From 292e8eceb9616b5b85df28fd72231a3aa73d50a5 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Wed, 4 Aug 2021 11:06:08 +0200 Subject: [PATCH] module: MALT/RUN (#646) * Specify more guidelines on input channels * Linting * Updates based on code review * Update README.md * Fix broken sentence * Add MALT with incomplete tests * Parameter typo fix * Clean up test yaml * Finish MALT module prior UNZIP and MALT_BUILD modiules * Add required modules for tests * Sync test out with malt-build * Fix input parameters in tests based on final build module * Update modules/malt/run/meta.yml Co-authored-by: Gregor Sturm Co-authored-by: Gregor Sturm --- modules/malt/run/functions.nf | 68 +++++++++++++++++++++++++++++++++ modules/malt/run/main.nf | 54 ++++++++++++++++++++++++++ modules/malt/run/meta.yml | 53 +++++++++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/malt/run/main.nf | 21 ++++++++++ tests/modules/malt/run/test.yml | 11 ++++++ 6 files changed, 211 insertions(+) create mode 100644 modules/malt/run/functions.nf create mode 100644 modules/malt/run/main.nf create mode 100644 modules/malt/run/meta.yml create mode 100644 tests/modules/malt/run/main.nf create mode 100644 tests/modules/malt/run/test.yml diff --git a/modules/malt/run/functions.nf b/modules/malt/run/functions.nf new file mode 100644 index 00000000..da9da093 --- /dev/null +++ b/modules/malt/run/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)}/$args.filename" + } + } +} diff --git a/modules/malt/run/main.nf b/modules/malt/run/main.nf new file mode 100644 index 00000000..7b327d6e --- /dev/null +++ b/modules/malt/run/main.nf @@ -0,0 +1,54 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process MALT_RUN { + + label 'process_high_memory' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::malt=0.5.2" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/malt:0.5.2--0" + } else { + container "quay.io/biocontainers/malt:0.5.2--0" + } + + input: + path fastqs + val mode + path index + + output: + path "*.rma6" , emit: rma6 + path "*.{tab,text,sam}", optional:true, emit: alignments + path "*.log" , emit: log + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def avail_mem = 6 + if (!task.memory) { + log.info '[MALT_RUN] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.' + } else { + avail_mem = task.memory.giga + } + + """ + malt-run \\ + -J-Xmx${avail_mem}g \\ + -t ${task.cpus} \\ + -v \\ + -o . \\ + $options.args \\ + --inFile ${fastqs.join(' ')} \\ + -m $mode \\ + --index $index/ |&tee malt-run.log + + echo \$(malt-run --help 2>&1) | grep -o 'version.* ' | cut -f 1 -d ',' | cut -f2 -d ' ' > ${software}.version.txt + """ +} diff --git a/modules/malt/run/meta.yml b/modules/malt/run/meta.yml new file mode 100644 index 00000000..30421a48 --- /dev/null +++ b/modules/malt/run/meta.yml @@ -0,0 +1,53 @@ +name: malt_run +description: MALT, an acronym for MEGAN alignment tool, is a sequence alignment and analysis tool designed for processing high-throughput sequencing data, especially in the context of metagenomics. +keywords: + - malt + - alignment + - metagenomics + - ancient DNA + - aDNA + - palaeogenomics + - archaeogenomics + - microbiome +tools: + - malt: + description: A tool for mapping metagenomic data + homepage: https://www.wsi.uni-tuebingen.de/lehrstuehle/algorithms-in-bioinformatics/software/malt/ + documentation: https://software-ab.informatik.uni-tuebingen.de/download/malt/manual.pdf + tool_dev_url: None + doi: "10.1038/s41559-017-0446-6" + licence: ['GPL v3'] + +input: + - fastqs: + type: file + description: Input FASTQ files + pattern: "*.{fastq.gz,fq.gz}" + - mode: + type: string + description: Program mode + pattern: 'Unknown|BlastN|BlastP|BlastX|Classifier' + - index: + type: directory + description: Index/database directory from malt-build + pattern: '*/' +output: + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - rma6: + type: file + description: MEGAN6 RMA6 file + pattern: "*.rma6" + - sam: + type: file + description: Alignment files in Tab, Text or MEGAN-compatible SAM format + pattern: "*.{tab,txt,sam}" + - log: + type: file + description: Log of verbose MALT stdout + pattern: "malt-run.log" + +authors: + - "@jfy133" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index dffe106a..39b267c7 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -478,6 +478,10 @@ malt/build: - modules/malt/build/** - tests/modules/malt/build_test/** +malt/run: + - modules/malt/run/** + - tests/modules/malt/run/** + mash/sketch: - modules/mash/sketch/** - tests/modules/mash/sketch/** diff --git a/tests/modules/malt/run/main.nf b/tests/modules/malt/run/main.nf new file mode 100644 index 00000000..6292ca61 --- /dev/null +++ b/tests/modules/malt/run/main.nf @@ -0,0 +1,21 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { UNZIP } from '../../../../modules/unzip/main.nf' addParams( options: [:] ) +include { MALT_BUILD } from '../../../../modules/malt/build/main.nf' addParams( options: [:] ) +include { MALT_RUN } from '../../../../modules/malt/run/main.nf' addParams( options: [:] ) + +workflow test_malt_run { + + fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + gff = file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true) + seq_type = "DNA" + map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) + input = file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) + mode = "BlastN" + + UNZIP ( map_db ) + MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive ) + MALT_RUN ( input, mode, MALT_BUILD.out.index ) +} diff --git a/tests/modules/malt/run/test.yml b/tests/modules/malt/run/test.yml new file mode 100644 index 00000000..cc6f5fac --- /dev/null +++ b/tests/modules/malt/run/test.yml @@ -0,0 +1,11 @@ +## TODO nf-core: Please run the following command to build this file: +# nf-core modules create-test-yml malt/run +- name: malt run + command: nextflow run ./tests/modules/malt/run -entry test_malt_run -c tests/config/nextflow.config + tags: + - malt + - malt/run + files: + - path: output/malt/test_1.rma6 + - path: output/malt/malt-run.log +