Add irescue module (#6691)

* Add irescue module

* Fix meta.yml not matching main.nf

* Fix linting

* Better tools description

* Apply suggestions from code review

Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

* Remove trailing whitespaces

---------

Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

modules/nf-core/irescue/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::irescue=1.1.2"

modules/nf-core/irescue/main.nf

@@ -0,0 +1,64 @@
+process IRESCUE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/irescue:1.1.2--pyhdfd78af_0':
+        'biocontainers/irescue:1.1.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(bam)
+    val genome
+    path bed
+
+    output:
+    tuple val(meta), path("${prefix}")            , emit: results
+    tuple val(meta), path("${prefix}/counts")     , emit: counts
+    tuple val(meta), path("${prefix}/irescue.log"), emit: log
+    tuple val(meta), path("${prefix}/tmp")        , emit: tmp, optional: true
+    path "versions.yml"                           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = bed ? "--regions $bed" : ''
+    def genome_assembly = reference ? '' : "--genome $genome"
+    """
+    mkdir -p $prefix
+
+    irescue \\
+        --bam $bam \\
+        $reference \\
+        $genome_assembly \\
+        --outdir $prefix \\
+        --threads $task.cpus \\
+        $args 2> >(tee -a ${prefix}/irescue.log >&2)
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        irescue: \$(irescue --version |& sed '1!d ; s/IRescue //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}/counts
+    touch \\
+        ${prefix}/counts/matrix.mtx \\
+        ${prefix}/counts/barcodes.tsv \\
+        ${prefix}/counts/features.tsv \\
+        ${prefix}/irescue.log
+    gzip ${prefix}/counts/*
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        irescue: \$(irescue --version |& sed '1!d ; s/IRescue //')
+    END_VERSIONS
+    """
+}

modules/nf-core/irescue/meta.yml

@@ -0,0 +1,95 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "irescue"
+description: Quantification of transposable elements expression in scRNA-seq
+keywords:
+  - scRNA-seq
+  - transposons
+  - repeats
+tools:
+  - "irescue":
+      description: "IRescue is a tool for uncertainty-aware quantification of transposable elements expression in scRNA-seq"
+      homepage: "https://pypi.org/project/IRescue"
+      documentation: "https://pypi.org/project/IRescue"
+      tool_dev_url: "https://github.com/bodegalab/irescue"
+      doi: "10.1093/nar/gkae793"
+      licence: ["MIT"]
+      identifier: biotools:irescue
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - bam:
+        type: file
+        description: Sorted BAM file
+        pattern: "*.bam"
+        ontologies:
+          - edam: "http://edamontology.org/format_2572"
+  - - genome:
+        type: string
+        description: |
+          Genome assembly symbol. Not used when bed file is provided.
+          In this case, it can be any value or an empty string.
+  - - bed:
+        type: file
+        description: Bed file of repeats genomic coordinates (optional).
+        pattern: "*.bed"
+        ontologies:
+          - edam: "http://edamontology.org/format_3003"
+
+output:
+  - versions:
+      - "versions.yml":
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+  - results:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - ${prefix}:
+          type: directory
+          description: Folder containing count matrices and logs
+          pattern: "${prefix}"
+  - counts:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - ${prefix}/counts:
+          type: directory
+          description: Folder containing count matrices
+          pattern: "${prefix}/counts"
+  - log:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - ${prefix}/irescue.log:
+          type: file
+          description: Text file contianing run informations
+          pattern: "${prefix}/irescue.log"
+  - tmp:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - ${prefix}/tmp:
+          type: directory
+          description: |
+            Folder containing temporary files,
+            if kept using the "--keeptmp" argument (optional).
+          pattern: "${prefix}/tmp"
+
+authors:
+  - "@bepoli"
+maintainers:
+  - "@bepoli"

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

@@ -0,0 +1,71 @@
+nextflow_process {
+
+    name "Test Process IRESCUE"
+    script "../main.nf"
+    process "IRESCUE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "irescue"
+
+    test("homo_sapiens 10xgenomics - bam") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/10x_cr12.bam', checkIfExists: true)
+                ]
+                input[1] = 'test'
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.counts,
+                    process.out.versions
+                ).match()
+                },
+                { assert file(process.out.log.get(0).get(1)).exists() }
+            )
+        }
+
+    }
+
+    test("homo_sapiens 10xgenomics - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/10x_cr12.bam', checkIfExists: true)
+                ]
+                input[1] = 'test'
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.counts,
+                    process.out.versions
+                ).match()
+                },
+                { assert file(process.out.log.get(0).get(1)).exists() }
+            )
+        }
+
+    }
+
+}

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

@@ -0,0 +1,50 @@
+{
+    "homo_sapiens 10xgenomics - bam": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    [
+                        "barcodes.tsv.gz:md5,5c151d3b6f48e4919687c47684c62395",
+                        "features.tsv.gz:md5,473997691921db70febf048bcdd20848",
+                        "matrix.mtx.gz:md5,8a3e6634400dd455f3199a6de258d526"
+                    ]
+                ]
+            ],
+            [
+                "versions.yml:md5,5097199e8c09d02a961b2277b2a91c9f"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-25T09:34:16.073380434"
+    },
+    "homo_sapiens 10xgenomics - bam - stub": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    [
+                        "barcodes.tsv.gz:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "features.tsv.gz:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "matrix.mtx.gz:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            ],
+            [
+                "versions.yml:md5,5097199e8c09d02a961b2277b2a91c9f"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-25T09:34:27.46106643"
+    }
+}