From ef811d952bc21f4e26a60fd96d57979ca4fb6ce7 Mon Sep 17 00:00:00 2001 From: Mei Wu <25568561+projectoriented@users.noreply.github.com> Date: Mon, 28 Feb 2022 14:23:12 +0100 Subject: [PATCH] bcftools/annotate ready2go (#1291) * bcf annotate ready2go * edited output name * fixed output * updated bcftools ver * changed contain output string * removed contain key entirely * fixed md5sum for test.yml Co-authored-by: Robert A. Petit III Co-authored-by: Sateesh <33637490+sateeshperi@users.noreply.github.com> --- modules/bcftools/annotate/main.nf | 42 +++++++++++++++++ modules/bcftools/annotate/meta.yml | 45 +++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/bcftools/annotate/main.nf | 14 ++++++ .../modules/bcftools/annotate/nextflow.config | 5 +++ tests/modules/bcftools/annotate/test.yml | 9 ++++ 6 files changed, 119 insertions(+) create mode 100644 modules/bcftools/annotate/main.nf create mode 100644 modules/bcftools/annotate/meta.yml create mode 100644 tests/modules/bcftools/annotate/main.nf create mode 100644 tests/modules/bcftools/annotate/nextflow.config create mode 100644 tests/modules/bcftools/annotate/test.yml diff --git a/modules/bcftools/annotate/main.nf b/modules/bcftools/annotate/main.nf new file mode 100644 index 00000000..437baaf3 --- /dev/null +++ b/modules/bcftools/annotate/main.nf @@ -0,0 +1,42 @@ +process BCFTOOLS_ANNOTATE { + tag "$meta.id" + label 'process_low' + + conda (params.enable_conda ? "bioconda::bcftools=1.15" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/bcftools:1.15--haf5b3da_0': + 'quay.io/biocontainers/bcftools:1.15--haf5b3da_0' }" + + input: + tuple val(meta), path(input) + + output: + tuple val(meta), path("*_annotated.vcf.gz"), optional:true , emit: vcf + tuple val(meta), path("*_annotated.bcf") , optional:true , emit: bcf + 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}" + + def matcher = input =~ /vcf/ + def output_suffix = matcher ? "vcf.gz" : "bcf" + def output_type_compressed = matcher ? "z" : "b" + """ + bcftools \\ + annotate \\ + $args \\ + --output ${prefix}_annotated.${output_suffix} \\ + --output-type $output_type_compressed \\ + --threads $task.cpus \\ + $input + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/bcftools/annotate/meta.yml b/modules/bcftools/annotate/meta.yml new file mode 100644 index 00000000..3ed124d5 --- /dev/null +++ b/modules/bcftools/annotate/meta.yml @@ -0,0 +1,45 @@ +name: bcftools_annotate +description: Add or remove annotations. +keywords: + - bcftools + - annotate + - vcf + - remove + - add +tools: + - annotate: + description: Add or remove annotations. + homepage: http://samtools.github.io/bcftools/bcftools.html + documentation: https://samtools.github.io/bcftools/bcftools.html#annotate + doi: 10.1093/bioinformatics/btp352 + licence: ['MIT'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - input: + type: files + description: Query VCF or BCF file, can be either uncompressed or compressed +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" + - vcf: + type: file + description: Compressed annotated VCF file + pattern: "*_annotated.vcf.gz" + - bcf: + type: file + description: Compressed annotated BCF file + pattern: "*_annotated.bcf" +authors: + - "@projectoriented" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index f4ed22c8..c553b9ce 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -98,6 +98,10 @@ bbmap/index: - modules/bbmap/index/** - tests/modules/bbmap/index/** +bcftools/annotate: + - modules/bcftools/annotate/** + - tests/modules/bcftools/annotate/** + bcftools/concat: - modules/bcftools/concat/** - tests/modules/bcftools/concat/** diff --git a/tests/modules/bcftools/annotate/main.nf b/tests/modules/bcftools/annotate/main.nf new file mode 100644 index 00000000..2f2b66c9 --- /dev/null +++ b/tests/modules/bcftools/annotate/main.nf @@ -0,0 +1,14 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { BCFTOOLS_ANNOTATE } from '../../../../modules/bcftools/annotate/main.nf' + +workflow test_bcftools_annotate { + + input = [ + [ id:'test_compressed', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ] + + BCFTOOLS_ANNOTATE ( input ) +} diff --git a/tests/modules/bcftools/annotate/nextflow.config b/tests/modules/bcftools/annotate/nextflow.config new file mode 100644 index 00000000..2670da17 --- /dev/null +++ b/tests/modules/bcftools/annotate/nextflow.config @@ -0,0 +1,5 @@ +process { + ext.args = "-x ID,INFO/DP,FORMAT/DP" + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} \ No newline at end of file diff --git a/tests/modules/bcftools/annotate/test.yml b/tests/modules/bcftools/annotate/test.yml new file mode 100644 index 00000000..43537180 --- /dev/null +++ b/tests/modules/bcftools/annotate/test.yml @@ -0,0 +1,9 @@ +- name: bcftools annotate test_bcftools_annotate + command: nextflow run tests/modules/bcftools/annotate -entry test_bcftools_annotate -c tests/config/nextflow.config + tags: + - bcftools/annotate + - bcftools + files: + - path: output/bcftools/test_compressed_annotated.vcf.gz + - path: output/bcftools/versions.yml + md5sum: b647b465acc221f6fe6fbcc319724eed