Add nf-test to TRIM_WORKFLOW

CHANGELOG.md

@@ -17,7 +17,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add nf-test to nf-core module: `PICARD_COLLECTRNASEQMETRICS` and update module [#551](https://github.com/nf-core/rnafusion/pull/551)
 - Add `--skip_vcf` boolean parameter to skip vcf file generation [#554](https://github.com/nf-core/rnafusion/pull/554)
 - Add nf-test to local module: `FUSIONREPORT_DOWNLOAD` [#560](https://github.com/nf-core/rnafusion/pull/560)
-- Add nf-test to local subworkflow: `QC_SUBWORKFLOW` [#568](https://github.com/nf-core/rnafusion/pull/568)
+- Add nf-test to local subworkflow: `QC_WORKFLOW` [#568](https://github.com/nf-core/rnafusion/pull/568)
+- Add nf-test to local subworkflow: `TRIM_WORKFLOW` [#572](https://github.com/nf-core/rnafusion/pull/572)
 
 ### Changed
 

subworkflows/local/trim_workflow/main.nf

@@ -0,0 +1,46 @@
+
+
+include { FASTP                      } from '../../../modules/nf-core/fastp/main'
+include { FASTQC as FASTQC_FOR_FASTP } from '../../../modules/nf-core/fastqc/main'
+
+workflow TRIM_WORKFLOW {
+
+    take:
+        reads           // channel [ meta, [ fastqs ] ]
+        adapter_fasta   // channel [ path ]
+        fastp_trim      // boolean
+
+    main:
+        ch_versions       = Channel.empty()
+        ch_fastp_html     = Channel.empty()
+        ch_fastp_json     = Channel.empty()
+        ch_fastqc_trimmed = Channel.empty()
+
+        if ( fastp_trim ) {
+            FASTP(reads, adapter_fasta.ifEmpty( [] ), false, false, false)
+            ch_versions = ch_versions.mix(FASTP.out.versions)
+
+            FASTQC_FOR_FASTP(FASTP.out.reads)
+            ch_versions = ch_versions.mix(FASTQC_FOR_FASTP.out.versions)
+
+            ch_reads_all           = FASTP.out.reads
+            ch_reads_fusioncatcher = ch_reads_all
+            ch_fastp_html          = FASTP.out.html
+            ch_fastp_json          = FASTP.out.json
+            ch_fastqc_trimmed      = FASTQC_FOR_FASTP.out.zip
+
+        }
+        else {
+            ch_reads_all           = reads
+            ch_reads_fusioncatcher = reads
+        }
+
+    emit:
+        ch_reads_all            // Channel [ meta, [reads]   ]
+        ch_reads_fusioncatcher  // Channel [ meta, [reads]   ]
+        ch_fastp_html           // Channel [ meta, path_html ]
+        ch_fastp_json           // Channel [ meta, path_json ]
+        ch_fastqc_trimmed       // Channel [ meta, path_zip  ]
+        versions = ch_versions  // Channel [ versions        ]
+    }
+

subworkflows/local/trim_workflow/tests/main.nf.test

@@ -0,0 +1,85 @@
+nextflow_workflow {
+
+    name "Test Subworkflow QC_WORKFLOW"
+    script "../main.nf"
+    workflow "TRIM_WORKFLOW"
+    tag "qc"
+    tag "subworkflow"
+
+    test("TRIM_WORKFLOW - Homo sapiens - FASTQs - FastP true") {
+
+        when {
+
+            workflow {
+                """
+                // ch_reads
+                input[0] = Channel.of(
+                    [
+                        [id: "test_fastq"],
+                        [
+                            file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz", checkIfExists: true),
+                            file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz", checkIfExists: true)
+                        ]
+                    ])
+                input[1] = Channel.empty()
+                input[2] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { with(workflow.out) {
+                    assert snapshot(
+                        versions.collect{ file(it) },
+                        ch_reads_all[0][1].collect { file(it) },
+                        ch_reads_fusioncatcher[0][1].collect { file(it) },
+                        file(ch_fastp_html[0][1]).name,
+                        file(ch_fastp_json[0][1]),
+                        ch_fastqc_trimmed[0][1].collect { file(it).name }
+                    ).match() }
+                }
+            )
+        }
+    }
+
+    test("TRIM_WORKFLOW - Homo sapiens - FASTQs - FastP false") {
+
+        when {
+
+            workflow {
+                """
+                // ch_reads
+                input[0] = Channel.of(
+                    [
+                        [id: "test_fastq"],
+                        [
+                            file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz", checkIfExists: true),
+                            file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz", checkIfExists: true)
+                        ]
+                    ])
+                input[1] = Channel.empty()
+                input[2] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { with(workflow.out) {
+                    assert snapshot(
+                        versions.size() == 0,
+                        ch_reads_all[0][1].size() == 2,
+                        ch_reads_fusioncatcher[0][1].size() == 2,
+                        ch_fastp_html.size() == 0,
+                        ch_fastp_json.size() == 0,
+                        ch_fastqc_trimmed.size() == 0
+                    ).match() }
+                }
+            )
+        }
+    }
+
+}

subworkflows/local/trim_workflow/tests/main.nf.test.snap

@@ -0,0 +1,44 @@
+{
+    "TRIM_WORKFLOW - Homo sapiens - FASTQs - FastP true": {
+        "content": [
+            [
+                "versions.yml:md5,16187796d989b6260f572247e7dc0fc6",
+                "versions.yml:md5,ea42abe9875f41f8362a55ee7533f102"
+            ],
+            [
+                "test_fastq_1.fastp.fastq.gz:md5,0c436583301dea48755a5252a2675b64",
+                "test_fastq_2.fastp.fastq.gz:md5,f7f38138255e63b33286b819b6177612"
+            ],
+            [
+                "test_fastq_1.fastp.fastq.gz:md5,0c436583301dea48755a5252a2675b64",
+                "test_fastq_2.fastp.fastq.gz:md5,f7f38138255e63b33286b819b6177612"
+            ],
+            "test_fastq.fastp.html",
+            "test_fastq.fastp.json:md5,62066ad48c3d5981045cdd43e354cb2b",
+            [
+                "test_fastq_trimmed_1_fastqc.zip",
+                "test_fastq_trimmed_2_fastqc.zip"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-05T14:11:12.374063253"
+    },
+    "TRIM_WORKFLOW - Homo sapiens - FASTQs - FastP false": {
+        "content": [
+            true,
+            true,
+            true,
+            true,
+            true,
+            true
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-05T14:21:42.396615145"
+    }
+}

workflows/rnafusion.nf

@@ -22,23 +22,25 @@ include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pi
 include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_rnafusion_pipeline'
 
 
-ch_chrgtf = params.starfusion_build ? Channel.fromPath(params.chrgtf).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_annot.gtf").map { it -> [[id:it.Name], it] }.collect()
-ch_starindex_ref = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
-ch_starindex_ensembl_ref = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_refflat = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
-ch_rrna_interval = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
-ch_fusionreport_ref = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_blacklist = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_known_fusions = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
+ch_chrgtf                     = params.starfusion_build ? Channel.fromPath(params.chrgtf).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_annot.gtf").map { it -> [[id:it.Name], it] }.collect()
+ch_starindex_ref              = params.starfusion_build ? Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.starfusion_ref}/ref_genome.fa.star.idx").map { it -> [[id:it.Name], it] }.collect()
+ch_starindex_ensembl_ref      = Channel.fromPath(params.starindex_ref).map { it -> [[id:it.Name], it] }.collect()
+ch_refflat                    = params.starfusion_build ? Channel.fromPath(params.refflat).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.gtf.refflat").map { it -> [[id:it.Name], it] }.collect()
+ch_rrna_interval              = params.starfusion_build ?  Channel.fromPath(params.rrna_intervals).map { it -> [[id:it.Name], it] }.collect() : Channel.fromPath("${params.ensembl_ref}/ref_annot.interval_list").map { it -> [[id:it.Name], it] }.collect()
+ch_adapter_fastp              = params.adapter_fasta ? Channel.fromPath(params.adapter_fasta, checkIfExists: true) : Channel.empty()
+ch_fusionreport_ref           = Channel.fromPath(params.fusionreport_ref).map { it -> [[id:it.Name], it] }.collect()
+ch_arriba_ref_blacklist       = Channel.fromPath(params.arriba_ref_blacklist).map { it -> [[id:it.Name], it] }.collect()
+ch_arriba_ref_known_fusions   = Channel.fromPath(params.arriba_ref_known_fusions).map { it -> [[id:it.Name], it] }.collect()
 ch_arriba_ref_protein_domains = Channel.fromPath(params.arriba_ref_protein_domains).map { it -> [[id:it.Name], it] }.collect()
-ch_arriba_ref_cytobands = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
-ch_hgnc_ref = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
-ch_hgnc_date = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
-ch_fasta = Channel.fromPath(params.fasta).map { it -> [[id:it.Name], it] }.collect()
-ch_gtf = Channel.fromPath(params.gtf).map { it -> [[id:it.Name], it] }.collect()
+ch_arriba_ref_cytobands       = Channel.fromPath(params.arriba_ref_cytobands).map { it -> [[id:it.Name], it] }.collect()
+ch_hgnc_ref     = Channel.fromPath(params.hgnc_ref).map { it -> [[id:it.Name], it] }.collect()
+ch_hgnc_date    = Channel.fromPath(params.hgnc_date).map { it -> [[id:it.Name], it] }.collect()
+ch_fasta        = Channel.fromPath(params.fasta).map { it -> [[id:it.Name], it] }.collect()
+ch_gtf          = Channel.fromPath(params.gtf).map { it -> [[id:it.Name], it] }.collect()
 ch_salmon_index = Channel.fromPath(params.salmon_index).map { it -> [[id:it.Name], it] }.collect()
-ch_transcript = Channel.fromPath(params.transcript).map { it -> [[id:it.Name], it] }.collect()
-ch_fai = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
+ch_transcript   = Channel.fromPath(params.transcript).map { it -> [[id:it.Name], it] }.collect()
+ch_fai          = Channel.fromPath(params.fai).map { it -> [[id:it.Name], it] }.collect()
+
 
 
 /*
@@ -51,6 +53,7 @@ workflow RNAFUSION {
 
     take:
     ch_samplesheet // channel: samplesheet read in from --input
+
     main:
 
     ch_versions = Channel.empty()
@@ -67,11 +70,13 @@ workflow RNAFUSION {
 
 
     TRIM_WORKFLOW (
-        ch_samplesheet
+        ch_samplesheet,
+        ch_adapter_fastp,
+        params.fastp_trim
     )
     ch_reads_fusioncatcher = TRIM_WORKFLOW.out.ch_reads_fusioncatcher
-    ch_reads_all = TRIM_WORKFLOW.out.ch_reads_all
-    ch_versions = ch_versions.mix(TRIM_WORKFLOW.out.versions)
+    ch_reads_all           = TRIM_WORKFLOW.out.ch_reads_all
+    ch_versions            = ch_versions.mix(TRIM_WORKFLOW.out.versions)
 
 
     SALMON_QUANT( ch_reads_all, ch_salmon_index.map{ meta, index ->  index  }, ch_gtf.map{ meta, gtf ->  gtf  }, [], false, 'A')