Add a module for MashMap (#6208)

* Module for MashMap

* Fix mashmap based on PR feedback

- Adjust the test_data path format
- Fixed versions.yml, it was empy
- Added meta2 for the reference input channel

modules/nf-core/mashmap/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "mashmap"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::mashmap=3.1.3"

modules/nf-core/mashmap/main.nf

@@ -0,0 +1,48 @@
+process MASHMAP {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mashmap:3.1.3--h07ea13f_0':
+        'biocontainers/mashmap:3.1.3--h07ea13f_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    tuple val(meta2), path(reference)
+
+    output:
+    tuple val(meta), path("*.paf"), emit: paf
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mashmap -q ${fasta} \\
+    -r ${reference} \\
+    -t ${task.cpus} \\
+    -o ${prefix}.paf \\
+    ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mashmap: \$(mashmap --version 2>&1)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.paf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mashmap: \$(mashmap --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/mashmap/meta.yml

@@ -0,0 +1,57 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "mashmap"
+description: Mashmap is an approximate long read or contig mapper based on Jaccard similarity
+keywords:
+  - mapper
+  - aligner
+  - minhash
+  - kmer
+tools:
+  - "mashmap":
+      description: "A fast approximate aligner for long DNA sequences."
+      homepage: "https://github.com/marbl/MashMap"
+      documentation: "https://github.com/marbl/MashMap"
+      tool_dev_url: "https://github.com/marbl/MashMap"
+      doi: "10.1007/978-3-319-56970-3_5"
+      licence: ["Public Domain"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - fasta:
+      type: file
+      description: Input fasta file containing query sequences
+      pattern: "*.{fa,fasta,fa.gz,fasta.gz}"
+
+  - reference:
+      type: file
+      description: Input fasta file containing reference sequences
+      pattern: "*.{fa,fasta,fa.gz,fasta.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - paf:
+      type: file
+      description: Alignment in PAF format
+      pattern: "*.paf"
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@mberacochea"
+
+maintainers:
+  - "@mberacochea"

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

@@ -0,0 +1,69 @@
+nextflow_process {
+
+    name "Test Process MASHMAP"
+    script "../main.nf"
+    process "MASHMAP"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "mashmap"
+
+    test("Should align the contigs to the genome") {
+
+        when {
+            process {
+                """
+                // Query
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+                ]
+                // Reference
+                input[1] = [
+                    [ id:'sarscov2_genome' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.gz', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("Should align the contigs to the genome - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                // Query
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+                ]
+                // Reference
+                input[1] = [
+                    [ id:'sarscov2_genome' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.gz', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/mashmap/tests/main.nf.test.snap

@@ -0,0 +1,72 @@
+{
+    "Should align the contigs to the genome - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,3dccac8ea537122bd63488e9ad5737bf"
+                ],
+                "paf": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,3dccac8ea537122bd63488e9ad5737bf"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-08-17T09:26:01.404111"
+    },
+    "Should align the contigs to the genome": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paf:md5,170c0c1e438154d743c595aa511f7e6e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,3dccac8ea537122bd63488e9ad5737bf"
+                ],
+                "paf": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.paf:md5,170c0c1e438154d743c595aa511f7e6e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,3dccac8ea537122bd63488e9ad5737bf"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-08-17T09:25:33.715838"
+    }
+}

modules/nf-core/mashmap/tests/tags.yml

@@ -0,0 +1,2 @@
+mashmap:
+  - "modules/nf-core/mashmap/**"