feat(homer): Add groseq subworkflow (#1492)

* feat(homer): Add groseq subworkflow

* fix(homer): Update groseq paths

* test(homer): Update groseq bam md5sums

* test(homer): Update bed process args wildcard

* test(homer): Update groseq bed md5s

* style: Run prettier

* style(homer): Align comments

Co-authored-by: Friederike Hanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

* docs(homer): Add groseq meta.yml

Co-authored-by: Friederike Hanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
This commit is contained in:
Edmund Miller 2022-04-04 13:21:37 -05:00 committed by GitHub
parent ae48653bd2
commit 13cc32399c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 158 additions and 0 deletions

View file

@ -0,0 +1,50 @@
/*
* Identify transcripts with homer
*/
include { HOMER_MAKETAGDIRECTORY } from '../../../../modules/homer/maketagdirectory/main'
include { HOMER_MAKEUCSCFILE } from '../../../../modules/homer/makeucscfile/main'
include { HOMER_FINDPEAKS } from '../../../../modules/homer/findpeaks/main'
include { HOMER_POS2BED } from '../../../../modules/homer/pos2bed/main'
workflow HOMER_GROSEQ {
take:
bam // channel: [ val(meta), [ reads ] ]
fasta // file: /path/to/bwa/index/
main:
ch_versions = Channel.empty()
/*
* Create a Tag Directory From The GRO-Seq experiment
*/
HOMER_MAKETAGDIRECTORY ( bam, fasta )
ch_versions = ch_versions.mix(HOMER_MAKETAGDIRECTORY.out.versions.first())
/*
* Creating UCSC Visualization Files
*/
HOMER_MAKEUCSCFILE ( HOMER_MAKETAGDIRECTORY.out.tagdir )
ch_versions = ch_versions.mix(HOMER_MAKEUCSCFILE.out.versions.first())
/*
* Find transcripts directly from GRO-Seq
*/
HOMER_FINDPEAKS ( HOMER_MAKETAGDIRECTORY.out.tagdir )
ch_versions = ch_versions.mix(HOMER_FINDPEAKS.out.versions.first())
/*
* Convert peak file to bed file
*/
HOMER_POS2BED ( HOMER_FINDPEAKS.out.txt )
ch_versions = ch_versions.mix(HOMER_POS2BED.out.versions.first())
emit:
tagdir = HOMER_MAKETAGDIRECTORY.out.tagdir // channel: [ val(meta), [ tagdir ] ]
bed_graph = HOMER_MAKEUCSCFILE.out.bedGraph // channel: [ val(meta), [ tag_dir/*ucsc.bedGraph.gz ] ]
peaks = HOMER_FINDPEAKS.out.txt // channel: [ val(meta), [ *peaks.txt ] ]
bed = HOMER_POS2BED.out.bed // channel: [ val(meta), [ *peaks.txt ] ]
versions = ch_versions // channel: [ versions.yml ]
}

View file

@ -0,0 +1,48 @@
name: homer_groseq
description: Perform variant calling on a set of normal samples using mutect2 panel of normals mode. Group them into a genomicsdbworkspace using genomicsdbimport, then use this to create a panel of normals using createsomaticpanelofnormals.
keywords:
- homer
- groseq
- nascent
modules:
- homer/maketagdirectory
- homer/makeucscfile
- homer/findpeaks
- homer/pos2bed
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- input:
type: list
description: list of BAM files, also able to take SAM and BED as input
pattern: "[ *.{bam/sam/bed} ]"
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
output:
- tagdir:
type: directory
description: The "Tag Directory"
pattern: "*_tagdir"
- bedGraph:
type: file
description: The UCSC bed graph
pattern: "*.bedGraph.gz"
- peaks:
type: file
description: The found peaks
pattern: "*.peaks.txt"
- bed:
type: file
description: A BED file of the found peaks
pattern: "*.bed"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@Emiller88"

View file

@ -0,0 +1,24 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { HOMER_GROSEQ as HOMER_GROSEQ_BAM
HOMER_GROSEQ as HOMER_GROSEQ_BED } from '../../../../../subworkflows/nf-core/homer/groseq/main'
workflow test_homer_groseq_bam {
def input = []
input = [[ id: 'test' ],
[ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)]]
def fasta = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
HOMER_GROSEQ_BAM ( input, fasta )
}
workflow test_homer_groseq_bed {
def input = []
input = [[ id: 'test' ],
[ file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)]]
def fasta = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
HOMER_GROSEQ_BED ( input, fasta )
}

View file

@ -0,0 +1,9 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
withName: '.*:HOMER_GROSEQ_BED:HOMER_MAKETAGDIRECTORY' {
ext.args = "-checkGC -format bed"
}
}

View file

@ -0,0 +1,27 @@
- name: subworkflow homer_groseq bam
command: nextflow run ./tests/subworkflows/nf-core/homer/groseq/ -entry test_homer_groseq_bam -c tests/config/nextflow.config -c tests/subworkflows/nf-core/homer/groseq/nextflow.config
tags:
- homer
files:
- path: output/homer/test.bed
md5sum: 8d40034dfe22c5cf973071aa1e8d3617
- path: output/homer/test.bedGraph.gz
md5sum: de2b2f8ab90a909b8bfbe755bdaba407
- path: output/homer/test.peaks.txt
md5sum: 8d40034dfe22c5cf973071aa1e8d3617
- path: output/homer/versions.yml
md5sum: c85dee03f1afabe406a87743a4c5506d
- name: subworkflow homer_groseq bed
command: nextflow run ./tests/subworkflows/nf-core/homer/groseq/ -entry test_homer_groseq_bed -c tests/config/nextflow.config -c tests/subworkflows/nf-core/homer/groseq/nextflow.config
tags:
- homer
files:
- path: output/homer/test.bed
md5sum: 25e8b64946012d1c4567a04062e90fae
- path: output/homer/test.bedGraph.gz
md5sum: 2d2d1c2d3242ff74c7a922695accb9d2
- path: output/homer/test.peaks.txt
md5sum: 25e8b64946012d1c4567a04062e90fae
- path: output/homer/versions.yml
md5sum: c9b5f1248d28c216b000cba8da738455