kkonganti@0: process CHECKM2_PREDICT {
kkonganti@0:     tag "$meta.id"
kkonganti@0:     label 'process_low'
kkonganti@0: 
kkonganti@0:     module (params.enable_module ? "${params.swmodulepath}${params.fs}checkm2${params.fs}1.0.1" : null)
kkonganti@0:     conda (params.enable_conda ? "conda-forge::scipy bioconda::checkm2=1.0.1" : null)
kkonganti@0:     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
kkonganti@0:         'https://depot.galaxyproject.org/singularity/checkm2:1.0.1--pyh7cba7a3_0' :
kkonganti@0:         'quay.io/biocontainers/checkm2:1.0.1--pyh7cba7a3_0+' }"
kkonganti@0: 
kkonganti@0:     input:
kkonganti@0:         tuple val(meta), path(database_path), path(acc_chunk_file, stageAs: 'acc_chunk_file.txt')
kkonganti@0: 
kkonganti@0:     output:
kkonganti@0:         tuple val(meta), path("**${params.fs}*quality_report.tsv")       , emit: quality_report
kkonganti@0:         tuple val(meta), path("**${params.fs}*quality_report.passed.tsv"), emit: quality_report_passed
kkonganti@0:         path "versions.yml"                                              , emit: versions
kkonganti@0: 
kkonganti@0:     when:
kkonganti@0:         task.ext.when == null || task.ext.when
kkonganti@0: 
kkonganti@0:     script:
kkonganti@0:         def args          = task.ext.args ?: ''
kkonganti@0:         def prefix        = task.ext.prefix ?: "${meta.id}"
kkonganti@0:         def outdir        = prefix + (task.index ?: '')
kkonganti@0:         def fgq_py_args   = []
kkonganti@0:         fgq_py_args.addAll([
kkonganti@0:             ("${params.fgq_py_cm2_extract}" ? "-extract ${params.fgq_py_cm2_extract}" : "-extract Name"),
kkonganti@0:             ("${params.fgq_py_cm2_fcn}" ? "-fcn ${params.fgq_py_cm2_fcn}" : "-fcn 'Completeness_General,Contamination,Completeness_Specific'"),
kkonganti@0:             ("${params.fgq_py_cm2_fcv}" ? "-fcv ${params.fgq_py_cm2_fcv}" : "-fcv '97.5,1,99'"),
kkonganti@0:             ("${params.fgq_py_cm2_conds}" ? "-conds ${params.fgq_py_cm2_conds}" : "-conds '>=,<=,>='")
kkonganti@0:         ]) 
kkonganti@0:         """
kkonganti@0:         datasets download genome accession \\
kkonganti@0:             --dehydrated \\
kkonganti@0:             --inputfile $acc_chunk_file
kkonganti@0: 
kkonganti@0:         unzip ncbi_dataset.zip
kkonganti@0: 
kkonganti@0:         datasets rehydrate \\
kkonganti@0:             --gzip \\
kkonganti@0:             --max-workers $task.cpus \\
kkonganti@0:             --directory "."
kkonganti@0: 
kkonganti@0:         stage_ncbi_dataset_genomes.py -in ncbi_dataset
kkonganti@0: 
kkonganti@0:         checkm2 \\
kkonganti@0:             predict \\
kkonganti@0:             --threads ${task.cpus} \\
kkonganti@0:             --database_path $database_path \\
kkonganti@0:             --input unscaffolded \\
kkonganti@0:             --output_directory $outdir \\
kkonganti@0:             $args
kkonganti@0: 
kkonganti@0:         filter_genomes_by_qual.py \\
kkonganti@0:             -tsv $outdir${params.fs}quality_report.tsv \\
kkonganti@0:             -outprefix "${outdir}_" \\
kkonganti@0:             ${fgq_py_args.join(' ')}
kkonganti@0: 
kkonganti@0:         cat <<-END_VERSIONS > versions.yml
kkonganti@0:         "${task.process}":
kkonganti@0:             datasets: \$( datasets --version | sed 's/datasets version: //g' )
kkonganti@0:             python: \$( python --version | sed 's/Python //g' )
kkonganti@0:             checkm2: \$( checkm2 --version )
kkonganti@0:         END_VERSIONS
kkonganti@0:         """
kkonganti@0: }