adding kmergenie module

modules/nf-core/kmergenie/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::kmergenie=1.7051"

modules/nf-core/kmergenie/main.nf

@@ -0,0 +1,51 @@
+process KMERGENIE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/5f/5f4197eec51307131e6cb0170a7969eda60995b23942d050f7495dc4a530b118/data':
+        'community.wave.seqera.io/library/kmergenie:1.7051--675dfe5a4c7ea92b' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*_report.html"), emit: html
+    tuple val(meta), path("*.histo")      , emit: histo
+    tuple val(meta), path("*.dat")        ,emit: dat
+    tuple val(meta), path("*.pdf")        ,emit: pdf
+    tuple val("${task.process}"), val('kmergenie'), eval('kmergenie --version |& sed "1!d ; s/KmerGenie //"'), emit: versions_kmergenie, topic: versions
+
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def read_list = reads.join("\n")
+
+    """
+    echo "$read_list" > ${prefix}_reads.txt
+
+    kmergenie \\
+        $args \\
+        -o ${prefix} \\
+        -t $task.cpus \\
+        ${prefix}_reads.txt
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo $args
+
+    touch ${prefix}_report.html
+    touch ${prefix}*.histo
+    touch ${prefix}.dat
+    touch ${prefix}*.pdf
+    """
+}

modules/nf-core/kmergenie/meta.yml

@@ -0,0 +1,104 @@
+name: "kmergenie"
+description: KmerGenie estimates the best k-mer length for genome de novo
+  assembly
+keywords:
+  - k-mer
+  - count
+  - genome assembly
+tools:
+  - "kmergenie":
+      description: "KmerGenie estimates the best k-mer length for genome de novo assembly.
+        Given a set of reads, KmerGenie first computes the k-mer abundance histogram
+        for many values of k. Then, for each value of k, it predicts the number of distinct
+        genomic k-mers in the dataset, and returns the k-mer length which maximizes
+        this number."
+      homepage: "http://kmergenie.bx.psu.edu/"
+      documentation: "http://kmergenie.bx.psu.edu/"
+      tool_dev_url: "https://github.com/movingpictures83/KMerGenie"
+      doi: "10.1093/bioinformatics/btt310"
+      licence:
+        - "MIT License"
+      identifier: biotools:kmergenie
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Input reads in FastQ format
+        pattern: "*.{fastq.gz, fastq, fq.gz, fq}"
+        ontologies: []
+output:
+  html:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*_report.html":
+          type: file
+          description: html file containing all the plotted histograms obtained
+            from different kmer size
+          pattern: "*_report.html"
+          ontologies: []
+  histo:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.histo":
+          type: file
+          description: histogram files (text) obtained from individual kmer sizes
+          pattern: "*.histo"
+          ontologies: []
+  dat:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.dat":
+          type: file
+          description: text file containing number of kmer for kmer sizes and
+            recommended coverage cut-off
+          pattern: "*.dat"
+          ontologies: []
+  pdf:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.pdf":
+          type: file
+          description: histogram plots obtained from individual kmer sizes
+          pattern: "*.pdf"
+          ontologies: []
+  versions_kmergenie:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - kmergenie:
+          type: string
+          description: The name of the tool
+      - kmergenie --version |& sed "1!d ; s/KmerGenie //":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - kmergenie:
+          type: string
+          description: The name of the tool
+      - kmergenie --version |& sed "1!d ; s/KmerGenie //":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@LiaOb21"
+maintainers:
+  - "@LiaOb21"

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

@@ -0,0 +1,74 @@
+nextflow_process {
+
+    name "Test Process KMERGENIE"
+    script "../main.nf"
+    process "KMERGENIE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "kmergenie"
+
+    test("test-kmergenie-sarscov2-illumina") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+				    [
+                        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)
+                    ]
+				]
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success  },
+                { assert process.out.html },
+                { assert process.out.html[0][1] ==~ /.*test_report\.html$/ },
+                { assert snapshot(
+                    process.out.histo,
+                    process.out.dat,
+                    process.out.findAll { key, val -> key.startsWith("versions")},
+                ).match() }
+            )
+        }
+
+    }
+
+    test("test-kmergenie-sarscov2-illumina-stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+				    [
+                        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)
+                    ]
+				]
+
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    process.out,
+                    process.out.findAll { key, val -> key.startsWith("versions")},
+                ).match() }
+            )
+        }
+
+    }
+
+}

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

@@ -0,0 +1,151 @@
+{
+    "test-kmergenie-sarscov2-illumina": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    [
+                        "test-k101.histo:md5,8b704b25eef6846204cf01c41597392d",
+                        "test-k111.histo:md5,33d471426d7b78a157891202a9b1a3ef",
+                        "test-k121.histo:md5,ea46186dd4511a99dafc6797cb4a644a",
+                        "test-k21.histo:md5,29d2bc08cff5a55714897f43c556ceb6",
+                        "test-k27.histo:md5,ae7e8f8b20e2f260522c14472a936287",
+                        "test-k29.histo:md5,ccf4348628725928d400cdb114d12be9",
+                        "test-k31.histo:md5,cd4a6a09b60c2ccab8b47894b8fa2622",
+                        "test-k33.histo:md5,94f30ce1bbe0430da655b67d8d2ba225",
+                        "test-k35.histo:md5,49f518a006d1a3f8ef98a387c431c78e",
+                        "test-k37.histo:md5,cb73e93156aae71b2b0b03de39570056",
+                        "test-k41.histo:md5,fc366d36b0b44b9d8fac35dd9b3caa61",
+                        "test-k51.histo:md5,74803bf3f6268112f3a370481f08e13a",
+                        "test-k61.histo:md5,a932b513b9a273c2967d2fd0791b71df",
+                        "test-k71.histo:md5,1ae35ad55212926c4d4aa7921bd3d878",
+                        "test-k81.histo:md5,389826e458cde3bd85c4b8ec30b44cca",
+                        "test-k91.histo:md5,d802c6b371d57ebdd605791b450cebf3"
+                    ]
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.dat:md5,040c8a22cb240ad160a851a29b04f9e4"
+                ]
+            ],
+            {
+                "versions_kmergenie": [
+                    [
+                        "KMERGENIE",
+                        "kmergenie",
+                        "1.7051"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-02-27T11:48:37.501863493",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "25.10.4"
+        }
+    },
+    "test-kmergenie-sarscov2-illumina-stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_report.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test*.histo:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.dat:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "3": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test*.pdf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "4": [
+                    [
+                        "KMERGENIE",
+                        "kmergenie",
+                        "1.7051"
+                    ]
+                ],
+                "dat": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.dat:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "histo": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test*.histo:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "html": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test_report.html:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "pdf": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test*.pdf:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions_kmergenie": [
+                    [
+                        "KMERGENIE",
+                        "kmergenie",
+                        "1.7051"
+                    ]
+                ]
+            },
+            {
+                "versions_kmergenie": [
+                    [
+                        "KMERGENIE",
+                        "kmergenie",
+                        "1.7051"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-02-27T11:05:23.598995518",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "25.10.4"
+        }
+    }
+}