Skip to content
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

Fix join mismatch error for joint tumor only Mutect2 #1181

Merged
merged 12 commits into from
Aug 31, 2023
Merged

Fix join mismatch error for joint tumor only Mutect2 #1181

Changes from 6 commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
9ac0723
inital tests working
berguner Aug 11, 2023
1330e1c
fixed tumor_only
berguner Aug 16, 2023
cca3144
clean somatic mutect2
berguner Aug 16, 2023
7d53f68
Merge branch 'dev' of github.com:nf-core/sarek into fix_join_mismatch
berguner Aug 16, 2023
372f2ee
remove by:0
berguner Aug 16, 2023
f6f1a16
Merge branch 'dev' into fix_join_mismatch
maxulysse Aug 31, 2023
d231b26
Update CHANGELOG.md
maxulysse Aug 31, 2023
f32e7f7
Update CHANGELOG.md
maxulysse Aug 31, 2023
8bc44fc
simplify meta data handling
maxulysse Aug 31, 2023
e1e573e
simplify meta data handling
maxulysse Aug 31, 2023
e68e19f
add comments
maxulysse Aug 31, 2023
4c1eced
change channels name
maxulysse Aug 31, 2023
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
29 changes: 20 additions & 9 deletions subworkflows/local/bam_variant_calling_tumor_only_mutect2/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,11 +90,22 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MUTECT2 {
MERGEMUTECTSTATS(stats_to_merge)

// Mix intervals and no_intervals channels together
vcf = Channel.empty().mix(MERGE_MUTECT2.out.vcf, vcf_branch.no_intervals)
tbi = Channel.empty().mix(MERGE_MUTECT2.out.tbi, tbi_branch.no_intervals)
stats = Channel.empty().mix(MERGEMUTECTSTATS.out.stats, stats_branch.no_intervals)
f1r2 = Channel.empty().mix(f1r2_to_merge, f1r2_branch.no_intervals)
// Remove unnecessary metadata
if (joint_mutect2) {
// Remove sample and status metadata as they become irrelevant for joint calling
vcf = Channel.empty().mix(MERGE_MUTECT2.out.vcf, vcf_branch.no_intervals).map{ meta, vcf -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type'), vcf ] }
tbi = Channel.empty().mix(MERGE_MUTECT2.out.tbi, tbi_branch.no_intervals).map{ meta, tbi -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type'), tbi ] }
stats = Channel.empty().mix(MERGEMUTECTSTATS.out.stats, stats_branch.no_intervals).map{ meta, stats -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type'), stats ] }
f1r2 = Channel.empty().mix(f1r2_to_merge, f1r2_branch.no_intervals).map{ meta, f1r2 -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type'), f1r2 ] }
}
else {
// Keep sample and status metadata
vcf = Channel.empty().mix(MERGE_MUTECT2.out.vcf, vcf_branch.no_intervals).map{ meta, vcf -> [ meta - meta.subMap('num_intervals', 'data_type'), vcf ] }
tbi = Channel.empty().mix(MERGE_MUTECT2.out.tbi, tbi_branch.no_intervals).map{ meta, tbi -> [ meta - meta.subMap('num_intervals', 'data_type'), tbi ] }
stats = Channel.empty().mix(MERGEMUTECTSTATS.out.stats, stats_branch.no_intervals).map{ meta, stats -> [ meta - meta.subMap('num_intervals', 'data_type'), stats ] }
f1r2 = Channel.empty().mix(f1r2_to_merge, f1r2_branch.no_intervals).map{ meta, f1r2 -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type'), f1r2 ] }

}
// Generate artifactpriors using learnreadorientationmodel on the f1r2 output of mutect2
LEARNREADORIENTATIONMODEL(f1r2)

Expand Down Expand Up @@ -125,13 +136,13 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MUTECT2 {

if (joint_mutect2) {
// Remove sample names and retain patient name as the main identifier
calculatecontamination_out_seg = CALCULATECONTAMINATION.out.segmentation.map{ meta, seg -> [ meta - meta.subMap('sample') + [id:meta.patient], seg ] }.groupTuple()
calculatecontamination_out_cont = CALCULATECONTAMINATION.out.contamination.map{ meta, cont -> [ meta - meta.subMap('sample') + [id:meta.patient], cont ] }.groupTuple()
calculatecontamination_out_seg = CALCULATECONTAMINATION.out.segmentation.map{ meta, seg -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type') + [id:meta.patient], seg ] }.groupTuple()
calculatecontamination_out_cont = CALCULATECONTAMINATION.out.contamination.map{ meta, cont -> [ meta - meta.subMap('sample', 'status', 'num_intervals', 'data_type') + [id:meta.patient], cont ] }.groupTuple()
}
else {
// Regular single sample mode
calculatecontamination_out_seg = CALCULATECONTAMINATION.out.segmentation
calculatecontamination_out_cont = CALCULATECONTAMINATION.out.contamination
calculatecontamination_out_seg = CALCULATECONTAMINATION.out.segmentation.map{ meta, seg -> [ meta - meta.subMap('num_intervals', 'data_type'), seg ] }
calculatecontamination_out_cont = CALCULATECONTAMINATION.out.contamination.map{ meta, cont -> [ meta - meta.subMap('num_intervals', 'data_type'), cont ] }
}

// Mutect2 calls filtered by filtermutectcalls using the contamination and segmentation tables
Expand All @@ -146,7 +157,7 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MUTECT2 {

vcf_filtered = FILTERMUTECTCALLS.out.vcf
// add variantcaller to meta map and remove no longer necessary field: num_intervals
.map{ meta, vcf -> [ meta - meta.subMap('num_intervals') + [ variantcaller:'mutect2' ], vcf ] }
.map{ meta, vcf -> [ meta + [ variantcaller:'mutect2' ], vcf ] }

versions = versions.mix(MERGE_MUTECT2.out.versions)
versions = versions.mix(CALCULATECONTAMINATION.out.versions)
Expand Down