From 9842a1083366a85a312458454d9b35bb1b5772cd Mon Sep 17 00:00:00 2001 From: JIANHONG OU Date: Thu, 27 May 2021 13:15:54 -0400 Subject: [PATCH] Pairtools parse (#521) * add software/pairtools * create a branch for pairtools/parse * fix the issue of bioconda output is different from docker. * remove customized code from test. Co-authored-by: Harshil Patel --- software/pairtools/parse/functions.nf | 68 +++++++++++++++++++++++++ software/pairtools/parse/main.nf | 44 ++++++++++++++++ software/pairtools/parse/meta.yml | 48 +++++++++++++++++ tests/config/pytest_software.yml | 4 ++ tests/software/pairtools/parse/main.nf | 14 +++++ tests/software/pairtools/parse/test.yml | 9 ++++ 6 files changed, 187 insertions(+) create mode 100644 software/pairtools/parse/functions.nf create mode 100644 software/pairtools/parse/main.nf create mode 100644 software/pairtools/parse/meta.yml create mode 100644 tests/software/pairtools/parse/main.nf create mode 100644 tests/software/pairtools/parse/test.yml diff --git a/software/pairtools/parse/functions.nf b/software/pairtools/parse/functions.nf new file mode 100644 index 00000000..da9da093 --- /dev/null +++ b/software/pairtools/parse/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)}/$args.filename" + } + } +} diff --git a/software/pairtools/parse/main.nf b/software/pairtools/parse/main.nf new file mode 100644 index 00000000..ad3169e1 --- /dev/null +++ b/software/pairtools/parse/main.nf @@ -0,0 +1,44 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process PAIRTOOLS_PARSE { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::pairtools=0.3.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/pairtools:0.3.0--py37hb9c2fc3_5" + } else { + container "quay.io/biocontainers/pairtools:0.3.0--py37hb9c2fc3_5" + } + + input: + tuple val(meta), path(bam) + path chromsizes + + output: + tuple val(meta), path("*.pairsam.gz") , emit: pairsam + tuple val(meta), path("*.pairsam.stat"), emit: stat + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + pairtools \\ + parse \\ + -c $chromsizes \\ + $options.args \\ + --output-stats ${prefix}.pairsam.stat \\ + -o ${prefix}.pairsam.gz \\ + $bam + + echo \$(pairtools --version 2>&1) | sed 's/pairtools.*version //' > ${software}.version.txt + """ +} diff --git a/software/pairtools/parse/meta.yml b/software/pairtools/parse/meta.yml new file mode 100644 index 00000000..311aa0ec --- /dev/null +++ b/software/pairtools/parse/meta.yml @@ -0,0 +1,48 @@ +name: pairtools_parse +description: Find ligation junctions in .sam, make .pairs +keywords: + - parse +tools: + - pairtools: + description: CLI tools to process mapped Hi-C data + homepage: http://pairtools.readthedocs.io/ + documentation: http://pairtools.readthedocs.io/ + tool_dev_url: https://github.com/mirnylab/pairtools + doi: "" + licence: ['MIT'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - chromsizes: + type: file + description: chromosome size file + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - pairsam: + type: file + description: parsed pair file + pattern: "*.{pairsam.gz}" + - stat: + type: file + description: stats of the pairs + pattern: "*.{pairsam.stat}" + +authors: + - "@jianhong" diff --git a/tests/config/pytest_software.yml b/tests/config/pytest_software.yml index 85a42f4b..ffb08197 100644 --- a/tests/config/pytest_software.yml +++ b/tests/config/pytest_software.yml @@ -463,6 +463,10 @@ pairtools/dedup: - software/pairtools/dedup/** - tests/software/pairtools/dedup/** +pairtools/parse: + - software/pairtools/parse/** + - tests/software/pairtools/parse/** + pangolin: - software/pangolin/** - tests/software/pangolin/** diff --git a/tests/software/pairtools/parse/main.nf b/tests/software/pairtools/parse/main.nf new file mode 100644 index 00000000..32a2db56 --- /dev/null +++ b/tests/software/pairtools/parse/main.nf @@ -0,0 +1,14 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { PAIRTOOLS_PARSE } from '../../../../software/pairtools/parse/main.nf' addParams( options: ['suffix':'.raw'] ) + +workflow test_pairtools_parse { + + input = [ [ id:'test', single_end:false ], // meta map + file("https://raw.githubusercontent.com/open2c/pairtools/master/tests/data/mock.sam", checkIfExists: true) ] + sizes = file("https://raw.githubusercontent.com/open2c/pairtools/master/tests/data/mock.chrom.sizes", checkIfExists:true) + + PAIRTOOLS_PARSE ( input, sizes ) +} diff --git a/tests/software/pairtools/parse/test.yml b/tests/software/pairtools/parse/test.yml new file mode 100644 index 00000000..91e1ab68 --- /dev/null +++ b/tests/software/pairtools/parse/test.yml @@ -0,0 +1,9 @@ +- name: pairtools parse test_pairtools_parse + command: nextflow run tests/software/pairtools/parse -entry test_pairtools_parse -c tests/config/nextflow.config + tags: + - pairtools + - pairtools/parse + files: + - path: output/pairtools/test.raw.pairsam.gz + - path: output/pairtools/test.raw.pairsam.stat + md5sum: 11e90f346f855ffd750c7c348ac1d456