nf-core_modules/modules/star/genomegenerate/main.nf
2022-05-27 11:35:04 +01:00

68 lines
2.5 KiB
Text

process STAR_GENOMEGENERATE {
tag "$fasta"
label 'process_high'
conda (params.enable_conda ? "bioconda::star=2.7.10a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' :
'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' }"
input:
path fasta
path gtf
output:
path "star" , emit: index
path "versions.yml", emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def args_list = args.tokenize()
def memory = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : ''
if (args_list.contains('--genomeSAindexNbases')) {
"""
mkdir star
STAR \\
--runMode genomeGenerate \\
--genomeDir star/ \\
--genomeFastaFiles $fasta \\
--sjdbGTFfile $gtf \\
--runThreadN $task.cpus \\
$memory \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
star: \$(STAR --version | sed -e "s/STAR_//g")
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
gawk: \$(echo \$(gawk --version 2>&1) | sed 's/^.*GNU Awk //; s/, .*\$//')
END_VERSIONS
"""
} else {
"""
samtools faidx $fasta
NUM_BASES=`gawk '{sum = sum + \$2}END{if ((log(sum)/log(2))/2 - 1 > 14) {printf "%.0f", 14} else {printf "%.0f", (log(sum)/log(2))/2 - 1}}' ${fasta}.fai`
mkdir star
STAR \\
--runMode genomeGenerate \\
--genomeDir star/ \\
--genomeFastaFiles $fasta \\
--sjdbGTFfile $gtf \\
--runThreadN $task.cpus \\
--genomeSAindexNbases \$NUM_BASES \\
$memory \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
star: \$(STAR --version | sed -e "s/STAR_//g")
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
gawk: \$(echo \$(gawk --version 2>&1) | sed 's/^.*GNU Awk //; s/, .*\$//')
END_VERSIONS
"""
}
}