From a6974060cc73ed95d26e63ad7f86dac292d0d17f Mon Sep 17 00:00:00 2001
From: Emmanuel Labaronne <emmanuel.labaronne@ens-lyon.fr>
Date: Tue, 10 Nov 2020 19:45:09 +0100
Subject: [PATCH] RNAseq.nf : fix beug on normalized coverage
---
src/RNAseq.config | 20 +++++--
src/RNAseq.nf | 143 +++++++++++++++++++++++++++++++---------------
2 files changed, 114 insertions(+), 49 deletions(-)
diff --git a/src/RNAseq.config b/src/RNAseq.config
index 5a4cf78f..00c35fde 100644
--- a/src/RNAseq.config
+++ b/src/RNAseq.config
@@ -203,7 +203,7 @@ profiles {
container = "lbmc/fastqc:0.11.5"
cpus = 4
}
- withName: adaptor_removal {
+ withName: trimming {
container = "lbmc/cutadapt:2.1"
cpus = 4
}
@@ -235,7 +235,7 @@ profiles {
container = "gcr.io/broad-cga-aarong-gtex/rnaseqc:latest"
cpus = 1
}
- withName: hisat2_postGenomic {
+ withName: hisat2_postgenome {
cpus = 4
container = "lbmc/hisat2:2.1.0"
}
@@ -251,9 +251,21 @@ profiles {
container = "lbmc/multiqc:1.7"
cpus = 1
}
+ withName: calc_scalingFactor{
+ container = "lbmc/hisat2:2.1.0"
+ cpus = 1
+ }
withName: coverage {
- container = "lbmc/deeptools:3.0.2"
- cpus = 8
+ container = "lbmc/deeptools:3.0.2"
+ cpus = 8
+ }
+ withName: calc_scalingFactor_with_postgenome{
+ container = "lbmc/hisat2:2.1.0"
+ cpus = 1
+ }
+ withName: coverage_with_postgenome {
+ container = "lbmc/deeptools:3.0.2"
+ cpus = 16
}
}
}
diff --git a/src/RNAseq.nf b/src/RNAseq.nf
index 65ed93b2..a8b41781 100644
--- a/src/RNAseq.nf
+++ b/src/RNAseq.nf
@@ -462,7 +462,7 @@ rnaseqc ${gtf} ${bam[0]} -s ${file_id} ./ \
/* HISAT2 POST_GENOMIC */
/////////////////////////
-process hisat2_postGenomic {
+process hisat2_postgenome {
tag "$file_id"
publishDir "${params.output}/05_post_genome_hisat2/", mode: 'copy'
@@ -569,52 +569,105 @@ process fastqc_postgenome {
/* Coverage */
//////////////
-process coverage_postgenome {
- tag "$file_id"
- publishDir "${params.output}/07_coverage/", mode: 'copy'
-
- input:
- set file_id, file(bam) from HISAT_ALIGNED_COV
- set file_id_2, file(post_genome) from POSTGENOME_ALIGNED_COV
-
- output:
- file "*.bigwig" into COVERAGE_OUTPUT
-
- when:
- params.do_postgenome
-
- shell:
- '''
- genome=$(samtools view !{bam[0]} | awk '{print $1}' | sort | uniq | wc -l)
- postgenome=$(samtools view !{post_genome[0]} | awk '{print $1}' | sort | uniq | wc -l)
- total=$(($genome + $postgenome))
- factor=$(awk -v c=$total 'BEGIN {print 1000000/c}')
- bamCoverage -p !{task.cpus} --binSize 1 -b !{bam[0]} -o !{file_id}_genome.bigwig
- bamCoverage -p !{task.cpus} --binSize 1 -b !{post_genome[0]} -o !{file_id}_postgenome.bigwig
- '''
-}
-
-process coverage {
- tag "$file_id"
- publishDir "${params.output}/07_coverage/", mode: 'copy'
-
- input:
- set file_id, file(bam) from HISAT_ALIGNED_COV_2
-
- output:
- file "*.bigwig" into COVERAGE_OUTPUT_2
-
- when:
- params.do_postgenome==false
- shell:
- '''
- genome=$(samtools view !{bam[0]} | awk '{print $1} | sort | uniq | wc -l)
- factor=$(awk -v c=$genome 'BEGIN {print 1000000/c}')
- bamCoverage -p !{task.cpus} --binSize 1 -b !{bam[0]} -o !{file_id}.bigwig
- '''
+if (params.do_postgenome){
+ HISAT_ALIGNED_COV.join(POSTGENOME_ALIGNED_COV)
+ .into{COVERAGE_MERGED_VALUES;COVERAGE_MERGED_BAM}
+
+ process calc_scalingFactor_with_postgenome{
+ tag "$file_id"
+
+ input:
+ set file_id, file(genome), file(post_genome) from COVERAGE_MERGED_VALUES
+
+ output:
+ set file_id, env(genome), env(postgenome), env(factor) into COVERAGE_MERGED_FACTOR
+
+ shell:
+ '''
+ genome=$(samtools view !{genome[0]} | awk '{print $1}' | sort | uniq | wc -l)
+ postgenome=$(samtools view !{post_genome[0]} | awk '{print $1}' | sort | uniq | wc -l)
+ total=$(($genome + $postgenome))
+ factor=$(awk -v c=$total 'BEGIN {print 1000000/c}')
+ '''
+ }
+
+ COVERAGE_MERGED_FACTOR.join(COVERAGE_MERGED_BAM)
+ .set{COVERAGE_MERGED_BIGWIG}
+
+ process coverage_with_postgenome{
+ tag "$file_id"
+ publishDir "${params.output}/07_coverage/", mode: 'copy'
+
+ input:
+ set file_id, val(genome), val(postgenome), val (factor), file(genome_bam), file(post_genome_bam) from COVERAGE_MERGED_BIGWIG
+
+ output:
+ file "*.bigwig" into COVERAGE_OUTPUT
+ file "*.txt" into COVERAGE_LOG
+
+ shell:
+ '''
+ total=$((!{genome} + !{postgenome}))
+ echo "genome aligment : !{genome} counts" >> !{file_id}.txt
+ echo "postgenome aligment : !{postgenome} counts" >> !{file_id}.txt
+ echo "total counts : $total" >> !{file_id}.txt
+ echo "scaling factor : !{factor}" >> !{file_id}.txt
+ if [ !{genome} -gt 0 ]
+ then
+ bamCoverage -p !{task.cpus} --binSize 1 --scaleFactor !{factor} -b !{genome_bam[0]} -o !{file_id}_genome.bigwig
+ fi
+ if [ !{postgenome} -gt 0 ]
+ then
+ bamCoverage -p !{task.cpus} --binSize 1 --scaleFactor !{factor} -b !{post_genome_bam[0]} -o !{file_id}_postgenome.bigwig
+ fi
+ '''
+ }
+} else {
+ HISAT_ALIGNED_COV.into{COVERAGE_MERGED_VALUES;COVERAGE_MERGED_BAM}
+
+ process calc_scalingFactor{
+ tag "$file_id"
+
+ input:
+ set file_id, file(genome) from COVERAGE_MERGED_VALUES
+
+ output:
+ set file_id, env(genome), env(factor) into COVERAGE_MERGED_FACTOR
+
+ shell:
+ '''
+ genome=$(samtools view !{genome[0]} | awk '{print $1}' | sort | uniq | wc -l)
+ factor=$(awk -v c=$genome 'BEGIN {print 1000000/c}')
+ '''
+ }
+
+ COVERAGE_MERGED_FACTOR.join(COVERAGE_MERGED_BAM)
+ .set{COVERAGE_MERGED_BIGWIG}
+
+
+ process coverage {
+ tag "$file_id"
+ publishDir "${params.output}/07_coverage/", mode: 'copy'
+
+ input:
+ set file_id, val(genome), val (factor), file(genome_bam) from COVERAGE_MERGED_BIGWIG
+
+ output:
+ file "*.bigwig" into COVERAGE_OUTPUT
+ file "*.txt" into COVERAGE_LOG
+
+ shell:
+ '''
+ echo "genome aligment : !{genome} counts" >> !{file_id}.txt
+ echo "scaling factor : !{factor}" >> !{file_id}.txt
+ if [ !{genome} -gt 0 ]
+ then
+ bamCoverage -p !{task.cpus} --binSize 1 --scaleFactor !{factor} -b !{genome_bam[0]} -o !{file_id}_genome.bigwig
+ fi
+ '''
+ }
}
-
/////////////
/* MultiQC */
/////////////
--
GitLab