Merge branch 'dev'

src/nf_modules/Bowtie2/mapping_single.config

+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+      $mapping_fastq {
+        container = "bowtie2:2.3.4.1"
+      }
+    }
+  }
+  sge {
+    process{
+      $mapping_fastq {
+        beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
+      }
+    }
+  }
+}

src/nf_modules/Bowtie2/tests/tests.sh → src/nf_modules/Bowtie2/tests.sh

-./nextflow src/nf_modules/Bowtie2/tests/index.nf \
-  -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/indexing.nf \
+  -c src/nf_modules/Bowtie2/indexing.config \
   -profile docker \
   --fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
 
-./nextflow src/nf_modules/Bowtie2/tests/mapping_single.nf \
-  -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/mapping_single.nf \
+  -c src/nf_modules/Bowtie2/mapping_single.config \
   -profile docker \
   --index "data/tiny_dataset/fasta/*.bt2" \
   --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
 
-./nextflow src/nf_modules/Bowtie2/tests/mapping_paired.nf \
-  -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/mapping_paired.nf \
+  -c src/nf_modules/Bowtie2/mapping_paired.config \
   -profile docker \
   --index "data/tiny_dataset/fasta/*.bt2" \
   --fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"

src/nf_modules/FastQC/fastqc.nf

-/*
-* fastqc :
-* Imputs : fastq files
-* Output : pdf files
-*/
-
-/*                      fastQC                                     */
-
-
-/*
-* 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: ${params.fastq}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .set { fastq_files }
-
-process fastqc_fastq {
-  tag "$file_id"
-  publishDir "results/fastq/fastqc/", mode: 'copy'
-  cpus = 1
-
-  input:
-  set file_id, file(reads) from fastq_files
-
-  output:
-    file "*.{zip,html}" into fastqc_report
-
-  script:
-"""
-fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ ${reads}
-"""
-}
-
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
-  .fromFilePairs( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-
-process fastqc_fastq {
-  tag "$pair_id"
-  publishDir "results/fastq/fastqc/", mode: 'copy'
-
-  input:
-  set pair_id, file(reads) from fastq_files
-
-  output:
-    file "*.{zip,html}" into fastqc_report
-
-  script:
-"""
-fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ \
-${reads[0]} ${reads[1]}
-"""
-}
-

src/nf_modules/FastQC/fastqc_single.config

+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+      $fastqc_fastq {
+        container = "fastqc:0.11.5"
+      }
+    }
+  }
+  sge {
+    process{
+      $fastqc_fastq {
+        beforeScript = "module purge; module load FastQC/0.11.5"
+        executor = "sge"
+        cpus = 1
+        memory = "5GB"
+        time = "6h"
+        queueSize = 1000
+        pollInterval = '60sec'
+        queue = 'monointeldeb128'
+      }
+    }
+  }
+}

src/nf_modules/FastQC/tests/tests.sh → src/nf_modules/FastQC/tests.sh

-nextflow src/nf_modules/FastQC/tests/fastqc_paired.nf \
-  -c src/nf_modules/FastQC/fastqc.config \
+nextflow src/nf_modules/FastQC/fastqc_paired.nf \
+  -c src/nf_modules/FastQC/fastqc_paired.config \
   -profile docker \
   --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
 
-nextflow src/nf_modules/FastQC/tests/fastqc_single.nf \
-  -c src/nf_modules/FastQC/fastqc.config \
+nextflow src/nf_modules/FastQC/fastqc_single.nf \
+  -c src/nf_modules/FastQC/fastqc_single.config \
   -profile docker \
   --fastq "data/tiny_dataset/fastq/tiny_S.fastq"

src/nf_modules/HTSeq/htseq.config

@@ -3,6 +3,9 @@ profiles {
     docker.temp = 'auto'
     docker.enabled = true
     process {
+      $sort_bam {
+        container = "samtools:1.7"
+      }
       $counting {
         container = "htseq:0.8.0"
       }
@@ -10,6 +13,9 @@ profiles {
   }
   sge {
     process{
+      $sort_bam {
+        beforeScript = "module purge; module load SAMtools/1.7"
+      }
       $trimming {
         beforeScript = "module purge; module load HTSeq/0.8.0"
       }

src/nf_modules/HTSeq/htseq.nf

-/*
-* htseq :
-* Imputs : sorted bams files
-* Imputs : gtf
-* Output : counts files
-*/
-/*                      quality trimming                                     */
-
 params.bam = "$baseDir/data/bam/*.bam"
 params.gtf = "$baseDir/data/annotation/*.gtf"
 
@@ -15,18 +7,36 @@ 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 ${bam}
+"""
+}
+
 process counting {
-  tag "$bam.baseName"
+  tag "$file_id"
   publishDir "results/quantification/", mode: 'copy'
 
   input:
-  file bam from bam_files
+  set file_id, file(bam) from sorted_bam_files
   file gtf from gtf_file
 
   output:
@@ -34,7 +44,9 @@ process counting {
 
   script:
 """
-htseq-count -r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
---format=bam ${bam} ${gtf} > ${bam.baseName}.count
+htseq-count ${bam} ${gtf} \
+-r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
+> ${file_id}.count
 """
 }
+

src/nf_modules/HTSeq/tests/tests.sh → src/nf_modules/HTSeq/tests.sh

-nextflow src/nf_modules/HTSeq/tests/counting.nf \
+nextflow src/nf_modules/HTSeq/htseq.nf \
   -c src/nf_modules/HTSeq/htseq.config \
   -profile docker \
   --gtf "data/tiny_dataset/annot/tiny.gff" \

src/nf_modules/HTSeq/tests/counting.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}" }
-  .set { bam_files }
-Channel
-  .fromPath( params.gtf )
-  .ifEmpty { error "Cannot find any gtf file matching: ${params.gtf}" }
-  .set { gtf_file }
-
-process counting {
-  tag "$bam.baseName"
-  publishDir "results/quantification/", mode: 'copy'
-
-  input:
-  file bam from bam_files
-  file gtf from gtf_file
-
-  output:
-  file "*.count" into count_files
-
-  script:
-"""
-htseq-count -r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
---format=bam ${bam} ${gtf} > ${bam.baseName}.count
-"""
-}
-

src/nf_modules/Kallisto/indexing.config

+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+      $index_fasta {
+        container = "kallisto:0.44.0"
+      }
+    }
+  }
+  sge {
+    process{
+      $index_fasta {
+        beforeScript = "module purge; module load Kallisto/0.44.0"
+        executor = "sge"
+        cpus = 1
+        memory = "5GB"
+        time = "6h"
+        queueSize = 1000
+        pollInterval = '60sec'
+        queue = 'h6-E5-2667v4deb128'
+        penv = 'openmp8'
+      }
+    }
+  }
+}

src/nf_modules/Kallisto/tests/index.nf → src/nf_modules/Kallisto/indexing.nf

@@ -17,11 +17,12 @@ process index_fasta {
 
   output:
     file "*.index*" into index_files
+    file "*_kallisto_report.txt" into index_files_report
 
   script:
 """
 kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \
-> ${fasta.baseName}_kallisto_report.txt
+2> ${fasta.baseName}_kallisto_report.txt
 """
 }
 

src/nf_modules/Kallisto/kallisto.nf

-/*
-* Kallisto :
-* Imputs : fastq files
-* Imputs : fasta files
-* Output : bam files
-*/
-
-/*                      fasta indexing                                     */
-params.fasta = "$baseDir/data/bam/*.fasta"
-
-log.info "fasta files : ${params.fasta}"
-
-Channel
-  .fromPath( params.fasta )
-  .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
-  .set { fasta_file }
-
-process index_fasta {
-  tag "$fasta.baseName"
-  publishDir "results/mapping/index/", mode: 'copy'
-
-  input:
-    file fasta from fasta_file
-
-  output:
-    file "*.index*" into index_files
-
-  script:
-"""
-kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \
-> ${fasta.baseName}_kallisto_report.txt
-"""
-}
-
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-params.index = "$baseDir/data/index/*.index.*"
-
-log.info "fastq files : ${params.fastq}"
-log.info "index files : ${params.index}"
-
-Channel
-  .fromFilePairs( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-Channel
-  .fromPath( params.index )
-  .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
-  .set { index_files }
-
-process mapping_fastq {
-  tag "$reads"
-  cpus 4
-  publishDir "results/mapping/quantification/", mode: 'copy'
-
-  input:
-  set pair_id, file(reads) from fastq_files
-  file index from index_files.collect()
-
-  output:
-  file "*" into counts_files
-
-  script:
-"""
-mkdir ${reads[0].baseName}
-kallisto quant -i ${index} -t ${task.cpus} \
---bias --bootstrap-samples 100 -o ${pair_id} \
-${reads[0]} ${reads[1]} &> ${pair_id}_kallisto_report.txt
-"""
-}
-
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-params.index = "$baseDir/data/index/*.index*"
-params.mean = 200
-params.sd = 100
-
-log.info "fastq files : ${params.fastq}"
-log.info "index files : ${params.index}"
-log.info "mean read size: ${params.mean}"
-log.info "sd read size: ${params.sd}"
-
-Channel
-  .fromPath( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .set { fastq_files }
-Channel
-  .fromPath( params.index )
-  .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
-  .set { index_files }
-
-process mapping_fastq {
-  tag "$file_id"
-  cpus 4
-  publishDir "results/mapping/quantification/", mode: 'copy'
-
-  input:
-  set file_id, file(reads) from fastq_files
-  file index from index_files.collect()
-
-  output:
-  file "*" into count_files
-
-  script:
-"""
-mkdir ${file_id}
-kallisto quant -i ${index} -t ${task.cpus} --single \
---bias --bootstrap-samples 100 -o ${file_id} \
--l ${params.mean} -s ${params.sd} \
-${reads} > ${file_id}_kallisto_report.txt
-"""
-}
-
-

src/nf_modules/Kallisto/kallisto.config → src/nf_modules/Kallisto/mapping_paired.config

@@ -3,9 +3,6 @@ profiles {
     docker.temp = 'auto'
     docker.enabled = true
     process {
-      $index_fasta {
-        container = "kallisto:0.44.0"
-      }
       $mapping_fastq {
         container = "kallisto:0.44.0"
       }
@@ -13,17 +10,6 @@ profiles {
   }
   sge {
     process{
-      $index_fasta {
-        beforeScript = "module purge; module load Kallisto/0.44.0"
-        executor = "sge"
-        cpus = 1
-        memory = "5GB"
-        time = "6h"
-        queueSize = 1000
-        pollInterval = '60sec'
-        queue = 'h6-E5-2667v4deb128'
-        penv = 'openmp8'
-      }
       $mapping_fastq {
         beforeScript = "module purge; module load Kallisto/0.44.0"
         executor = "sge"

src/nf_modules/Kallisto/mapping_single.config

+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+      $mapping_fastq {
+        container = "kallisto:0.44.0"
+      }
+    }
+  }
+  sge {
+    process{
+      $mapping_fastq {
+        beforeScript = "module purge; module load Kallisto/0.44.0"
+        executor = "sge"
+        cpus = 4
+        memory = "5GB"
+        time = "6h"
+        queueSize = 1000
+        pollInterval = '60sec'
+        queue = 'h6-E5-2667v4deb128'
+        penv = 'openmp8'
+      }
+    }
+  }
+}