Rmats work in progress PR

modules/nf-core/rmats/prep/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::rmats=4.3.0"

modules/nf-core/rmats/prep/main.nf

@@ -0,0 +1,73 @@
+process RMATS_PREP {
+    tag "${meta.id}"
+    label 'process_single'
+
+    // TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below.
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/rmats:4.3.0--py311hf2f0b74_5'
+        : 'biocontainers/rmats:4.3.0--py311hf2f0b74_5'}"
+
+    input:
+    // TODO nf-core: Update the information obtained from bio.tools and make sure that it is correct
+
+    tuple val(meta), path(genome_bam)
+    // TODO - post seems to need only the BAM *names*, not the actual files. Could we just get the first line of each file to get the names?
+    // for file in `ls multi_bam_rmats_prep_tmp/*.rmats`; do head -1 $file; done | tr '\n' ','
+    // TODO - for stats, it should be possible to parse the formula using patsy, but if we include PAIRADISE we might have R - just do this in R, first pass
+    path reference_gtf
+    val rmats_read_len
+
+    output:
+    // TODO nf-core: Update the information obtained from bio.tools and make sure that it is correct
+    tuple val(meta), path("*.rmats"), emit: prep_rmats_file
+    tuple val(meta), path("*outcomes_by_bam.txt"), emit: prep_read_outcomes_file
+    tuple val("${task.process}"), val('rmats'), eval('rmats.py --version | sed -e "s/v//g"'), emit: versions_rmats, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    // TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10
+    //               If the software is unable to output a version number on the command-line then it can be manually specified
+    //               e.g. https://github.com/nf-core/modules/blob/master/modules/nf-core/homer/annotatepeaks/main.nf
+    //               Each software used MUST provide the software name and version number in the YAML version file (versions.yml)
+
+    //   --readLength READLENGTH
+    //                    The length of each read. Required parameter, with the
+    //                    value set according to the RNA-seq read length
+    // TODO - question. Does this definition mean I should change it by read length? If so, look at a samtools command to figure it out. Samtools stats!
+    // TODO - should I modify the prefix to include rmats_prep only in a subworkflow via modules.config? It seems so, see example at https://github.com/nf-core/rnaseq/blob/e049f51f0214b2aef7624b9dd496a404a7c34d14/conf/modules.config#L576
+    """
+    echo ${genome_bam} > ${prefix}.prep.b1.txt
+
+    rmats.py \\
+        --task prep \\
+        ${args} \\
+        --nthread ${task.cpus} \\
+        --b1 ${prefix}.prep.b1.txt \\
+        --gtf ${reference_gtf} \\
+        --readLength ${rmats_read_len} \\
+        --tmp ${prefix}_rmats_tmp \\
+        --od ${prefix}_rmats_prep
+
+    for file in `ls ${prefix}_rmats_tmp/*`
+    do
+    cp \${file} ${prefix}_prep_\$(basename \${file})
+    done
+    """
+
+    // NOTES for post - post requires the rmats files to be in the tmp directory, otherwise it fails
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo ${args}
+
+    touch ${prefix}.rmats
+    touch ${prefix}_outcomes_by_bam.txt
+    """
+}

modules/nf-core/rmats/prep/meta.yml

@@ -0,0 +1,88 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+# # TODO nf-core: Add a description of the module and list keywords
+name: "rmats_prep"
+description: MATS is a computational tool to detect differential alternative splicing events from RNA-Seq data.
+keywords:
+  - splicing
+  - RNA-Seq
+  - alternative splicing
+  - exon
+  - intron
+  - rMATS
+tools:
+  ## TODO nf-core: Add a description and other details for the software below
+  - "rmats":
+      description: "MATS is a computational tool to detect differential alternative
+        splicing events from RNA-Seq data."
+      homepage: "https://github.com/Xinglab/rmats-turbo"
+      documentation: "https://github.com/Xinglab/rmats-turbo/blob/v4.3.0/README.md"
+      doi: "10.1038/s41596-023-00944-2"
+      licence: ["FreeBSD for non-commercial use, see LICENSE file"]
+      identifier: biotools:rmats
+
+input:
+  # TODO nf-core: Update the information obtained from bio.tools and make sure that it is correct
+  - - meta:
+        type: map
+        description: Groovy Map containing sample information. e.g. `[ id:'sample1', single_end:false, strandness:'auto']`
+    - genome_bam:
+        type: file
+        description: BAM file aligned to the genome
+        pattern: "*.{bam}"
+        ontologies:
+          - edam: http://edamontology.org/format_2572 # BAM
+  - reference_gtf:
+      type: file
+      description: Annotation GTF file
+      pattern: "*.{gtf}"
+      ontologies:
+        - edam: http://edamontology.org/format_2306 # GTF
+  - rmats_read_len:
+      type: integer
+      description: Read length in bases
+output:
+  # TODO nf-core: Update the information obtained from bio.tools and make sure that it is correct
+  prep_rmats_file:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information. e.g. `[ id:'sample1'single_end:false, strandness:'auto']`
+      - "*.{}":
+          type: file
+          description: text file containing rmats processed splice junctions
+          pattern: "*.rmats"
+          ontologies: []
+  prep_read_outcomes_file:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information. e.g. `[ id:'sample1'single_end:false, strandness:'auto']`
+      - "*.{}":
+          type: file
+          description: text file containing the numbers of reads for each outcome (USED, NOT_PAIRED, etc.)
+          pattern: "*.txt"
+          ontologies: []
+            - edam: http://edamontology.org/format_2330
+  versions_rmats:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rmats:
+          type: string
+          description: The name of the tool
+      - rmats.py --version | sed -e "s/v//g":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rmats:
+          type: string
+          description: The name of the tool
+      - rmats.py --version | sed -e "s/v//g":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@akaviaLab"
+maintainers:
+  - "@akaviaLab"

modules/nf-core/rmats/prep/optional_parameters

@@ -0,0 +1,2 @@
+--variable-read-length
+--allow-clipping

modules/nf-core/rmats/prep/tests/main.nf.test

@@ -0,0 +1,74 @@
+// TODO nf-core: Once you have added the required tests, please run the following command to build this file:
+// nf-core modules test rmats/prep
+nextflow_process {
+
+    name "Test Process RMATS_PREP"
+    script "../main.nf"
+    process "RMATS_PREP"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "rmats"
+    tag "rmats/prep"
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used
+    test("sarscov2 - bam") {
+
+        // TODO nf-core: If you are created a test for a chained module
+        // (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 {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+                // See https://nf-co.re/docs/contributing/tutorials/nf-test_assertions for more information and examples.
+            )
+        }
+
+    }
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used but keep the " - stub" suffix.
+    test("sarscov2 - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+            )
+        }
+
+    }
+
+}

modules/nf-core/rmats/prep/tests/nextflow.config

@@ -0,0 +1,15 @@
+process {
+
+    withName: RMATS_PREP {
+        ext.args = {[
+            "--variable-read-length --allow-clipping",
+            meta.single_end                 ?   '-t single' : '',
+            meta.strandness == "forward" ? "--libType fr-firststrand" : '',
+            meta.strandness == "reverse" ? "--libType fr-secondstrand" : '',
+            params.novel_splice_site ? "--novelSS" : "",
+            (params.novel_splice_site && params.minimum_intron_length) ? "--mil ${params.minimum_intron_length}" : "",
+            (params.novel_splice_site && params.max_exon_length) ? "--mel ${params.max_exon_length}" : "",
+        ].join(' ').trim()}
+    }
+
+}