From 5ebe62612cc05b1b39359e4a2a2eda79c65fdd73 Mon Sep 17 00:00:00 2001 From: "Robert A. Petit III" Date: Sun, 21 Nov 2021 05:14:02 -0700 Subject: [PATCH] add ectyper module (#948) * add ectyper module * fix-lint * try zcat * Update main.nf * fix lint * Update main.nf * Apply suggestions from code review Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com> * Update main.nf * pass lint * Update main.nf * fix lint Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com> Co-authored-by: Harshil Patel --- modules/ectyper/functions.nf | 78 +++++++++++++++++++++++++++++++++ modules/ectyper/main.nf | 51 +++++++++++++++++++++ modules/ectyper/meta.yml | 51 +++++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/ectyper/main.nf | 13 ++++++ tests/modules/ectyper/test.yml | 11 +++++ 6 files changed, 208 insertions(+) create mode 100644 modules/ectyper/functions.nf create mode 100644 modules/ectyper/main.nf create mode 100644 modules/ectyper/meta.yml create mode 100644 tests/modules/ectyper/main.nf create mode 100644 tests/modules/ectyper/test.yml diff --git a/modules/ectyper/functions.nf b/modules/ectyper/functions.nf new file mode 100644 index 00000000..85628ee0 --- /dev/null +++ b/modules/ectyper/functions.nf @@ -0,0 +1,78 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Extract name of module from process name using $task.process +// +def getProcessName(task_process) { + return task_process.tokenize(':')[-1] +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + + // Do not publish versions.yml unless running from pytest workflow + if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) { + return null + } + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } +} diff --git a/modules/ectyper/main.nf b/modules/ectyper/main.nf new file mode 100644 index 00000000..b5d8202d --- /dev/null +++ b/modules/ectyper/main.nf @@ -0,0 +1,51 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process ECTYPER { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::ectyper=1.0.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/ectyper:1.0.0--pyhdfd78af_1" + } else { + container "quay.io/biocontainers/ectyper:1.0.0--pyhdfd78af_1" + } + + input: + tuple val(meta), path(fasta) + + output: + tuple val(meta), path("*.log"), emit: log + tuple val(meta), path("*.tsv"), emit: tsv + tuple val(meta), path("*.txt"), emit: txt + path "versions.yml" , emit: versions + + script: + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def is_compressed = fasta.getName().endsWith(".gz") ? true : false + def fasta_name = fasta.getName().replace(".gz", "") + """ + if [ "$is_compressed" == "true" ]; then + gzip -c -d $fasta > $fasta_name + fi + + ectyper \\ + $options.args \\ + --cores $task.cpus \\ + --output ./ \\ + --input $fasta_name + mv output.tsv ${prefix}.tsv + + cat <<-END_VERSIONS > versions.yml + ${getProcessName(task.process)}: + ${getSoftwareName(task.process)}: \$(echo \$(ectyper --version 2>&1) | sed 's/.*ectyper //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/ectyper/meta.yml b/modules/ectyper/meta.yml new file mode 100644 index 00000000..a6beca29 --- /dev/null +++ b/modules/ectyper/meta.yml @@ -0,0 +1,51 @@ +name: ectyper +description: In silico prediction of E. coli serotype +keywords: + - escherichia coli + - fasta + - serotype +tools: + - ectyper: + description: ECtyper is a python program for serotyping E. coli genomes + homepage: https://github.com/phac-nml/ecoli_serotyping + documentation: https://github.com/phac-nml/ecoli_serotyping + tool_dev_url: https://github.com/phac-nml/ecoli_serotyping + doi: "" + licence: ['Apache 2'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - fasta: + type: file + description: FASTA formatted assembly file + pattern: "*.{fasta,fasta.gz,fa,fa.gz,fna,fna.gz}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - log: + type: file + description: ectyper log output + pattern: "*.log" + - tsv: + type: file + description: ectyper serotyping results in TSV format + pattern: "*.tsv" + - txt: + type: file + description: Allele report generated from BLAST results + pattern: "*.tst" + +authors: + - "@rpetit3" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index 55223f55..5a879cdc 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -406,6 +406,10 @@ dshbio/splitgff3: - modules/dshbio/splitgff3/** - tests/modules/dshbio/splitgff3/** +ectyper: + - modules/ectyper/** + - tests/modules/ectyper/** + emmtyper: - modules/emmtyper/** - tests/modules/emmtyper/** diff --git a/tests/modules/ectyper/main.nf b/tests/modules/ectyper/main.nf new file mode 100644 index 00000000..123df68d --- /dev/null +++ b/tests/modules/ectyper/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { ECTYPER } from '../../../modules/ectyper/main.nf' addParams( options: [:] ) + +workflow test_ectyper { + + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ] + + ECTYPER ( input ) +} diff --git a/tests/modules/ectyper/test.yml b/tests/modules/ectyper/test.yml new file mode 100644 index 00000000..c6f4c668 --- /dev/null +++ b/tests/modules/ectyper/test.yml @@ -0,0 +1,11 @@ +- name: ectyper test_ectyper + command: nextflow run tests/modules/ectyper -entry test_ectyper -c tests/config/nextflow.config + tags: + - ectyper + files: + - path: output/ectyper/blast_output_alleles.txt + md5sum: 27f3f5e84f7da451b2948d61589cdb06 + - path: output/ectyper/ectyper.log + contains: ['Serotype', 'RefSeq', 'O-type', 'finished'] + - path: output/ectyper/test.tsv + md5sum: ba923d7c7ee7d1047466aafc9a9df208