feat: samclip module

modules/nf-core/samclip/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - bioconda::samclip=0.4.0
+  - bioconda::samtools=1.22.1

modules/nf-core/samclip/main.nf

@@ -0,0 +1,54 @@
+process SAMCLIP {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'oras://community.wave.seqera.io/library/samclip_samtools:7af2916e4ae6f461'
+        : 'community.wave.seqera.io/library/samclip_samtools:00cc7aefd75be672'}"
+
+    input:
+    tuple val(meta), path(bam)
+    tuple val(meta2), path(reference), path(reference_index)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}.samclip"
+    def is_compressed = reference.getName().endsWith(".gz")
+    def ref_filename = reference.getName().replaceAll(/\.gz$/, "")
+    """
+    # decompress reference if gzipped
+    ${is_compressed ? "gzip -c -d ${reference} > ${ref_filename}" : ""}
+
+    samtools view -h --output-fmt sam ${bam} | \\
+    samclip ${args} --ref ${ref_filename} | \\
+    samtools sort -n -O BAM -T /tmp | \\
+    samtools fixmate -m - - | \\
+    samtools sort -O BAM > ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samclip: \$(echo \$(samclip --version 2>&1) | sed 's/^.*samclip //g' )
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}.samclip"
+    """
+    touch ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samclip: \$(echo \$(samclip --version 2>&1) | sed 's/^.*samclip //g' )
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/samclip/meta.yml

@@ -0,0 +1,70 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: samclip
+description: Filters SAM file for soft and hard clipped alignments
+keywords:
+  - soft-clipped reads
+  - hard-clipped reads
+  - genomics
+  - sam
+tools:
+  - samclip:
+      description: Filters SAM file for soft and hard clipped alignments
+      homepage: https://github.com/tseemann/samclip
+      documentation: https://github.com/tseemann/samclip
+      tool_dev_url: https://github.com/tseemann/samclip
+      doi: "no DOI available"
+      licence: ["GPL v3"]
+      identifier: biotools:samclip
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+
+    - bam:
+        type: file
+        description: BAM file
+        pattern: "*.bam"
+        ontologies:
+          - edam: http://edamontology.org/format_2572 # BAM
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing fasta reference information
+          e.g. [ id:'test' ]
+    - reference:
+        type: file
+        description: |
+          reference FASTA file
+        pattern: "*.{fasta,fa}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+    - reference_index:
+        type: file
+        description: |
+          reference FASTA file index
+        pattern: "*.{fai}"
+        ontologies: []
+output:
+  bam:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information. e.g. [ id:'test']
+      - "*.bam":
+          type: file
+          description: Filtered BAM
+          ontologies:
+            - edam: http://edamontology.org/format_2572 # BAM
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: versions.yml
+        ontologies:
+          - edam: http://edamontology.org/format_3750 # YAML
+authors:
+  - "@emmcauley"
+maintainers:
+  - "@emmcauley"

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

@@ -0,0 +1,81 @@
+nextflow_process {
+
+    name "Test Process SAMCLIP"
+    script "../main.nf"
+    process "SAMCLIP"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "samclip"
+    tag "samtools/view"
+
+    test("test-data - NA12878.chr22.bam") {
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'NA12878_chr22' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.bam', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.bam.bai', checkIfExists: true),
+
+                ]
+
+                input[1] = [
+                    [ id:'chr22_ref' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta.fai', checkIfExists: true),
+                ]
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("test-data - NA12878.chr22.bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'NA12878_chr22' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.bam', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/NA12878.chr22.bam.bai', checkIfExists: true),
+
+                ]
+
+                input[1] = [
+                    [ id:'chr22_ref' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta.fai', checkIfExists: true),
+                ]
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                        process.out,
+                        process.out.versions.collect{ path(it).yaml }
+                    ).match() }
+            )
+        }
+
+    }
+
+}

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

@@ -0,0 +1,76 @@
+{
+    "test-data - NA12878.chr22.bam": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "NA12878_chr22"
+                        },
+                        "NA12878_chr22.samclip.bam:md5,d5b1f9b1420caf42922adb0fe1080f02"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,b47fb65111012518aa3353d09574787d"
+                ],
+                "bam": [
+                    [
+                        {
+                            "id": "NA12878_chr22"
+                        },
+                        "NA12878_chr22.samclip.bam:md5,d5b1f9b1420caf42922adb0fe1080f02"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,b47fb65111012518aa3353d09574787d"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "25.04.6"
+        },
+        "timestamp": "2025-09-14T14:22:07.416493"
+    },
+    "test-data - NA12878.chr22.bam - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "NA12878_chr22"
+                        },
+                        "NA12878_chr22.samclip.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,b47fb65111012518aa3353d09574787d"
+                ],
+                "bam": [
+                    [
+                        {
+                            "id": "NA12878_chr22"
+                        },
+                        "NA12878_chr22.samclip.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,b47fb65111012518aa3353d09574787d"
+                ]
+            },
+            [
+                {
+                    "SAMCLIP": {
+                        "samclip": "0.4.0",
+                        "samtools": "1.22.1"
+                    }
+                }
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "25.04.6"
+        },
+        "timestamp": "2025-09-14T14:05:27.817109"
+    }
+}

modules/nf-core/samclip/tests/nextflow.config

@@ -0,0 +1,6 @@
+process {
+    withName: SAMTOOLS_VIEW {
+        ext.args = "-h --output-fmt bam"
+    }
+
+}