diff --git a/src/RNAseq_sen1D.nf b/src/RNAseq_sen1D.nf index 7d3fb5ab13f7db7218f690a174acd004a6e814df..cb3062e441f4a4161c97eb28b9f0b03c170c299f 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