nf-core_modules/modules/gatk4/markduplicates/main.nf
2022-05-16 15:53:26 +02:00

46 lines
1.5 KiB
Text

process GATK4_MARKDUPLICATES {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*.bai") , optional:true, emit: bai
tuple val(meta), path("*.metrics"), emit: metrics
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 input_list = bam.collect{"--INPUT $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" MarkDuplicates \\
$input_list \\
--OUTPUT ${prefix}.bam \\
--METRICS_FILE ${prefix}.metrics \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}