Added PL tag in read group information for downstream analysis (#649)

Co-authored-by: Maxime U. Garcia <max.u.garcia@gmail.com>
This commit is contained in:
praveenraj2018 2021-08-04 11:16:51 +02:00 committed by GitHub
parent 292e8eceb9
commit 5de3f2c50e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 16 additions and 20 deletions

View file

@ -39,11 +39,12 @@ process STAR_ALIGN {
tuple val(meta), path('*.out.junction') , optional:true, emit: junction
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
def ignore_gtf = params.star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf"
def seq_center = params.seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$params.seq_center' 'SM:$prefix'" : "--outSAMattrRGline ID:$prefix 'SM:$prefix'"
def out_sam_type = (options.args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted'
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
def ignore_gtf = params.star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf"
def seq_platform = params.seq_platform ? "'PL:$params.seq_platform'" : ""
def seq_center = params.seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$params.seq_center' 'SM:$prefix' $seq_platform " : "--outSAMattrRGline ID:$prefix 'SM:$prefix' $seq_platform "
def out_sam_type = (options.args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted'
def mv_unsorted_bam = (options.args.contains('--outSAMtype BAM Unsorted SortedByCoordinate')) ? "mv ${prefix}.Aligned.out.bam ${prefix}.Aligned.unsort.out.bam" : ''
"""
STAR \\

View file

@ -2,9 +2,9 @@
nextflow.enable.dsl = 2
include { STAR_GENOMEGENERATE } from '../../../../modules/star/genomegenerate/main.nf' addParams( options: [args: '--genomeSAindexNbases 9'] )
include { STAR_ALIGN } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat'] )
include { STAR_ALIGN as STAR_FOR_ARRIBA } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat --outSAMtype BAM Unsorted --outSAMunmapped Within --outBAMcompression 0 --outFilterMultimapNmax 50 --peOverlapNbasesMin 10 --alignSplicedMateMapLminOverLmate 0.5 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentMin 10 --chimOutType WithinBAM HardClip --chimJunctionOverhangMin 10 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0 --chimScoreSeparation 1 --chimSegmentReadGapMax 3 --chimMultimapNmax 50'] )
include { STAR_GENOMEGENERATE } from '../../../../modules/star/genomegenerate/main.nf' addParams( options: [args: '--genomeSAindexNbases 9'])
include { STAR_ALIGN } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat'], seq_platform: 'illumina')
include { STAR_ALIGN as STAR_FOR_ARRIBA } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat --outSAMtype BAM Unsorted --outSAMunmapped Within --outBAMcompression 0 --outFilterMultimapNmax 50 --peOverlapNbasesMin 10 --alignSplicedMateMapLminOverLmate 0.5 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentMin 10 --chimOutType WithinBAM HardClip --chimJunctionOverhangMin 10 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0 --chimScoreSeparation 1 --chimSegmentReadGapMax 3 --chimMultimapNmax 50'], seq_platform: 'illumina')
include { STAR_ALIGN as STAR_FOR_STARFUSION } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat --outSAMtype BAM Unsorted --outReadsUnmapped None --twopassMode Basic --outSAMstrandField intronMotif --outSAMunmapped Within --chimSegmentMin 12 --chimJunctionOverhangMin 8 --chimOutJunctionFormat 1 --alignSJDBoverhangMin 10 --alignMatesGapMax 100000 --alignIntronMax 100000 --alignSJstitchMismatchNmax 5 -1 5 5 --chimMultimapScoreRange 3 --chimScoreJunctionNonGTAG -4 --chimMultimapNmax 20 --chimNonchimScoreDropMin 10 --peOverlapNbasesMin 12 --peOverlapMMp 0.1 --alignInsertionFlush Right --alignSplicedMateMapLminOverLmate 0 --alignSplicedMateMapLmin 30'] )
workflow test_star_alignment_single_end {
@ -13,7 +13,6 @@ workflow test_star_alignment_single_end {
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
}
@ -25,7 +24,6 @@ workflow test_star_alignment_paired_end {
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
}
@ -38,7 +36,6 @@ workflow test_star_alignment_paired_end_for_fusion {
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_FOR_ARRIBA ( input, STAR_GENOMEGENERATE.out.index, gtf )
}
@ -50,7 +47,6 @@ workflow test_star_alignment_paired_end_for_starfusion {
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_FOR_STARFUSION ( input, STAR_GENOMEGENERATE.out.index, gtf )
}

View file

@ -1,8 +1,8 @@
- name: star align test_star_alignment_single_end
command: nextflow run tests/modules/star/align -entry test_star_alignment_single_end -c tests/config/nextflow.config
tags:
- star
- star/align
- star
files:
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
@ -36,7 +36,7 @@
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: 509d7f1fba3350913c8ea13f01917085
md5sum: b9f5e2f6a624b64c300fe25dc3ac801f
- path: output/star/test.Log.final.out
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
@ -45,8 +45,8 @@
- name: star align test_star_alignment_paired_end
command: nextflow run tests/modules/star/align -entry test_star_alignment_paired_end -c tests/config/nextflow.config
tags:
- star
- star/align
- star
files:
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
@ -80,8 +80,7 @@
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: 64b408fb1d61e2de8ff51c847cd5bc52
- path: output/star/test.Log.final.out
md5sum: 38d08f0b944a2a1b981a250d675aa0d9
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
- path: output/star/test.SJ.out.tab
@ -89,8 +88,8 @@
- name: star align test_star_alignment_paired_end_for_fusion
command: nextflow run tests/modules/star/align -entry test_star_alignment_paired_end_for_fusion -c tests/config/nextflow.config
tags:
- star
- star/align
- star
files:
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
@ -124,7 +123,7 @@
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: d724ca90a102347b9c5052a33ea4d308
md5sum: c740d5177067c1fcc48ab7a16cd639d7
- path: output/star/test.Log.final.out
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
@ -133,8 +132,8 @@
- name: star align test_star_alignment_paired_end_for_starfusion
command: nextflow run tests/modules/star/align -entry test_star_alignment_paired_end_for_starfusion -c tests/config/nextflow.config
tags:
- star
- star/align
- star
files:
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da