Merge pull request #568 from alanmmobbs93/qc_subworkflow_test

QC subworkflow test
nf-core · Dec 4, 2024 · fa2c71d · fa2c71d
2 parents 489161e + c8247c8
commit fa2c71d
Show file tree

Hide file tree

Showing 7 changed files with 214 additions and 44 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -17,6 +17,7 @@ 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)
 
 ### Changed
 

diff --git a/subworkflows/local/qc_workflow.nf b/subworkflows/local/qc_workflow.nf
diff --git a/subworkflows/local/qc_workflow/main.nf b/subworkflows/local/qc_workflow/main.nf
@@ -0,0 +1,40 @@
+//
+// Extract descriptive values from BAMs
+//
+
+include { PICARD_COLLECTRNASEQMETRICS       } from '../../../modules/nf-core/picard/collectrnaseqmetrics'
+include { GATK4_MARKDUPLICATES              } from '../../../modules/nf-core/gatk4/markduplicates'
+include { PICARD_COLLECTINSERTSIZEMETRICS   } from '../../../modules/nf-core/picard/collectinsertsizemetrics'
+
+workflow QC_WORKFLOW {
+    take:
+        ch_bam_sorted           // channel [ meta, bam        ]
+        ch_chrgtf               // channel [ meta, gtf        ]
+        ch_refflat              // channel [ meta, refflat    ]
+        ch_fasta                // channel [ meta, fasta      ]
+        ch_fai                  // channel [ meta, fai        ]
+        ch_rrna_interval        // channel [ meta, interval   ]
+
+    main:
+        ch_versions = Channel.empty()
+
+        PICARD_COLLECTRNASEQMETRICS(ch_bam_sorted, ch_refflat.map{ meta, refflat -> [ refflat ] }, ch_fasta.map{ meta, fasta -> [ fasta ] }, ch_rrna_interval.map{ meta, intervals -> [ intervals ] }.ifEmpty([]) ) // Some chromosome or annotation may not have rRNA genes
+        ch_versions = ch_versions.mix(PICARD_COLLECTRNASEQMETRICS.out.versions)
+        ch_rnaseq_metrics = PICARD_COLLECTRNASEQMETRICS.out.metrics
+
+        GATK4_MARKDUPLICATES(ch_bam_sorted, ch_fasta.map { meta, fasta -> [ fasta ]}, ch_fai.map { meta, fasta_fai -> [ fasta_fai ]})
+        ch_versions = ch_versions.mix(GATK4_MARKDUPLICATES.out.versions)
+        ch_duplicate_metrics = GATK4_MARKDUPLICATES.out.metrics
+
+        PICARD_COLLECTINSERTSIZEMETRICS(ch_bam_sorted)
+        ch_versions = ch_versions.mix(PICARD_COLLECTINSERTSIZEMETRICS.out.versions)
+        ch_insertsize_metrics = PICARD_COLLECTINSERTSIZEMETRICS.out.metrics
+
+    emit:
+        versions            = ch_versions            // channel [ path       ]
+        rnaseq_metrics      = ch_rnaseq_metrics      // channel [ meta, path ]
+        duplicate_metrics   = ch_duplicate_metrics   // channel [ meta, path ]
+        insertsize_metrics  = ch_insertsize_metrics  // channel [ meta, path ]
+
+}
+
diff --git a/subworkflows/local/qc_workflow/test/main.nf.test b/subworkflows/local/qc_workflow/test/main.nf.test
@@ -0,0 +1,127 @@
+nextflow_workflow {
+
+    name "Test Subworkflow QC_WORKFLOW"
+    script "../main.nf"
+    config "./nextflow.config"
+    workflow "QC_WORKFLOW"
+    tag "qc"
+    tag "subworkflow"
+
+    test("QC_WORKFLOW - Homo sapiens chr22") {
+
+        // Generate refflat file
+        setup {
+
+            // Create refflat reference
+            run("UCSC_GTFTOGENEPRED") {
+                script "../../../../modules/nf-core/ucsc/gtftogenepred/main.nf"
+                process {
+                    """
+                    input[0] =
+                        Channel.fromPath(
+                            "https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.gtf",
+                            checkIfExists: true
+                        )
+                        .map{ [ [id:it.Name], it ] }
+                    """
+                }
+            }
+
+            // Filter GTF to extract rRNA genes
+            run("RRNATRANSCRIPTS") {
+                script "../../../../modules/nf-core/rrnatranscripts/main.nf"
+                process {
+                    """
+                    input[0] = Channel.fromPath("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.gtf", checkIfExists: true)
+                    """
+                }
+            }
+
+            // Convert rRNA GTF to BED
+            run("BEDOPS_CONVERT2BED") {
+                script "../../../../modules/nf-core/bedops/convert2bed/main.nf"
+                process {
+                    """
+                    input[0] = RRNATRANSCRIPTS.out.rrna_gtf.map{ it -> [ [id:it.Name], it ] }
+                    """
+                }
+            }
+
+            // Convert rRNA BED to interval list (the necessary file)
+            run("GATK4_BEDTOINTERVALLIST") {
+                script "../../../../modules/nf-core/gatk4/bedtointervallist/main.nf"
+                process {
+                    """
+                    input[0] = BEDOPS_CONVERT2BED.out.bed
+                    input[1] = Channel.of(
+                        [
+                            [id: 'chr22_dic'],
+                            file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.dic", checkIfExist: true)
+                        ]
+                    )
+                    """
+                }
+            }
+
+        }
+
+        when {
+            // Params to activate modules ext.when condition
+            params {
+                skip_qc              = false
+                fusioninspector_only = false
+                starfusion           = true
+                all                  = true
+            }
+
+            workflow {
+                """
+                // ch_bam_sorted
+                input[0] = Channel.of(
+                    [
+                        [id: "chr22_bam"],
+                        file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam", checkIfExists: true)
+                    ])
+
+                // ch_chrgtf
+                input[1] = Channel.of(
+                    [
+                        [ id: "chr22_gtf" ],
+                        file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.gtf", checkIfExists: true)
+                    ])
+
+                // ch_refflat
+                input[2] = UCSC_GTFTOGENEPRED.out.refflat
+
+                // ch_fasta
+                input[3] = Channel.of(
+                    [
+                        [ id: "test_ref" ],
+                        file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.fasta", checkIfExist: true)
+                    ] )
+
+                // ch_fai
+                input[4] = Channel.of(
+                    [
+                        [ id: "test_ref" ],
+                        file("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/homo_sapiens/genome/genome.fasta.fai", checkIfExist: true)
+                    ] )
+
+                // ch rRNA interval list
+                input[5] = GATK4_BEDTOINTERVALLIST.out.interval_list
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(file( workflow.out.versions[0] )).match('versions' )                                                },
+                { assert snapshot(file( workflow.out.rnaseq_metrics[0][1]     ).readLines()[4..-1]).md5().match('rnaseq_metrics'    ) },
+                { assert snapshot(file( workflow.out.duplicate_metrics[0][1]  ).readLines()[4..-1]).md5().match('duplicate_metrics' ) },
+                { assert snapshot(file( workflow.out.insertsize_metrics[0][1] ).readLines()[4..-1]).md5().match('insertsize_metrics') }
+            )
+        }
+    }
+
+}
diff --git a/subworkflows/local/qc_workflow/test/main.nf.test.snap b/subworkflows/local/qc_workflow/test/main.nf.test.snap
@@ -0,0 +1,36 @@
+{
+    "duplicate_metrics": {
+        "content": "651d8a4702f9f9871e94afbce3e50e34",
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-04T19:29:09.711230835"
+    },
+    "versions": {
+        "content": [
+            "versions.yml:md5,3f13b395c67e317f74194b3b6c89f139"
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-04T19:29:09.686297468"
+    },
+    "rnaseq_metrics": {
+        "content": "84a348c3735ed2f6c47f346eeed661f4",
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-04T19:29:09.704632753"
+    },
+    "insertsize_metrics": {
+        "content": "160db81b19843c4d46fe74ac61f9f013",
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-04T19:29:09.717929716"
+    }
+}
diff --git a/subworkflows/local/qc_workflow/test/nextflow.config b/subworkflows/local/qc_workflow/test/nextflow.config
@@ -0,0 +1,10 @@
+process {
+    withName: PICARD_COLLECTRNASEQMETRICS {
+        ext.args = "--STRAND_SPECIFICITY SECOND_READ_TRANSCRIPTION_STRAND"
+    }
+
+    withName: GATK4_BEDTOINTERVALLIST {
+        ext.args = "--KEEP_LENGTH_ZERO_INTERVALS true"
+    }
+
+}
diff --git a/workflows/rnafusion.nf b/workflows/rnafusion.nf
@@ -147,7 +147,6 @@ workflow RNAFUSION {
 
     //QC
     QC_WORKFLOW (
-        ch_reads_all,
         STARFUSION_WORKFLOW.out.ch_bam_sorted,
         ch_chrgtf,
         ch_refflat,