Merge pull request #674 from nf-core/rework_trimming

rannick · web-flow · commit 5f574e8f88a5 · 2025-07-04T09:18:52.000+02:00
Rework trimming
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -45,6 +45,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added `--star_limit_bam_sort_ram` to set the maximum memory for sorting the BAM files in STAR. [#668](https://github.com/nf-core/rnafusion/pull/668)
 - Update STAR-Fusion to 1.15.0 and update nf-core modules [#664](https://github.com/nf-core/rnafusion/pull/664)
 - Update fusionreport 4.0.0 that replaces the score of a fusion with a Fusion Indication Index [#667](https://github.com/nf-core/rnafusion/pull/667)
+- Added a extra trimming step for fusioncatcher in case a different read-length is wished for this tool only [#674](https://github.com/nf-core/rnafusion/pull/674)
 
 ### Changed
 
@@ -97,6 +98,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - The `FUSIONINSPECTOR` process will no longer fail when no fusions have been found. [#651](https://github.com/nf-core/rnafusion/pull/651)
 - Fixed STAR-Fusion build would fail when downloading Pfam and Dfam resources behind SSL. [#653](https://github.com/nf-core/rnafusion/pull/653)
 - Fix bug in argument handling for FusionInspector [#669](https://github.com/nf-core/rnafusion/pull/669)
+- Fix missing memory unit for fusioncatcher [#674](https://github.com/nf-core/rnafusion/pull/674)
 
 ### Removed
 
@@ -118,6 +120,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `--stringtie`         | `--tools stringtie`             |
 | `--all`               | `--tools all`                   |
 |                       | `--fusioncatcher_download_link` |
+|                       | `--trim_tail_fusioncatcher`     |
 
 ## v3.0.2 - [2024-04-10]
 
diff --git a/README.md b/README.md
@@ -113,12 +113,14 @@ For more details about the output files and reports, please refer to the
 
 nf-core/rnafusion was written by Martin Proks ([@matq007](https://github.com/matq007)), Maxime Garcia ([@maxulysse](https://github.com/maxulysse)) and Annick Renevey ([@rannick](https://github.com/rannick))
 
-We thank the following people for their help in the development of this pipeline:
+## We thank the following people for their help in the development of this pipeline
 
 - [Phil Ewels](https://github.com/ewels)
 - [Rickard Hammarén](https://github.com/Hammarn)
 - [Alexander Peltzer](https://github.com/apeltzer)
 - [Praveen Raj](https://github.com/praveenraj2018)
+- [Anabella Trigila](https://github.com/atrigila)
+- [Nicolas Vannieuwkerke](https://github.com/nvnieuwk)
 
 ## Contributions and Support
 
diff --git a/conf/modules.config b/conf/modules.config
@@ -65,7 +65,22 @@ process {
     }
 
     withName: 'FASTP' {
-        ext.args = { params.trim_tail ? "--trim_tail1 ${params.trim_tail} --trim_tail2 ${params.trim_tail} " : '' }
+        ext.args = { params.trim_tail > 0 ? "--trim_tail1 ${params.trim_tail} --trim_tail2 ${params.trim_tail} " : '' }
+        publishDir = [
+            path: { "${params.outdir}/fastp" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'FASTP_FOR_FUSIONCATCHER' {
+        ext.args = { params.trim_tail_fusioncatcher > 0 ? "--trim_tail1 ${params.trim_tail_fusioncatcher} --trim_tail2 ${params.trim_tail_fusioncatcher} " : '' }
+        ext.prefix = { "${meta.id}_trimmed_for_fusioncatcher" }
+        publishDir = [
+            path: { "${params.outdir}/fastp_for_fusioncatcher" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
     }
 
     withName: 'FASTQC' {
diff --git a/docs/output.md b/docs/output.md
@@ -133,7 +133,7 @@ If multiple libraries or runs have been provided for the same sample in the inpu
 
 ### Fastp
 
-If `--trim_fastp` is selected, [fastp](https://github.com/OpenGene/fastp) will filter low quality reads as well as bases at the 5' and 3' ends, trim adapters (automatically detected, but input with parameter `--adapter_fasta` is possible). 3' trimming is also possible via parameter `--trim_tail`.
+If `--tools fastp` is present, [fastp](https://github.com/OpenGene/fastp) will filter low quality reads as well as bases at the 5' and 3' ends, trim adapters (automatically detected, but input with parameter `--adapter_fasta` is possible). 3' trimming is also possible via parameter `--trim_tail`.
 
 <details markdown="1">
 <summary>Output files</summary>
@@ -147,6 +147,22 @@ If `--trim_fastp` is selected, [fastp](https://github.com/OpenGene/fastp) will f
 
 </details>
 
+### Fastp for fusioncatcher
+
+If `trim_tail_fusioncatcher` has any value other than 0, [fastp](https://github.com/OpenGene/fastp) will be run again as above. This allows for additional trimming of read tails before running FusionCatcher. For example if reads are 150bp, using `--trim_tail_fusioncatcher 50` will shorten reads to 100 bp by 50 bases from the 3′ end. 100 bp is the recommended read length to feed into FusionCatcher. The default for `--trim_tail_fusioncatcher` is 0 (no trimming).
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `fastp/`
+  - `<sample>_trimmed_for_fusioncatcher_1.fastp.fastq.gz`
+  - `<sample>_trimmed_for_fusioncatcher_2.fastp.fastq.gz`
+  - `<sample>_trimmed_for_fusioncatcher.fastp.html`
+  - `<sample>_trimmed_for_fusioncatcher.fastp.json`
+  - `<sample>_trimmed_for_fusioncatcher.fastp.log`
+
+</details>
+
 ### FastQC
 
 <details markdown="1">
diff --git a/docs/usage.md b/docs/usage.md
@@ -268,6 +268,8 @@ nextflow run nf-core/rnafusion \
 --adapter_fastq <PATH/TO/ADAPTER/FASTQ> (optional)
 ```
 
+The additional `--trim_tail_fusioncatcher` flag will toggle an additional `fastp` process, especially useful is reads are above 100 bp, which is not handled well by FusionCatcher. The parameter `--trim_tail_fusioncatcher`need to be provided with the number of bases to remove from the tail end.
+
 #### Filter fusions detected by 2 or more tools
 
 ```bash
diff --git a/modules.json b/modules.json
@@ -42,7 +42,7 @@
                     },
                     "fusioncatcher/fusioncatcher": {
                         "branch": "master",
-                        "git_sha": "2a227f75f33415f74a884ef8b33555b151e33de9",
+                        "git_sha": "1037205706929921360f57e8042eae6819825e31",
                         "installed_by": ["modules"]
                     },
                     "gatk4/bedtointervallist": {
diff --git a/modules/nf-core/fusioncatcher/fusioncatcher/main.nf b/modules/nf-core/fusioncatcher/fusioncatcher/main.nf
diff --git a/nextflow.config b/nextflow.config
@@ -39,7 +39,8 @@ params {
     tools_cutoff               = 1
 
     // Trimming
-    trim_tail                  = null
+    trim_tail                  = 0
+    trim_tail_fusioncatcher    = 0
     adapter_fasta              = []
 
     // Compression
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -263,7 +263,13 @@
                 "trim_tail": {
                     "type": "integer",
                     "description": "The amount of bases to trim at the tail of each read, none will be trimmed by default",
-                    "minimum": 1,
+                    "minimum": 0,
+                    "fa_icon": "fas fa-cut"
+                },
+                "trim_tail_fusioncatcher": {
+                    "type": "integer",
+                    "description": "The amount of bases to trim at the tail of each read for fusioncatcher, none will be trimmed by default",
+                    "minimum": 0,
                     "fa_icon": "fas fa-cut"
                 },
                 "adapter_fasta": {
diff --git a/subworkflows/local/fusioncatcher_workflow/main.nf b/subworkflows/local/fusioncatcher_workflow/main.nf
@@ -1,4 +1,5 @@
-include { FUSIONCATCHER_FUSIONCATCHER } from '../../../modules/nf-core/fusioncatcher/fusioncatcher/main'
+include { FASTP as FASTP_FOR_FUSIONCATCHER } from '../../../modules/nf-core/fastp/main'
+include { FUSIONCATCHER_FUSIONCATCHER }      from '../../../modules/nf-core/fusioncatcher/fusioncatcher/main'
 
 // TODO: Remove fusioncatcher_fusions as parameter.
 // TODO: remove dummy file. Work with Channel.empty()
@@ -7,6 +8,8 @@ include { FUSIONCATCHER_FUSIONCATCHER } from '../../../modules/nf-core/fusioncat
 workflow FUSIONCATCHER_WORKFLOW {
     take:
         reads                   // channel [ meta, [ fastqs ] ]
+        fusioncatcher_trimming  // boolean
+        adapter_fasta           // channel [ path ]
         fusioncatcher_ref       // channel [ meta, path       ]
         fusioncatcher_fusions   // path, string
 
@@ -18,6 +21,17 @@ workflow FUSIONCATCHER_WORKFLOW {
             ch_fusioncatcher_fusions = reads.combine(Channel.value(file(fusioncatcher_fusions, checkIfExists:true)))
                                         .map { meta, _reads, fusions -> [ meta, fusions ] }
         } else {
+            if (fusioncatcher_trimming) {
+                FASTP_FOR_FUSIONCATCHER(
+                    reads,
+                    adapter_fasta,
+                    false, // discard_trimmed_pass
+                    false, // save_trimmed_fail
+                    false  // skip_qc
+                )
+                ch_versions = ch_versions.mix(FASTP_FOR_FUSIONCATCHER.out.versions)
+                reads = FASTP_FOR_FUSIONCATCHER.out.reads
+            }
 
             FUSIONCATCHER_FUSIONCATCHER (
                 reads,
diff --git a/subworkflows/local/fusioncatcher_workflow/tests/main.nf.test b/subworkflows/local/fusioncatcher_workflow/tests/main.nf.test
@@ -0,0 +1,53 @@
+nextflow_workflow {
+
+    name "Test Subworkflow FUSIONCATCHER_WORKFLOW"
+    script "../main.nf"
+    workflow "FUSIONCATCHER_WORKFLOW"
+
+    tag "subworkflow"
+    tag "fusioncatcher_workflow"
+    tag "fusioncatcher"
+
+    test("FUSIONCATCHER_WORKFLOW - Stub") {
+        options "-stub"
+
+        when {
+            workflow {
+                """
+                // Input channels
+                input[0] = Channel.of(
+                    [ [ id:'test_sample' ],
+                    file("https://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_1.fq.gz"),
+                    file("https://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_2.fq.gz") ]
+                )
+
+                input[1] = true
+
+                input[2] = []
+
+                input[3] = [
+                    [ id:'fusioncatcher_ref' ],
+                    []
+                ]
+
+                input[4] = []
+
+                """
+            }
+            params {
+                tools                   = 'fusioncatcher'
+                trim_tail_fusioncatcher = 50
+                outdir                  = "$outputDir"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    workflow.out.versions
+                ).match() }
+            )
+        }
+    }
+}
diff --git a/subworkflows/local/fusioncatcher_workflow/tests/main.nf.test.snap b/subworkflows/local/fusioncatcher_workflow/tests/main.nf.test.snap
@@ -0,0 +1,15 @@
+{
+    "FUSIONCATCHER_WORKFLOW - Stub": {
+        "content": [
+            [
+                "versions.yml:md5,24a191a82bb19899f88f6493ad4f1b8c",
+                "versions.yml:md5,aeee6dd3b4dcf4cb11af80dfa0a7bf72"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "25.04.2"
+        },
+        "timestamp": "2025-06-13T16:36:48.833043"
+    }
+}
diff --git a/subworkflows/local/fusionreport_workflow/tests/main.nf.test b/subworkflows/local/fusionreport_workflow/tests/main.nf.test
@@ -23,25 +23,19 @@ nextflow_workflow {
         when {
             workflow {
                 """
-                // Input channels
-                input[0] = Channel.of(
-                    [ [ id:'test_sample' ],
-                    file("https://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_1.fq.gz") ]
-                )
-
-                input[1] = FUSIONREPORT_DOWNLOAD.out.fusionreport_ref
+                input[0] = FUSIONREPORT_DOWNLOAD.out.fusionreport_ref
 
-                input[2] = Channel.of(
+                input[1] = Channel.of(
                     [[ id:'test_sample' ],
                         file("https://github.com/Clinical-Genomics/fusion-report/raw/master/tests/test_data/arriba.tsv") ]
                 )
 
-                input[3] =  Channel.of(
+                input[2] =  Channel.of(
                     [[ id:'test_sample' ],
                         file("https://github.com/Clinical-Genomics/fusion-report/raw/master/tests/test_data/starfusion.tsv") ]
                 )
 
-                input[4] =  Channel.of(
+                input[3] =  Channel.of(
                     [[ id:'test_sample' ],
                         file("https://github.com/Clinical-Genomics/fusion-report/raw/master/tests/test_data/fusioncatcher.txt") ]
                 )
@@ -50,12 +44,12 @@ nextflow_workflow {
             }
             params {
                 fusioninspector_only = false
-                tools_cutoff = 1
+                tools_cutoff    = 1
                 arriba          = true
                 starfusion      = true
                 fusioncatcher   = true
                 no_cosmic       = true
-                outdir               = "$outputDir"
+                outdir          = "$outputDir"
             }
         }
 
diff --git a/subworkflows/local/fusionreport_workflow/tests/main.nf.test.snap b/subworkflows/local/fusionreport_workflow/tests/main.nf.test.snap
@@ -22,25 +22,25 @@
                     {
                         "id": "test_sample"
                     },
-                    "test_sample_fusionreport_index.html:md5,3513bcaa58446399c0957db69402d3bd"
+                    "test_sample_fusionreport_index.html:md5,9dfbf94471173bebbd8085e440515e4d"
                 ]
             ],
             [
                 [
                     {
                         "id": "test_sample"
                     },
-                    "test_sample.fusions.csv:md5,49f378c2112d7e0b3b17d9095c79e6bd"
+                    "test_sample.fusions.csv:md5,ee6c6838110d68bc75a13c19dca0a321"
                 ]
             ],
             [
-                "versions.yml:md5,90749dbf8e3e7b259c935eabb8c6ce1e"
+                "versions.yml:md5,5b80da331704f6d2093b7609537222e8"
             ]
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.3"
+            "nextflow": "25.04.2"
         },
-        "timestamp": "2025-01-07T13:31:41.215356596"
+        "timestamp": "2025-06-19T11:32:39.322725"
     }
 }
diff --git a/tests/test_stub.nf.test b/tests/test_stub.nf.test
@@ -135,6 +135,39 @@ nextflow_pipeline {
         }
     }
 
+    test("stub test fusioncatcher trim") {
+
+        when {
+            params {
+                outdir           = "$outputDir"
+                tools            = "fusioncatcher"
+                trim_tail_fusioncatcher = 50
+                fusion_annot_lib = 'https://github.com/STAR-Fusion/STAR-Fusion-Tutorial/raw/master/CTAT_HumanFusionLib.mini.dat.gz'
+
+            }
+        }
+        then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            // Ignore files with timestamps in their names
+            def stable_name = getAllFilesFromDir(params.outdir, relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}'])
+            // stable_path: All files in ${params.outdir}/ with stable content
+            // def stable_path = getAllFilesFromDir(params.outdir, ignoreFile: 'tests/.nftignore') //TODO uncomment once -stub is removed
+            assertAll(
+                { assert workflow.success},
+                { assert snapshot(
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_rnafusion_software_mqc_versions.yml"),
+                    // All stable path name, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    // stable_path // TODO uncomment once -stub is removed
+                ).match() }
+            )
+        }
+    }
+
     test("stub test starfusion") {
 
         when {
diff --git a/tests/test_stub.nf.test.snap b/tests/test_stub.nf.test.snap
diff --git a/tests/test_stub_bam.nf.test b/tests/test_stub_bam.nf.test
diff --git a/tests/test_stub_bam.nf.test.snap b/tests/test_stub_bam.nf.test.snap
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
