Mercurial > repos > galaxytrakr > hfp_cronology_awsbatch
comparison 0.2.0/modules/gunc/run/main.nf @ 0:9e8b1c747a6a draft default tip
planemo upload
| author | galaxytrakr |
|---|---|
| date | Fri, 29 May 2026 13:32:17 +0000 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:9e8b1c747a6a |
|---|---|
| 1 process GUNC_RUN { | |
| 2 tag "$meta.id" | |
| 3 label 'process_medium' | |
| 4 | |
| 5 module (params.enable_module ? "${params.swmodulepath}${params.fs}gunc${params.fs}1.0.5" : null) | |
| 6 conda (params.enable_conda ? "conda-forge::pandas=1.5.1 bioconda::gunc=1.0.5" : null) | |
| 7 container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? | |
| 8 'https://depot.galaxyproject.org/singularity/gunc:1.0.5--pyhdfd78af_0' : | |
| 9 'quay.io/biocontainers/gunc:1.0.5--pyhdfd78af_0' }" | |
| 10 | |
| 11 input: | |
| 12 tuple val(meta), path(database_path), path(fasta_ford, stageAs: 'fasta_ford.txt') | |
| 13 | |
| 14 output: | |
| 15 tuple val(meta), path("**${params.fs}*maxCSS_level.tsv") , emit: maxcss_level_tsv | |
| 16 tuple val(meta), path("**${params.fs}*all_levels.tsv") , emit: all_levels_tsv, optional: true | |
| 17 tuple val(meta), path("**${params.fs}*.maxCSS_level.passed.tsv"), emit: quality_report_passed | |
| 18 path "versions.yml" , emit: versions | |
| 19 | |
| 20 when: | |
| 21 task.ext.when == null || task.ext.when | |
| 22 | |
| 23 script: | |
| 24 def args = task.ext.args ?: '' | |
| 25 def prefix = task.ext.prefix ?: "${meta.id}" | |
| 26 def outdir = prefix + (task.index ?: '') | |
| 27 def input = "${fasta_ford}" | |
| 28 def fgq_py_args = [] | |
| 29 fgq_py_args.addAll([ | |
| 30 ("${params.fgq_py_gunc_extract}" ? "-extract ${params.fgq_py_gunc_extract}" : "-extract genome"), | |
| 31 ("${params.fgq_py_gunc_fcn}" ? "-fcn ${params.fgq_py_gunc_fcn}" : "-fcn 'clade_separation_score,contamination_portion'"), | |
| 32 ("${params.fgq_py_gunc_fcv}" ? "-fcv ${params.fgq_py_gunc_fcv}" : "-fcv '0.05,0.05'"), | |
| 33 ("${params.fgq_py_gunc_conds}" ? "-conds ${params.fgq_py_gunc_conds}" : "-conds '<=,<='") | |
| 34 ]) | |
| 35 if (params.guncrun_in_is_dir) { | |
| 36 input = "--input_dir ${fasta_ford}" | |
| 37 } else if (params.guncrun_in_is_fofn) { | |
| 38 input = "--input_file ${fasta_ford}" | |
| 39 } else if (params.guncrun_in_is_fasta) { | |
| 40 input = "--input_fasta ${fasta_ford}" | |
| 41 } else { | |
| 42 input = "--input_dir unscaffolded" | |
| 43 } | |
| 44 """ | |
| 45 mkdir -p $outdir || exit 1 | |
| 46 | |
| 47 datasets download genome accession \\ | |
| 48 --dehydrated \\ | |
| 49 --inputfile $fasta_ford | |
| 50 | |
| 51 unzip ncbi_dataset.zip | |
| 52 | |
| 53 datasets rehydrate \\ | |
| 54 --gzip \\ | |
| 55 --max-workers $task.cpus \\ | |
| 56 --directory "." | |
| 57 | |
| 58 stage_ncbi_dataset_genomes.py -in ncbi_dataset | |
| 59 | |
| 60 gunc \\ | |
| 61 run \\ | |
| 62 --db_file $database_path \\ | |
| 63 --threads $task.cpus \\ | |
| 64 --out_dir $outdir \\ | |
| 65 $input \\ | |
| 66 $args | |
| 67 | |
| 68 filter_genomes_by_qual.py \\ | |
| 69 -tsv $outdir${params.fs}GUNC.progenomes_2.1.maxCSS_level.tsv \\ | |
| 70 -outprefix "${outdir}_" \\ | |
| 71 ${fgq_py_args.join(' ')} | |
| 72 | |
| 73 cat <<-END_VERSIONS > versions.yml | |
| 74 "${task.process}": | |
| 75 datasets: \$( datasets --version | sed 's/datasets version: //g' ) | |
| 76 python: \$( python --version | sed 's/Python //g' ) | |
| 77 gunc: \$( gunc --version ) | |
| 78 END_VERSIONS | |
| 79 """ | |
| 80 } |
