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

Use 20.07-RC1, add skip_qc to MD #252

Merged
merged 6 commits into from
Jul 22, 2020
Merged

Use 20.07-RC1, add skip_qc to MD #252

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c758a88
Use 20.07-RC1, add skip_qc to MD
FriederikeHanssen Jul 22, 2020
b6552f2
Add blank line for linting
FriederikeHanssen Jul 22, 2020
f34fc2f
Bump minimal version to 20.07
FriederikeHanssen Jul 22, 2020
b151dd5
Fix version naming
FriederikeHanssen Jul 22, 2020
7c78d31
use nextflow.enable.dsl and fix some minor things for that
FriederikeHanssen Jul 22, 2020
9bb93fc
Bump nf version in badge
FriederikeHanssen Jul 22, 2020
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 @@ -8,6 +8,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a

- [#238](https://github.com/nf-core/sarek/pull/238) -Add subworkflow for building all the indices
- [#241](https://github.com/nf-core/sarek/pull/241) -Add modules and workflows parts for preprocessing steps

## [dev](https://github.com/nf-core/sarek/tree/dev)

- [#234](https://github.com/nf-core/sarek/pull/234) -Switching to DSL2
Expand Down
76 changes: 18 additions & 58 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,8 +258,9 @@ include { BWAMEM2_MEM } from './modules/local/bwamem2_mem.nf'
include { GET_SOFTWARE_VERSIONS } from './modules/local/get_software_versions'
include { OUTPUT_DOCUMENTATION } from './modules/local/output_documentation'
include { TRIM_GALORE } from './modules/local/trim_galore.nf'
include { MERGE_BAM_MAPPED } from './modules/local/merge_mapped_bam' addParams(params)
include { MARK_DUPLICATES } from './modules/local/mark_duplicates' params(params)
include { MERGE_BAM_MAPPED } from './modules/local/merge_mapped_bam'
include { MARK_DUPLICATES } from './modules/local/mark_duplicates' addParams(skip_qc: skip_qc)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I see, now I understand better

//include { BASE_RECALIBRATION } from './modules/local/base_recalibration' params(params)

/*
================================================================================
Expand Down Expand Up @@ -346,8 +347,6 @@ workflow {
pon_tbi = params.pon ? params.pon_index ?: BUILD_INDICES.out.pon_tbi : Channel.empty()

// PREPROCESSING
intervals_bed.dump(tag:'bedintervals')

if(!('fastqc' in skip_qc))
result_fastqc = FASTQC(input_sample)
else
Expand Down Expand Up @@ -380,8 +379,20 @@ workflow {

bam_mapped.view()

mark_duplicates_report = !(params.skip_markduplicates) ? MARK_DUPLICATES(bam_mapped).duplicates_marked_report : Channel.empty()
if(!(params.skip_markduplicates)){
MARK_DUPLICATES(bam_mapped)
mark_duplicates_report = MARK_DUPLICATES.out.duplicates_marked_report
bam_duplicates_marked = MARK_DUPLICATES.out.bam_duplicates_marked
}
else {
mark_duplicates_report = Channel.empty()
bam_duplicates_marked = Channel.empty()
}

bamBaseRecalibrator = bam_duplicates_marked.combine(BUILD_INDICES.out.intervals_bed)

//BASE_RECALIBRATION(bamBaseRecalibrator,dbsnp, dbsnp_index,fasta,)

OUTPUT_DOCUMENTATION(
output_docs,
output_docs_images)
Expand Down Expand Up @@ -546,6 +557,7 @@ workflow.onComplete {

// (bam_mapped_merged, bam_mapped_merged_to_index) = bam_mapped_merged.into(2)

//@Maxime: You included this process in merged_bam.nf, right?
// process IndexBamFile {
// label 'cpus_8'

Expand Down Expand Up @@ -597,56 +609,6 @@ workflow.onComplete {
// }
// // STEP 2: MARKING DUPLICATES

// process MarkDuplicates {
// label 'cpus_16'

// tag "${idPatient}-${idSample}"

// publishDir params.outdir, mode: params.publish_dir_mode,
// saveAs: {
// if (it == "${idSample}.bam.metrics") "Reports/${idSample}/MarkDuplicates/${it}"
// else "Preprocessing/${idSample}/DuplicatesMarked/${it}"
// }

// input:
// set idPatient, idSample, file("${idSample}.bam") from bam_mapped_merged

// output:
// set idPatient, idSample, file("${idSample}.md.bam"), file("${idSample}.md.bam.bai") into bam_duplicates_marked
// set idPatient, idSample into tsv_bam_duplicates_marked
// file ("${idSample}.bam.metrics") optional true into duplicates_marked_report

// when: !(params.skip_markduplicates)

// script:
// markdup_java_options = task.memory.toGiga() > 8 ? params.markdup_java_options : "\"-Xms" + (task.memory.toGiga() / 2).trunc() + "g -Xmx" + (task.memory.toGiga() - 1) + "g\""
// metrics = 'markduplicates' in skip_qc ? '' : "-M ${idSample}.bam.metrics"
// if (params.no_gatk_spark)
// """
// gatk --java-options ${markdup_java_options} \
// MarkDuplicates \
// --MAX_RECORDS_IN_RAM 50000 \
// --INPUT ${idSample}.bam \
// --METRICS_FILE ${idSample}.bam.metrics \
// --TMP_DIR . \
// --ASSUME_SORT_ORDER coordinate \
// --CREATE_INDEX true \
// --OUTPUT ${idSample}.md.bam

// mv ${idSample}.md.bai ${idSample}.md.bam.bai
// """
// else
// """
// gatk --java-options ${markdup_java_options} \
// MarkDuplicatesSpark \
// -I ${idSample}.bam \
// -O ${idSample}.md.bam \
// ${metrics} \
// --tmp-dir . \
// --create-output-bam-index true \
// --spark-master local[${task.cpus}]
// """
// }

// (tsv_bam_duplicates_marked, tsv_bam_duplicates_marked_sample) = tsv_bam_duplicates_marked.into(2)

Expand Down Expand Up @@ -681,9 +643,7 @@ workflow.onComplete {

// (bamMD, bamMDToJoin, bam_duplicates_marked) = bam_duplicates_marked.into(3)

// bamBaseRecalibrator = bamMD.combine(intBaseRecalibrator)

// bamBaseRecalibrator = bamBaseRecalibrator.dump(tag:'BAM FOR BASERECALIBRATOR')
//

// // STEP 2': SENTIEON DEDUP

Expand Down
2 changes: 1 addition & 1 deletion modules/local/mark_duplicates.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ process MARK_DUPLICATES {
output:
tuple idPatient, idSample, path("${idSample}.md.bam"), path("${idSample}.md.bam.bai"), emit: bam_duplicates_marked
tuple idPatient, idSample, emit: tsv_bam_duplicates_marked
path "${idSample}.bam.metrics", emit: duplicates_marked_report //is optional , applies when skip_qc is used(not implemented yet)
path "${idSample}.bam.metrics", optional : true, emit: duplicates_marked_report //is optional , applies when skip_qc is used(not implemented yet)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actually we will need to rename this option.

you can't actually skip markduplicates with skip_qc, but you actually don't keep the report.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah, I see. So maybe skip_markduplicates_report and make it an extra parameter not included in the skip_qc list?


script:
markdup_java_options = task.memory.toGiga() > 8 ? params.markdup_java_options : "\"-Xms" + (task.memory.toGiga() / 2).trunc() + "g -Xmx" + (task.memory.toGiga() - 1) + "g\""
Expand Down