Prepare gens input data module

modules/nf-core/gens/preparecovandbaf/environment.yml

@@ -0,0 +1,11 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::htslib=1.23
+  - conda-forge::pip=25.3
+  - conda-forge::python=3.14.2
+  - pip:
+      - gens-input-data-tools==2.0.0

modules/nf-core/gens/preparecovandbaf/main.nf

@@ -0,0 +1,46 @@
+process PREPARECOVANDBAF {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/a9/a9f414681caefff508dcab89f4872ae3cda18d15b9b610b679fa5eb5023b4b7c/data':
+        'community.wave.seqera.io/library/tabix_pip_gens-input-data-tools:5d39cfe6f6bf258b' }"
+
+    input:
+    tuple val(meta), path(read_counts), path(gvcf), path(gvcf_tbi)
+    path baf_positions
+
+    output:
+    tuple val(meta), path("*.cov.bed.gz")     , emit: cov_gz
+    tuple val(meta), path("*.cov.bed.gz.tbi") , emit: cov_tbi
+    tuple val(meta), path("*.baf.bed.gz")     , emit: baf_gz
+    tuple val(meta), path("*.baf.bed.gz.tbi") , emit: baf_tbi
+    tuple val("${task.process}"), val('preparecovandbaf'), eval("generate_cov_and_baf --version"), topic: versions, emit: versions_preparecovandbaf
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    generate_cov_and_baf \\
+        --coverage $read_counts \\
+        --gvcf $gvcf \\
+        --label $prefix \\
+        --baf_positions $baf_positions \\
+        --bgzip_tabix_output \\
+        $args \\
+        --outdir .
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo "" | gzip > ${prefix}.cov.bed.gz
+    touch ${prefix}.cov.bed.gz.tbi
+    echo "" | gzip > ${prefix}.baf.bed.gz
+    touch ${prefix}.baf.bed.gz.tbi
+    """
+}

modules/nf-core/gens/preparecovandbaf/meta.yml

@@ -0,0 +1,110 @@
+name: "preparecovandbaf"
+description: Tools for preparing inputs for visualization in Gens
+keywords:
+  - gens
+  - preparecovandbaf
+  - preprocessing
+  - genomics
+  - CNV
+tools:
+  - "gens":
+      description: "Scripts for preparing input data to Gens"
+      homepage: "https://github.com/SMD-Bioinformatics-Lund/Prepare-Gens-input-data"
+      documentation: "https://github.com/SMD-Bioinformatics-Lund/Prepare-Gens-input-data/README.md"
+      tool_dev_url: "https://github.com/SMD-Bioinformatics-Lund/Prepare-Gens-input-data"
+      licence: [MIT]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - read_counts:
+        type: file
+        description: Binned coverage calculations from GATK
+        pattern: "*.{tsv}"
+        ontologies:
+          - edam: http://edamontology.org/format_3475 # TSV
+    - gvcf:
+        type: file
+        description: GVCF. It is used to calculate B-allele frequencies at the sites specified in baf_positions. It can be generated using any SNV-caller.
+        pattern: "*.vcf.gz"
+        ontologies:
+          - edam: http://edamontology.org/format_3989 # GZIP format
+    - gvcf_tbi:
+        type: file
+        description: GVCF tabix index
+        pattern: "*.vcf.gz.tbi"
+        ontologies: []
+  - baf_positions:
+      type: file
+      description: Sites to sample for BAF calculations
+      pattern: "*.{tsv,tsv.gz}"
+
+      ontologies:
+        - edam: http://edamontology.org/format_3475 # TSV
+output:
+  cov_gz:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+      - "*.cov.bed.gz":
+          type: file
+          description: Coverage bed (bgzipped)
+
+  cov_tbi:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+      - "*.cov.bed.gz.tbi":
+          type: file
+          description: Tabix index for coverage bed
+
+  baf_gz:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+      - "*.baf.bed.gz":
+          type: file
+          description: BAF bed (bgzipped)
+
+  baf_tbi:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+      - "*.baf.bed.gz.tbi":
+          type: file
+          description: Tabix index for BAF bed
+
+  versions_preparecovandbaf:
+    - - "${task.process}":
+          type: string
+          description: The process the versions were collected from
+      - "preparecovandbaf":
+          type: string
+          description: The tool name
+      - "generate_cov_and_baf --version":
+          type: string
+          description: The command used to generate the version of the tool
+
+topics:
+  versions:
+    - - "${task.process}":
+          type: string
+          description: The process the versions were collected from
+      - "preparecovandbaf":
+          type: string
+          description: The tool name
+      - "generate_cov_and_baf --version":
+          type: eval
+          description: The expression used to obtain the tool version
+authors:
+  - "@jakob37"
+maintainers:
+  - "@jakob37"

modules/nf-core/gens/preparecovandbaf/tests/main.nf.test

@@ -0,0 +1,66 @@
+nextflow_process {
+
+    name "Test Process PREPARECOVANDBAF"
+    script "modules/nf-core/gens/preparecovandbaf/main.nf"
+    process "PREPARECOVANDBAF"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "gens"
+    tag "gens/preparecovandbaf"
+
+    test("gens_preparecovandbaf") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz.tbi", checkIfExists: true),
+                ]
+                input[1] = [
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz", checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("gens_preparecovandbaf - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz.tbi", checkIfExists: true),
+                ]
+                input[1] = [
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz", checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}