nf-core_modules/modules/sratools/fasterqdump/main.nf
2022-02-04 09:53:32 +01:00

52 lines
1.8 KiB
Text

process SRATOOLS_FASTERQDUMP {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? 'bioconda::sra-tools=2.11.0 conda-forge::pigz=2.6' : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' :
'quay.io/biocontainers/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' }"
input:
tuple val(meta), path(sra)
output:
tuple val(meta), path(output), emit: reads
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
def config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
// Paired-end data extracted by fasterq-dump (--split-3 the default) always creates
// *_1.fastq *_2.fastq files but sometimes also an additional *.fastq file
// for unpaired reads which we ignore here.
output = meta.single_end ? '*.fastq.gz' : '*_{1,2}.fastq.gz'
"""
eval "\$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
if [[ ! -f "\${NCBI_SETTINGS}" ]]; then
mkdir -p "\$(dirname "\${NCBI_SETTINGS}")"
printf '${config}' > "\${NCBI_SETTINGS}"
fi
fasterq-dump \\
$args \\
--threads $task.cpus \\
${sra.name}
pigz \\
$args2 \\
--no-name \\
--processes $task.cpus \\
*.fastq
cat <<-END_VERSIONS > versions.yml
"${task.process}":
sratools: \$(fasterq-dump --version 2>&1 | grep -Eo '[0-9.]+')
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
END_VERSIONS
"""
}