Added new module oarfish

modules/nf-core/oarfish/alignmentmode/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::oarfish=0.10.3"

modules/nf-core/oarfish/alignmentmode/main.nf

@@ -0,0 +1,49 @@
+process OARFISH_ALIGNMENTMODE {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/89/890d90ebb61b3756527fabe481d801a8e203453fde05a67ccc01640a9a445cd9/data':
+        'community.wave.seqera.io/library/oarfish:0.10.3--837f9667a3c87dbb' }"
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("${prefix}.quant")         , emit: quant
+    tuple val(meta), path("${prefix}.meta_info.json"), emit: meta_info
+    tuple val(meta), path("${prefix}.ambig_info.tsv"), emit: ambig_info
+    tuple val(meta), path("${prefix}.infreps.pq")    , optional: true, emit: infreps
+    tuple val(meta), path("${prefix}.prob.lz4")      , optional: true, emit: prob
+    tuple val("${task.process}"), val('oarfish'), eval("oarfish --version | sed 's/oarfish //'"), topic: versions, emit: versions_oarfish
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    oarfish \\
+        --alignments ${bam} \\
+        --output ${prefix} \\
+        --threads ${task.cpus} \\
+        --filter-group no-filters \\
+        --model-coverage \\
+        --verbose \\
+        ${args}
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}.quant
+    touch ${prefix}.ambig_info.tsv
+    touch ${prefix}.infreps.pq
+    touch ${prefix}.prob.lz4
+    touch ${prefix}.meta_info.json
+    """
+}

modules/nf-core/oarfish/alignmentmode/meta.yml

@@ -0,0 +1,118 @@
+name: "oarfish_alignmentmode"
+description: oarfish is a program for quantifying transcript-level expression
+  from long-read (i.e. Oxford nanopore cDNA and direct RNA and PacBio)
+  sequencing technologies. It handles multi-mapping reads through the use of
+  probabilistic allocation via an expectation-maximization (EM) algorithm.
+keywords:
+  - bam
+  - transcript
+  - quantification
+  - alignment-mode
+tools:
+  - "oarfish":
+      description: "oarfish is a tool for fast, accurate and versatile transcript quantification
+        from long-read RNA-seq data"
+      homepage: "https://github.com/COMBINE-lab/oarfish"
+      documentation: "https://github.com/COMBINE-lab/oarfish"
+      tool_dev_url: "https://github.com/COMBINE-lab/oarfish"
+      doi: "10.1101/2024.02.28.582591v1"
+      licence:
+        - "BSD-3-clause"
+      identifier: biotools:oarfish
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - bam:
+        type: file
+        description: Sorted BAM/CRAM/SAM file from long-read RNA-seq data
+        pattern: "*.{bam,cram,sam}"
+        ontologies:
+          - edam: "http://edamontology.org/format_2572"
+output:
+  quant:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}.quant:
+          type: file
+          description: Quantification results in TSV format
+          pattern: "${prefix}.quant"
+          ontologies: []
+  meta_info:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}.meta_info.json:
+          type: file
+          description: Meta information in JSON format
+          pattern: "${prefix}.meta_info.json"
+          ontologies:
+            - edam: "http://edamontology.org/format_3464"
+  ambig_info:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}.ambig_info.tsv:
+          type: file
+          description: Ambiguity information in TSV format
+          pattern: "${prefix}.ambig_info.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  infreps:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}.infreps.pq:
+          type: file
+          description: Estimated counts in Parquet format
+          pattern: "${prefix}.infreps.pq"
+          ontologies:
+            - edam: "http://edamontology.org/format_3940"
+  prob:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}.prob.lz4:
+          type: file
+          description: Assignment probabilities in LZ4-compressed format
+          pattern: "${prefix}.prob.lz4"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  versions_oarfish:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - oarfish:
+          type: string
+          description: The name of the tool
+      - oarfish --version | sed 's/oarfish //':
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - oarfish:
+          type: string
+          description: The name of the tool
+      - oarfish --version | sed 's/oarfish //':
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@khersameesh24"
+maintainers:
+  - "@khersameesh24"

modules/nf-core/oarfish/alignmentmode/tests/main.nf.test

@@ -0,0 +1,148 @@
+nextflow_process {
+
+    name "Test Process OARFISH_ALIGNMENTMODE"
+    script "../main.nf"
+    process "OARFISH_ALIGNMENTMODE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "oarfish"
+    tag "oarfish/alignmentmode"
+    tag "samtools/collate"
+
+    test("long-read pacbio - bam") {
+
+        setup {
+            run("SAMTOOLS_COLLATE") {
+                script "modules/nf-core/samtools/collate/main.nf"
+                process {
+                    """
+                    input[0] = [
+                        [id:'test'],
+                        file('https://raw.githubusercontent.com/khersameesh24/test-datasets/modules/data/genomics/homo_sapiens/pacbio/bam/test_sample.mmaligned.sorted.bam', checkIfExists: true)
+                    ]
+                    input[1] = [[], [], []]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = SAMTOOLS_COLLATE.out.bam
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(sanitizeOutput(process.out, unstableKeys: ['meta_info'])).match() }
+            )
+        }
+    }
+
+    test("long-read pacbio - bam - stub") {
+
+        options "-stub"
+
+        setup {
+            run("SAMTOOLS_COLLATE") {
+                script "modules/nf-core/samtools/collate/main.nf"
+                process {
+                    """
+                    input[0] = [
+                        [id:'test'],
+                        file('https://raw.githubusercontent.com/khersameesh24/test-datasets/modules/data/genomics/homo_sapiens/pacbio/bam/test_sample.mmaligned.sorted.bam', checkIfExists: true)
+                    ]
+                    input[1] = [[], [], []]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = SAMTOOLS_COLLATE.out.bam
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(sanitizeOutput(process.out)).match() }
+            )
+        }
+    }
+
+    test("long-read ont - bam") {
+
+        setup {
+            run("SAMTOOLS_COLLATE") {
+                script "modules/nf-core/samtools/collate/main.nf"
+                process {
+                    """
+                    input[0] = [
+                        [id:'test'],
+                        file('https://raw.githubusercontent.com/khersameesh24/test-datasets/modules/data/genomics/homo_sapiens/nanopore/bam/test_sample.mmaligned.sorted.bam', checkIfExists: true)
+                    ]
+                    input[1] = [[], [], []]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = SAMTOOLS_COLLATE.out.bam
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(sanitizeOutput(process.out, unstableKeys: ['meta_info'])).match() }
+            )
+        }
+    }
+
+    test("long-read ont - bam - stub") {
+
+        options "-stub"
+
+        setup {
+            run("SAMTOOLS_COLLATE") {
+                script "modules/nf-core/samtools/collate/main.nf"
+                process {
+                    """
+                    input[0] = [
+                        [id:'test'],
+                        file('https://raw.githubusercontent.com/khersameesh24/test-datasets/modules/data/genomics/homo_sapiens/nanopore/bam/test_sample.mmaligned.sorted.bam', checkIfExists: true)
+                    ]
+                    input[1] = [[], [], []]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = SAMTOOLS_COLLATE.out.bam
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(sanitizeOutput(process.out)).match() }
+            )
+        }
+    }
+}