Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Re-add picard createorreplacereadgroups for MultiVCFanalyzer #930

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jfy133 merged 3 commits into from
Oct 27, 2022
Merged

Re-add picard createorreplacereadgroups for MultiVCFanalyzer #930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
701847d
Re-add picard replacereadgroups for MVA only
jfy133 Oct 24, 2022
d1039b8
Update CHANGELOG.md
jfy133 Oct 24, 2022
415d05e
Update CHANGELOG.md
jfy133 Oct 24, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.

- Changed endors.py license from GPL to MIT (by @aidaanva)
- Removed erroneous R2 in single-end example in input TSV of usage docs (by @aidaanva)
- [#928](https://github.com/nf-core/eager/issues/928) Fixed read group incompatibility by re-adding picard AddOrReplaceReadGroups for MultiVCFAnalyzer (♥ to @aidaanva, @meganemichel for reporting)

### `Dependencies`

Expand Down
46 changes: 38 additions & 8 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2332,43 +2332,73 @@ process qualimap {
// Reroute files for genotyping; we have to ensure to select lib-merged BAMs, as input channel will also contain the un-merged ones resulting in unwanted multi-sample VCFs
if ( params.run_genotyping && params.genotyping_source == 'raw' ) {
ch_output_from_bamutils
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( params.run_genotyping && params.genotyping_source == "trimmed" && !params.run_trim_bam ) {
exit 1, "[nf-core/eager] error: Cannot run genotyping with 'trimmed' source without running BAM trimming (--run_trim_bam)! Please check input parameters."

} else if ( params.run_genotyping && params.genotyping_source == "trimmed" && params.run_trim_bam ) {
ch_output_from_bamutils
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( params.run_genotyping && params.genotyping_source == "pmd" && !params.run_pmdtools ) {
exit 1, "[nf-core/eager] error: Cannot run genotyping with 'pmd' source without running pmdtools (--run_pmdtools)! Please check input parameters."

} else if ( params.run_genotyping && params.genotyping_source == "pmd" && params.run_pmdtools ) {
ch_output_from_pmdtools
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( params.run_genotyping && params.genotyping_source == "rescaled" && params.run_mapdamage_rescaling) {
ch_output_from_damagerescaling
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( params.run_genotyping && params.genotyping_source == "rescaled" && !params.run_mapdamage_rescaling) {
exit 1, "[nf-core/eager] error: Cannot run genotyping with 'rescaled' source without running damage rescaling (--run_damagescaling)! Please check input parameters."

} else if ( !params.run_genotyping && !params.run_trim_bam && !params.run_pmdtools ) {
ch_rmdup_for_skipdamagemanipulation
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( !params.run_genotyping && !params.run_trim_bam && params.run_pmdtools ) {
ch_rmdup_for_skipdamagemanipulation
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

} else if ( !params.run_genotyping && params.run_trim_bam && !params.run_pmdtools ) {
ch_rmdup_for_skipdamagemanipulation
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }
.into { ch_damagemanipulation_for_skipgenotyping; ch_damagemanipulation_for_readgroupreplacement; ch_damagemanipulation_for_genotyping_ug; ch_damagemanipulation_for_genotyping_hc; ch_damagemanipulation_for_genotyping_freebayes; ch_damagemanipulation_for_genotyping_pileupcaller; ch_damagemanipulation_for_genotyping_angsd }

}

// replace readgroups to ensure single 'sample' per VCF for MultiVCFAnalyzer only

process picard_addorreplacereadgroups {
label 'sc_tiny'
tag "${samplename}"

when:
params.run_genotyping && params.genotyping_tool == 'ug' && params.run_multivcfanalyzer

input:
tuple samplename, libraryid, lane, seqtype, organism, strandedness, udg, path(bam), path(bai) from ch_damagemanipulation_for_readgroupreplacement

output:
tuple samplename, val("${samplename}"), lane, seqtype, organism, strandedness, udg, path("*rg.bam"), path("*rg.bam.{bai,csi}") into ch_readgroup_replacement_for_ug

script:
def size = params.large_ref ? '-c' : ''
"""
picard -Xmx${task.memory.toGiga()}g AddOrReplaceReadGroups I=${bam} O=${samplename}_rg.bam RGID=1 RGLB="${samplename}_rg" RGPL=illumina RGPU=4410 RGSM="${samplename}_rg" VALIDATION_STRINGENCY=LENIENT
samtools index ${samplename}_rg.bam ${size}
"""

}

if ( params.run_genotyping && params.genotyping_tool == 'ug' && params.run_multivcfanalyzer ) {
ch_input_for_ug = ch_readgroup_replacement_for_ug
} else {
ch_input_for_ug = ch_damagemanipulation_for_genotyping_ug
}

// Unified Genotyper - although not-supported, better for aDNA (because HC does de novo assembly which requires higher coverages), and needed for MultiVCFAnalyzer

process genotyping_ug {
Expand All @@ -2380,7 +2410,7 @@ process genotyping_ug {
params.run_genotyping && params.genotyping_tool == 'ug'

input:
tuple samplename, libraryid, lane, seqtype, organism, strandedness, udg, file(bam), file(bai) from ch_damagemanipulation_for_genotyping_ug
tuple samplename, libraryid, lane, seqtype, organism, strandedness, udg, file(bam), file(bai) from ch_input_for_ug
file fasta from ch_fasta_for_genotyping_ug.collect()
file fai from ch_fai_for_ug.collect()
file dict from ch_dict_for_ug.collect()
Expand Down