Skip to content

Commit

Permalink
improve workflow logic for fastq_align_dedup_bismark (#7005)
Browse files Browse the repository at this point in the history 
* improve workflow logic

* add paired-end tests

* update meta.yml

* minor formatting fix

* apply suggestions from code review
  • Loading branch information
@sateeshperi
sateeshperi authored Nov 18, 2024
1 parent c3fe6e9 commit af84433
Show file tree
Hide file tree
Showing 5 changed files with 491 additions and 190 deletions.
127 changes: 64 additions & 63 deletions subworkflows/nf-core/fastq_align_dedup_bismark/main.nf
View file
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
include { BISMARK_ALIGN } from '../../../modules/nf-core/bismark/align/main'
include { BISMARK_DEDUPLICATE } from '../../../modules/nf-core/bismark/deduplicate/main'
include { BISMARK_METHYLATIONEXTRACTOR } from '../../../modules/nf-core/bismark/methylationextractor/main'
include { BISMARK_COVERAGE2CYTOSINE } from '../../../modules/nf-core/bismark/coverage2cytosine/main'
include { BISMARK_REPORT } from '../../../modules/nf-core/bismark/report/main'
include { BISMARK_SUMMARY } from '../../../modules/nf-core/bismark/summary/main'
include { SAMTOOLS_SORT as SAMTOOLS_SORT_DEDUPLICATED } from '../../../modules/nf-core/samtools/sort/main'
include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DEDUPLICATED } from '../../../modules/nf-core/samtools/index/main'
include { BISMARK_ALIGN } from '../../../modules/nf-core/bismark/align/main'
include { BISMARK_DEDUPLICATE } from '../../../modules/nf-core/bismark/deduplicate/main'
include { SAMTOOLS_SORT } from '../../../modules/nf-core/samtools/sort/main'
include { SAMTOOLS_INDEX } from '../../../modules/nf-core/samtools/index/main'
include { BISMARK_METHYLATIONEXTRACTOR } from '../../../modules/nf-core/bismark/methylationextractor/main'
include { BISMARK_COVERAGE2CYTOSINE } from '../../../modules/nf-core/bismark/coverage2cytosine/main'
include { BISMARK_REPORT } from '../../../modules/nf-core/bismark/report/main'
include { BISMARK_SUMMARY } from '../../../modules/nf-core/bismark/summary/main'

workflow FASTQ_ALIGN_DEDUP_BISMARK {

Expand All @@ -17,18 +17,20 @@ workflow FASTQ_ALIGN_DEDUP_BISMARK {
cytosine_report // boolean: whether the run coverage2cytosine

main:
ch_versions = Channel.empty()
ch_coverage2cytosine_coverage = Channel.empty()
ch_coverage2cytosine_report = Channel.empty()
ch_coverage2cytosine_summary = Channel.empty()
ch_alignments = Channel.empty()
ch_alignment_reports = Channel.empty()
ch_methylation_bedgraph = Channel.empty()
ch_methylation_calls = Channel.empty()
ch_methylation_coverage = Channel.empty()
ch_methylation_report = Channel.empty()
ch_methylation_mbias = Channel.empty()
ch_coverage2cytosine_coverage = Channel.empty()
ch_coverage2cytosine_report = Channel.empty()
ch_coverage2cytosine_summary = Channel.empty()
ch_bismark_report = Channel.empty()
ch_bismark_summary = Channel.empty()
ch_multiqc_files = Channel.empty()
ch_versions = Channel.empty()

/*
* Align with bismark
Expand All @@ -38,28 +40,44 @@ workflow FASTQ_ALIGN_DEDUP_BISMARK {
ch_fasta,
ch_bismark_index
)
ch_alignments = BISMARK_ALIGN.out.bam
ch_alignment_reports = BISMARK_ALIGN.out.report.map{ meta, report -> [ meta, report, [] ] }
ch_versions = ch_versions.mix(BISMARK_ALIGN.out.versions)

if (skip_deduplication) {
alignments = BISMARK_ALIGN.out.bam
alignment_reports = BISMARK_ALIGN.out.report.map{ meta, report -> [ meta, report, [] ] }
} else {
if (!skip_deduplication) {
/*
* Run deduplicate_bismark
*/
BISMARK_DEDUPLICATE (
BISMARK_ALIGN.out.bam
)
alignments = BISMARK_DEDUPLICATE.out.bam
alignment_reports = BISMARK_ALIGN.out.report.join(BISMARK_DEDUPLICATE.out.report)
ch_versions = ch_versions.mix(BISMARK_DEDUPLICATE.out.versions)
ch_alignments = BISMARK_DEDUPLICATE.out.bam
ch_alignment_reports = BISMARK_ALIGN.out.report.join(BISMARK_DEDUPLICATE.out.report)
ch_versions = ch_versions.mix(BISMARK_DEDUPLICATE.out.versions)
}

/*
* MODULE: Run samtools sort on aligned or deduplicated bam
*/
SAMTOOLS_SORT (
ch_alignments,
[[:],[]] // [ [meta], [fasta]]
)
ch_versions = ch_versions.mix(SAMTOOLS_SORT.out.versions)

/*
* MODULE: Run samtools index on aligned or deduplicated bam
*/
SAMTOOLS_INDEX (
SAMTOOLS_SORT.out.bam
)
ch_versions = ch_versions.mix(SAMTOOLS_INDEX.out.versions)

/*
* Run bismark_methylation_extractor
*/
BISMARK_METHYLATIONEXTRACTOR (
alignments,
ch_alignments,
ch_bismark_index
)
ch_methylation_bedgraph = BISMARK_METHYLATIONEXTRACTOR.out.bedgraph
Expand All @@ -74,7 +92,7 @@ workflow FASTQ_ALIGN_DEDUP_BISMARK {
*/
if (cytosine_report) {
BISMARK_COVERAGE2CYTOSINE (
BISMARK_METHYLATIONEXTRACTOR.out.coverage,
ch_methylation_coverage,
ch_fasta,
ch_bismark_index
)
Expand All @@ -88,7 +106,7 @@ workflow FASTQ_ALIGN_DEDUP_BISMARK {
* Generate bismark sample reports
*/
BISMARK_REPORT (
alignment_reports
ch_alignment_reports
.join(ch_methylation_report)
.join(ch_methylation_mbias)
)
Expand All @@ -100,54 +118,37 @@ workflow FASTQ_ALIGN_DEDUP_BISMARK {
*/
BISMARK_SUMMARY (
BISMARK_ALIGN.out.bam.collect{ meta, bam -> bam.name },
alignment_reports.collect{ meta, align_report, dedup_report -> align_report },
alignment_reports.collect{ meta, align_report, dedup_report -> dedup_report }.ifEmpty([]),
BISMARK_METHYLATIONEXTRACTOR.out.report.collect{ meta, report -> report },
BISMARK_METHYLATIONEXTRACTOR.out.mbias.collect{ meta, mbias -> mbias }
ch_alignment_reports.collect{ meta, align_report, dedup_report -> align_report },
ch_alignment_reports.collect{ meta, align_report, dedup_report -> dedup_report }.ifEmpty([]),
ch_methylation_report.collect{ meta, report -> report },
ch_methylation_mbias.collect{ meta, mbias -> mbias }
)
ch_bismark_summary = BISMARK_SUMMARY.out.summary
ch_versions = ch_versions.mix(BISMARK_SUMMARY.out.versions)

/*
* MODULE: Run samtools sort on dedup bam
*/
SAMTOOLS_SORT_DEDUPLICATED (
alignments,
[[:],[]] // [ [meta], [fasta]]
)
ch_versions = ch_versions.mix(SAMTOOLS_SORT_DEDUPLICATED.out.versions)

/*
* MODULE: Run samtools index on dedup bam
*/
SAMTOOLS_INDEX_DEDUPLICATED (
SAMTOOLS_SORT_DEDUPLICATED.out.bam
)
ch_versions = ch_versions.mix(SAMTOOLS_INDEX_DEDUPLICATED.out.versions)

/*
* Collect MultiQC inputs
*/
ch_multiqc_files = BISMARK_SUMMARY.out.summary
.mix(alignment_reports.collect{ meta, align_report, dedup_report -> align_report })
.mix(alignment_reports.collect{ meta, align_report, dedup_report -> dedup_report })
.mix(BISMARK_METHYLATIONEXTRACTOR.out.report.collect{ meta, report -> report })
.mix(BISMARK_METHYLATIONEXTRACTOR.out.mbias.collect{ meta, mbias -> mbias })
.mix(BISMARK_REPORT.out.report.collect{ meta, report -> report })
ch_multiqc_files = ch_bismark_summary
.mix(ch_alignment_reports.collect{ meta, align_report, dedup_report -> align_report })
.mix(ch_alignment_reports.collect{ meta, align_report, dedup_report -> dedup_report })
.mix(ch_methylation_report.collect{ meta, report -> report })
.mix(ch_methylation_mbias.collect{ meta, mbias -> mbias })
.mix(ch_bismark_report.collect{ meta, report -> report })

emit:
dedup_bam = SAMTOOLS_SORT_DEDUPLICATED.out.bam // channel: [ val(meta), [ bam ] ]
dedup_bam_index = SAMTOOLS_INDEX_DEDUPLICATED.out.bai // channel: [ val(meta), [ bai ] ]
coverage2cytosine_coverage = ch_coverage2cytosine_coverage // channel: [ val(meta), [ coverage ] ]
coverage2cytosine_report = ch_coverage2cytosine_report // channel: [ val(meta), [ report ] ]
coverage2cytosine_summary = ch_coverage2cytosine_summary // channel: [ val(meta), [ summary ] ]
methylation_bedgraph = ch_methylation_bedgraph // channel: [ val(meta), [ bedgraph ] ]
methylation_calls = ch_methylation_calls // channel: [ val(meta), [ methylation_calls ] ]
methylation_coverage = ch_methylation_coverage // channel: [ val(meta), [ coverage ] ]
methylation_report = ch_methylation_report // channel: [ val(meta), [ report ] ]
methylation_mbias = ch_methylation_mbias // channel: [ val(meta), [ mbias ] ]
bismark_report = ch_bismark_report // channel: [ val(meta), [ report ] ]
bismark_summary = ch_bismark_summary // channel: [ val(meta), [ summary ] ]
multiqc = ch_multiqc_files // path: *{html,txt}
versions = ch_versions // path: *.version.txt
bam = SAMTOOLS_SORT.out.bam // channel: [ val(meta), [ bam ] ]
bai = SAMTOOLS_INDEX.out.bai // channel: [ val(meta), [ bai ] ]
coverage2cytosine_coverage = ch_coverage2cytosine_coverage // channel: [ val(meta), [ coverage ] ]
coverage2cytosine_report = ch_coverage2cytosine_report // channel: [ val(meta), [ report ] ]
coverage2cytosine_summary = ch_coverage2cytosine_summary // channel: [ val(meta), [ summary ] ]
methylation_bedgraph = ch_methylation_bedgraph // channel: [ val(meta), [ bedgraph ] ]
methylation_calls = ch_methylation_calls // channel: [ val(meta), [ methylation_calls ] ]
methylation_coverage = ch_methylation_coverage // channel: [ val(meta), [ coverage ] ]
methylation_report = ch_methylation_report // channel: [ val(meta), [ report ] ]
methylation_mbias = ch_methylation_mbias // channel: [ val(meta), [ mbias ] ]
bismark_report = ch_bismark_report // channel: [ val(meta), [ report ] ]
bismark_summary = ch_bismark_summary // channel: [ val(meta), [ summary ] ]
multiqc = ch_multiqc_files // path: *{html,txt}
versions = ch_versions // path: *.version.txt
}
10 changes: 5 additions & 5 deletions subworkflows/nf-core/fastq_align_dedup_bismark/meta.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ input:
description: |
Structure: [ val(meta), path(fasta) ]
pattern: "*.{fa,fa.gz}"
- ch_index:
- ch_bismark_index:
description: |
Bismark genome index files
Structure: [ val(meta), path(index) ]
Expand All @@ -46,16 +46,16 @@ input:
description: |
Produce coverage2cytosine reports that relates methylation calls back to genomic cytosine contexts
output:
- dedup_bam:
- bam:
type: file
description: |
Channel containing deduplicated BAM files.
Channel containing aligned or deduplicated BAM files.
Structure: [ val(meta), path(bam) ]
pattern: "*.bam"
- dedup_bam_index:
- bai:
type: file
description: |
Channel containing deduplicated BAM index files.
Channel containing aligned or deduplicated BAM index files.
Structure: [ val(meta), path(bam.bai) ]
pattern: "*.bai"
- coverage2cytosine_coverage:
Expand Down
Loading

0 comments on commit af84433

Please sign in to comment.