adding chewbbaca/createschema module

modules/nf-core/chewbbaca/createschema/main.nf

@@ -0,0 +1,63 @@
+process CHEWBBACA_CREATESCHEMA {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "bioconda::chewbbaca=3.3.1"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/chewbbaca:3.3.1--pyhdfd78af_0':
+        'biocontainers/chewbbaca:3.3.1--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta, stageAs: "input_genomes/*")
+    path prodigal_tf
+    path cds
+
+    output:
+    path 'results/*'                                   , emit: schema
+    path "results/cds_coordinates.tsv"                 , emit: cds_coordinates
+    path "results/invalid_cds.txt"                     , emit: invalid_cds
+    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 schema = "--n ${prefix}"
+    def prodigal_tf = prodigal_tf ? "--ptf ${prodigal_tf}" : ""
+    def cds = cds ? "--cds ${cds}" : ""
+
+    """
+    find ./input_genomes/ -name "*.gz" | sed 's/.gz//' | xargs -I {} bash -c 'gzip -cdf {}.gz > {}'
+
+    chewie \\
+        CreateSchema \\
+        -i input_genomes/ \\
+        -o results \\
+        $schema \\
+        $args \\
+        $prodigal_tf \\
+        $cds \\
+        --cpu $task.cpus
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        chewbbaca: \$(echo \$(chewie --version 2>&1 | sed 's/^.*chewBBACA version: //g; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def schema = "--n ${prefix}"
+
+    """
+    mkdir -p results/$schema
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        chewbbaca: \$(echo \$(chewie --version 2>&1 | sed 's/^.*chewBBACA version: //g; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/chewbbaca/createschema/meta.yml

@@ -0,0 +1,63 @@
+---
+name: "chewbbaca_createschema"
+description: Create a schema to determine the allelic profiles of a genome
+keywords:
+  - cgMLST
+  - WGS
+  - genomics
+tools:
+  - "chewbbaca":
+      description: "A complete suite for gene-by-gene schema creation and strain identification."
+      homepage: "https://chewbbaca.readthedocs.io/en/latest/index.html"
+      documentation: "https://chewbbaca.readthedocs.io/en/latest/index.html"
+      tool_dev_url: "https://github.com/B-UMMI/chewBBACA"
+      doi: "10.1099/mgen.0.000166"
+      licence: ["GPL v3"]
+
+## 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 ]`
+
+  - fasta:
+      type: directory
+      description: One or multiple FASTA files to create schema from
+      pattern: "*.{fasta,fa,fas,fna,fasta.gz,fa.gz,fas.gz,fna.gz}"
+
+  - prodigal_tf:
+      type: file
+      description: File containing the prodigal training file
+      pattern: "*.ptf"
+
+  - cds:
+      type: file
+      description: File containing the prodigal cds file
+      pattern: "*.cds"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - schema_dir:
+      type: directory
+      description: schema directory
+      pattern: "*/"
+
+  - tsv:
+      type: file
+      description: file contains the coordinates of the CDS in the input sample
+      pattern: "*_cds_coordinates.tsv"
+  - txt:
+      type: file
+      description: file contains the list of alleles predicted by Prodigal that were excluded
+      pattern: "*_invalid_cds.txt"
+
+authors:
+  - "@anwarMZ"

tests/config/pytest_modules.yml

@@ -615,6 +615,10 @@ checkv/updatedatabase:
   - modules/nf-core/checkv/updatedatabase/**
   - tests/modules/nf-core/checkv/updatedatabase/**
 
+chewbbaca/createschema:
+  - modules/nf-core/chewbbaca/createschema/**
+  - tests/modules/nf-core/chewbbaca/createschema/**
+
 chromap/chromap:
   - modules/nf-core/chromap/chromap/**
   - tests/modules/nf-core/chromap/chromap/**

tests/modules/nf-core/chewbbaca/createschema/main.nf

@@ -0,0 +1,40 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CHEWBBACA_CREATESCHEMA } from '../../../../../modules/nf-core/chewbbaca/createschema/main.nf'
+
+workflow test_chewbbaca_createschema {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true)]
+    ptf = []
+    cds = []
+
+    CHEWBBACA_CREATESCHEMA ( input, ptf, cds)
+}
+
+workflow test_chewbbaca_createschema_multi {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
+            file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)] ]
+    ptf = []
+    cds = []
+
+    CHEWBBACA_CREATESCHEMA ( input, ptf, cds)
+}
+
+workflow test_chewbbaca_createschema_gz {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
+            file(params.test_data['sarscov2']['genome']['genome_fasta_gz'], checkIfExists: true)] ]
+    ptf = []
+    cds = []
+
+    CHEWBBACA_CREATESCHEMA ( input, ptf, cds)
+}

tests/modules/nf-core/chewbbaca/createschema/nextflow.config

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