From 1bc3f6cf39dc0365cf1453814cfa0d89b0465de2 Mon Sep 17 00:00:00 2001 From: Abhinav Sharma Date: Wed, 15 Sep 2021 17:36:49 +0200 Subject: [PATCH] module: snp-dists (#697) * initial commit for draft [ci skip] * baseline code [ci skip] * update the test [ci skip] * finalize the description and all tests passing * accomodate optional args [ci skip] * fix the leftover todo statement * Update modules/snpdists/main.nf Co-authored-by: Harshil Patel --- modules/snpdists/functions.nf | 68 +++++++++++++++++++++++++++++++++ modules/snpdists/main.nf | 38 ++++++++++++++++++ modules/snpdists/meta.yml | 41 ++++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/snpdists/main.nf | 13 +++++++ tests/modules/snpdists/test.yml | 7 ++++ 6 files changed, 171 insertions(+) create mode 100644 modules/snpdists/functions.nf create mode 100644 modules/snpdists/main.nf create mode 100644 modules/snpdists/meta.yml create mode 100644 tests/modules/snpdists/main.nf create mode 100644 tests/modules/snpdists/test.yml diff --git a/modules/snpdists/functions.nf b/modules/snpdists/functions.nf new file mode 100644 index 00000000..da9da093 --- /dev/null +++ b/modules/snpdists/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${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)}/$args.filename" + } + } +} diff --git a/modules/snpdists/main.nf b/modules/snpdists/main.nf new file mode 100644 index 00000000..c103bb33 --- /dev/null +++ b/modules/snpdists/main.nf @@ -0,0 +1,38 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SNPDISTS { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::snp-dists=0.8.2" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/snp-dists:0.8.2--h5bf99c6_0" + } else { + container "quay.io/biocontainers/snp-dists:0.8.2--h5bf99c6_0" + } + + input: + tuple val(meta), path(alignment) + + output: + tuple val(meta), path("*.tsv"), emit: tsv + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + snp-dists \\ + $options.args \\ + $alignment > ${prefix}.tsv + + echo \$(snp-dists -v 2>&1) | sed 's/snp-dists //;' > ${software}.version.txt + """ +} diff --git a/modules/snpdists/meta.yml b/modules/snpdists/meta.yml new file mode 100644 index 00000000..590d034a --- /dev/null +++ b/modules/snpdists/meta.yml @@ -0,0 +1,41 @@ +name: snpdists +description: Pairwise SNP distance matrix from a FASTA sequence alignment +keywords: + - snp-dists + - distance-matrix +tools: + - snpdists: + description: Convert a FASTA alignment to SNP distance matrix + homepage: https://github.com/tseemann/snp-dists + documentation: https://github.com/tseemann/snp-dists + tool_dev_url: https://github.com/tseemann/snp-dists + doi: "" + licence: ['GPL v3'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - alignment: + type: file + description: The input FASTA sequence alignment file + pattern: "*.{fasta,fasta.gz}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - tsv: + type: file + description: The output TSV file containing SNP distance matrix + pattern: "*.tsv" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@abhi18av" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index 6d1f5dac..48a68a64 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -831,6 +831,10 @@ shovill: - modules/shovill/** - tests/modules/shovill/** +snpdists: + - modules/snpdists/** + - tests/modules/snpdists/** + snpeff: - modules/snpeff/** - tests/modules/snpeff/** diff --git a/tests/modules/snpdists/main.nf b/tests/modules/snpdists/main.nf new file mode 100644 index 00000000..8a29effa --- /dev/null +++ b/tests/modules/snpdists/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { SNPDISTS } from '../../../modules/snpdists/main.nf' addParams( options: [:] ) + +workflow test_snpdists { + + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['genome']['informative_sites_fas'], checkIfExists: true) ] + + SNPDISTS ( input ) +} diff --git a/tests/modules/snpdists/test.yml b/tests/modules/snpdists/test.yml new file mode 100644 index 00000000..d140ce6e --- /dev/null +++ b/tests/modules/snpdists/test.yml @@ -0,0 +1,7 @@ +- name: snpdists + command: nextflow run ./tests/modules/snpdists -entry test_snpdists -c tests/config/nextflow.config + tags: + - snpdists + files: + - path: output/snpdists/test.tsv + md5sum: 0018e5ec43990eb16abe2411fff4e47e