From 0a015caa8e984e8d616cf65d03ceb81cd931cd8a Mon Sep 17 00:00:00 2001
From: Laurent Modolo <laurent@modolo.fr>
Date: Tue, 31 Mar 2020 11:31:04 +0200
Subject: [PATCH] RNASeq: add experimental biologists practical solution
---
src/RNASeq.config | 126 ++++++++++++++++++++++++++++++++++++++++++++--
src/RNASeq.nf | 95 ++++++++++++++++++++++++++++++++--
2 files changed, 213 insertions(+), 8 deletions(-)
diff --git a/src/RNASeq.config b/src/RNASeq.config
index ed42799d..69f61457 100644
--- a/src/RNASeq.config
+++ b/src/RNASeq.config
@@ -4,9 +4,25 @@ profiles {
docker.enabled = true
process {
withName: adaptor_removal {
- container = "lbmc/cutadapt:2.4"
+ container = "lbmc/cutadapt:2.1"
cpus = 1
}
+ withName: trimming {
+ cpus = 4
+ container = "lbmc/urqt:d62c1f8"
+ }
+ withName: fasta_from_bed {
+ container = "lbmc/bedtools:2.25.0"
+ cpus = 1
+ }
+ withName: index_fasta {
+ container = "lbmc/kallisto:0.44.0"
+ cpus = 4
+ }
+ withName: mapping_fastq {
+ container = "lbmc/kallisto:0.44.0"
+ cpus = 4
+ }
}
}
singularity {
@@ -14,16 +30,53 @@ profiles {
singularity.cacheDir = "./bin/"
process {
withName: adaptor_removal {
- container = "lbmc/cutadapt:2.4"
+ container = "lbmc/cutadapt:2.1"
+ cpus = 1
+ }
+ withName: trimming {
+ cpus = 4
+ container = "lbmc/urqt:d62c1f8"
+ }
+ withName: fasta_from_bed {
+ container = "lbmc/bedtools:2.25.0"
cpus = 1
}
+ withName: index_fasta {
+ container = "lbmc/kallisto:0.44.0"
+ cpus = 4
+ }
+ withName: mapping_fastq {
+ container = "lbmc/kallisto:0.44.0"
+ cpus = 4
+ }
}
}
psmn{
process{
withName: adaptor_removal {
beforeScript = "source $baseDir/.conda_psmn.sh"
- conda = "$baseDir/.conda_envs/cutadapt_2.4"
+ conda = "$baseDir/.conda_envs/cutadapt_2.1"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ cpus = 1
+ memory = "20GB"
+ time = "12h"
+ queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+ }
+ 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'
+ }
+ withName: fasta_from_bed {
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/bedtools_2.25.0"
executor = "sge"
clusterOptions = "-cwd -V"
cpus = 1
@@ -31,6 +84,28 @@ profiles {
time = "12h"
queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
}
+ withName: index_fasta {
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/kallisto_0.44.0"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ cpus = 16
+ memory = "30GB"
+ time = "24h"
+ queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ penv = 'openmp16'
+ }
+ withName: mapping_fastq {
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/kallisto_0.44.0"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ cpus = 16
+ memory = "30GB"
+ time = "24h"
+ queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ penv = 'openmp16'
+ }
}
}
ccin2p3 {
@@ -39,7 +114,28 @@ profiles {
singularity.runOptions = "--bind /pbs,/sps,/scratch"
process{
withName: adaptor_removal {
- container = "lbmc/cutadapt:2.4"
+ container = "lbmc/cutadapt:2.1"
+ 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: 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'
+ }
+ withName: fasta_from_bed {
+ container = "lbmc/bedtools:2.25.0"
scratch = true
stageInMode = "copy"
stageOutMode = "rsync"
@@ -48,6 +144,28 @@ profiles {
cpus = 1
queue = 'huge'
}
+ withName: index_fasta {
+ container = "lbmc/kallisto:0.44.0"
+ 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: mapping_fastq {
+ container = "lbmc/kallisto:0.44.0"
+ scratch = true
+ stageInMode = "copy"
+ stageOutMode = "rsync"
+ executor = "sge"
+ clusterOptions = "-P P_lbmc -l os=cl7 -l sps=1 -r n\
+ "
+ cpus = 1
+ queue = 'huge'
+ }
}
}
}
diff --git a/src/RNASeq.nf b/src/RNASeq.nf
index c59eaaaa..73940d65 100644
--- a/src/RNASeq.nf
+++ b/src/RNASeq.nf
@@ -1,5 +1,15 @@
log.info "fastq files : ${params.fastq}"
+log.info "fasta file : ${params.fasta}"
+log.info "bed file : ${params.bed}"
+Channel
+ .fromPath( params.fasta )
+ .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
+ .set { fasta_files }
+Channel
+ .fromPath( params.bed )
+ .ifEmpty { error "Cannot find any bed files matching: ${params.bed}" }
+ .set { bed_files }
Channel
.fromFilePairs( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
@@ -16,9 +26,86 @@ process adaptor_removal {
set pair_id, "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
script:
- """
- cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \
- -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
- ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
"""
+
+ cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \
+ -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
+ ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
+ """
+}
+
+process trimming {
+ tag "${reads}"
+ publishDir "results/fastq/trimming/", mode: 'copy'
+
+ input:
+ set pair_id, file(reads) from fastq_files_cut
+
+ 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 \
+> ${pair_id}_trimming_report.txt
+"""
+}
+
+process fasta_from_bed {
+ tag "${bed.baseName}"
+ publishDir "results/fasta/", mode: 'copy'
+
+ input:
+ file fasta from fasta_files
+ file bed from bed_files
+
+ output:
+ file "*_extracted.fasta" into fasta_files_extracted
+
+ script:
+"""
+bedtools getfasta -name \
+-fi ${fasta} -bed ${bed} -fo ${bed.baseName}_extracted.fasta
+"""
+}
+
+process index_fasta {
+ tag "$fasta.baseName"
+ publishDir "results/mapping/index/", mode: 'copy'
+
+ input:
+ file fasta from fasta_files_extracted
+
+ 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} \
+2> ${fasta.baseName}_kallisto_report.txt
+"""
+}
+
+process mapping_fastq {
+ tag "$reads"
+ publishDir "results/mapping/quantification/", mode: 'copy'
+
+ input:
+ set pair_id, file(reads) from fastq_files_trim
+ file index from index_files.collect()
+
+ output:
+ file "*" into counts_files
+
+ script:
+"""
+mkdir ${pair_id}
+
+kallisto quant -i ${index} -t ${task.cpus} \
+--bias --bootstrap-samples 100 -o ${pair_id} \
+${reads[0]} ${reads[1]} &> ${pair_id}/kallisto_report.txt
+"""
}
--
GitLab