Add dotseq/dotseq

modules/nf-core/dotseq/dotseq/environment.yml

@@ -0,0 +1,17 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::bioconductor-dotseq=1.0.0
+  - conda-forge::r-dplyr=1.2.1
+  - conda-forge::r-eulerr=7.1.0
+  - conda-forge::r-ggplot2=4.0.3
+  - conda-forge::r-ggrepel=0.9.8
+  - conda-forge::r-ggsignif=0.6.4
+  - conda-forge::r-optparse=1.8.2
+  - conda-forge::r-purrr=1.2.2
+  - conda-forge::r-readr=2.2.0
+  - conda-forge::r-tibble=3.3.1
+  - conda-forge::r-tidyr=1.3.2

modules/nf-core/dotseq/dotseq/main.nf

@@ -0,0 +1,57 @@
+process DOTSEQ_DOTSEQ {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/12/12667d472e9ae0f1602041dc018ba6bde294e6190e67999d71b65e7a2df7ea1f/data' :
+        'community.wave.seqera.io/library/bioconductor-dotseq_r-dplyr_r-eulerr_r-ggplot2_pruned:6c8a9ebdec36c958' }"
+
+    input:
+    tuple val(meta), val(contrast_variable), val(reference), val(target)
+    tuple val(meta2), path(samplesheet), path(counts), path(annotation)
+
+    output:
+    tuple val(meta), path("*.translation.dotseq.results.tsv")    , emit: translation
+    tuple val(meta), path("*.dou.dotseq.results.tsv")            , emit: dou
+    tuple val(meta), path("*.dou_strategy.dotseq.results.tsv")   , emit: dou_strategy , optional: true
+    tuple val(meta), path("*.dte_strategy.dotseq.results.tsv")   , emit: dte_strategy , optional: true
+    tuple val(meta), path("*.volcano.png")                       , emit: volcano_plot  , optional: true
+    tuple val(meta), path("*.composite.png")                     , emit: composite_plot, optional: true
+    tuple val(meta), path("*.venn.png")                          , emit: venn_plot     , optional: true
+    tuple val(meta), path("*.heatmap.png")                       , emit: heatmap_plot  , optional: true
+    tuple val(meta), path("*.interaction_p_distribution.png")    , emit: interaction_p_distribution_plot, optional: true
+    tuple val(meta), path("*.DOTSeqDataSets.rds")                , emit: rdata
+    tuple val(meta), path("*.R_sessionInfo.log")                 , emit: session_info
+    path "versions.yml"                                          , emit: versions, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'dotseq.R'
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.translation.dotseq.results.tsv
+    touch ${prefix}.dou.dotseq.results.tsv
+    touch ${prefix}.dou_strategy.dotseq.results.tsv
+    touch ${prefix}.dte_strategy.dotseq.results.tsv
+    touch ${prefix}.volcano.png
+    touch ${prefix}.composite.png
+    touch ${prefix}.venn.png
+    touch ${prefix}.heatmap.png
+    touch ${prefix}.interaction_p_distribution.png
+    touch ${prefix}.DOTSeqDataSets.rds
+    touch ${prefix}.R_sessionInfo.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bioconductor-dotseq: \$(Rscript -e "cat(as.character(packageVersion('DOTSeq')))")
+        r-optparse: \$(Rscript -e "cat(as.character(packageVersion('optparse')))")
+        r-readr: \$(Rscript -e "cat(as.character(packageVersion('readr')))")
+        r-dplyr: \$(Rscript -e "cat(as.character(packageVersion('dplyr')))")
+    END_VERSIONS
+    """
+}

modules/nf-core/dotseq/dotseq/meta.yml

@@ -0,0 +1,207 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "dotseq_dotseq"
+description: |
+  Detect differential ORF usage (DOU) and ORF-level differential
+  translation efficiency (DTE) from Ribo-seq with matched RNA-seq using
+  DOTSeq. Wraps DOTSeqDataSetsFromSummarizeOverlaps() + DOTSeq() +
+  getContrasts() and emits the package's native contrast tables plus
+  plotDOT() visualisations.
+keywords:
+  - riboseq
+  - rnaseq
+  - translation
+  - differential
+  - orf
+tools:
+  - "dotseq":
+      description: "Differential ORF Translation analysis for Ribo-seq with matched RNA-seq"
+      homepage: "https://bioconductor.org/packages/release/bioc/html/DOTSeq.html"
+      documentation: "https://bioconductor.org/packages/release/bioc/vignettes/DOTSeq/inst/doc/DOTSeq.html"
+      tool_dev_url: "https://github.com/compgenom/DOTSeq"
+      licence:
+        - "MIT"
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+    - contrast_variable:
+        type: string
+        description: Sample-sheet column that holds the experimental condition (mapped to DOTSeq's `condition` internally).
+    - reference:
+        type: string
+        description: Value of the contrast_variable to use as reference (baseline).
+    - target:
+        type: string
+        description: Value of the contrast_variable to use as target (non-reference).
+  - - meta2:
+        type: map
+        description: Groovy map containing study-wide metadata
+    - samplesheet:
+        type: file
+        description: |
+          CSV or TSV sample sheet with `run`, `strategy`, `replicate`, and
+          `condition` columns (defaults; can be overridden via
+          task.ext.args). Both Ribo-seq and RNA-seq samples are required:
+          DOTSeq's design is `~ condition * strategy` and the interaction
+          term is unestimable without both strategies.
+        ontologies:
+          - edam: "http://edamontology.org/format_3752"
+          - edam: "http://edamontology.org/format_3475"
+    - counts:
+        type: file
+        description: |
+          Per-ORF count matrix. First column is the ORF identifier (default
+          `orf_id`, override via `--orf_id_col`); remaining columns are
+          sample IDs that must match the `run` values in the sample sheet.
+          Both Ribo-seq and RNA-seq sample columns belong in this single
+          matrix; the sample sheet's `strategy` column distinguishes them.
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+    - annotation:
+        type: file
+        description: |
+          Per-ORF annotation table (one row per ORF). Required columns:
+          `orf_id` (matches the count matrix) and `gene_id` (parent gene;
+          DOTSeq's DOU model groups child ORFs by gene). Optional columns:
+          `orf_type` (mORF / uORF / dORF; used by plotDOT()'s heatmap and
+          defaults to mORF when absent) and `chrom`, `start`, `end`,
+          `strand` (used only for downstream inspection - dummy ranges
+          are generated when absent because DOTSeq's fit does not depend
+          on genomic coordinates). Column names can be overridden via
+          task.ext.args (`--gene_id_col`, `--orf_type_col`, etc.).
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+
+output:
+  translation:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.translation.dotseq.results.tsv":
+          type: file
+          description: |
+            Per-ORF differential translation efficiency: DOTSeq's DTE
+            interaction-term results (DESeq2 + ashr shrinkage).
+          pattern: ".translation.dotseq.results.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  dou:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.dou.dotseq.results.tsv":
+          type: file
+          description: |
+            DOTSeq Differential ORF Usage results (beta-binomial GLM
+            modelling Ribo / RNA proportion changes within each gene,
+            shrunk with ashr). DOTSeq-unique.
+          pattern: ".dou.dotseq.results.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  dou_strategy:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.dou_strategy.dotseq.results.tsv":
+          type: file
+          description: DOU strategy contrasts (Ribo vs RNA effect per condition), when present.
+          pattern: ".dou_strategy.dotseq.results.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  dte_strategy:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.dte_strategy.dotseq.results.tsv":
+          type: file
+          description: DTE strategy contrasts (Ribo vs RNA effect per condition), when present.
+          pattern: ".dte_strategy.dotseq.results.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  volcano_plot:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.volcano.png":
+          type: file
+          description: DOTSeq plotDOT() volcano (DOU + DTE significance).
+          pattern: ".volcano.png"
+          ontologies:
+            - edam: "http://edamontology.org/format_3603"
+  composite_plot:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.composite.png":
+          type: file
+          description: DOTSeq plotDOT() composite scatter (DOU vs DTE effect sizes).
+          pattern: ".composite.png"
+          ontologies:
+            - edam: "http://edamontology.org/format_3603"
+  venn_plot:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.venn.png":
+          type: file
+          description: DOTSeq plotDOT() Venn diagram of DOU vs DTE significant ORFs.
+          pattern: ".venn.png"
+          ontologies:
+            - edam: "http://edamontology.org/format_3603"
+  heatmap_plot:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.heatmap.png":
+          type: file
+          description: DOTSeq plotDOT() heatmap of DOU across top genes.
+          pattern: ".heatmap.png"
+          ontologies:
+            - edam: "http://edamontology.org/format_3603"
+  interaction_p_distribution_plot:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.interaction_p_distribution.png":
+          type: file
+          description: Histogram of DOTSeq's DTE adjusted p-values.
+          pattern: ".interaction_p_distribution.png"
+          ontologies:
+            - edam: "http://edamontology.org/format_3603"
+  rdata:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.DOTSeqDataSets.rds":
+          type: file
+          description: Serialised DOTSeqDataSets object containing DOU + DTE fits
+          pattern: ".DOTSeqDataSets.rds"
+          ontologies: []
+  session_info:
+    - - meta:
+          type: map
+          description: Groovy Map containing contrast information. e.g. [ id:'treatment_vs_control' ]
+      - "*.R_sessionInfo.log":
+          type: file
+          description: dump of R sessionInfo()
+          pattern: "*.log"
+          ontologies:
+            - edam: "http://edamontology.org/data_1678"
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: "http://edamontology.org/format_3750"
+topics:
+  versions:
+    - versions.yml:
+        type: string
+        description: The name of the process
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"