feat(fastq_qc_trim_filter_setstrandedness): Add Bowtie2 as alternative rRNA removal tool

modules/nf-core/ribodetector/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::ribodetector=0.3.1"
+  - "bioconda::ribodetector=0.3.2"

modules/nf-core/ribodetector/main.nf

@@ -4,8 +4,8 @@ process RIBODETECTOR {
 
 	conda "${moduleDir}/environment.yml"
 	container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-		'https://depot.galaxyproject.org/singularity/ribodetector:0.3.1--pyhdfd78af_0':
-		'biocontainers/ribodetector:0.3.1--pyhdfd78af_0' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/4d/4de8fe74d21198e6fc8218cb3209d929b3d7dab750678501b096b0ccc324307b/data' :
+        'community.wave.seqera.io/library/ribodetector:0.3.2--cbe1c77fa14eeb53' }"
 
 	input:
 	tuple val(meta), path(fastq)
@@ -14,7 +14,7 @@ process RIBODETECTOR {
 	output:
 	tuple val(meta), path("*.nonrna*.fastq.gz"), emit: fastq
 	tuple val(meta), path("*.log")             , emit: log
-	path "versions.yml"                        , emit: versions
+	tuple val("${task.process}"), val('ribodetector'), eval('ribodetector --version | sed "s/ribodetector //"'), emit: versions_ribodetector, topic: versions
 
 	when:
 	task.ext.when == null || task.ext.when
@@ -35,11 +35,6 @@ process RIBODETECTOR {
 		--log ${prefix}.log \\
 		${ribodetector_mem} \\
 		${args}
-
-	cat <<-END_VERSIONS > versions.yml
-	"${task.process}":
-		ribodetector: \$(ribodetector --version | sed 's/ribodetector //g')
-	END_VERSIONS
 	"""
 
 	stub:
@@ -50,12 +45,7 @@ process RIBODETECTOR {
 	echo $args
 
 	echo | gzip > ${prefix}.nonrna.1.fastq.gz
-    echo | gzip > ${prefix}.nonrna.2.fastq.gz
+	echo | gzip > ${prefix}.nonrna.2.fastq.gz
 	touch ${prefix}.log
-
-	cat <<-END_VERSIONS > versions.yml
-	"${task.process}":
-		ribodetector: \$(ribodetector --version | sed 's/ribodetector //g')
-	END_VERSIONS
 	"""
 }

modules/nf-core/ribodetector/meta.yml

@@ -1,7 +1,6 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "ribodetector"
-description: Accurate and rapid RiboRNA sequences Detector based on deep
-  learning
+description: Accurate and rapid RiboRNA sequences Detector based on deep learning
 keywords:
   - RNA
   - RNAseq
@@ -16,10 +15,10 @@ keywords:
 tools:
   - ribodetector:
       description: Accurate and rapid RiboRNA sequences detector based on deep learning.
-        RiboDetector uses a deep learning approach to identify rRNA sequences in
-        ribosome profiling (Ribo-seq) data. It can be used to filter out rRNA reads
-        from Ribo-seq datasets, improving the quality of downstream analyses. As of version
-        0.3.1, Ribodetector doesn't support setting a random seed, so results may not be fully
+        RiboDetector uses a deep learning approach to identify rRNA sequences in ribosome
+        profiling (Ribo-seq) data. It can be used to filter out rRNA reads from Ribo-seq
+        datasets, improving the quality of downstream analyses. As of version 0.3.1,
+        Ribodetector doesn't support setting a random seed, so results may not be fully
         deterministic across runs.
       homepage: "https://github.com/hzi-bifo/RiboDetector"
       documentation: "https://github.com/hzi-bifo/RiboDetector"
@@ -67,13 +66,27 @@ output:
           description: Log file from RiboDetector
           pattern: "*.log"
           ontologies: []
+  versions_ribodetector:
+    - - ${task.process}:
+          type: string
+          description: Name of the process
+      - ribodetector:
+          type: string
+          description: Name of the tool
+      - ribodetector --version | sed "s/ribodetector //:
+          type: string
+          description: Version of ribodetector used
+topics:
   versions:
-    - versions.yml:
-        type: file
-        description: File containing software versions
-        pattern: versions.yml
-        ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+    - - ${task.process}:
+          type: string
+          description: Name of the process
+      - ribodetector:
+          type: string
+          description: Name of the tool
+      - ribodetector --version | sed "s/ribodetector //:
+          type: string
+          description: Version of ribodetector used
 authors:
   - "@maxibor"
 maintainers:

modules/nf-core/ribodetector/tests/main.nf.test

@@ -29,8 +29,8 @@ nextflow_process {
                 { assert process.success },
                 { assert process.out.fastq },
                 { assert process.out.log },
-                { assert path(process.out.log[0][1]).getText().contains("Writing output non-rRNA sequences") },
-                { assert snapshot(process.out.versions).match() }
+                { assert path(process.out.log[0][1]).getText().contains("Writing output non-rRNA sequences") }
+                // Note: versions collected via topic, not snapshotted
             )
         }
 

modules/nf-core/ribodetector/tests/main.nf.test.snap

@@ -1,16 +1,4 @@
 {
-    "ribodetector - rnaseq PE input": {
-        "content": [
-            [
-                "versions.yml:md5,f98df8f0eaa704e4db74785adc9cc791"
-            ]
-        ],
-        "meta": {
-            "nf-test": "0.9.3",
-            "nextflow": "25.10.0"
-        },
-        "timestamp": "2025-11-07T13:20:15.909875"
-    },
     "ribodetector - stub rnaseq PE input": {
         "content": [
             {
@@ -36,7 +24,11 @@
                     ]
                 ],
                 "2": [
-                    "versions.yml:md5,f98df8f0eaa704e4db74785adc9cc791"
+                    [
+                        "RIBODETECTOR",
+                        "ribodetector",
+                        "0.3.2"
+                    ]
                 ],
                 "fastq": [
                     [
@@ -59,15 +51,19 @@
                         "test.log:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "versions": [
-                    "versions.yml:md5,f98df8f0eaa704e4db74785adc9cc791"
+                "versions_ribodetector": [
+                    [
+                        "RIBODETECTOR",
+                        "ribodetector",
+                        "0.3.2"
+                    ]
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.3",
             "nextflow": "25.10.0"
         },
-        "timestamp": "2025-11-07T13:20:26.026547"
+        "timestamp": "2025-11-29T20:07:13.509994907"
     }
 }

subworkflows/nf-core/fastq_qc_trim_filter_setstrandedness/main.nf

@@ -1,13 +1,10 @@
 include { BBMAP_BBSPLIT                         } from '../../../modules/nf-core/bbmap/bbsplit'
 include { CAT_FASTQ                             } from '../../../modules/nf-core/cat/fastq/main'
-include { RIBODETECTOR                          } from '../../../modules/nf-core/ribodetector/main'
-include { SEQKIT_STATS                          } from '../../../modules/nf-core/seqkit/stats/main'
-include { SORTMERNA                             } from '../../../modules/nf-core/sortmerna/main'
-include { SORTMERNA as SORTMERNA_INDEX          } from '../../../modules/nf-core/sortmerna/main'
 include { FQ_LINT                               } from '../../../modules/nf-core/fq/lint/main'
 include { FQ_LINT as FQ_LINT_AFTER_TRIMMING     } from '../../../modules/nf-core/fq/lint/main'
 include { FQ_LINT as FQ_LINT_AFTER_BBSPLIT      } from '../../../modules/nf-core/fq/lint/main'
 include { FQ_LINT as FQ_LINT_AFTER_RIBO_REMOVAL } from '../../../modules/nf-core/fq/lint/main'
+include { FASTQ_REMOVE_RRNA                     } from '../fastq_remove_rrna'
 include { FASTQ_SUBSAMPLE_FQ_SALMON             } from '../fastq_subsample_fq_salmon'
 include { FASTQ_FASTQC_UMITOOLS_TRIMGALORE      } from '../fastq_fastqc_umitools_trimgalore'
 include { FASTQ_FASTQC_UMITOOLS_FASTP           } from '../fastq_fastqc_umitools_fastp'
@@ -84,29 +81,6 @@ def multiqcTsvFromList(tsv_data, header) {
     return tsv_string
 }
 
-//
-// Function that parses seqkit stats TSV output to extract the mean read length
-// for use with RiboDetector's -l parameter
-//
-def getReadLengthFromSeqkitStats(stats_file) {
-    def lines = stats_file.text.readLines()
-    if (lines.size() < 2) {
-        return 100 // Default fallback
-    }
-
-    def header = lines[0].split('\t')
-    def avgLenIdx = header.findIndexOf { it == 'avg_len' }
-    if (avgLenIdx < 0) {
-        return 100 // Default fallback if column not found
-    }
-
-    // Calculate mean avg_len across all files in the stats output
-    def avgLens = lines[1..-1].collect { it.split('\t')[avgLenIdx] as float }
-    def meanAvgLen = avgLens.sum() / avgLens.size()
-
-    return Math.round(meanAvgLen) as int
-}
-
 workflow FASTQ_QC_TRIM_FILTER_SETSTRANDEDNESS {
     take:
     // Input channels
@@ -116,8 +90,9 @@ workflow FASTQ_QC_TRIM_FILTER_SETSTRANDEDNESS {
     ch_gtf               // channel: /path/to/genome.gtf
     ch_salmon_index      // channel: /path/to/salmon/index/ (optional)
     ch_sortmerna_index   // channel: /path/to/sortmerna/index/ (optional)
+    ch_bowtie2_index     // channel: /path/to/bowtie2/index/ (optional)
     ch_bbsplit_index     // channel: /path/to/bbsplit/index/ (optional)
-    ch_rrna_fastas       // channel: one or more fasta files containing rrna sequences to be passed to SortMeRNA (optional)
+    ch_rrna_fastas       // channel: one or more fasta files containing rrna sequences to be passed to SortMeRNA/Bowtie2 (optional)
 
     // Skip options
     skip_bbsplit         // boolean: Skip BBSplit for removal of non-reference genome reads.
@@ -129,6 +104,7 @@ workflow FASTQ_QC_TRIM_FILTER_SETSTRANDEDNESS {
     // Index generation
     make_salmon_index    // boolean: Whether to create salmon index before running salmon quant
     make_sortmerna_index // boolean: Whether to create a sortmerna index before running sortmerna
+    make_bowtie2_index   // boolean: Whether to create a bowtie2 index before running bowtie2
 
     // Trimming options
     trimmer              // string (enum): 'fastp' or 'trimgalore'
@@ -138,7 +114,7 @@ workflow FASTQ_QC_TRIM_FILTER_SETSTRANDEDNESS {
 
     // rRNA removal options
     remove_ribo_rna           // boolean: true/false: whether to remove rRNA
-    ribo_removal_tool         // string (enum): 'sortmerna' or 'ribodetector'
+    ribo_removal_tool         // string (enum): 'sortmerna', 'ribodetector', or 'bowtie2'
 
     // UMI options
     with_umi             // boolean: true/false: Enable UMI-based read deduplication.
@@ -294,64 +270,22 @@ workflow FASTQ_QC_TRIM_FILTER_SETSTRANDEDNESS {
     }
 
     //
-    // MODULE: Remove ribosomal RNA reads
+    // SUBWORKFLOW: Remove ribosomal RNA reads
     //
     if (remove_ribo_rna) {
-        if (ribo_removal_tool == 'sortmerna') {
-            ch_sortmerna_fastas = ch_rrna_fastas
-                .collect()
-                .map { [[id: 'rrna_refs'], it] }
-
-            if (make_sortmerna_index) {
-                SORTMERNA_INDEX(
-                    [[], []],
-                    ch_sortmerna_fastas,
-                    [[], []],
-                )
-                ch_sortmerna_index = SORTMERNA_INDEX.out.index.first()
-            }
-
-            SORTMERNA(
-                ch_filtered_reads,
-                ch_sortmerna_fastas,
-                ch_sortmerna_index,
-            )
-
-            SORTMERNA.out.reads.set { ch_filtered_reads }
-
-            ch_multiqc_files = ch_multiqc_files.mix(SORTMERNA.out.log)
-
-            ch_versions = ch_versions.mix(SORTMERNA.out.versions.first())
-        }
-        else if (ribo_removal_tool == 'ribodetector') {
-            // Run seqkit stats to determine average read length
-            SEQKIT_STATS(
-                ch_filtered_reads
-            )
-
-            ch_versions = ch_versions.mix(SEQKIT_STATS.out.versions.first())
-
-            // Join stats with reads and calculate read length for RiboDetector
-            ch_filtered_reads
-                .join(SEQKIT_STATS.out.stats)
-                .multiMap { meta, reads, stats ->
-                    def readLength = getReadLengthFromSeqkitStats(stats)
-                    reads: [meta, reads]
-                    length: readLength
-                }
-                .set { ch_reads_with_length }
-
-            RIBODETECTOR(
-                ch_reads_with_length.reads,
-                ch_reads_with_length.length,
-            )
-
-            RIBODETECTOR.out.fastq.set { ch_filtered_reads }
-
-            ch_multiqc_files = ch_multiqc_files.mix(RIBODETECTOR.out.log)
+        FASTQ_REMOVE_RRNA(
+            ch_filtered_reads,
+            ch_rrna_fastas,
+            ch_sortmerna_index,
+            ch_bowtie2_index,
+            ribo_removal_tool,
+            make_sortmerna_index,
+            make_bowtie2_index,
+        )
 
-            ch_versions = ch_versions.mix(RIBODETECTOR.out.versions.first())
-        }
+        ch_filtered_reads = FASTQ_REMOVE_RRNA.out.reads
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQ_REMOVE_RRNA.out.multiqc_files)
+        ch_versions = ch_versions.mix(FASTQ_REMOVE_RRNA.out.versions)
 
         if (!skip_linting) {
             FQ_LINT_AFTER_RIBO_REMOVAL(

subworkflows/nf-core/fastq_qc_trim_filter_setstrandedness/meta.yml

@@ -9,14 +9,9 @@ keywords:
   - strandedness
 components:
   - bbmap/bbsplit
-  - samtools/sort
-  - samtools/index
-  - cat
   - cat/fastq
   - fq/lint
-  - ribodetector
-  - seqkit/stats
-  - sortmerna
+  - fastq_remove_rrna
   - fastq_subsample_fq_salmon
   - fastq_fastqc_umitools_trimgalore
   - fastq_fastqc_umitools_fastp
@@ -79,6 +74,15 @@ input:
         - index:
             type: directory
             description: SortMeRNA index directory
+  - ch_bowtie2_index:
+      description: Directory containing bowtie2 index for rRNA removal
+      structure:
+        - meta:
+            type: map
+            description: Metadata for the Bowtie2 index
+        - index:
+            type: directory
+            description: Bowtie2 index directory
   - ch_bbsplit_index:
       description: Path to directory or tar.gz archive for pre-built BBSplit index
       structure:
@@ -90,7 +94,7 @@ input:
             description: BBSplit index directory or tar.gz archive
             pattern: "{*,*.tar.gz}"
   - ch_rrna_fastas:
-      description: Channel containing one or more FASTA files containing rRNA sequences for use with SortMeRNA
+      description: Channel containing one or more FASTA files containing rRNA sequences for use with SortMeRNA or Bowtie2
       structure:
         - meta:
             type: map
@@ -120,6 +124,9 @@ input:
   - make_sortmerna_index:
       type: boolean
       description: Whether to create sortmerna index before running sortmerna
+  - make_bowtie2_index:
+      type: boolean
+      description: Whether to create bowtie2 index before running bowtie2 for rRNA removal
   - trimmer:
       type: string
       description: Specifies the trimming tool to use
@@ -140,7 +147,7 @@ input:
   - ribo_removal_tool:
       type: string
       description: Specifies the rRNA removal tool to use
-      enum: ["sortmerna", "ribodetector"]
+      enum: ["sortmerna", "ribodetector", "bowtie2"]
   - with_umi:
       type: boolean
       description: Enable UMI-based read deduplication