Skip to content

Add quilt imputation subworkflow #9443

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

Open
LouisLeNezet wants to merge 8 commits into
base: master
Choose a base branch
from
Open

Add quilt imputation subworkflow #9443

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8d92d3b
Add sbwf quilt
LouisLeNezet Nov 24, 2025
f1b02e4
Fix tags
LouisLeNezet Nov 24, 2025
f9f026e
Merge branch 'master' into sbwf_quilt
LouisLeNezet Nov 24, 2025
2945648
Merge branch 'master' into sbwf_quilt
LouisLeNezet Nov 25, 2025
88102dd
Update meta
LouisLeNezet Nov 25, 2025
d75633a
Merge branch 'master' into sbwf_quilt
LouisLeNezet Nov 27, 2025
d84e459
Use modules repo files
LouisLeNezet Nov 27, 2025
d969d2a
Merge branch 'master' into sbwf_quilt
LouisLeNezet Dec 4, 2025
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
11 changes: 7 additions & 4 deletions modules/nf-core/quilt/quilt/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,14 +25,17 @@ process QUILT_QUILT {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def suffix = task.ext.suffix ?: "vcf.gz"
def extensions = bams.collect { it.extension }
def extensions = bams.collect { path -> path.extension }
def extension = extensions.flatten().unique()
def list_command = extension == ["bam"] ? "--bamlist=" :
extension == ["cram"] ? "--reference=${fasta} --cramlist=" : ""
def genetic_map_command = genetic_map ? "--genetic_map_file=${genetic_map}" : ""
def posfile_command = posfile ? "--posfile=${posfile}" : ""
def phasefile_command = phasefile ? "--phasefile=${phasefile}" : ""
def samplename_command = samplename ? "--sampleNames_file=${samplename}" : ""
def start_command = regions_start ? "--regionStart=$regions_start" : ""
def end_command = regions_end ? "--regionEnd=$regions_end" : ""
def buffer_command = buffer ? "--buffer=$buffer" : ""

if (!(args ==~ /.*--seed.*/)) {args += " --seed=1"}

Expand All @@ -52,10 +55,10 @@ process QUILT_QUILT {
$phasefile_command \\
$samplename_command \\
--chr=$chr \\
--regionStart=$regions_start \\
--regionEnd=$regions_end \\
$start_command \\
$end_command \\
$buffer_command \\
--nGen=$ngen \\
--buffer=$buffer \\
--nCores=$task.cpus \\
--outputdir="." \\
--reference_haplotype_file=$reference_haplotype_file \\
Expand Down
75 changes: 34 additions & 41 deletions modules/nf-core/quilt/quilt/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,16 +13,16 @@ nextflow_process {

config "./nextflow.config"

test("QUILT") {
test("homo_sapiens - bam, hap, legend, posfile, phasefile, map - fasta") {
setup {
run("BCFTOOLS_QUERY") {
script "../../../bcftools/query/main.nf"
process {
"""
input[0] = [
[id: 'NA12878'],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/vcf/NA12878.chr22.1X.vcf.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/vcf/NA12878.chr22.1X.vcf.gz.csi', checkIfExists: true)
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/vcf/NA12878.chr21_22.1X.glimpse2.vcf.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/vcf/NA12878.chr21_22.1X.glimpse2.vcf.gz.csi', checkIfExists: true)
]
input[1] = []
input[2] = []
Expand All @@ -42,44 +42,31 @@ nextflow_process {
"""
}
}

run("GAWK", alias: "GAWK_POSFILE") {
script "../../../gawk/main.nf"
process {
"""
program = Channel.of('BEGIN{OFS=\"\\t\"} NR>1 {split(\$1, a, \"[:-_]\"); print a[1],\$2,\$3,\$4}').collectFile(name: 'program.txt', newLine: true)
input[0] = [
[id: 'NA12878'],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.legend.gz', checkIfExists: true)
]
input[1] = program
input[2] = false
"""
}
}
}

when {
params{
quilt_args = "--save_prepared_reference=TRUE --make_plots=TRUE --seed=1"
bcftools_query_args = "-f '[%GT]\\n'"
bcftools_query_suffix = "genfile.txt"
gawk_posfile_suffix = "posfile.txt"
gawk_name_suffix = "genfile.name.txt"
bcftools_query_args = "-f '[%GT]\\n' -r chr22"
bcftools_query_suffix = "phasefile.txt"
gawk_name_suffix = "phasefile.name.txt"
}
process {
"""
input[0] = Channel.of([
[ id:'NA12878', chr:'chr22' ],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam.bai', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam.bai', checkIfExists: true),
[], [],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.hap.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.legend.gz', checkIfExists: true)
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.legend.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.posfile', checkIfExists: true),
])
.combine(GAWK_POSFILE.out.output.map{ it[1] })
.combine(GAWK_NAME.out.output.map{ it[1] })
.combine(Channel.of([[], "chr22", "16570000", "16610000", "100", "10000", []]))
.combine(channel.of([
[], "chr22", "16570000", "16610000", "100", "10000",
file(params.modules_testdata_base_path + "genomics/homo_sapiens/genome/genetic_map/genome.GRCh38.chr22.stitch.map", checkIfExist:true)
]))
input[1] = [
[id: 'GRCh38'],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true),
Expand All @@ -96,13 +83,15 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.vcf,
process.out.tbi,
list.sort(),
process.out.rdata,
process.out.versions,
process.out.vcf.collect{ path(it[1]).vcf.header.getGenotypeSamples().sort() },
process.out.vcf.collect{ path(it[1]).vcf.variantsMD5 }
process.out.vcf.collect{ meta, vcf -> [
meta,
path(vcf).vcf.header.getGenotypeSamples().sort(),
path(vcf).vcf.variantsMD5
]}
).match() }
)
}
Expand Down Expand Up @@ -156,8 +145,8 @@ nextflow_process {
"""
input[0] = [
[ id:'test', chr:'chr22' ],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam.bai', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam.bai', checkIfExists: true),
[], [],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.hap.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.legend.gz', checkIfExists: true),
Expand All @@ -174,12 +163,14 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.vcf,
process.out.tbi,
process.out.rdata,
process.out.versions,
process.out.vcf.collect{ path(it[1]).vcf.header.getGenotypeSamples().sort() },
process.out.vcf.collect{ path(it[1]).vcf.variantsMD5 }
process.out.vcf.collect{ meta, vcf -> [
meta,
path(vcf).vcf.header.getGenotypeSamples().sort(),
path(vcf).vcf.variantsMD5
]}
).match() }
)
}
Expand All @@ -193,7 +184,7 @@ nextflow_process {
process {
"""
bamlist = Channel.of(
"NA12878.chr22.1X.bam",
"NA12878.chr21_22.1X.bam",
).collectFile(name : 'bamlist.txt', newLine : true)

bamnames = Channel.of(
Expand All @@ -202,8 +193,8 @@ nextflow_process {

ch_input = Channel.of([
[ id:'test', chr:'chr20' ],
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.1X.bam.bai', checkIfExists: true)
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr21_22.1X.bam.bai', checkIfExists: true)
])
.combine(bamlist)
.combine(bamnames)
Expand All @@ -225,12 +216,14 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.vcf,
process.out.tbi,
process.out.rdata,
process.out.versions,
process.out.vcf.collect{ path(it[1]).vcf.header.getGenotypeSamples().sort() },
process.out.vcf.collect{ path(it[1]).vcf.variantsMD5 }
process.out.vcf.collect{ meta, vcf -> [
meta,
path(vcf).vcf.header.getGenotypeSamples().sort(),
path(vcf).vcf.variantsMD5
]}
).match() }
)
}
Expand Down
Loading
Loading