add aardvark merge

modules/nf-core/aardvark/merge/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::aardvark=0.10.5

modules/nf-core/aardvark/merge/main.nf

@@ -0,0 +1,66 @@
+process AARDVARK_MERGE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/aardvark:0.10.5--h4349ce8_0':
+        'quay.io/biocontainers/aardvark:0.10.5--h4349ce8_0' }"
+
+    input:
+    tuple val(meta), path(vcfs), path(indexes)
+    tuple val(meta2), path(fasta)
+    tuple val(meta3), path(bed)
+
+    output:
+    tuple val(meta), path('*.summary.tsv')                    , emit: summary
+    tuple val(meta), path('*.passing.vcf.gz')                 , emit: passing_vcf
+    tuple val(meta), path('*.passing.vcf.gz.tbi')             , emit: passing_vcf_index
+    tuple val(meta), path('*.regions.bed.gz')                 , emit: passing_regions
+    tuple val(meta), path('*.regions.bed.gz.tbi')             , emit: passing_regions_index
+    tuple val(meta), path('*.failed_regions.bed.gz')          , emit: failed_regions
+    tuple val(meta), path('*.failed_regions.bed.gz.tbi')      , emit: failed_regions_index
+    tuple val(meta), path('*.json')                           , emit: runinfo
+    tuple val("${task.process}"), val('aardvark'), eval("aardvark merge --version 2>&1 | sed 's/aardvark-bio-merge //; s/-conda//'"), topic: versions, emit: versions_aardvark
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def inputs = vcfs.collect { file -> "--input-vcf ${file}" }.join(' ')
+
+    """
+    aardvark merge \\
+        --threads $task.cpus \\
+        --reference $fasta \\
+        $inputs \\
+        --regions ${bed} \\
+        --output-vcfs $prefix \\
+        --output-debug $prefix \\
+        --output-summary ${prefix}.summary.tsv \\
+        $args
+
+    for f in ${prefix}/*; do
+        mv "\$f" "${prefix}.\${f##*/}"
+    done
+
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo $args
+
+    echo "" | gzip > ${prefix}.passing.vcf.gz
+    echo "" | gzip > ${prefix}.regions.bed.gz
+    echo "" | gzip > ${prefix}.failed_regions.bed.gz
+    touch ${prefix}.passing.vcf.gz.tbi
+    touch ${prefix}.regions.bed.gz.tbi
+    touch ${prefix}.failed_regions.bed.gz.tbi   
+    touch ${prefix}.summary.tsv
+    touch ${prefix}.cli_settings.json
+    """
+}

modules/nf-core/aardvark/merge/meta.yml

@@ -0,0 +1,160 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "aardvark_merge"
+description: A tool to evaluate and merge multiple variant calls into a consensus VCF.
+keywords:
+  - variant calling
+  - vcf
+  - comparison
+  - consensus
+  - merging
+tools:
+  - aardvark:
+      description: |
+        The aardvark merge command provides a method to merge variant calls. This functionality is helpful when multiple 
+        variant callers or technologies are used for the same sample. Merging variant sets can be complex and Aardvark 
+        simplifies this process by modeling the variants as haplotypes. This allows for different merge strategies for 
+        resolving conflicting variant sets.
+      homepage: "https://github.com/PacificBiosciences/aardvark"
+      documentation: "https://github.com/PacificBiosciences/aardvark/blob/main/docs/methods.md#merge-strategies"
+      tool_dev_url: "https://github.com/PacificBiosciences/aardvark"
+      doi: "10.1101/2025.10.03.680257"
+      licence: ["MIT"]
+      identifier: biotools:aardvark
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - vcfs:
+        type: file
+        description: List of VCF files to be merged
+        pattern: "*.{vcf.gz}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3016"
+    - indexes:
+        type: file
+        description: List of index files for the input VCF files
+        pattern: "*.{vcf.gz.tbi,vcf.gz.csi,tbi,csi}"
+  - - meta2:
+        type: map
+        description: Groovy Map containing reference fasta information
+    - fasta:
+        type: file
+        description: Reference genome fasta file
+        pattern: "*.{fasta,fa,fasta.gz,fa.gz}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+  - - meta3:
+        type: map
+        description: Groovy Map containing bed information
+    - bed:
+        type: file
+        description: Optional BED file containing genomic regions to restrict the merge operation
+        pattern: "*.{bed}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3586"
+
+output:
+  summary:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.summary.tsv":
+          type: file
+          description: Global summary statistics of the variant merge
+          pattern: "*.summary.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475" # TSV
+  passing_vcf:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.passing.vcf.gz":
+          type: file
+          description: Merged VCF file containing passing variants
+          pattern: "*.passing.vcf.gz"
+          ontologies:
+          - edam: "http://edamontology.org/format_3016"
+  passing_vcf_index:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.passing.vcf.gz.tbi":
+          type: file
+          description: Index file for the merged passing VCF
+          pattern: "*.passing.vcf.gz.tbi"
+  passing_regions:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.regions.bed.gz":
+          type: file
+          description: BED file of regions containing passing variants
+          pattern: "*.regions.bed.gz"
+          ontologies:
+          - edam: "http://edamontology.org/format_3586"
+  passing_regions_index:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.regions.bed.gz.tbi":
+          type: file
+          description: Index file for the passing regions BED
+          pattern: "*.regions.bed.gz.tbi"
+  failed_regions:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.failed_regions.bed.gz":
+          type: file
+          description: BED file of regions that failed merging criteria
+          pattern: "*.failed_regions.bed.gz"
+          ontologies:
+          - edam: "http://edamontology.org/format_3586"
+  failed_regions_index:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.failed_regions.bed.gz.tbi":
+          type: file
+          description: Index file for the failed regions BED
+          pattern: "*.failed_regions.bed.gz.tbi"
+  runinfo:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.json":
+          type: file
+          description: JSON file containing parameter settings used during the run
+          pattern: "*.json"
+          ontologies:
+            - edam: http://edamontology.org/format_3464 # JSON
+  versions_aardvark:
+    - - "${task.process}":
+          type: string
+          description: The name of the process
+      - "aardvark":
+          type: string
+          description: The name of the tool
+      - "aardvark merge --version 2>&1 | sed 's/aardvark-bio-merge //; s/-conda//'":
+          type: eval
+          description: The expression to obtain the version of the tool
+
+topics:
+  versions:
+    - - "${task.process}":
+          type: string
+          description: The name of the process
+      - "aardvark":
+          type: string
+          description: The name of the tool
+      - "aardvark merge --version 2>&1 | sed 's/aardvark-bio-merge //; s/-conda//'":
+          type: eval
+          description: The expression to obtain the version of the tool
+
+authors:
+  - "@kubranarci"
+maintainers:
+  - "@kubranarci"

modules/nf-core/aardvark/merge/tests/main.nf.test

@@ -0,0 +1,98 @@
+nextflow_process {
+
+    name "Test Process AARDVARK_MERGE"
+    script "../main.nf"
+    process "AARDVARK_MERGE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "aardvark"
+    tag "aardvark/merge"
+
+    config "./nextflow.config"
+
+    test("homo_sapiens - vcf.gz") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                        [ id:'test' ], // meta map
+                        [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz', checkIfExists: true),
+                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz', checkIfExists: true)
+                         ],
+                        [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi', checkIfExists: true),
+                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi', checkIfExists: true)
+                         ]
+                        ]
+                input[1] = [
+                        [ id:'fasta' ], // meta map
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true)
+                        ]
+                input[2] = [
+                        [id:'bed' ], // meta map
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed', checkIfExists: true)
+                        ]
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    path(process.out.passing_vcf[0][1]).vcf.summary,
+                    file(process.out.passing_vcf[0][1]).name,
+                    file(process.out.passing_vcf_index[0][1]).name,
+                    file(process.out.failed_regions[0][1]).name,
+                    process.out.passing_regions,
+                    process.out.passing_regions_index,
+                    process.out.failed_regions_index,
+                    process.out.runinfo,
+                    process.out.summary,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                    ).match()
+                }
+            )
+        }
+
+    }
+
+    test("homo_sapiens - vcf.gz - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                        [ id:'test' ], // meta map
+                        [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz', checkIfExists: true),
+                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz', checkIfExists: true)
+                         ],
+                        [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi', checkIfExists: true),
+                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi', checkIfExists: true)
+                         ]
+                        ]
+                input[1] = [
+                        [ id:'fasta' ], // meta map
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true)
+                        ]
+                input[2] = [
+                        [id:'bed' ], // meta map
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed', checkIfExists: true)
+                        ]
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}