Add ribotricer/detectorfs (nf-core#5112)

* Add ribotricer/detectorfs

* Don't snapshot PDFs

* Complete meta.yml

* Add test for --report_all, address linting things

* Fix tag, add stub tests

* Appease eclint

* Add missing configs

* Make ribotricer versioning more reliable in conda

* Conda differs in floating point precision

* Update nf-test.config

* Apply suggestions from code review

Co-authored-by: Adam Talbot <[email protected]>

* Update modules/nf-core/ribotricer/detectorfs/main.nf

Co-authored-by: Adam Talbot <[email protected]>

* Clarify language around strandedness inference

* default -> filtered

* Fix typo

Co-authored-by: Adam Talbot <[email protected]>

* ifelse -> switch to appease @adamrtalbot

* variables need to be defined outsite switch

* unstranded is broken

* More tests

* Appease eclint

* Fix configs

---------

Co-authored-by: Adam Talbot <[email protected]>

modules/nf-core/ribotricer/detectorfs/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "ribotricer_detectorfs"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::ribotricer=1.3.3"

modules/nf-core/ribotricer/detectorfs/main.nf

@@ -0,0 +1,86 @@
+process RIBOTRICER_DETECTORFS {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ribotricer:1.3.3--pyhdfd78af_0':
+        'biocontainers/ribotricer:1.3.3--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    tuple val(meta2), path(candidate_orfs)
+
+    output:
+    tuple val(meta), path('*_protocol.txt')             , emit: protocol, optional: true
+    tuple val(meta), path('*_bam_summary.txt')          , emit: bam_summary
+    tuple val(meta), path('*_read_length_dist.pdf')     , emit: read_length_dist
+    tuple val(meta), path('*_metagene_profiles_5p.tsv') , emit: metagene_profile_5p
+    tuple val(meta), path('*_metagene_profiles_3p.tsv') , emit: metagene_profile_3p
+    tuple val(meta), path('*_metagene_plots.pdf')       , emit: metagene_plots
+    tuple val(meta), path('*_psite_offsets.txt')        , emit: psite_offsets, optional: true
+    tuple val(meta), path('*_pos.wig')                  , emit: pos_wig
+    tuple val(meta), path('*_neg.wig')                  , emit: neg_wig
+    tuple val(meta), path('*_translating_ORFs.tsv')     , emit: orfs
+    path "versions.yml"                                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def strandedness_cmd = ''
+
+    switch(meta.strandedness) {
+        case "forward":
+            strandedness_cmd = "--stranded yes"
+            break
+        case "reverse":
+            strandedness_cmd = "--stranded reverse"
+            break
+        //
+        // Specifying unstranded seems broken - see
+        // https://github.com/smithlabcode/ribotricer/issues/153. Leaving it
+        // undefined works, though ribotricer may incorrectly infer
+        // strandednesss?
+        //
+        //case "unstranded":
+        //    strandedness_cmd = "--stranded no"
+        //    break
+    }
+    """
+    ribotricer detect-orfs \\
+        --bam $bam \\
+        --ribotricer_index $candidate_orfs \\
+        --prefix $prefix \\
+        $strandedness_cmd \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ribotricer: \$(ribotricer --version 2>&1 | grep ribotricer | sed '1!d ; s/ribotricer, version //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_protocol.txt
+    touch ${prefix}_bam_summary.txt
+    touch ${prefix}_read_length_dist.pdf
+    touch ${prefix}_metagene_profiles_5p.tsv
+    touch ${prefix}_metagene_profiles_3p.tsv
+    touch ${prefix}_metagene_plots.pdf
+    touch ${prefix}_psite_offsets.txt
+    touch ${prefix}_pos.wig
+    touch ${prefix}_neg.wig
+    touch ${prefix}_translating_ORFs.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ribotricer: \$(ribotricer --version 2>&1 | grep ribotricer | sed '1!d ; s/ribotricer, version //')
+    END_VERSIONS
+    """
+}

modules/nf-core/ribotricer/detectorfs/meta.yml

@@ -0,0 +1,99 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "ribotricer_detectorfs"
+description: "Accurate detection of short and long active ORFs using Ribo-seq data"
+keywords:
+  - riboseq
+  - orf
+  - genomics
+tools:
+  - "ribotricer":
+      description: "Python package to detect translating ORF from Ribo-seq data"
+      homepage: "https://github.com/smithlabcode/ribotricer"
+      documentation: "https://github.com/smithlabcode/ribotricer"
+      tool_dev_url: "https://github.com/smithlabcode/ribotricer"
+      doi: "10.1093/bioinformatics/btz878"
+      licence: ["GNU General Public v3 (GPL v3)"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Map containing riboseq sample information
+        e.g. `[ id:'sample1', single_end:false, strandedness: 'single' ]
+  - bam_ribo:
+      type: file
+      description: Sorted riboseq BAM file(s)
+      pattern: "*.{bam}"
+  - bai_ribo:
+      type: file
+      description: Index for sorted riboseq bam file(s)
+      pattern: "*.{bai}"
+  - meta2:
+      type: map
+      description: |
+        Map containing reference information for the candidate ORFs
+        e.g. `[ id:'Ensembl human v.111' ]`
+  - candidate_orfs:
+      type: file
+      description: "TSV file with candidate ORFs from 'ribotricer prepareorfs'"
+      pattern: "*.tsv"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing riboseq sample information
+        e.g. `[ id:'sample1', single_end:false ]
+  - protocol:
+      type: file
+      description: "txt file containing inferred protocol if it was inferred (not supplied as input)"
+      pattern: "*_protocol.txt"
+  - bam_summary:
+      type: file
+      description: "Text summary of reads found in the BAM"
+      pattern: "*_bam_summary.txt"
+  - read_length_dist:
+      type: file
+      description: "PDF-format read length distribution as quality control"
+      pattern: "*_read_length_dist.pdf"
+  - metagene_profile_5p:
+      type: file
+      description: "Metagene profile aligning with the start codon"
+      pattern: "*_metagene_profiles_5p.tsv"
+  - metagene_profile_3p:
+      type: file
+      description: "Metagene profile aligning with the stop codon"
+      pattern: "*_metagene_profiles_3p.tsv"
+  - metagene_plots:
+      type: file
+      description: "Metagene plots for quality control"
+      pattern: "*_metagene_plots.pdf"
+  - psite_offsets:
+      type: file
+      description: |
+        "If the P-site offsets are not provided, txt file containing the
+        derived relative offsets"
+      pattern: "*_psite_offsets.txt"
+  - pos_wig:
+      type: file
+      description: "Positive strand WIG file for visualization in Genome Browser"
+      pattern: "*_pos.wig"
+  - neg_wig:
+      type: file
+      description: "Negative strand WIG file for visualization in Genome Browser"
+      pattern: "*_neg.wig"
+  - orfs:
+      type: file
+      description: |
+        "TSV with ORFs assessed as translating in this BAM file. You can output
+        all ORFs regardless of the translation status with option --report_all"
+      pattern: "*_translating_ORFs.tsv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"