New module: parsesdrf/convert

modules/nf-core/parsesdrf/convert/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::sdrf-pipelines=0.1.4"

modules/nf-core/parsesdrf/convert/main.nf

@@ -0,0 +1,81 @@
+process PARSESDRF_CONVERT {
+    tag "${meta.id}"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sdrf-pipelines:0.1.4--pyhdfd78af_0':
+        'quay.io/biocontainers/sdrf-pipelines:0.1.4--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(sdrf)
+    val format
+
+    output:
+    tuple val(meta), path("${prefix}_samplesheet.tsv"), path("${prefix}_presets.tsv"),             emit: mhcquant,     optional: true
+    tuple val(meta), path("${prefix}_samplesheet.tsv"), path("${prefix}_experimental_design.tsv"), emit: openms,       optional: true
+    tuple val(meta), path("${prefix}.xml"),             path("${prefix}_design.txt"),              emit: maxquant,     optional: true
+    tuple val(meta), path("${prefix}.csv"),                                                        emit: msstats,      optional: true
+    tuple val(meta), path("${prefix}_design.csv"),      path("${prefix}_comparisons.csv"),         emit: normalyzerde, optional: true
+    tuple val(meta), path("${prefix}.cfg"),             path("${prefix}_design.tsv"),              emit: diann,        optional: true
+    tuple val("${task.process}"), val('sdrf-pipelines'), eval("parse_sdrf --version | cut -d ' ' -f 2"), topic: versions, emit: versions_sdrfpipelines
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def args = task.ext.args ?: ''
+    def output_args = ''
+    def post = ''
+
+    if (format == 'mhcquant') {
+        output_args = "-os ${prefix}_samplesheet.tsv -op ${prefix}_presets.tsv"
+    } else if (format == 'openms') {
+        // convert-openms writes openms.tsv + (optionally) experimental_design.tsv
+        post = "mv openms.tsv ${prefix}_samplesheet.tsv ; [ -f experimental_design.tsv ] && mv experimental_design.tsv ${prefix}_experimental_design.tsv || true"
+    } else if (format == 'maxquant') {
+        // --fastafilepath and --raw_folder must be supplied via task.ext.args
+        output_args = "-o1 ${prefix}.xml -o2 ${prefix}_design.txt"
+    } else if (format == 'msstats') {
+        output_args = "-o ${prefix}.csv"
+    } else if (format == 'normalyzerde') {
+        output_args = "-o ${prefix}_design.csv -oc ${prefix}_comparisons.csv"
+    } else if (format == 'diann') {
+        // convert-diann writes diann_config.cfg + diann_design.tsv with fixed names
+        post = "mv diann_config.cfg ${prefix}.cfg && mv diann_design.tsv ${prefix}_design.tsv"
+    } else {
+        error "PARSESDRF_CONVERT: unsupported format '${format}' (expected one of: mhcquant, openms, maxquant, msstats, normalyzerde, diann)"
+    }
+
+    """
+    parse_sdrf convert-${format} \\
+        -s ${sdrf} \\
+        ${output_args} \\
+        ${args}
+    ${post}
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def stub_files
+    if (format == 'mhcquant') {
+        stub_files = ["${prefix}_samplesheet.tsv", "${prefix}_presets.tsv"]
+    } else if (format == 'openms') {
+        stub_files = ["${prefix}_samplesheet.tsv", "${prefix}_experimental_design.tsv"]
+    } else if (format == 'maxquant') {
+        stub_files = ["${prefix}.xml", "${prefix}_design.txt"]
+    } else if (format == 'msstats') {
+        stub_files = ["${prefix}.csv"]
+    } else if (format == 'normalyzerde') {
+        stub_files = ["${prefix}_design.csv", "${prefix}_comparisons.csv"]
+    } else if (format == 'diann') {
+        stub_files = ["${prefix}.cfg", "${prefix}_design.tsv"]
+    } else {
+        error "PARSESDRF_CONVERT: unsupported format '${format}'"
+    }
+    def touches = stub_files.collect { f -> "touch ${f}" }.join('\n    ')
+    """
+    ${touches}
+    """
+}

modules/nf-core/parsesdrf/convert/meta.yml

@@ -0,0 +1,168 @@
+name: "parsesdrf_convert"
+description: |
+  Convert an SDRF (Sample and Data Relationship Format) file into a
+  pipeline-specific samplesheet/configuration using the `parse_sdrf
+  convert-<format>` subcommands of the sdrf-pipelines package. The chosen
+  `format` selects the subcommand; the module owns the output filenames and
+  emits one tuple per supported format (mhcquant, openms, maxquant, msstats,
+  normalyzerde, diann).
+keywords:
+  - sdrf
+  - sdrf-pipelines
+  - samplesheet
+  - proteomics
+  - immunopeptidomics
+  - mhcquant
+  - openms
+  - maxquant
+  - msstats
+  - normalyzerde
+  - diann
+  - metadata
+tools:
+  - "sdrf-pipelines":
+      description: "A set of tools to validate and convert SDRF files for proteomics
+        pipelines."
+      homepage: "https://github.com/bigbio/sdrf-pipelines"
+      documentation: "https://github.com/bigbio/sdrf-pipelines"
+      tool_dev_url: "https://github.com/bigbio/sdrf-pipelines"
+      doi: "10.1021/acs.jproteome.1c00505"
+      licence:
+        - "Apache-2.0"
+      identifier: "biotools:sdrf-pipelines"
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample/run information
+          e.g. `[ id:'PXD009752' ]`
+    - sdrf:
+        type: file
+        description: SDRF file describing the experimental design and sample metadata.
+        pattern: "*.{tsv,sdrf.tsv}"
+        ontologies:
+          - edam: http://edamontology.org/format_3475
+  - format:
+      type: string
+      description: |
+        Target converter. One of: `mhcquant`, `openms`, `maxquant`,
+        `msstats`, `normalyzerde`, `diann`. Selects the
+        `parse_sdrf convert-<format>` subcommand. For `maxquant`, the
+        required `--fastafilepath` and `--raw_folder` arguments must be
+        passed via `task.ext.args`.
+output:
+  mhcquant:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}_samplesheet.tsv":
+          type: file
+          description: MHCquant samplesheet TSV (`-os`).
+          pattern: "*_samplesheet.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+      - "${prefix}_presets.tsv":
+          type: file
+          description: MHCquant search-preset TSV (`-op`).
+          pattern: "*_presets.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  openms:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}_samplesheet.tsv":
+          type: file
+          description: OpenMS samplesheet TSV (renamed from `openms.tsv`).
+          pattern: "*_samplesheet.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+      - "${prefix}_experimental_design.tsv":
+          type: file
+          description: OpenMS experimental design TSV.
+          pattern: "*_experimental_design.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  maxquant:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}.xml":
+          type: file
+          description: MaxQuant `mqpar.xml` (`-o1`). Requires `aux=[fasta, raw_folder]`.
+          pattern: "*.xml"
+          ontologies:
+            - edam: http://edamontology.org/format_2332
+      - "${prefix}_design.txt":
+          type: file
+          description: MaxQuant experimental design TXT (`-o2`).
+          pattern: "*_design.txt"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  msstats:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}.csv":
+          type: file
+          description: MSstats annotation CSV (`-o`).
+          pattern: "*.csv"
+          ontologies:
+            - edam: http://edamontology.org/format_3752
+  normalyzerde:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}_design.csv":
+          type: file
+          description: NormalyzerDE design CSV (`-o`).
+          pattern: "*_design.csv"
+          ontologies:
+            - edam: http://edamontology.org/format_3752
+      - "${prefix}_comparisons.csv":
+          type: file
+          description: NormalyzerDE comparisons CSV (`-oc`).
+          pattern: "*_comparisons.csv"
+          ontologies:
+            - edam: http://edamontology.org/format_3752
+  diann:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample/run information
+      - "${prefix}.cfg":
+          type: file
+          description: DIA-NN config (renamed from `diann_config.cfg`).
+          pattern: "*.cfg"
+          ontologies:
+            - edam: http://edamontology.org/format_2330
+      - "${prefix}_design.tsv":
+          type: file
+          description: DIA-NN experimental design TSV (renamed from `diann_design.tsv`).
+          pattern: "*_design.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  versions_sdrfpipelines:
+    - - "${task.process}":
+          type: string
+          description: The name of the process
+      - "sdrf-pipelines":
+          type: string
+          description: The name of the tool
+      - "parse_sdrf --version | cut -d ' ' -f 2":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - "${task.process}":
+          type: string
+          description: The name of the process
+      - "sdrf-pipelines":
+          type: string
+          description: The name of the tool
+      - "parse_sdrf --version | cut -d ' ' -f 2":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@jonasscheid"
+maintainers:
+  - "@jonasscheid"