From 22aa168622d6fa8c8da5a845979ddd3e8c619005 Mon Sep 17 00:00:00 2001 From: "Robert A. Petit III" Date: Sat, 6 Nov 2021 09:34:39 -0600 Subject: [PATCH] add scoary module (#1034) Co-authored-by: Gregor Sturm --- modules/scoary/functions.nf | 78 +++++++++++++++++++++++++++++++++ modules/scoary/main.nf | 45 +++++++++++++++++++ modules/scoary/meta.yml | 51 +++++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/scoary/main.nf | 15 +++++++ tests/modules/scoary/test.yml | 9 ++++ 6 files changed, 202 insertions(+) create mode 100644 modules/scoary/functions.nf create mode 100644 modules/scoary/main.nf create mode 100644 modules/scoary/meta.yml create mode 100644 tests/modules/scoary/main.nf create mode 100644 tests/modules/scoary/test.yml diff --git a/modules/scoary/functions.nf b/modules/scoary/functions.nf new file mode 100644 index 00000000..85628ee0 --- /dev/null +++ b/modules/scoary/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{ + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + + // Do not publish versions.yml unless running from pytest workflow + if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) { + return null + } + if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)}/$args.filename" + } +} diff --git a/modules/scoary/main.nf b/modules/scoary/main.nf new file mode 100644 index 00000000..5720b4e5 --- /dev/null +++ b/modules/scoary/main.nf @@ -0,0 +1,45 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SCOARY { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::scoary=1.6.16" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/scoary:1.6.16--py_2" + } else { + container "quay.io/biocontainers/scoary:1.6.16--py_2" + } + + input: + tuple val(meta), path(genes), path(traits) + path(tree) + + output: + tuple val(meta), path("*.csv"), emit: csv + path "versions.yml" , emit: versions + + script: + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def newick_tree = tree ? "-n ${tree}" : "" + """ + scoary \\ + $options.args \\ + --no-time \\ + --threads $task.cpus \\ + --traits $traits \\ + --genes $genes + + cat <<-END_VERSIONS > versions.yml + ${getProcessName(task.process)}: + ${getSoftwareName(task.process)}: \$( scoary --version 2>&1 ) + END_VERSIONS + """ +} diff --git a/modules/scoary/meta.yml b/modules/scoary/meta.yml new file mode 100644 index 00000000..e8e8515e --- /dev/null +++ b/modules/scoary/meta.yml @@ -0,0 +1,51 @@ +name: scoary +description: Use pangenome outputs for GWAS +keywords: + - gwas + - pangenome + - prokaryote +tools: + - scoary: + description: Microbial pan-GWAS using the output from Roary + homepage: https://github.com/AdmiralenOla/Scoary + documentation: https://github.com/AdmiralenOla/Scoary + tool_dev_url: https://github.com/AdmiralenOla/Scoary + doi: "10.1186/s13059-016-1108-8" + licence: ['GPL v3'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - genes: + type: file + description: A presence/absence matrix of genes in the pan-genome + pattern: "*.csv" + - traits: + type: file + description: A CSV file containing trait information per-sample + pattern: "*.csv" + - tree: + type: file + description: A Newick formtted tree for phylogenetic analyses + pattern: "*.{dnd,nwk,treefile}" + +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" + - csv: + type: file + description: Gene associations in a CSV file per trait + pattern: "*.csv" + +authors: + - "@rpetit3" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index a8fa40df..6d9d0d12 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -1083,6 +1083,10 @@ samtools/view: - modules/samtools/view/** - tests/modules/samtools/view/** +scoary: + - modules/scoary/** + - tests/modules/scoary/** + seacr/callpeak: - modules/seacr/callpeak/** - tests/modules/seacr/callpeak/** diff --git a/tests/modules/scoary/main.nf b/tests/modules/scoary/main.nf new file mode 100644 index 00000000..ec3f6e9f --- /dev/null +++ b/tests/modules/scoary/main.nf @@ -0,0 +1,15 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { SCOARY } from '../../../modules/scoary/main.nf' addParams( options: [:] ) + +workflow test_scoary { + + input = [ [ id:'test', single_end:false ], // meta map + file("https://github.com/AdmiralenOla/Scoary/raw/master/scoary/exampledata/Gene_presence_absence.csv", checkIfExists: true), + file("https://github.com/AdmiralenOla/Scoary/raw/master/scoary/exampledata/Tetracycline_resistance.csv", checkIfExists: true) ] + + tree = [] + SCOARY ( input, tree) +} diff --git a/tests/modules/scoary/test.yml b/tests/modules/scoary/test.yml new file mode 100644 index 00000000..c5269293 --- /dev/null +++ b/tests/modules/scoary/test.yml @@ -0,0 +1,9 @@ +- name: scoary test_scoary + command: nextflow run tests/modules/scoary -entry test_scoary -c tests/config/nextflow.config + tags: + - scoary + files: + - path: output/scoary/Bogus_trait.results.csv + md5sum: 9550c692bbe6ff0ac844357bfabb809b + - path: output/scoary/Tetracycline_resistance.results.csv + md5sum: a87740818ab4de69a758fc75d7b879dd