From c74300a49a90b650aa909264782f248223951798 Mon Sep 17 00:00:00 2001 From: kohjy-ag Date: Fri, 20 May 2022 13:18:31 +0800 Subject: [PATCH] humann8 --- modules/humann/main.nf | 76 ++++++++++++++++++++++++++++ modules/humann/meta.yml | 51 +++++++++++++++++++ tests/modules/humann/main.nf | 18 +++++++ tests/modules/humann/nextflow.config | 5 ++ tests/modules/humann/test.yml | 7 +++ 5 files changed, 157 insertions(+) create mode 100644 modules/humann/main.nf create mode 100644 modules/humann/meta.yml create mode 100644 tests/modules/humann/main.nf create mode 100644 tests/modules/humann/nextflow.config create mode 100644 tests/modules/humann/test.yml diff --git a/modules/humann/main.nf b/modules/humann/main.nf new file mode 100644 index 000000000000..81f46e29dd40 --- /dev/null +++ b/modules/humann/main.nf @@ -0,0 +1,76 @@ +// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :) +// https://github.com/nf-core/modules/tree/master/modules +// You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace: +// https://nf-co.re/join +// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters. +// All other parameters MUST be provided using the "task.ext" directive, see here: +// https://www.nextflow.io/docs/latest/process.html#ext +// where "task.ext" is a string. +// Any parameters that need to be evaluated in the context of a particular sample +// e.g. single-end/paired-end data MUST also be defined and evaluated appropriately. +// TODO nf-core: Software that can be piped together SHOULD be added to separate module files +// unless there is a run-time, storage advantage in implementing in this way +// e.g. it's ok to have a single module for bwa to output BAM instead of SAM: +// bwa mem | samtools view -B -T ref.fasta +// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty +// list (`[]`) instead of a file can be used to work around this issue. + +process HUMANN { + tag "$meta.id" + label 'process_low' + + // TODO nf-core: List required Conda package(s). + // Software MUST be pinned to channel (i.e. "bioconda"), version (i.e. "1.10"). + // For Conda, the build (i.e. "h9402c20_2") must be EXCLUDED to support installation on different operating systems. + // TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below. + conda (params.enable_conda ? "bioconda::humann=3.0.0" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/humann:3.0.0--pyh5e36f6f_1': + 'quay.io/biocontainers/humann:3.0.0--pyh5e36f6f_1' }" + + input: + // TODO nf-core: Where applicable all sample-specific information e.g. "id", "single_end", "read_group" + // MUST be provided as an input via a Groovy Map called "meta". + // This information may not be required in some instances e.g. indexing reference genome files: + // https://github.com/nf-core/modules/blob/master/modules/bwa/index/main.nf + // TODO nf-core: Where applicable please provide/convert compressed files as input/output + // e.g. "*.fastq.gz" and NOT "*.fastq", "*.bam" and NOT "*.sam" etc. + tuple val(meta), path(sample), path(nt),path(protein),path(metadb) + + output: + // TODO nf-core: Named file extensions MUST be emitted for ALL output channels + tuple val(meta), path("outdir"), emit: outdir + // TODO nf-core: List additional required output channels/values here + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + // TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10 + // If the software is unable to output a version number on the command-line then it can be manually specified + // e.g. https://github.com/nf-core/modules/blob/master/modules/homer/annotatepeaks/main.nf + // Each software used MUST provide the software name and version number in the YAML version file (versions.yml) + // TODO nf-core: It MUST be possible to pass additional parameters to the tool as a command-line string via the "task.ext.args" directive + // TODO nf-core: If the tool supports multi-threading then you MUST provide the appropriate parameter + // using the Nextflow "task" variable e.g. "--threads $task.cpus" + // TODO nf-core: Please replace the example samtools command below with your module's command + // TODO nf-core: Please indent the command appropriately (4 spaces!!) to help with readability ;) + """ + humann \\ + -o outdir \\ + --threads $task.cpus \\ + -i $sample \\ + --nucleotide-database $nt \\ + --protein-database $protein \\ + --metaphlan-options "-x $prefix --bowtie2db $metadb " + + + cat <<-END_VERSIONS > versions.yml + humann: \$(echo \$(humann --version 2>&1) ) + END_VERSIONS + + """ +} diff --git a/modules/humann/meta.yml b/modules/humann/meta.yml new file mode 100644 index 000000000000..988217818ea4 --- /dev/null +++ b/modules/humann/meta.yml @@ -0,0 +1,51 @@ +name: "humann" +## TODO nf-core: Add a description of the module and list keywords +description: write your description here +keywords: + - sort +tools: + - "humann": + ## TODO nf-core: Add a description and other details for the software below + description: "HUMAnN: The HMP Unified Metabolic Analysis Network, version 3" + homepage: "http://huttenhower.sph.harvard.edu/humann" + documentation: "http://huttenhower.sph.harvard.edu/humann" + tool_dev_url: "https://github.com/biobakery/humann" + doi: "" + licence: "['MIT']" + +## TODO nf-core: Add a description of all of the variables used as input +input: + # Only when we have meta + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + # + ## TODO nf-core: Delete / customise this example input + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + +## TODO nf-core: Add a description of all of the variables used as output +output: + #Only when we have meta + - 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" + ## TODO nf-core: Delete / customise this example output + - bam: + type: file + description: Sorted BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + +authors: + - "@kohjy-ag" diff --git a/tests/modules/humann/main.nf b/tests/modules/humann/main.nf new file mode 100644 index 000000000000..87896a4c87e9 --- /dev/null +++ b/tests/modules/humann/main.nf @@ -0,0 +1,18 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { HUMANN } from '../../../modules/humann/main.nf' + +workflow test_humann { + + input = [ + [ id:'mpa_v30_CHOCOPhlAn_201901' ], // meta map + file('https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/umi-dna/qiaseq/SRR7545951-small_1.fastq.gz', checkIfExists: true), + file('chocophlan', checkIfExists: true), + file('uniref', checkIfExists: true), + file('metaphlandb', checkIfExists: true) + ] + + HUMANN ( input ) +} diff --git a/tests/modules/humann/nextflow.config b/tests/modules/humann/nextflow.config new file mode 100644 index 000000000000..50f50a7a3579 --- /dev/null +++ b/tests/modules/humann/nextflow.config @@ -0,0 +1,5 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} \ No newline at end of file diff --git a/tests/modules/humann/test.yml b/tests/modules/humann/test.yml new file mode 100644 index 000000000000..10542d2baa8d --- /dev/null +++ b/tests/modules/humann/test.yml @@ -0,0 +1,7 @@ +- name: humann test_humann + command: nextflow run tests/modules/humann -entry test_humann -c tests/config/nextflow.config + tags: + - humann + files: + - path: output/humann/versions.yml + md5sum: f6ffecc08eaf8ab67253798065a54158