Add new module: saltshaker/classify

modules/nf-core/saltshaker/classify/environment.yml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - pip==26.0.1
+  - pip:
+      - saltshaker==1.0.0

modules/nf-core/saltshaker/classify/main.nf

@@ -0,0 +1,56 @@
+process SALTSHAKER_CLASSIFY {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/e9/e93d703b195dd27cd920cee46669d3f51043216c12fd05168c937e93adf170e8/data':
+        'community.wave.seqera.io/library/pip_saltshaker:e08e38a6d45f8f32' }"
+
+    input:
+    tuple val(meta), path(call)
+    val dominant_fraction
+    val group_radius
+    val high_heteroplasmy
+    val multiple_threshold
+    val noise_threshold
+
+    output:
+    tuple val(meta), path("*_classify_metadata.tsv"), emit: classify
+    tuple val(meta), path("*_classify.txt")         , emit: txt
+    tuple val(meta), path("*saltshaker.vcf")        , emit: vcf, optional: true
+    tuple val("${task.process}"), val('saltshaker'), val("1.0.0"), topic: versions, emit: versions_saltshaker
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    saltshaker classify \\
+        --prefix $prefix \\
+        --input-dir . \\
+        --dominant-fraction $dominant_fraction \\
+        --radius $group_radius \\
+        --high-het $high_heteroplasmy \\
+        --multiple-threshold $multiple_threshold \\
+        --noise $noise_threshold \\
+        $args
+
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def touch_vcf = args.contains('--vcf') ? "touch ${prefix}.saltshaker.vcf" : ''
+
+    """
+    echo $args
+
+    $touch_vcf
+    touch ${prefix}.saltshaker_classify.txt
+    touch ${prefix}.saltshaker_classify_metadata.tsv
+    """
+}

modules/nf-core/saltshaker/classify/meta.yml

@@ -0,0 +1,106 @@
+name: "saltshaker_classify"
+description: mtDNA deletion and duplication classification downstream of mitosalt
+keywords:
+  - saltshaker
+  - mitosalt
+  - mtDNA
+  - structural-variant calling
+tools:
+  - "saltshaker":
+      description: "A Python package for classifying and visualizing mitochondrial structural variants from MitoSAlt pipeline output."
+      homepage: "https://github.com/aksenia/saltshaker"
+      documentation: "https://github.com/aksenia/saltshaker/tree/main/saltshaker/docs"
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - call:
+        type: file
+        description: call metadata file from saltshaker_call
+        pattern: "*_call_metadata.tsv"
+        ontologies:
+          - edam: http://edamontology.org/operation_3227 #variant calling
+          - edam: http://edamontology.org/format_3475 #tsv
+  - dominant_fraction:
+      type: float
+      description: Minimum heteroplasmy fraction to classify as dominant in saltshaker
+  - group_radius:
+      type: integer
+      description: Spatial clustering radius for saltshaker grouping
+  - high_heteroplasmy:
+      type: float
+      description: High heteroplasmy threshold for saltshaker classification
+  - multiple_threshold:
+      type: float
+      description: Heteroplasmy threshold for multiple classification in saltshaker
+  - noise_threshold:
+      type: float
+      description: Heteroplasmy threshold for noise in saltshaker classification
+output:
+  classify:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*_classify_metadata.tsv":
+          type: file
+          description: tsv with classified call metadata to be used in saltshaker_plot
+          pattern: "*_classify_metadata.tsv"
+          ontologies:
+            - edam: http://edamontology.org/operation_3225 #classification
+            - edam: http://edamontology.org/format_3475 #tsv
+  txt:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*_classify.txt":
+          type: file
+          description: txt file with case classification
+          pattern: "*_classify.txt"
+          ontologies:
+            - edam: http://edamontology.org/operation_3225 #classification
+            - edam: http://edamontology.org/format_2330 #txt
+  vcf:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*saltshaker.vcf":
+          type: file
+          description: vcf file with classified calls
+          pattern: "*saltshaker.vcf"
+          ontologies:
+            - edam: http://edamontology.org/operation_3225 #classification
+            - edam: http://edamontology.org/format_3016 #vcf
+  versions_saltshaker:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - saltshaker:
+          type: string
+          description: The name of the tool
+      - 1.0.0:
+          type: string
+          description: Hardcoded version of saltshaker used in the module
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - saltshaker:
+          type: string
+          description: The name of the tool
+      - 1.0.0:
+          type: string
+          description: Hardcoded version of saltshaker used in the module
+authors:
+  - "@ieduba"
+maintainers:
+  - "@ieduba"

modules/nf-core/saltshaker/classify/tests/main.nf.test

@@ -0,0 +1,164 @@
+nextflow_process {
+
+    name "Test Process SALTSHAKER_CLASSIFY"
+    script "../main.nf"
+    process "SALTSHAKER_CLASSIFY"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "saltshaker"
+    tag "saltshaker/call"
+    tag "saltshaker/classify"
+
+    setup {
+        run("SALTSHAKER_CALL") {
+            script "../../call/main.nf"
+            process {
+            """
+            input[0] = [
+                [ id:'test' ],
+                file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/mitosalt/test_mitosalt.breakpoint', checkIfExists: true),
+                file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/mitosalt/test_mitosalt.cluster', checkIfExists: true),
+            ]
+
+            input[1] = [
+                [ id:'hg38' ],
+                file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/human_mt_rCRS.fasta', checkIfExists: true),
+            ]
+
+            input[2] = 15
+            input[3] = 0.01
+            input[4] = 16569
+            input[5] = 16081
+            input[6] = 407
+            input[7] = 5730
+            input[8] = 5763
+            """
+        }
+        }
+    }
+
+    test("classify - vcf") {
+
+        when {
+            params {
+                module_args = '--blacklist --vcf'
+            }
+            process {
+                """
+                input[0] = SALTSHAKER_CALL.out.call
+                input[1] = 0.5
+                input[2] = 600
+                input[3] = 10
+                input[4] = 5
+                input[5] = 0.3
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    sanitizeOutput(process.out),
+                ).match() }
+
+            )
+        }
+
+    }
+
+    test("classify - vcf - stub") {
+
+        options "-stub"
+
+        when {
+            params {
+                module_args = '--blacklist --vcf'
+            }
+            process {
+                """
+                input[0] = SALTSHAKER_CALL.out.call
+                input[1] = 0.5
+                input[2] = 600
+                input[3] = 10
+                input[4] = 5
+                input[5] = 0.3
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    sanitizeOutput(process.out),
+                ).match() }
+            )
+        }
+
+    }
+
+    test("classify - no-vcf") {
+
+        when {
+            params {
+                module_args = '--blacklist'
+            }
+            process {
+                """
+                input[0] = SALTSHAKER_CALL.out.call
+                input[1] = 0.5
+                input[2] = 600
+                input[3] = 10
+                input[4] = 5
+                input[5] = 0.3
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    sanitizeOutput(process.out),
+                ).match() }
+
+            )
+        }
+
+    }
+
+    test("classify - no-vcf - stub") {
+
+        options "-stub"
+
+        when {
+            params {
+                module_args = '--blacklist'
+            }
+            process {
+                """
+                input[0] = SALTSHAKER_CALL.out.call
+                input[1] = 0.5
+                input[2] = 600
+                input[3] = 10
+                input[4] = 5
+                input[5] = 0.3
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    sanitizeOutput(process.out),
+                ).match() }
+            )
+        }
+
+    }
+
+}