feat(rpbp): add 8 rpbp modules + fasta_gtf_bam_rpbp subworkflow

modules/nf-core/rpbp/estimatemetagenebayesfactors/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::rpbp=4.0.1

modules/nf-core/rpbp/estimatemetagenebayesfactors/main.nf

@@ -0,0 +1,42 @@
+process RPBP_ESTIMATEMETAGENEBAYESFACTORS {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/14/146c3f15abf184a5ec13531d2a040ba7b9235c1091723aa37c7a119817411367/data' :
+        'community.wave.seqera.io/library/rpbp:4.0.1--71297b462026e13b' }"
+
+    input:
+    tuple val(meta), path(profile_csv)
+
+    output:
+    tuple val(meta), path("${prefix}.metagene-periodicity-bayes-factors.csv.gz"), emit: bayes_factors
+    tuple val("${task.process}"), val('rpbp'), eval('python -c "import rpbp; print(rpbp.__version__)"'), emit: versions_rpbp, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    RPBP_MODELS_BASE=\$(python3 -c "import os, inspect, rpbp; print(os.path.join(os.path.dirname(inspect.getfile(rpbp)), 'models'))")
+    PERIODIC=\$(ls "\$RPBP_MODELS_BASE"/periodic/*.stan)
+    NONPERIODIC=\$(ls "\$RPBP_MODELS_BASE"/nonperiodic/*.stan)
+
+    estimate-metagene-profile-bayes-factors \\
+        ${profile_csv} \\
+        ${prefix}.metagene-periodicity-bayes-factors.csv.gz \\
+        --periodic-models \$PERIODIC \\
+        --nonperiodic-models \$NONPERIODIC \\
+        --num-cpus ${task.cpus} \\
+        ${args}
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo "" | gzip > ${prefix}.metagene-periodicity-bayes-factors.csv.gz
+    """
+}

modules/nf-core/rpbp/estimatemetagenebayesfactors/meta.yml

@@ -0,0 +1,79 @@
+name: "rpbp_estimatemetagenebayesfactors"
+description: |
+  Score how strongly each per-read-length metagene profile shows the
+  3-nucleotide periodicity expected of actively translating ribosomes.
+  For each candidate (read length, P-site offset) pair, Rp-Bp fits two
+  competing Bayesian models to the count window around annotated start
+  codons: a "periodic" model whose signal repeats every three
+  nucleotides, and a "non-periodic" background model. The Bayes factor
+  (ratio of the two marginal likelihoods) quantifies how much the data
+  prefer the periodic explanation.
+
+  Returns one row per (length, offset) pair with the mean and variance of
+  the log Bayes factor across MCMC samples. Downstream,
+  `rpbp/selectperiodicoffsets` picks the best offset per length from
+  this table, and `rpbp/getperiodiclengthsoffsets` filters to the
+  high-confidence pairs that drive ORF-level scoring.
+
+  Uses the Stan models bundled inside the rpbp Python package.
+keywords:
+  - rpbp
+  - metagene
+  - bayes
+  - orf
+  - riboseq
+tools:
+  - "rpbp":
+      description: "Rp-Bp - Bayesian inference of ribosome profiling data for identifying translated open reading frames"
+      homepage: "https://github.com/dieterich-lab/rp-bp"
+      documentation: "https://rp-bp.readthedocs.io"
+      tool_dev_url: "https://github.com/dieterich-lab/rp-bp"
+      doi: "10.1093/nar/gkw1350"
+      licence:
+        - "MIT"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information, e.g. `[ id:'sample1' ]`.
+    - profile_csv:
+        type: file
+        description: Metagene profile CSV produced by `rpbp/extractmetageneprofiles`.
+        pattern: "*.metagene-profile.csv.gz"
+        ontologies: []
+output:
+  bayes_factors:
+    - - meta:
+          type: map
+          description: Groovy Map inherited from input meta.
+      - "${prefix}.metagene-periodicity-bayes-factors.csv.gz":
+          type: file
+          description: Per-read-length metagene periodicity Bayes factors.
+          pattern: "*.metagene-periodicity-bayes-factors.csv.gz"
+          ontologies: []
+  versions_rpbp:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rpbp:
+          type: string
+          description: The name of the tool
+      - python -c "import rpbp; print(rpbp.__version__)":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rpbp:
+          type: string
+          description: The name of the tool
+      - python -c "import rpbp; print(rpbp.__version__)":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"

modules/nf-core/rpbp/estimatemetagenebayesfactors/tests/main.nf.test

@@ -0,0 +1,58 @@
+nextflow_process {
+
+    name "Test Process RPBP_ESTIMATEMETAGENEBAYESFACTORS"
+    script "../main.nf"
+    process "RPBP_ESTIMATEMETAGENEBAYESFACTORS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "rpbp"
+    tag "rpbp/estimatemetagenebayesfactors"
+
+    test("homo_sapiens chr20 - metagene bayes factors") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:true, strandedness:'forward' ],
+                    file("https://raw.githubusercontent.com/pinin4fjords/test-datasets/rpbp-test-data/data/genomics/homo_sapiens/riboseq_expression/rpbp/SRX11780888_chr20.metagene-profile.csv.gz", checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    file(process.out.bayes_factors[0][1]).name,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
+            )
+        }
+    }
+
+    test("homo_sapiens chr20 - metagene bayes factors - stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'test', single_end:true, strandedness:'forward' ],
+                    file("https://raw.githubusercontent.com/pinin4fjords/test-datasets/rpbp-test-data/data/genomics/homo_sapiens/riboseq_expression/rpbp/SRX11780888_chr20.metagene-profile.csv.gz", checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/nf-core/rpbp/estimatemetagenebayesfactors/tests/main.nf.test.snap

@@ -0,0 +1,66 @@
+{
+    "homo_sapiens chr20 - metagene bayes factors": {
+        "content": [
+            "test.metagene-periodicity-bayes-factors.csv.gz",
+            {
+                "versions_rpbp": [
+                    [
+                        "RPBP_ESTIMATEMETAGENEBAYESFACTORS",
+                        "rpbp",
+                        "4.0.1"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-05-20T10:38:07.590598565",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.1"
+        }
+    },
+    "homo_sapiens chr20 - metagene bayes factors - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true,
+                            "strandedness": "forward"
+                        },
+                        "test.metagene-periodicity-bayes-factors.csv.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
+                ],
+                "1": [
+                    [
+                        "RPBP_ESTIMATEMETAGENEBAYESFACTORS",
+                        "rpbp",
+                        "4.0.1"
+                    ]
+                ],
+                "bayes_factors": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": true,
+                            "strandedness": "forward"
+                        },
+                        "test.metagene-periodicity-bayes-factors.csv.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
+                ],
+                "versions_rpbp": [
+                    [
+                        "RPBP_ESTIMATEMETAGENEBAYESFACTORS",
+                        "rpbp",
+                        "4.0.1"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-05-20T10:38:11.903165804",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.1"
+        }
+    }
+}

modules/nf-core/rpbp/estimateorfbayesfactors/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::rpbp=4.0.1

modules/nf-core/rpbp/estimateorfbayesfactors/main.nf

@@ -0,0 +1,44 @@
+process RPBP_ESTIMATEORFBAYESFACTORS {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/14/146c3f15abf184a5ec13531d2a040ba7b9235c1091723aa37c7a119817411367/data' :
+        'community.wave.seqera.io/library/rpbp:4.0.1--71297b462026e13b' }"
+
+    input:
+    tuple val(meta),  path(profiles)
+    tuple val(meta2), path(orfs_genomic_bed)
+
+    output:
+    tuple val(meta), path("${prefix}.bayes-factors.bed.gz"), emit: bayes_factors
+    tuple val("${task.process}"), val('rpbp'), eval('python -c "import rpbp; print(rpbp.__version__)"'), emit: versions_rpbp, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    RPBP_MODELS_BASE=\$(python3 -c "import os, inspect, rpbp; print(os.path.join(os.path.dirname(inspect.getfile(rpbp)), 'models'))")
+    TRANSLATED=\$(ls "\$RPBP_MODELS_BASE"/translated/*.stan)
+    UNTRANSLATED=\$(ls "\$RPBP_MODELS_BASE"/untranslated/*.stan)
+
+    estimate-orf-bayes-factors \\
+        ${profiles} \\
+        ${orfs_genomic_bed} \\
+        ${prefix}.bayes-factors.bed.gz \\
+        --translated-models \$TRANSLATED \\
+        --untranslated-models \$UNTRANSLATED \\
+        --num-cpus ${task.cpus} \\
+        ${args}
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo "" | gzip > ${prefix}.bayes-factors.bed.gz
+    """
+}

modules/nf-core/rpbp/estimateorfbayesfactors/meta.yml

@@ -0,0 +1,87 @@
+name: "rpbp_estimateorfbayesfactors"
+description: |
+  Score every candidate ORF for evidence of active translation. For
+  each ORF, Rp-Bp fits two competing Bayesian models to its per-codon
+  P-site count vector: a "translated" model that expects P-site density
+  to concentrate at codon-start positions (the in-frame signal a
+  translating ribosome produces), and an "untranslated" / noise model
+  for the same data. The Bayes factor (ratio of marginal likelihoods)
+  quantifies how much the data favour the translated hypothesis.
+
+  Emits a BED-style table with one row per ORF carrying genomic
+  coordinates plus the mean and variance of the log Bayes factor across
+  MCMC samples. Downstream, `rpbp/selectfinalpredictionset` applies
+  Bayes-factor, length and overlap rules to this table to produce the
+  final filtered prediction set.
+
+  Uses the Stan models bundled inside the rpbp Python package.
+keywords:
+  - rpbp
+  - orf
+  - bayes
+  - translation
+  - riboseq
+tools:
+  - "rpbp":
+      description: "Rp-Bp - Bayesian inference of ribosome profiling data for identifying translated open reading frames"
+      homepage: "https://github.com/dieterich-lab/rp-bp"
+      documentation: "https://rp-bp.readthedocs.io"
+      tool_dev_url: "https://github.com/dieterich-lab/rp-bp"
+      doi: "10.1093/nar/gkw1350"
+      licence:
+        - "MIT"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information, e.g. `[ id:'sample1' ]`.
+    - profiles:
+        type: file
+        description: Per-ORF P-site profile matrix from `rpbp/extractorfprofiles`.
+        pattern: "*.profiles.mtx.gz"
+        ontologies: []
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map identifying the reference (e.g. `[ id:'reference' ]`).
+    - orfs_genomic_bed:
+        type: file
+        description: Per-ORF genomic BED from `rpbp/preparegenome`.
+        pattern: "*.orfs-genomic.annotated.bed.gz"
+        ontologies: []
+output:
+  bayes_factors:
+    - - meta:
+          type: map
+          description: Groovy Map inherited from input meta.
+      - "${prefix}.bayes-factors.bed.gz":
+          type: file
+          description: Per-ORF translation Bayes factors (BED).
+          pattern: "*.bayes-factors.bed.gz"
+          ontologies: []
+  versions_rpbp:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rpbp:
+          type: string
+          description: The name of the tool
+      - python -c "import rpbp; print(rpbp.__version__)":
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - rpbp:
+          type: string
+          description: The name of the tool
+      - python -c "import rpbp; print(rpbp.__version__)":
+          type: eval
+          description: The expression to obtain the version of the tool
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"