New kma module

modules/nf-core/kma/kma/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+ - bioconda
+ - conda-forge
+dependencies:
+ - kma==1.4.15

modules/nf-core/kma/kma/main.nf

@@ -0,0 +1,66 @@
+process KMA {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kma:1.4.15--he4a0461_0' :
+        'biocontainers/kma:1.4.15--he4a0461_0' }"
+
+    input:
+    tuple val(meta) , path(reads)
+    tuple val(meta2), path(index)
+    val interleaved
+    val mat_format
+
+    output:
+    tuple val(meta), path("*.res"),     optional: true, emit: res
+    tuple val(meta), path("*.fsa"),     optional: true, emit: fsa
+    tuple val(meta), path("*.aln"),     optional: true, emit: aln
+    tuple val(meta), path("*.frag.gz"), optional: true, emit: frag
+    tuple val(meta), path("*.mat.gz"),  optional: true, emit: mat   // if mat_format == true
+    tuple val(meta), path("*.spa"),     optional: true, emit: spa   // if ext.args contains '-Sparse' (only output in this case)
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args            = task.ext.args ?: ''
+    def prefix          = task.ext.prefix ?: "${meta.id}.${meta2.id}.kma"
+    def input_style     = interleaved ? "-int ${reads}" : "-ipe ${reads}"
+    def create_mat      = mat_format ? "-matrix" : ''
+    """
+    INDEX=`find -L ./ -name "*.name" | sed 's/\\.name\$//'`
+
+    kma \\
+        ${input_style} \\
+        -o ${prefix} \\
+        -t_db \$INDEX \\
+        ${create_mat} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kma: \$(echo \$(kma -v 2>&1) | sed 's/^KMA-\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix      = task.ext.prefix ?: "${meta.id}.${meta2.id}.kma"
+    def create_mat  = mat_format ? "touch ${prefix}.mat.gz" : ''
+    def create_spa  = task.ext.args.contains('-Sparse') ? "touch ${prefix}.spa" : ''
+    """
+    touch ${prefix}.res \\
+    touch ${prefix}.fsa \\
+    touch ${prefix}.aln \\
+    touch ${prefix}.frag.gz \\
+    ${create_mat} \\
+    ${create_spa}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kma: \$(echo \$(kma -v 2>&1) | sed 's/^KMA-\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/kma/kma/meta.yml

@@ -0,0 +1,118 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "KMA"
+description: Aligning reads to a DB via KMA alignment
+keywords:
+  - fastq
+  - reads
+  - alignment
+  - kma
+tools:
+  - "kma":
+      description: "Rapid and precise alignment of raw reads against redundant databases with KMA"
+      homepage: "https://bitbucket.org/genomicepidemiology/kma/src/master/"
+      documentation: "https://bitbucket.org/genomicepidemiology/kma/src/master/"
+      tool_dev_url: "https://bitbucket.org/genomicepidemiology/kma/src/master/"
+      doi: "10.1186/s12859-018-2336-6"
+      licence:
+        ["http://www.apache.org/licenses/LICENSE-2.0"]
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'sample' ]
+    - reads:
+        type: file
+        description: FASTQ files
+        pattern: "*.{fastq,fq}"
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing reference index information
+          e.g. [ id:'reference' ]
+    - index:
+        type: file
+        description: kma database file generated via kma_index
+        pattern: "*.{comp.b,length.b,name,seq.b}"
+  - - interleaved:
+        type: boolean
+        description: use one interleaved fastq file (true) or two paired fastq files (false)
+        pattern: "true or false"
+  - - mat_format:
+        type: boolean
+        description: generate additional matrix file (true) or not (false)
+        pattern: "true or false"
+
+output:
+  - res:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.res':
+        type: file
+        description: A result overview giving the most common statistics for each mapped template.
+        pattern: "*.{res}"
+  - fsa:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.fsa':
+        type: file
+        description: The consensus sequences drawn from the alignments.
+        pattern: "*.{fsa}"
+  - aln:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.aln':
+        type: file
+        description: The consensus alignment of the reads against their template.
+        pattern: "*.{aln}"
+  - frag:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.frag.gz':
+        type: file
+        description: Mapping information on each mapped read, where the columns are read, number of equally well mapping templates, mapping score, start position, end position (w.r.t. template), the choosen template.
+        pattern: "*.{frag.gz}"
+  - mat:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.mat.gz':
+        type: file
+        description: Base counts on each position in each template, (only if -matrix is enabled).
+        pattern: "*.{mat.gz}"
+  - spa:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'reference' ]
+    - '*.spa':
+        type: file
+        description: Text file containing the top scoring references.
+        pattern: "*.{spa}"
+  - versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+
+authors:
+  - "@Krannich479"
+maintainers:
+  - "@Krannich479"

modules/nf-core/kma/kma/tests/main.nf.test

@@ -0,0 +1,84 @@
+nextflow_process {
+
+    name "Test Process KMA_KMA"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "kma"
+    tag "kma/kma"
+
+    script "../main.nf"
+    process "KMA_KMA"
+
+    setup {
+        run("KMA_INDEX") {
+            script "../../index/main.nf"
+            config "nextflow.config"
+
+            process {
+                """
+                input[0] = [
+                    [ id: 'MT192765.1', single_end:false ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+    }
+
+/*
+    test("sarscov2 - fasta") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'nfcore_testsample', single_end:false ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                    ]
+                input[1] = KMA_INDEX.out.db
+                input[2] = false
+                input[3] = false
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+*/
+
+/*
+    test("sarscov2 - fasta - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'MT192765.1', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+*/
+
+}

modules/nf-core/kma/kma/tests/nextflow.config

@@ -0,0 +1,11 @@
+process {
+
+    withName: 'KMA_INDEX' {
+        ext.args = '-Sparse'
+    }
+
+    withName: 'KMA' {
+        ext.args = '-1t1 -Sparse'
+    }
+
+}