nf-core_modules/modules/gatk4/markduplicates/main.nf
FriederikeHanssen 598d7abdb2
Log4j again (#1202)
* Log4j again

* Update checksums
2022-01-12 13:55:54 +01:00

43 lines
1.5 KiB
Text

process GATK4_MARKDUPLICATES {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::gatk4=4.2.4.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.4.1--hdfd78af_0' :
'quay.io/biocontainers/gatk4:4.2.4.1--hdfd78af_0' }"
input:
tuple val(meta), path(bams)
output:
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*.bai") , emit: bai
tuple val(meta), path("*.metrics"), emit: metrics
path "versions.yml" , emit: versions
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def bam_list = bams.collect(){ bam -> "--INPUT ".concat(bam.toString()) }.join(" ")
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" MarkDuplicates \\
$bam_list \\
--METRICS_FILE ${prefix}.metrics \\
--TMP_DIR . \\
--CREATE_INDEX true \\
--OUTPUT ${prefix}.bam \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}