Add BEDPE output (#112)

* add bedpe output * add tests for bedpe output * pre-commit * fix family merge tests
nf-cmgg · Feb 21, 2025 · 81d4118 · 81d4118
1 parent 7492949
commit 81d4118
Show file tree

Hide file tree

Showing 16 changed files with 482 additions and 18 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -37,6 +37,7 @@ jobs:
           - "pipeline_repeats"
           - "pipeline_duplicates"
           - "pipeline_families"
+          - "pipeline_bedpe"
           - "bam_cnv_calling"
           - "bam_prepare_samtools"
           - "bam_repeat_estimation_expansionhunter"

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -8,7 +8,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 1. Added the samplesheet to the pipeline output as `OUTDIR/samplesheet.csv`
-2. Added parallelization on SV type to the delly flow
+2. Added the `--bedpe` parameter. This makes the pipeline output BEDPE files alongside the VCF files.
+3. Added parallelization on SV type to the delly flow
 
 ### `Changes`
 

diff --git a/main.nf b/main.nf
@@ -101,6 +101,7 @@ workflow {
         // booleans
         params.annotate,
         params.concat_output,
+        params.bedpe,
 
         // values
         params.callers,
@@ -127,13 +128,14 @@ workflow {
     )
 
     publish:
-    STRUCTURAL.out.caller_vcfs >> 'caller_vcfs'
-    STRUCTURAL.out.sample_vcfs >> 'sample_vcfs'
-    STRUCTURAL.out.family_vcfs >> 'family_vcfs'
-    STRUCTURAL.out.qdnaseq_out >> 'qdnaseq_out'
-    STRUCTURAL.out.wisecondorx_out >> 'wisecondorx_out'
-    STRUCTURAL.out.multiqc_report >> 'multiqc'
-    STRUCTURAL.out.multiqc_data >> 'multiqc_data'
+    STRUCTURAL.out.caller_vcfs      >> 'caller_vcfs'
+    STRUCTURAL.out.sample_vcfs      >> 'sample_vcfs'
+    STRUCTURAL.out.family_vcfs      >> 'family_vcfs'
+    STRUCTURAL.out.qdnaseq_out      >> 'qdnaseq_out'
+    STRUCTURAL.out.wisecondorx_out  >> 'wisecondorx_out'
+    STRUCTURAL.out.bedpe            >> 'bedpe'
+    STRUCTURAL.out.multiqc_report   >> 'multiqc'
+    STRUCTURAL.out.multiqc_data     >> 'multiqc_data'
 
 }
 
@@ -183,6 +185,12 @@ output {
             return "${meta.id}/${new_name}"
         } }
     }
+    'bedpe' {
+        path { meta, _bedpe -> { file ->
+            def base = "${meta.id}/${meta.id}${meta.variant_type ? '.' + meta.variant_type : ''}"
+            return "${base}.bedpe"
+        } }
+    }
     'multiqc' {
         path { _report -> { _file -> "multiqc/multiqc_report.html"}}
     }

diff --git a/modules.json b/modules.json
@@ -128,6 +128,11 @@
                         "git_sha": "f2fdc5e81efe36beff213752ce1a8e71fceeacba",
                         "installed_by": ["modules"]
                     },
+                    "svtools/vcftobedpe": {
+                        "branch": "master",
+                        "git_sha": "5cf15e4c5ad6d06718b35e5ec1655c7c0a105880",
+                        "installed_by": ["modules"]
+                    },
                     "svync": {
                         "branch": "master",
                         "git_sha": "916a4cbc4f831d501860495b157c4857833e22a7",

diff --git a/modules/nf-core/svtools/vcftobedpe/environment.yml b/modules/nf-core/svtools/vcftobedpe/environment.yml
diff --git a/modules/nf-core/svtools/vcftobedpe/main.nf b/modules/nf-core/svtools/vcftobedpe/main.nf
diff --git a/modules/nf-core/svtools/vcftobedpe/meta.yml b/modules/nf-core/svtools/vcftobedpe/meta.yml
diff --git a/modules/nf-core/svtools/vcftobedpe/tests/main.nf.test b/modules/nf-core/svtools/vcftobedpe/tests/main.nf.test
diff --git a/modules/nf-core/svtools/vcftobedpe/tests/main.nf.test.snap b/modules/nf-core/svtools/vcftobedpe/tests/main.nf.test.snap
diff --git a/nextflow.config b/nextflow.config
@@ -21,6 +21,7 @@ params {
     annotate                        = false
     concat_output                   = false
     annotations_filter              = null
+    bedpe                           = false
 
     // Delly parameters
     delly_map_qual                  = 1

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -335,6 +335,10 @@
                     "type": "string",
                     "description": "The filter arguments to use after annotating.",
                     "help_text": "A common use case for this is to filter out common variants. You can supply a VCF file with common variants to VCFanno and filter out the matching variants using this parameter"
+                },
+                "bedpe": {
+                    "type": "boolean",
+                    "description": "Output BEDPE files derived from the VCF files alongside the VCF files"
                 }
             }
         },

diff --git a/subworkflows/local/vcf_merge_family_jasmine/main.nf b/subworkflows/local/vcf_merge_family_jasmine/main.nf
@@ -20,7 +20,6 @@ workflow VCF_MERGE_FAMILY_JASMINE {
     def ch_versions     = Channel.empty()
 
     def ch_jasmine_input = ch_vcfs
-        .filter { meta, _vcf, _tbi -> meta.family_count > 1 }
         .map { meta, vcf, tbi ->
             def new_meta = meta - meta.subMap("sample", "sex") + ["id":meta.variant_type ? "${meta.family}.${meta.variant_type}" : meta.family]
             [ groupKey(new_meta, meta.family_count), vcf, tbi ]