Merge pull request #1574 from jvhagey/srst2/srst2

new module: srst2/srst2

modules/srst2/srst2/main.nf

@@ -0,0 +1,47 @@
+process SRST2_SRST2 {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::srst2=0.2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/srst2%3A0.2.0--py27_2':
+        'quay.io/biocontainers/srst2:0.2.0--py27_2'}"
+
+    input:
+    tuple val(meta), path(fastq_s), path(db)
+
+    output:
+    tuple val(meta), path("*_genes_*_results.txt")               , optional:true, emit: gene_results
+    tuple val(meta), path("*_fullgenes_*_results.txt")           , optional:true, emit: fullgene_results
+    tuple val(meta), path("*_mlst_*_results.txt")                , optional:true, emit: mlst_results
+    tuple val(meta), path("*.pileup")                            ,                emit: pileup
+    tuple val(meta), path("*.sorted.bam")                        ,                emit: sorted_bam
+    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 read_s = meta.single_end ? "--input_se ${fastq_s}" : "--input_pe ${fastq_s[0]} ${fastq_s[1]}"
+    if (meta.db=="gene") {
+        database = "--gene_db ${db}"
+    } else if (meta.db=="mlst") {
+        database = "--mlst_db ${db}"
+    } else {
+        error "Please set meta.db to either \"gene\" or \"mlst\""
+    }
+    """
+    srst2 \\
+        ${read_s} \\
+        --threads $task.cpus \\
+        --output ${prefix} \\
+        ${database} \\
+        $args
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        srst2: \$(echo \$(srst2 --version 2>&1) | sed 's/srst2 //' ))
+    END_VERSIONS
+    """
+}

modules/srst2/srst2/meta.yml

@@ -0,0 +1,72 @@
+name: srst2_srst2
+description: |
+  Short Read Sequence Typing for Bacterial Pathogens is a program designed to take Illumina sequence data,
+  a MLST database and/or a database of gene sequences (e.g. resistance genes, virulence genes, etc)
+  and report the presence of STs and/or reference genes.
+keywords:
+  - mlst
+  - typing
+  - illumina
+tools:
+  - srst2:
+      description: "Short Read Sequence Typing for Bacterial Pathogens"
+      homepage: "http://katholt.github.io/srst2/"
+      documentation: "https://github.com/katholt/srst2/blob/master/README.md"
+      tool_dev_url: "https://github.com/katholt/srst2"
+      doi: "10.1186/s13073-014-0090-6"
+      licence: ["BSD"]
+
+input:
+  - meta:
+      type: map0.2.0-4
+      description: |
+        Groovy Map containing sample information
+        id: should be the identification number or sample name
+        single_end: should be true for single end data and false for paired in data
+        db: should be either 'gene' to use the --gene_db option or "mlst" to use the --mlst_db option
+        e.g. [ id:'sample', single_end:false , db:'gene']
+  - fasta:
+      type: file
+      description: |
+        gzipped fasta file. If files are NOT in
+        MiSeq format sample_S1_L001_R1_001.fastq.gz uses --forward and --reverse parameters; otherwise
+        default is _1, i.e. expect forward reads as sample_1.fastq.gz).
+      pattern: "*.fastq.gz"
+  - db:
+      type: file
+      description: Database in FASTA format
+      pattern: "*.fasta"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'sample', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - txt:
+      type: file
+      description: A detailed report, with one row per gene per sample described here github.com/katholt/srst2#gene-typing
+      pattern: "*_fullgenes_*_results.txt"
+  - txt:
+      type: file
+      description: A tabulated summary report of samples x genes.
+      pattern: "*_genes_*_results.txt"
+  - txt:
+      type: file
+      description: A tabulated summary report of mlst subtyping.
+      pattern: "*_mlst_*_results.txt"
+  - bam:
+      type: file
+      description: Sorted BAM file
+      pattern: "*.sorted.bam"
+  - pileup:
+      type: file
+      description: SAMtools pileup file
+      pattern: "*.pileup"
+
+authors:
+  - "@jvhagey"

tests/config/pytest_modules.yml

@@ -1775,6 +1775,10 @@ sratools/prefetch:
   - modules/sratools/prefetch/**
   - tests/modules/sratools/prefetch/**
 
+srst2/srst2:
+  - modules/srst2/srst2/**
+  - tests/modules/srst2/srst2/**
+
 ssuissero:
   - modules/ssuissero/**
   - tests/modules/ssuissero/**

tests/modules/srst2/srst2/main.nf

@@ -0,0 +1,53 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SRST2_SRST2 } from '../../../../modules/srst2/srst2/main.nf'
+
+workflow test_srst2_srst2_exit {
+
+    input = [
+        [ id:'test', single_end:false, db:"test"], // meta map
+        [ file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true),
+          file(params.test_data['bacteroides_fragilis']['illumina']['test1_2_fastq_gz'], checkIfExists: true) ],
+//        [("")]
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/resFinder_20180221_srst2.fasta')
+    ]
+
+    SRST2_SRST2(input)
+}
+
+workflow test_srst2_srst2_mlst {
+
+    input = [
+        [ id:'test', single_end:false, db:"mlst"], // meta map
+        [ file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/SRR9067271_1.fastq.gz", checkIfExists: true),
+          file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/SRR9067271_2.fastq.gz", checkIfExists: true) ],
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/MLST_DB.fas')
+    ]
+
+    SRST2_SRST2(input)
+}
+
+workflow test_srst2_srst2_paired_end {
+
+    input = [
+        [ id:'test', single_end:false, db:"gene"], // meta map
+        [ file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true),
+          file(params.test_data['bacteroides_fragilis']['illumina']['test1_2_fastq_gz'], checkIfExists: true) ],
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/resFinder_20180221_srst2.fasta')  // Change to params.test_data syntax after the data is included in tests/config/test_data.config
+    ]
+
+    SRST2_SRST2(input)
+}
+
+workflow test_srst2_srst2_single_end {
+
+    input = [
+        [ id:'test', single_end:true, db:"gene" ], // meta map
+        file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true),
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/resFinder_20180221_srst2.fasta')  // Change to params.test_data syntax after the data is included in tests/config/test_data.config
+    ]
+
+    SRST2_SRST2(input)
+}

tests/modules/srst2/srst2/nextflow.config

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

tests/modules/srst2/srst2/test.yml

@@ -0,0 +1,51 @@
+- name: srst2 srst2 test_srst2_srst2_exit #Testing pipeline exit when not meta.db
+  command: nextflow run tests/modules/srst2/srst2 -entry test_srst2_srst2_exit -c tests/config/nextflow.config
+  tags:
+    - srst2/srst2
+    - srst2
+  exit_code: 1
+
+- name: srst2 srst2 test_srst2_srst2_mlst
+  command: nextflow run tests/modules/srst2/srst2 -entry test_srst2_srst2_mlst -c tests/config/nextflow.config
+  tags:
+    - srst2/srst2
+    - srst2
+  files:
+    - path: output/srst2/test__SRR9067271.MLST_DB.pileup
+      contains:
+        - "dnaJ-1	2	C	17	.........,.......	FFFFFFFFFFFFFFFFF"
+    - path: output/srst2/test__SRR9067271.MLST_DB.sorted.bam
+    - path: output/srst2/test__mlst__MLST_DB__results.txt
+      md5sum: ec1b1f69933401d67c57f64cad11a098
+    - path: output/srst2/versions.yml
+      md5sum: a0c256a2fd3636069710b8ef22ee5ea7
+
+- name: srst2 srst2 test_srst2_srst2_paired_end
+  command: nextflow run tests/modules/srst2/srst2 -entry test_srst2_srst2_paired_end -c tests/config/nextflow.config
+  tags:
+    - srst2/srst2
+    - srst2
+  files:
+    - path: output/srst2/test__genes__resFinder_20180221_srst2__results.txt
+      md5sum: 099aa6cacec5524b311f606debdfb3a9
+    - path: output/srst2/test__test1.resFinder_20180221_srst2.pileup
+      md5sum: 64b512ff495b828c456405ec7b676ad1
+    - path: output/srst2/test__test1.resFinder_20180221_srst2.sorted.bam
+    - path: output/srst2/versions.yml
+      md5sum: b446a70f1a2b4f60757829bcd744a214
+
+- name: srst2 srst2 test_srst2_srst2_single_end
+  command: nextflow run tests/modules/srst2/srst2 -entry test_srst2_srst2_single_end -c tests/config/nextflow.config
+  tags:
+    - srst2/srst2
+    - srst2
+  files:
+    - path: output/srst2/test__fullgenes__resFinder_20180221_srst2__results.txt
+      md5sum: d0762ef8c38afd0e0a34cce52ed1a3db
+    - path: output/srst2/test__genes__resFinder_20180221_srst2__results.txt
+      md5sum: b8850c6644406d8b131e471ecc3f9013
+    - path: output/srst2/test__test1_1.resFinder_20180221_srst2.pileup
+      md5sum: 5f6279dc8124aa762a9dfe3d7a871277
+    - path: output/srst2/test__test1_1.resFinder_20180221_srst2.sorted.bam
+    - path: output/srst2/versions.yml
+      md5sum: 790fe00493c6634d17801a930073218b