtf"
-
-log.info "bam files : ${params.bam}"
-log.info "gtf files : ${params.gtf}"
-
-Channel
-  .fromPath( params.bam )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.bam}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .set { bam_files }
-Channel
-  .fromPath( params.gtf )
-  .ifEmpty { error "Cannot find any gtf file matching: ${params.gtf}" }
-  .set { gtf_file }
-
-process sort_bam {
-  tag "$file_id"
-  cpus 4
-
-  input:
-    set file_id, file(bam) from bam_files
-
-  output:
-    set file_id, "*_sorted.sam" into sorted_bam_files
-
-  script:
-"""
-# sort bam by name
-samtools sort -@ ${task.cpus} -n -O SAM -o ${file_id}_sorted.sam ${bam}
-"""
-}
-
-process counting {
-  tag "$file_id"
-  publishDir "results/quantification/", mode: 'copy'
-
-  input:
-  set file_id, file(bam) from sorted_bam_files
-  file gtf from gtf_file
-
-  output:
-  file "*.count" into count_files
-
-  script:
-"""
-featureCounts ${bam} -a ${gtf} -p \
-  -o ${file_id}.count \
-  -R BAM
-"""
-}
-

src/nf_modules/subread/tests.sh

-./nextflow src/nf_modules/subread/subread.nf \
-  -c src/nf_modules/subread/subread.config \
-  -profile docker \
-  --gtf "data/tiny_dataset/annot/tiny.gff" \
-  --bam "data/tiny_dataset/map/tiny_v2.bam" \
-  -resume
-
-if [ -x "$(command -v singularity)" ]; then
-./nextflow src/nf_modules/subread/subread.nf \
-  -c src/nf_modules/subread/subread.config \
-  -profile singularity \
-  --gtf "data/tiny_dataset/annot/tiny.gff" \
-  --bam "data/tiny_dataset/map/tiny_v2.bam" \
-  -resume
-fi

src/nf_modules/trinity/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "2.13.2"
+container_url = "lbmc/trinity:${version}"
+
+params.sample = 3
+params.min_glue = 1
+params.min_contig_length = 200
+params.assembly_out = ""
+
+
+workflow assembly {
+  take:
+    fastq
+  main:
+    complete_assembly(fastq)
+    super_transcript(complete_assembly.out.fasta)
+
+  emit:
+    fasta = complete_assembly.out.fasta
+    super_transcript = super_transcript.out.fasta
+}
+
+process complete_assembly {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+  tag "$file_id"
+  if (params.assembly_out != "") {
+    publishDir "results/${params.assembly_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(fastq)
+
+  output:
+    tuple val(file_id), path("trinity_output_${file_prefix}/"), emit: folder
+    tuple val(file_id), path("trinity_output_${file_prefix}.Trinity.fasta"), emit: fasta
+    tuple val(file_id), path("trinity_output_${file_prefix}.Trinity.fasta.gene_trans_map"), emit: gene_map 
+    tuple val(file_id), path("trinity_output_${file_prefix}/salmon_outdir/quant.sf"), emit: quant
+
+  script:
+
+  switch(file_id) {
+    case {it instanceof List}:
+      file_prefix = file_id[0]
+    break;
+    case {it instanceof Map}:
+      file_prefix = file_id.values()[0]
+    break;
+    default:
+      file_prefix = file_id
+    break;
+  };
+  def memory = "${task.memory}" - ~/\s*GB/
+
+  if (fastq.size() == 2)
+"""
+  mkdir trinity_output_${file_prefix}
+  Trinity \
+    --seqType fq \
+    --max_memory ${memory}G \
+    --left ${fastq[0]} \
+    --right ${fastq[1]} \
+    --CPU ${task.cpus} \
+    --min_glue ${params.min_glue} \
+    --min_contig_length ${params.min_contig_length} \
+    --output trinity_output_${file_prefix}
+"""
+  else
+"""
+  mkdir trinity_output_${file_prefix}
+  Trinity \
+    --seqType fq \
+    --max_memory ${memory}G \
+    --single ${fastq} \
+    --CPU ${task.cpus} \
+    --min_glue ${params.min_glue} \
+    --min_contig_length ${params.min_contig_length} \
+    --output trinity_output_${file_prefix}
+"""
+}
+
+
+process super_transcript {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.assembly_out != "") {
+    publishDir "results/${params.assembly_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(fasta)
+
+  output:
+    tuple val(file_id), path("trinity_genes.fasta"), path("trinity_genes.gtf"), emit: fasta
+
+  script:
+
+  switch(file_id) {
+    case {it instanceof List}:
+      file_prefix = file_id[0]
+    break;
+    case {it instanceof Map}:
+      file_prefix = file_id.values()[0]
+    break;
+    default:
+      file_prefix = file_id
+    break;
+  };
+  def memory = "${task.memory}" - ~/\s*GB/
+
+"""
+Trinity_gene_splice_modeler.py \
+  --trinity_fasta ${fasta}
+"""
+}

src/nf_modules/ucsc/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "407"
+container_url = "lbmc/ucsc:${version}"
+
+include {
+  index_fasta
+} from './../samtools/main'
+
+params.bedgraph_to_bigwig = ""
+params.bedgraph_to_bigwig_out = ""
+process bedgraph_to_bigwig {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bedgraph_to_bigwig_out != "") {
+    publishDir "results/${params.bedgraph_to_bigwig_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(bg)
+  tuple val(file_id), path(bed)
+
+  output:
+  tuple val(file_id), path("*.bw"), emit: bw
+
+  script:
+"""
+LC_COLLATE=C
+# transform bed file of start-stop chromosome size to stop chromosome size
+awk -v OFS="\\t" '{print \$1, \$3}' ${bed} > chromsize.txt
+
+sort -T ./ -k1,1 -k2,2n ${bg} > \
+  bedGraphToBigWig ${params.bedgraph_to_bigwig} - \
+    chromsize.txt \
+    ${bg.simpleName}_norm.bw
+"""
+}
+
+params.wig_to_bedgraph = ""
+params.wig_to_bedgraph_out = ""
+workflow wig_to_bedgraph {
+  take:
+    fasta
+    wig
+  main:
+    wig_to_bigwig(
+      fasta,
+      wig
+    )
+    bigwig_to_bedgraph(
+      wig_to_bigwig.out.bw
+    )
+  emit:
+  bg = bigwig_to_bedgraph.out.bg
+}
+
+workflow wig2_to_bedgraph2 {
+  take:
+    fasta
+    wig
+  main:
+    wig2_to_bigwig2(
+      fasta,
+      wig
+    )
+    bigwig2_to_bedgraph2(
+      wig2_to_bigwig2.out.bw
+    )
+  emit:
+  bg = bigwig2_to_bedgraph2.out.bg
+}
+
+params.bigwig_to_bedgraph = ""
+params.bigwig_to_bedgraph_out = ""
+process bigwig_to_bedgraph {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_bedgraph_out != "") {
+    publishDir "results/${params.bigwig_to_bedgraph_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(bw)
+
+  output:
+  tuple val(file_id), path("*.bg"), emit: bg
+
+  script:
+"""
+bigWigToBedGraph ${bw} ${bw.simpleName}.bg
+"""
+}
+
+params.bigwig2_to_bedgraph2 = ""
+params.bigwig2_to_bedgraph2_out = ""
+process bigwig2_to_bedgraph2 {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_bedgraph_out != "") {
+    publishDir "results/${params.bigwig_to_bedgraph_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(bw_a), path(bw_b)
+
+  output:
+  tuple val(file_id), path("${bw_a.simpleName}.bg"), path("${bw_b.simpleName}.bg"), emit: bg
+
+  script:
+"""
+bigWigToBedGraph ${bw_a} ${bw_a.simpleName}.bg
+bigWigToBedGraph ${bw_b} ${bw_b.simpleName}.bg
+"""
+}
+
+params.bigwig_to_wig = ""
+params.bigwig_to_wig_out = ""
+process bigwig_to_wig {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_wig_out != "") {
+    publishDir "results/${params.bigwig_to_wig_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(bw)
+
+  output:
+  tuple val(file_id), path("*.wig"), emit: wig
+
+  script:
+"""
+bigWigToBedGraph ${bw} ${bw.simpleName}.bg
+bedgraph_to_wig.pl --bedgraph ${bw.simpleName}.bg --wig ${bw.simpleName}.wig --step 10
+"""
+}
+
+params.bigwig2_to_wig2 = ""
+params.bigwig2_to_wig2_out = ""
+process bigwig2_to_wig2 {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_wig_out != "") {
+    publishDir "results/${params.bigwig_to_wig_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(bw_a), path(bw_b)
+
+  output:
+  tuple val(file_id), path("${bw_a.simpleName}.wig"), path("${bw_b.simpleName}.wig"), emit: wig
+
+  script:
+"""
+bigWigToBedGraph ${bw_a} ${bw_a.simpleName}.bg
+bedgraph_to_wig.pl --bedgraph ${bw_a.simpleName}.bg --wig ${bw_a.simpleName}.wig --step 10
+bigWigToBedGraph ${bw_b} ${bw_b.simpleName}.bg
+bedgraph_to_wig.pl --bedgraph ${bw_b.simpleName}.bg --wig ${bw_b.simpleName}.wig --step 10
+"""
+}
+
+params.wig_to_bigwig = ""
+params.wig_to_bigwig_out = ""
+
+workflow wig_to_bigwig {
+  take:
+    fasta
+    wig
+  main:
+    index_fasta(fasta)
+    wig_to_bigwig_sub(
+      wig,
+      index_fasta.out.index
+    )
+  emit:
+  bw = wig_to_bigwig_sub.out.bw
+}
+
+process wig_to_bigwig_sub {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_wig_out != "") {
+    publishDir "results/${params.bigwig_to_wig_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(w)
+  tuple val(idx_id), path(fasta_idx)
+
+  output:
+  tuple val(file_id), path("${w.simpleName}.bw"), emit: bw
+
+  script:
+"""
+cut -f 1,2 ${fasta_idx} > ${fasta_idx.simpleName}.sizes
+wigToBigWig -clip ${w} ${fasta_idx.simpleName}.sizes ${w.simpleName}.bw
+"""
+}
+
+params.wig2_to_bigwig2 = ""
+params.wig2_to_bigwig2_out = ""
+
+workflow wig2_to_bigwig2 {
+  take:
+    fasta
+    wigs
+  main:
+    index_fasta(fasta)
+    wig2_to_bigwig2_sub(
+      wigs,
+      index_fasta.out.index
+    )
+  emit:
+  bw = wig2_to_bigwig2_sub.out.bw
+}
+
+process wig2_to_bigwig2_sub {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "${file_id}"
+  if (params.bigwig_to_wig_out != "") {
+    publishDir "results/${params.bigwig_to_wig_out}", mode: 'copy'
+  }
+
+  input:
+  tuple val(file_id), path(w_a), path(w_b)
+  tuple val(idx_id), path(fasta_idx)
+
+  output:
+  tuple val(file_id), path("${w_a.simpleName}.bw"), path("${w_b.simpleName}.bw"), emit: bw
+
+  script:
+"""
+cut -f 1,2 ${fasta_idx} > ${fasta_idx.simpleName}.sizes
+wigToBigWig -clip ${w_a} ${fasta_idx.simpleName}.sizes ${w_a.simpleName}.bw
+wigToBigWig -clip ${w_b} ${fasta_idx.simpleName}.sizes ${w_b.simpleName}.bw
+"""
+}
\ No newline at end of file

src/nf_modules/urqt/main.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+version = "d62c1f8"
+container_url = "lbmc/urqt:${version}"
+
+trim_quality = "20"
+
+params.trimming = "--t 20"
+process trimming {
+  container = "${container_url}"
+  label "big_mem_multi_cpus"
+  tag "${file_id}"
+
+  input:
+  tuple val(file_id), path(reads)
+
+  output:
+  tuple val(pair_id), path("*_trim_R{1,2}.fastq.gz"), emit: fastq
+  path "*_report.txt", emit: report
+
+  script:
+  if (file_id instanceof List){
+    file_prefix = file_id[0]
+  } else {
+    file_prefix = file_id
+  }
+  if (reads.size() == 2)
+"""
+UrQt ${params.trimming} --m ${task.cpus} --gz \
+  --in ${reads[0]} --inpair ${reads[1]} \
+  --out ${file_prefix}_trim_R1.fastq.gz --outpair ${file_prefix}_trim_R2.fastq.gz \
+  > ${pair_id}_trimming_report.txt
+"""
+  else
+"""
+UrQt ${params.trimming} --m ${task.cpus} --gz \
+  --in ${reads[0]} \
+  --out ${file_prefix}_trim.fastq.gz \
+  > ${file_prefix}_trimming_report.txt
+"""
+}
\ No newline at end of file

src/nf_modules/urqt/tests.sh

-./nextflow src/nf_modules/urqt/trimming_paired.nf \
-  -c src/nf_modules/urqt/trimming_paired.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq" \
-  -resume
-
-./nextflow src/nf_modules/urqt/trimming_single.nf \
-  -c src/nf_modules/urqt/trimming_single.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq" \
-  -resume
-
-if [ -x "$(command -v singularity)" ]; then
-./nextflow src/nf_modules/urqt/trimming_single.nf \
-  -c src/nf_modules/urqt/trimming_single.config \
-  -profile singularity \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq" \
-  -resume
-
-./nextflow src/nf_modules/urqt/trimming_single.nf \
-  -c src/nf_modules/urqt/trimming_single.config \
-  -profile singularity \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq" \
-  -resume
-fi

src/nf_modules/urqt/trimming_paired.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      withName: trimming {
-        cpus = 4
-        container = "lbmc/urqt:d62c1f8"
-      }
-    }
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.cacheDir = "./bin/"
-    process {
-      withName: trimming {
-        cpus = 4
-        container = "lbmc/urqt:d62c1f8"
-      }
-    }
-  }
-  psmn{
-    process{
-      withName: trimming {
-        beforeScript = "source $baseDir/.conda_psmn.sh"
-        conda = "$baseDir/.conda_envs/urqt_d62c1f8"
-        executor = "sge"
-        clusterOptions = "-cwd -V"
-        memory = "5GB"
-        cpus = 16
-        time = "12h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
-      }
-    }
-  }
-  ccin2p3 {
-    singularity.enabled = true
-    singularity.cacheDir = "/sps/lbmc/common/singularity/"
-    singularity.runOptions = "--bind /pbs,/sps,/scratch"
-    process{
-      withName: trimming {
-        container = "lbmc/urqt:d62c1f8"
-        scratch = true
-        stageInMode = "copy"
-        stageOutMode = "rsync"
-        executor = "sge"
-        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n\
-        "
-        cpus = 1
-        queue = 'huge'
-      }
-    }
-  }
-}
-

src/nf_modules/urqt/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}"
-  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/trimming_single.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      withName: trimming {
-        container = "lbmc/urqt:d62c1f8"
-        cpus = 4
-      }
-    }
-  }
-  singularity {
-    singularity.enabled = true
-    singularity.cacheDir = "./bin/"
-    process {
-      withName: trimming {
-        container = "lbmc/urqt:d62c1f8"
-        cpus = 4
-      }
-    }
-  }
-  psmn{
-    process{
-      withName: trimming {
-        beforeScript = "source $baseDir/.conda_psmn.sh"
-        conda = "$baseDir/.conda_envs/urqt_d62c1f8"
-        executor = "sge"
-        clusterOptions = "-cwd -V"
-        cpus = 16
-        memory = "5GB"
-        time = "12h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
-      }
-    }
-  }
-  ccin2p3 {
-    singularity.enabled = true
-    singularity.cacheDir = "/sps/lbmc/common/singularity/"
-    singularity.runOptions = "--bind /pbs,/sps,/scratch"
-    process{
-      withName: trimming {
-        container = "lbmc/urqt:d62c1f8"
-        scratch = true
-        stageInMode = "copy"
-        stageOutMode = "rsync"
-        executor = "sge"
-        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n\
-        "
-        cpus = 1
-        queue = 'huge'
-      }
-    }
-  }
-}
-

src/nf_modules/urqt/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: ${params.fastq}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .set { fastq_files }
-
-process trimming {
-  tag "$file_id"
-  echo true
-
-  input:
-  set file_id, file(reads) from fastq_files
-
-  output:
-  set file_id, "*_trim.fastq.gz" into fastq_files_trim
-
-  script:
-  """
-  UrQt --t 20 --m ${task.cpus} --gz \
-  --in ${reads} \
-  --out ${file_id}_trim.fastq.gz \
-  > ${file_id}_trimming_report.txt
-  """
-}
-

src/solution_RNASeq.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+nextflow.enable.dsl=2
+
+include { fastp } from "./nf_modules/fastp/main.nf"
+include { fasta_from_bed } from "./nf_modules/bedtools/main.nf"
+include { index_fasta; mapping_fastq } from './nf_modules/kallisto/main.nf' addParams(mapping_fastq_out: "quantification/")
+
+
+params.fastq = "data/fastq/*_{1,2}.fastq"
+
+log.info "fastq files: ${params.fastq}"
+log.info "fasta file : ${params.fasta}"
+log.info "bed file : ${params.bed}"
+
+channel
+  .fromFilePairs( params.fastq, size: -1)
+  .set { fastq_files }
+
+channel
+  .fromPath( params.fasta )
+  .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
+  .map { it -> [it.simpleName, it]}
+  .set { fasta_files }
+channel
+  .fromPath( params.bed )
+  .ifEmpty { error "Cannot find any bed files matching: ${params.bed}" }
+  .map { it -> [it.simpleName, it]}
+  .set { bed_files }
+
+workflow {
+  fastp(fastq_files)
+  fasta_from_bed(fasta_files, bed_files)
+  index_fasta(fasta_from_bed.out.fasta)
+  mapping_fastq(index_fasta.out.index.collect(), fastp.out.fastq)
+}

src/training_dataset.config

+# SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+#
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
 profiles {
   docker {
-    docker.temp = 'auto'
+    docker.temp = "auto"
     docker.enabled = true
     process {
       withName: build_synthetic_bed {
@@ -125,7 +129,7 @@ profiles {
         cpus = 1
         memory = "20GB"
         time = "12h"
-        queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+        queue = "monointeldeb128"
       }
       withName: fasta_from_bed {
         beforeScript = "source $baseDir/.conda_psmn.sh"
@@ -135,106 +139,235 @@ profiles {
         cpus = 1
         memory = "20GB"
         time = "12h"
-        queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+        queue = "monointeldeb128"
       }
       withName: index_fasta {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/bowtie2_2.3.4.1"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "20GB"
         time = "12h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: mapping_fastq_paired {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/bowtie2_2.3.4.1"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: bam_2_fastq_paired {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: sort_bam_paired {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: index_bam_paired {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: mapping_fastq_single {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/bowtie2_2.3.4.1"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: bam_2_fastq_single {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: sort_bam_single {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
       }
       withName: index_bam_single {
         beforeScript = "source $baseDir/.conda_psmn.sh"
         conda = "$baseDir/.conda_envs/samtools_1.7"
         executor = "sge"
         clusterOptions = "-m e -cwd -V"
-        cpus = 16
+        cpus = 32
         memory = "30GB"
         time = "24h"
-        queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
-        penv = 'openmp16'
+        queue = "CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D"
+        penv = "openmp32"
+      }
+    }
+  }
+  ccin2p3 {
+    singularity.enabled = true
+    singularity.cacheDir = "$baseDir/.singularity_in2p3/"
+    singularity.runOptions = "--bind /pbs,/sps,/scratch"
+    process{
+      withName: fasta_from_bed {
+        container = "lbmc/bedtools:2.25.0"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+    }
+    process{
+      withName: build_synthetic_bed {
+        container = "lbmc/bedtools:2.25.0"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: fasta_from_bed {
+        container = "lbmc/bedtools:2.25.0"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: index_fasta {
+        container = "lbmc/bowtie2:2.3.4.1"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: mapping_fastq_paired {
+        container = "lbmc/bowtie2:2.3.4.1"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: bam_2_fastq_paired {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: sort_bam_paired {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: index_bam_paired {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: mapping_fastq_single {
+        container = "lbmc/bowtie2:2.3.4.1"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: bam_2_fastq_single {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: sort_bam_single {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
+      }
+      withName: index_bam_single {
+        container = "lbmc/samtools:1.7"
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "sge"
+        clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n"
+        cpus = 1
+        queue = "huge"
       }
     }
   }

src/training_dataset.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
 /*
 small pipeline to build a training dataset from whole genome data