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

Jump to bottom

Workflow output definitions #189

Draft
wants to merge 11 commits into
base: dev
Choose a base branch
from
Draft

Workflow output definitions #189

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
1f9bbf7
first tryout
nvnieuwk Aug 29, 2024
c23f3f5
Merge branch 'ben-made-me-do-this' into output-definitions
nvnieuwk Aug 29, 2024
3a417c7
setup basic output definitions
nvnieuwk Aug 29, 2024
8e50f17
implement workflow output definitions
nvnieuwk Aug 29, 2024
13e9ee0
simplify modules.config
nvnieuwk Aug 29, 2024
5709297
fix a missing colon
nvnieuwk Aug 30, 2024
b45f74e
update failing tests
nvnieuwk Aug 30, 2024
2569410
fix more tests
nvnieuwk Aug 30, 2024
7530ae5
fix weird issue with gvcfs
nvnieuwk Aug 30, 2024
55f3cb5
fix even more tests
nvnieuwk Aug 30, 2024
2850288
fix last tests
nvnieuwk Aug 30, 2024
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
691 changes: 211 additions & 480 deletions conf/modules.config
View file
Open in desktop

Large diffs are not rendered by default.

110 changes: 108 additions & 2 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,9 @@
----------------------------------------------------------------------------------------
*/

// Enables the workflow output definition: https://www.nextflow.io/docs/latest/workflow.html#workflow-output-def
nextflow.preview.output = true

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS
Expand Down Expand Up @@ -47,6 +50,7 @@ params.vcfanno_config = getGenomeAttribute('vcfanno_config', params.genome
include { GERMLINE } from './workflows/germline'
include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_cmgg_germline_pipeline'
include { PIPELINE_COMPLETION } from './subworkflows/local/utils_cmgg_germline_pipeline'
include { samplesheetToList } from 'plugin/nf-schema'

//
// WORKFLOW: Run main analysis pipeline depending on type of input
Expand Down Expand Up @@ -132,7 +136,18 @@ workflow NFCMGG_GERMLINE {
)

emit:
multiqc_report = GERMLINE.out.multiqc_report // channel: /path/to/multiqc_report.html
vcf_tbi = GERMLINE.out.vcf_tbi // channel: [ val(meta), path(vcf), path(tbi) ]
multiqc_report = GERMLINE.out.multiqc_report // channel: /path/to/multiqc/report.html
validation = GERMLINE.out.validation
individual_reports = GERMLINE.out.individual_reports
family_reports = GERMLINE.out.family_reports
individuals_bed = GERMLINE.out.individuals_bed
family_bed = GERMLINE.out.family_bed
gvcf_tbi = GERMLINE.out.gvcf_tbi
updio = GERMLINE.out.updio
automap = GERMLINE.out.automap
db = GERMLINE.out.db
ped = GERMLINE.out.ped

}

Expand Down Expand Up @@ -194,7 +209,6 @@ workflow {

def multiqc_logo = params.multiqc_logo ?: "$projectDir/assets/CMGG_logo.png"


//
// SUBWORKFLOW: Run initialisation tasks
//
Expand Down Expand Up @@ -232,6 +246,98 @@ workflow {
params.hook_url,
NFCMGG_GERMLINE.out.multiqc_report
)

// TODO: remove this once dynamic publish paths have been added to nextflow
workflow.onComplete = {
def date = params.skip_date_project ? "" : "${new Date().format("yyyy-MM-dd")}_"
def final_output = "${params.outdir}/${params.project ? "${date}${params.project}" : "${date}${workflow.runName}"}"
def ids = samplesheetToList(params.input, "assets/schema_input.json").collect { entry ->
[ entry[0].id, entry[0].family ]
}
.flatten()
.findAll { id -> id instanceof String && id.length() > 0 }
.unique()

// Move around the output directory
file(params.outdir).eachFileRecurse { file ->
if (file.isDirectory()) {
return
}
def file_name = file.name
def file_full_name = file.toString()
def caller = file_full_name.contains("haplotypecaller") ? "haplotypecaller" :
file_full_name.contains("vardict") ? "vardict" : ""
def dot_caller = caller ? ".${caller}" : ""
def id = ids.find { id_ss -> file_name.contains(id_ss) } ?: ""
def custom_suffix = "${params.output_suffix ?: dot_caller}"
if (file_full_name.contains("/temp/vcfs/")) {
def extension = file_name.endsWith(".tbi") ? "vcf.gz.tbi" : "vcf.gz"
file.moveTo("${final_output}/${id}/${id}${custom_suffix}.${extension}")
}
else if (file_full_name.contains("/temp/validation/")) {
def validation_file = file_name.replace("${dot_caller}", "")
file.moveTo("${params.outdir}/${id}/validation/${caller}/${validation_file}")
}
else if (file_full_name.contains("/temp/individuals_reports/")) {
def report_extension = file_name.replace(dot_caller, "").replace(id, "")
file.moveTo("${params.outdir}/${id}/reports/${id}${custom_suffix}${report_extension}")
}
else if (file_full_name.contains("/temp/family_reports/")) {
def report_extension = file_name.replace(dot_caller, "").replace(id, "")
file.moveTo("${final_output}/${id}/reports/${id}${custom_suffix}${report_extension}")
}
else if (file_full_name.contains("/temp/individuals_beds/")) {
file.moveTo("${params.outdir}/${id}/${id}.bed")
}
else if (file_full_name.contains("/temp/family_beds/")) {
file.moveTo("${final_output}/${id}/${id}.bed")
}
else if (file_full_name.contains("/temp/gvcfs/")) {
def extension = file_name.endsWith(".tbi") ? "g.vcf.gz.tbi" : "g.vcf.gz"
file.moveTo("${params.outdir}/${id}/${id}.${caller}.${extension}")
}
else if (file_full_name.contains("/temp/updio/")) {
def sample = id
id = file_full_name.split("/temp/updio/")[-1].split("/")[0].replace("updio_${caller}_", "")
file.moveTo("${final_output}/${id}/updio_${caller}/${sample}/${file_name}")
}
else if (file_full_name.contains("/temp/automap/")) {
def sample = id
id = file_full_name.split("/temp/automap/")[-1].split("/")[0].replace("automap_${caller}_", "")
file.moveTo("${final_output}/${id}/automap_${caller}/${sample}/${file_name}")
}
else if (file_full_name.contains("/temp/ped/")) {
file.moveTo("${final_output}/${id}/${id}${custom_suffix}.ped")
}
else if (file_full_name.contains("/temp/db/")) {
file.moveTo("${final_output}/${id}/${id}${custom_suffix}.db")
}
}
file("${params.outdir}/temp").deleteDir()
}

publish:
NFCMGG_GERMLINE.out.vcf_tbi >> 'temp/vcfs/'
NFCMGG_GERMLINE.out.validation >> 'temp/validation/'
NFCMGG_GERMLINE.out.individual_reports >> 'temp/individuals_reports/'
NFCMGG_GERMLINE.out.family_reports >> 'temp/family_reports/'
NFCMGG_GERMLINE.out.individuals_bed >> 'temp/individuals_beds/'
NFCMGG_GERMLINE.out.family_bed >> 'temp/family_beds/'
NFCMGG_GERMLINE.out.gvcf_tbi >> 'temp/gvcfs/'
NFCMGG_GERMLINE.out.multiqc_report >> 'multiqc/'
NFCMGG_GERMLINE.out.updio >> 'temp/updio/'
NFCMGG_GERMLINE.out.automap >> 'temp/automap/'
NFCMGG_GERMLINE.out.db >> 'temp/db/'
NFCMGG_GERMLINE.out.ped >> 'temp/ped/'
}

output {
directory "${params.outdir}"
// TODO: add index once dynamic publish paths have been added to nextflow
// index {
// path 'index.csv'
// }

}

/*
Expand Down
11 changes: 7 additions & 4 deletions subworkflows/local/cram_call_genotype_gatk4/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,7 @@ workflow CRAM_CALL_GENOTYPE_GATK4 {
}
.mix(CRAM_CALL_GATK4.out.gvcfs)

ch_joint_beds = Channel.empty()
if(!only_call) {

GVCF_JOINT_GENOTYPE_GATK4(
Expand All @@ -61,7 +62,7 @@ workflow CRAM_CALL_GENOTYPE_GATK4 {
scatter_count
)
ch_versions = ch_versions.mix(GVCF_JOINT_GENOTYPE_GATK4.out.versions)

ch_joint_beds = GVCF_JOINT_GENOTYPE_GATK4.out.joint_beds
}

if(!only_call && !only_merge) {
Expand All @@ -83,9 +84,11 @@ workflow CRAM_CALL_GENOTYPE_GATK4 {
}

emit:
vcfs = ch_vcfs // channel: [ val(meta), path(vcf), path(tbi) ]
gvcfs = CRAM_CALL_GATK4.out.gvcfs
vcfs = ch_vcfs // channel: [ val(meta), path(vcf), path(tbi) ]
joint_beds = ch_joint_beds // channel: [ val(meta), path(bed) ]

reports = ch_reports // channel: [ path(reports) ]
versions = ch_versions // channel: [ versions.yml ]
reports = ch_reports // channel: [ path(reports) ]
versions = ch_versions // channel: [ versions.yml ]

}
1 change: 1 addition & 0 deletions subworkflows/local/cram_prepare_samtools_bedtools/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,6 +150,7 @@ workflow CRAM_PREPARE_SAMTOOLS_BEDTOOLS {
ch_fasta
)
ch_versions = ch_versions.mix(MOSDEPTH.out.versions.first())
ch_reports = ch_reports.mix(MOSDEPTH.out.global_txt, MOSDEPTH.out.summary_txt)

ch_ready_rois
.join(MOSDEPTH.out.quantized_bed, failOnDuplicate:true, failOnMismatch:true)
Expand Down
9 changes: 6 additions & 3 deletions subworkflows/local/gvcf_joint_genotype_gatk4/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ workflow GVCF_JOINT_GENOTYPE_GATK4 {
)
ch_versions = ch_versions.mix(GATK4_GENOMICSDBIMPORT.out.versions.first())

ch_joint_beds = Channel.empty()
if(!only_merge) {

BCFTOOLS_QUERY(
Expand Down Expand Up @@ -108,13 +109,14 @@ workflow GVCF_JOINT_GENOTYPE_GATK4 {
ch_fai
)
ch_versions = ch_versions.mix(MERGE_BEDS.out.versions.first())
ch_joint_beds = MERGE_BEDS.out.bed

//
// Split BED file into multiple BEDs specified by --scatter_count
//

INPUT_SPLIT_BEDTOOLS(
MERGE_BEDS.out.bed.map { meta, bed ->
ch_joint_beds.map { meta, bed ->
// Multiply the scatter count by the family size to better scatter big families
[meta, bed, (scatter_count * meta.family_count)]
},
Expand Down Expand Up @@ -162,7 +164,8 @@ workflow GVCF_JOINT_GENOTYPE_GATK4 {
}

emit:
vcfs = ch_vcfs // [ val(meta), path(vcf) ]
versions = ch_versions // [ path(versions) ]
vcfs = ch_vcfs // [ val(meta), path(vcf) ]
joint_beds = ch_joint_beds // [ val(meta), path(bed) ]
versions = ch_versions // [ path(versions) ]

}
32 changes: 31 additions & 1 deletion tests/nextflow.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,9 +58,39 @@ params {
igenomes_ignore = true
genomes_ignore = true

validationSchemaIgnoreParams = 'genomes,igenomes_base,test_data,cram1,cram2,cram3,crai1,crai2,crai3,vcf1,vcf2,vcf3,tbi1,tbi2,tbi3,gvcf1,gvcf2,gvcf3,gtbi1,gtbi2,gtbi3,famvcf,famtbi,ped,bed,split1,split2,split3'
}

validation.ignoreParams = [
'genomes',
'igenomes_base',
'test_data',
'cram1',
'cram2',
'cram3',
'crai1',
'crai2',
'crai3',
'vcf1',
'vcf2',
'vcf3',
'tbi1',
'tbi2',
'tbi3',
'gvcf1',
'gvcf2',
'gvcf3',
'gtbi1',
'gtbi2',
'gtbi3',
'famvcf',
'famtbi',
'ped',
'bed',
'split1',
'split2',
'split3'
]

process {
// Limit resources so that this can run on GitHub Actions
resourceLimits = [
Expand Down
75 changes: 36 additions & 39 deletions tests/pipeline/callers/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@
"NA24385/reports/NA24385.global.dist.txt",
"NA24385/reports/NA24385.haplotypecaller.bcftools_stats.txt",
"NA24385/reports/NA24385.summary.txt",
"multiqc/multiqc_plots",
"multiqc/multiqc_report.html",
"samplesheet.csv",
"test/Ashkenazim/Ashkenazim.bed",
Expand Down Expand Up @@ -64,37 +63,36 @@
"NA24385/reports/NA24385.global.dist.txt",
"NA24385/reports/NA24385.haplotypecaller.bcftools_stats.txt",
"NA24385/reports/NA24385.summary.txt",
"multiqc/multiqc_plots",
"multiqc/multiqc_report.html",
"samplesheet.csv",
"test/Ashkenazim/Ashkenazim.bed",
"test/Ashkenazim/Ashkenazim.haplotypecaller.ped",
"test/Ashkenazim/Ashkenazim.haplotypecaller.vcf.gz",
"test/Ashkenazim/Ashkenazim.haplotypecaller.vcf.gz.tbi",
"test/Ashkenazim/NA24143.vardict.ped",
"test/Ashkenazim/NA24143.vardict.vcf.gz",
"test/Ashkenazim/NA24143.vardict.vcf.gz.tbi",
"test/Ashkenazim/NA24149.vardict.ped",
"test/Ashkenazim/NA24149.vardict.vcf.gz",
"test/Ashkenazim/NA24149.vardict.vcf.gz.tbi",
"test/Ashkenazim/NA24385.vardict.ped",
"test/Ashkenazim/NA24385.vardict.vcf.gz",
"test/Ashkenazim/NA24385.vardict.vcf.gz.tbi",
"test/Ashkenazim/reports/Ashkenazim.haplotypecaller.bcftools_stats.txt",
"test/Ashkenazim/reports/Ashkenazim.haplotypecaller.somalier.html",
"test/Ashkenazim/reports/NA24143.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24143.vardict.somalier.html",
"test/Ashkenazim/reports/NA24149.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24149.vardict.somalier.html",
"test/Ashkenazim/reports/NA24385.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24385.vardict.somalier.html"
"test/NA24143/NA24143.vardict.ped",
"test/NA24143/NA24143.vardict.vcf.gz",
"test/NA24143/NA24143.vardict.vcf.gz.tbi",
"test/NA24143/reports/NA24143.vardict.bcftools_stats.txt",
"test/NA24143/reports/NA24143.vardict.somalier.html",
"test/NA24149/NA24149.vardict.ped",
"test/NA24149/NA24149.vardict.vcf.gz",
"test/NA24149/NA24149.vardict.vcf.gz.tbi",
"test/NA24149/reports/NA24149.vardict.bcftools_stats.txt",
"test/NA24149/reports/NA24149.vardict.somalier.html",
"test/NA24385/NA24385.vardict.ped",
"test/NA24385/NA24385.vardict.vcf.gz",
"test/NA24385/NA24385.vardict.vcf.gz.tbi",
"test/NA24385/reports/NA24385.vardict.bcftools_stats.txt",
"test/NA24385/reports/NA24385.vardict.somalier.html"
]
],
"meta": {
"nf-test": "0.8.4",
"nextflow": "24.02.0"
"nf-test": "0.9.0",
"nextflow": "24.04.4"
},
"timestamp": "2024-03-27T15:41:56.768447097"
"timestamp": "2024-08-30T12:15:27.996022227"
},
"vardict": {
"content": [
Expand All @@ -111,30 +109,29 @@
"NA24385/NA24385.bed",
"NA24385/reports/NA24385.global.dist.txt",
"NA24385/reports/NA24385.summary.txt",
"multiqc/multiqc_plots",
"multiqc/multiqc_report.html",
"samplesheet.csv",
"test/Ashkenazim/NA24143.vardict.ped",
"test/Ashkenazim/NA24143.vardict.vcf.gz",
"test/Ashkenazim/NA24143.vardict.vcf.gz.tbi",
"test/Ashkenazim/NA24149.vardict.ped",
"test/Ashkenazim/NA24149.vardict.vcf.gz",
"test/Ashkenazim/NA24149.vardict.vcf.gz.tbi",
"test/Ashkenazim/NA24385.vardict.ped",
"test/Ashkenazim/NA24385.vardict.vcf.gz",
"test/Ashkenazim/NA24385.vardict.vcf.gz.tbi",
"test/Ashkenazim/reports/NA24143.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24143.vardict.somalier.html",
"test/Ashkenazim/reports/NA24149.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24149.vardict.somalier.html",
"test/Ashkenazim/reports/NA24385.vardict.bcftools_stats.txt",
"test/Ashkenazim/reports/NA24385.vardict.somalier.html"
"test/NA24143/NA24143.vardict.ped",
"test/NA24143/NA24143.vardict.vcf.gz",
"test/NA24143/NA24143.vardict.vcf.gz.tbi",
"test/NA24143/reports/NA24143.vardict.bcftools_stats.txt",
"test/NA24143/reports/NA24143.vardict.somalier.html",
"test/NA24149/NA24149.vardict.ped",
"test/NA24149/NA24149.vardict.vcf.gz",
"test/NA24149/NA24149.vardict.vcf.gz.tbi",
"test/NA24149/reports/NA24149.vardict.bcftools_stats.txt",
"test/NA24149/reports/NA24149.vardict.somalier.html",
"test/NA24385/NA24385.vardict.ped",
"test/NA24385/NA24385.vardict.vcf.gz",
"test/NA24385/NA24385.vardict.vcf.gz.tbi",
"test/NA24385/reports/NA24385.vardict.bcftools_stats.txt",
"test/NA24385/reports/NA24385.vardict.somalier.html"
]
],
"meta": {
"nf-test": "0.8.4",
"nextflow": "24.02.0"
"nf-test": "0.9.0",
"nextflow": "24.04.4"
},
"timestamp": "2024-03-27T15:39:37.704366119"
"timestamp": "2024-08-30T12:07:42.137754836"
}
}
1 change: 0 additions & 1 deletion tests/pipeline/default/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@
"NA24385/reports/NA24385.global.dist.txt",
"NA24385/reports/NA24385.haplotypecaller.bcftools_stats.txt",
"NA24385/reports/NA24385.summary.txt",
"multiqc/multiqc_plots",
"multiqc/multiqc_report.html",
"samplesheet.csv",
"test/Ashkenazim/Ashkenazim.bed",
Expand Down
1 change: 0 additions & 1 deletion tests/pipeline/gvcfs/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@

],
[
"multiqc/multiqc_plots",
"multiqc/multiqc_report.html",
"samplesheet.csv",
"test/Ashkenazim/Ashkenazim.bed",
Expand Down
Loading
Loading