.gitignore

@@ -2,3 +2,5 @@ nextflow
 .nextflow.log*
 .nextflow/
 work/
+.DS_Store
+.Rhistory

src/RNAseq_sen1D.config

+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+    $adaptor_removal {
+      container = "cutadapt:1.14"
+    }
+    $random_bases_4_trimming {
+      container = "cutadapt:1.14"
+    }
+    }
+  }
+  sge {
+    process{
+      $adaptor_removal {
+        beforeScript = "module purge; module load cutadapt/1.14"
+        executor = "sge"
+        cpus = 1
+        memory = "5GB"
+        time = "6h"
+        queueSize = 1000
+        pollInterval = '60sec'
+        queue = 'h6-E5-2667v4deb128'
+        penv = 'openmp8'
+      }
+
+      $random_bases_4_trimming {
+        beforeScript = "module purge; module load cutadapt/1.14"
+        executor = "sge"
+        cpus = 1
+        memory = "5GB"
+        time = "6h"
+        queueSize = 1000
+        pollInterval = '60sec'
+        queue = 'h6-E5-2667v4deb128'
+        penv = 'openmp8'
+      }
+    }
+  }
+}
+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'
+      }
+    }
+  }
+}
+profiles {
+  docker {
+    docker.temp = 'auto'
+    docker.enabled = true
+    process {
+      $index_fasta {
+        container = "bowtie2:2.3.4.1"
+      }
+      $mapping_fastq {
+        container = "bowtie2:2.3.4.1"
+      }
+    }
+  }
+  sge {
+    process{
+      $index_fasta {
+        beforeScript = "module purge; module load Bowtie2/2.3.4.1"
+      }
+      $mapping_fastq {
+        beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
+      }
+    }
+  }
+}
+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"
+      }
+    }
+  }
+  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"
+      }
+    }
+  }
+}

src/RNAseq_sen1D.nf

+/*
+* cutadapt :
+* Imputs : fastq files
+* Output : fastq files
+*/
+
+/*                     Small RNA-seq Illumina adaptor removal NEXTflex Small RNA Seq Kit v3                            */
+
+/*
+* for paired-end data
+*/
+
+params.fastq = "$baseDir/data/fastq/*_R{1,2}.fastq.gz"
+
+log.info "fastq files : ${params.fastq}"
+
+Channel
+  .fromFilePairs( params.fastq )
+  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+  .set { fastq_files }
+
+process adaptor_removal {
+  tag "$pair_id"
+
+  input:
+  set pair_id, file(reads) from fastq_files
+
+  output:
+  set pair_id, "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
+
+  script:
+  """
+  cutadapt -a TGGAATTCTCGGGTGCCAAGG -g CCTTGGCACCCGAGAATTCCA \
+  -o ${pair_id}_cut_R1.fastq.gz \
+  ${reads[0]} > ${pair_id}_report.txt
+
+  cutadapt -a GATCGTCGGACTGTAGAACTCTGAAC -g GTTCAGAGTTCTACAGTCCGACGATC \
+  -o ${pair_id}_cut_R2.fastq.gz \
+  ${reads[1]} > ${pair_id}_report.txt
+  """
+}
+
+process random_bases_4_trimming {
+  tag "$pair_id"
+  publishDir "results/fastq/adaptor_removal/", mode: 'copy'
+
+  input:
+  set pair_id, file(reads) from fastq_files_cut
+
+  output:
+  set pair_id, "*_cut4_R{1,2}.fastq.gz" into fastq_files_cut4
+
+  script:
+  """
+  cutadapt -u 4 -u -4 \
+  -o ${pair_id}_cut4_R1.fastq.gz -p ${pair_id}_cut4_R2.fastq.gz \
+  ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
+  """
+}
+/*
+* urqt :
+* Imputs : fastq files
+* Output : fastq files
+*/
+/*                      quality trimming                                     */
+
+/*
+* for paired-end data
+*/
+
+process trimming {
+  tag "${reads}"
+  cpus 4
+  publishDir "results/fastq/trimming/", mode: 'copy'
+
+  input:
+  set pair_id, file(reads) from fastq_files_cut4
+
+  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 \
+> ${pair_id}_trimming_report.txt
+"""
+}
+
+/*
+* Bowtie2 :
+* Imputs : fastq files
+* Imputs : fasta files
+* Output : bam files
+*/
+
+/*                      fasta indexing                                     */
+params.fasta = "$baseDir/data/bam/*.fasta"
+
+log.info "fasta files : ${params.fasta}"
+
+Channel
+  .fromPath( params.fasta )
+  .ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
+  .set { fasta_file }
+
+process index_fasta {
+  tag "$fasta.baseName"
+  cpus 4
+  publishDir "results/mapping/index/", mode: 'copy'
+
+  input:
+    file fasta from fasta_file
+
+  output:
+    file "*.index*" into index_files
+
+  script:
+"""
+bowtie2-build --threads ${task.cpus} ${fasta} ${fasta.baseName}.index &> ${fasta.baseName}_bowtie2_report.txt
+
+if grep -q "Error" ${fasta.baseName}_bowtie2_report.txt; then
+  exit 1
+fi
+"""
+}
+
+
+/*
+* for paired-end data
+*/
+
+process mapping_fastq {
+  tag "$pair_id"
+  cpus 4
+  publishDir "results/mapping/bams/", mode: 'copy'
+
+  input:
+  set pair_id, file(reads) from fastq_files_trim
+  file index from index_files.toList()
+
+  output:
+  set pair_id, "*.bam" into bam_files
+
+  script:
+"""
+ bowtie2 --very-sensitive -p ${task.cpus} -x ${index[0].baseName} \
+ -1 ${reads[0]} -2 ${reads[1]} 2> \
+ ${pair_id}_bowtie2_report.txt | \
+ samtools view -Sb - > ${pair_id}.bam
+
+if grep -q "Error" ${pair_id}_bowtie2_report.txt; then
+  exit 1
+fi
+"""
+}
+
+/*                      bams sorting                                    */
+process sort_bam {
+  tag "$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 ${bam}
+"""
+}
+
+/*                      bams indexing                                     */
+
+process index_bam {
+  tag "$bam.baseName"
+  input:
+    file bam from sorted_bam_files
+  output:
+    file "*bam*" into indexed_bam_file
+  script:
+"""
+samtools index ${bam}
+"""
+}
+
+
+/*                      bams spliting                                     */
+
+process split_bam {
+  tag "$bam.baseName"
+  cpus 2
+
+  input:
+    file bam from indexed_bam_file
+
+  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/RNAseq_sen1D.sh

+./nextflow src/RNASeq_sen1D.nf -c src/RNASeq_sen1D.config -profile docker -resume -with-dag results/RNASeq_dag.pdf -with-timeline results/RNASeq_timeline --fasta data/bam/S_pombe_full_genome_ncbi_2017_04_27.fasta --fastq "data/fastq/*_R{1,2}.fastq.gz"