Merge pull request #1534 from matthdsm/tool/elprep-merge

Tool/elprep merge
This commit is contained in:
Matthias De Smet 2022-04-29 15:18:45 +02:00 committed by GitHub
commit 86484f3361
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 121 additions and 0 deletions

View file

@ -0,0 +1,43 @@
process ELPREP_MERGE {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("output/**.{bam,sam}") , emit: bam
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def suffix = args.contains("--output-type sam") ? "sam" : "bam"
def single_end = meta.single_end ? " --single-end" : ""
"""
# create directory and move all input so elprep can find and merge them before splitting
mkdir input
mv ${bam} input/
elprep merge \\
input/ \\
output/${prefix}.${suffix} \\
$args \\
${single_end} \\
--nr-of-threads $task.cpus
cat <<-END_VERSIONS > versions.yml
"${task.process}":
elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,44 @@
name: "elprep_merge"
description: Merge split bam/sam chunks in one file
keywords:
- bam
- sam
- merge
tools:
- "elprep":
description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
homepage: "https://github.com/ExaScience/elprep"
documentation: "https://github.com/ExaScience/elprep"
tool_dev_url: "https://github.com/ExaScience/elprep"
doi: "10.1371/journal.pone.0244471"
licence: "['AGPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: List of BAM/SAM chunks to merge
pattern: "*.{bam,sam}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
#
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- bam:
type: file
description: Merged BAM/SAM file
pattern: "*.{bam,sam}"
authors:
- "@matthdsm"

View file

@ -603,6 +603,10 @@ elprep/filter:
- modules/elprep/filter/** - modules/elprep/filter/**
- tests/modules/elprep/filter/** - tests/modules/elprep/filter/**
elprep/merge:
- modules/elprep/merge/**
- tests/modules/elprep/merge/**
elprep/split: elprep/split:
- modules/elprep/split/** - modules/elprep/split/**
- tests/modules/elprep/split/** - tests/modules/elprep/split/**

View file

@ -0,0 +1,17 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { ELPREP_SPLIT } from '../../../../modules/elprep/split/main.nf'
include { ELPREP_MERGE } from '../../../../modules/elprep/merge/main.nf'
workflow test_elprep_merge {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
]
ELPREP_SPLIT ( input )
ELPREP_MERGE ( ELPREP_SPLIT.out.bam )
}

View file

@ -0,0 +1,5 @@
process {
withName : ELPREP_MERGE {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
}
}

View file

@ -0,0 +1,8 @@
- name: elprep merge test_elprep_merge
command: nextflow run tests/modules/elprep/merge -entry test_elprep_merge -c tests/config/nextflow.config
tags:
- elprep
- elprep/merge
files:
- path: output/elprep/output/test.bam
- path: output/elprep/versions.yml