New module: Vsearch sintax (#2094)

* Add vsearch sintax process

* Add tests for vsearch sintax

* Add vsearch sintax process

* Add tests for vsearch sintax

* Update format with prettier

* Remove trailing whitespace

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

modules/vsearch/sintax/main.nf

@@ -0,0 +1,38 @@
+process VSEARCH_SINTAX {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::vsearch=2.21.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vsearch:2.21.1--h95f258a_0':
+        'quay.io/biocontainers/vsearch:2.21.1--h95f258a_0' }"
+
+    input:
+    tuple val(meta), path(queryfasta)
+    path db
+
+    output:
+    tuple val(meta), path('*.tsv')   , optional: true, emit: tsv
+    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}"
+
+    """
+    vsearch \\
+        --sintax $queryfasta \\
+        --db $db \\
+        --threads $task.cpus \\
+        $args \\
+        --tabbedout ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vsearch: \$(vsearch --version 2>&1 | head -n 1 | sed 's/vsearch //g' | sed 's/,.*//g' | sed 's/^v//' | sed 's/_.*//')
+    END_VERSIONS
+    """
+}

modules/vsearch/sintax/meta.yml

@@ -0,0 +1,39 @@
+name: "vsearch_sintax"
+description: Taxonomic classification using the sintax algorithm.
+keywords:
+  - vsearch
+  - sintax
+tools:
+  - "vsearch":
+      description: "VSEARCH is a versatile open-source tool for microbiome analysis, including chimera detection, clustering, dereplication and rereplication, extraction, FASTA/FASTQ/SFF file processing, masking, orienting, pair-wise alignment, restriction site cutting, searching, shuffling, sorting, subsampling, and taxonomic classification of amplicon sequences for metagenomics, genomics, and population genetics. (USEARCH alternative)"
+      homepage: "https://github.com/torognes/vsearch"
+      documentation: "None"
+      tool_dev_url: "https://github.com/torognes/vsearch"
+      doi: "doi: 10.7717/peerj.2584"
+      licence: "['GPL v3-or-later OR BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: Groovy Map containing query file information e.g. [ id:'test' ]
+  - queryfasta:
+      type: file
+      description: Query sequences in FASTA or FASTQ format
+      pattern: "*.{fasta,fa,fna,faa,fastq,fq}"
+  - db:
+      type: file
+      description: Reference database file in FASTA or UDB format
+      pattern: "*"
+
+output:
+  - tsv:
+      type: file
+      description: Results written to tab-delimited file
+      pattern: "*.{tsv}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@jtangrot"

tests/config/pytest_modules.yml

@@ -2452,6 +2452,10 @@ vcftools:
   - modules/vcftools/**
   - tests/modules/vcftools/**
 
+vsearch/sintax:
+  - modules/vsearch/sintax/**
+  - tests/modules/vsearch/sintax/**
+
 vsearch/usearchglobal:
   - modules/vsearch/usearchglobal/**
   - tests/modules/vsearch/usearchglobal/**

tests/modules/vsearch/sintax/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { VSEARCH_SINTAX } from '../../../../modules/vsearch/sintax/main.nf'
+
+workflow test_vsearch_sintax {
+    
+    query = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    db = file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true)
+
+    VSEARCH_SINTAX ( [[id:'test'], query], db )
+}

tests/modules/vsearch/sintax/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/vsearch/sintax/test.yml

@@ -0,0 +1,8 @@
+- name: vsearch sintax test_vsearch_sintax
+  command: nextflow run ./tests/modules/vsearch/sintax -entry test_vsearch_sintax -c ./tests/config/nextflow.config  -c ./tests/modules/vsearch/sintax/nextflow.config
+  tags:
+    - vsearch
+    - vsearch/sintax
+  files:
+    - path: output/vsearch/test.tsv
+      md5sum: 93bc75fb89343e23fbae971df157b14a