Vembrane filter

.pre-commit-config.yaml

@@ -1,13 +1,13 @@
 repos:
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: "v3.1.0"
+    rev: "v4.0.0-alpha.8"
     hooks:
       - id: prettier
         additional_dependencies:
           - [email protected]
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
@@ -22,7 +22,7 @@ repos:
           )$
 
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: 0.33.2
+    rev: 0.34.1
     hooks:
       - id: check-jsonschema
         name: "Match meta.ymls in one of the subdirectories of modules/nf-core"
@@ -43,15 +43,15 @@ repos:
 
   # use ruff for python files
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.9
+    rev: v0.14.2
     hooks:
       - id: ruff
         files: \.py$
         args: [--fix, --exit-non-zero-on-fix, "--select", "I,E1,E4,E7,E9,F,UP,N"] # sort imports and fix (rules taken from nf-core/tools)
       - id: ruff-format # formatter
     # NOTE This runs with Docker instead of the binary. Hoping anyone messing with Dockerfiles has Docker installed
   - repo: https://github.com/hadolint/hadolint
-    rev: v2.12.0
+    rev: v2.14.0
     hooks:
       - id: hadolint-docker
   - repo: https://github.com/nf-core/tools

modules/nf-core/vembrane/filter/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::vembrane=2.4.0"

modules/nf-core/vembrane/filter/main.nf

@@ -0,0 +1,56 @@
+process VEMBRANE_FILTER {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vembrane:2.4.0--pyhdfd78af_0':
+        'biocontainers/vembrane:2.4.0--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(variant)
+    val(expression)
+
+    output:
+    tuple val(meta), path("*.{vcf,bcf,vcf.gz,bcf.gz}"), emit: filtered_variant
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    vembrane filter \\
+        ${args} \\
+        ${expression} \\
+        -o ${prefix}_filtered.vcf \\
+        $variant
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vembrane: \$(vembrane --version)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo $args
+
+    vembrane filter \\
+        ${args} \\
+        ${expression} \\
+        -o ${prefix}_filtered.vcf \\
+        $variant
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vembrane: \$(vembrane --version)
+    END_VERSIONS
+    """
+}

modules/nf-core/vembrane/filter/meta.yml

@@ -0,0 +1,60 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "vembrane_filter"
+description: write your description here
+keywords:
+  - filter
+  - table
+  - sort
+tools:
+  - "vembrane":
+      description: "Filter VCF/BCF files with Python expressions."
+      homepage: "https://github.com/vembrane/vembrane/tree/main"
+      documentation: "https://github.com/vembrane/vembrane/blob/main/docs/filter.md"
+      tool_dev_url: "https://github.com/vembrane/vembrane.git"
+      doi: "10.1093/bioinformatics/btac810"
+      licence: ["MIT"]
+      identifier: biotools:vembrane/filter
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - variant:
+        type: file
+        description: |
+          Path to the VCF/BCF file to be filtered.
+          e.g. 'file.vcf', 'file.vcf.gz', 'file.bcf', 'file.bcf.gz'
+        ontologies: []
+  - expression:
+      type: string
+      description: |
+        The filter expression can be any valid python expression that evaluates to a value of type bool.
+        e.g. 'ANN["SYMBOL"] == "CDH2"'
+      ontologies: []
+
+output:
+  filtered_variant:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.{vcf,bcf,vcf.gz,bcf.gz}":
+          type: file
+          description: VCF normalized output file
+          pattern: "*.{vcf,bcf,vcf.gz,bcf.gz}"
+          ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750 # YAML
+authors:
+  - "@trangdo-hsc"
+  - "@mkatsanto"
+maintainers:
+  - "@trangdo-hsc"

modules/nf-core/vembrane/filter/tests/main.nf.test

@@ -0,0 +1,108 @@
+nextflow_process {
+
+    name "Test Process VEMBRANE"
+    script "../main.nf"
+    process "VEMBRANE_FILTER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "vembrane"
+    tag "vembrane/filter"
+
+    test("homo sapiens - vcf") {
+
+        //
+        // (the module requires running more than one process to generate the required output)
+        // add the 'setup' method here.
+        // You can find more information about how to use a 'setup' method in the docs (https://nf-co.re/docs/contributing/modules#steps-for-creating-nf-test-for-chained-modules).
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf', checkIfExists: true),
+                ]
+                input[1] = "'QUAL >= 30'"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("homo sapiens - vcf.gz") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.vcf.gz', checkIfExists: true),
+                ]
+                input[1] = "'QUAL >= 30'"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out
+                    ).match() }
+            )
+        }
+
+    }
+
+    test("homo sapiens - bcf") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.bcf', checkIfExists: true),
+                ]
+                input[1] = "'QUAL >= 30'"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+test("homo sapiens - bcf.gz") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bcf.gz', checkIfExists: true),
+                ]
+                input[1] = "'QUAL >= 30'"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}