From 3eff31942c91bcc73130295f6024d2ed48abb16d Mon Sep 17 00:00:00 2001
From: Vincent Vanoosthuyse <vincent.vanoosthuyse@ens-lyon.fr>
Date: Mon, 23 Jul 2018 11:49:59 +0200
Subject: [PATCH] amendments to cutadapt to remove adapters in 5' and 3' from
R1 and R2
---
src/RNAseq_sen1D.nf | 41 ++++++++++++++++++++++++++---------------
1 file changed, 26 insertions(+), 15 deletions(-)
diff --git a/src/RNAseq_sen1D.nf b/src/RNAseq_sen1D.nf
index 7d3fb5a..cb3062e 100644
--- a/src/RNAseq_sen1D.nf
+++ b/src/RNAseq_sen1D.nf
@@ -21,22 +21,42 @@ Channel
process adaptor_removal {
tag "$pair_id"
- publishDir "results/fastq/adaptor_removal/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files
output:
- set pair_id, "*_cut_R{1,2}_001.fastq.gz" into fastq_files_cut
+ set pair_id, "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
script:
"""
- cutadapt -a TGGAATTCTCGGGTGCCAAGG -A GTTCAGAGTTCTACAGTCCGACGATC \
- -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
- ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
+ 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]} > ${pair_id}_report.txt
"""
}
+process 4_random_bases_trimming {
+ tag "$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_cut
+
+ script:
+ """
+ cutadapt -u 4 -u -4 \
+ -o ${pair_id}_cut4_R1.fastq.gz -p ${pair_id}_cut4_R2.fastq.gz \
+ ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
+ """
+}
/*
* urqt :
* Imputs : fastq files
@@ -48,22 +68,13 @@ process adaptor_removal {
* for paired-end data
*/
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromFilePairs( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
process trimming {
tag "${reads}"
cpus 4
publishDir "results/fastq/trimming/", mode: 'copy'
input:
- set pair_id, file(reads) from fastq_files_cut
+ set pair_id, file(reads) from fastq_files_cut4
output:
set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
--
GitLab