nf-cmgg · nvnieuwk · Feb 21, 2025 · Feb 11, 2025 · Feb 12, 2025 · Feb 12, 2025
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -21,7 +21,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 6. Removed the old output publishing code and used the new workflow output definitions instead
 7. Bumped the minimal nextflow version to 24.10.0
 8. VCFanno will now run when `--vcfanno_toml` has been given and `--annotate` has not been given. You still need to supply `--annotate` to get the full annotation, but this can be used check for common variants without having to perform full annotation.
-9. Removed the `--delly_sv_types` parameter.
+9. Changed the `--annotations_filter` parameter to a `--filter` parameter. This parameter takes an argument of `bcftools filter` to filter the resulting VCFs.
+10. Removed the `--delly_sv_types` parameter.
 
 ### `Fixed`
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -251,12 +251,18 @@ process {
 
     withName: "^.*VCF_ANNOTATE_VCFANNO:VCFANNO\$" {
         ext.prefix = {"${meta.id}.${meta.variant_type}.vcfanno"}
-        ext.args = "-permissive-overlap -ends"
+        ext.args = "-ends"
     }
 
-    withName: "^.*VCF_ANNOTATE_VCFANNO:BCFTOOLS_FILTER\$" {
+    /*
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+        SV AND CNV FILTERING
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    */
+
+    withName: "^.*STRUCTURAL:BCFTOOLS_FILTER\$" {
         ext.prefix = {"${meta.id}.${meta.variant_type}.filtered"}
-        ext.args = "${params.annotations_filter} --output-type z --write-index=tbi"
+        ext.args = "${params.filter} --output-type z --write-index=tbi"
     }
 
     /*

diff --git a/docs/parameters.md b/docs/parameters.md
@@ -80,7 +80,7 @@ Options specific to the execution of this pipeline
 | `cnv_callers_support` | The minimum amount of CNV callers that should detect a variant. All variants that have a lower amount of callers supporting it, will be removed. (Only used when more than one caller is given)                                                                                                                                                                              | `integer` | 1                                              |          |        |
 | `annotate`            | Run the annotation with Ensembl VEP and AnnotSV (and optionally VCFanno).                                                                                                                                                                                                                                                                                                    | `boolean` |                                                |          |        |
 | `concat_output`       | Also output a concatenated VCF with all variant types analysed included.                                                                                                                                                                                                                                                                                                     | `boolean` |                                                |          |        |
-| `annotations_filter`  | The filter arguments to use after annotating. <details><summary>Help</summary><small>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</small></details>                                                                                      | `string`  |                                                |          |        |
+| `filter`              | The filter options to perform on SV and CNV VCF files as postprocessing <details><summary>Help</summary><small>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</small></details>                                                            | `string`  |                                                |          |        |
 
 ## Delly parameters
 

diff --git a/main.nf b/main.nf
@@ -111,7 +111,7 @@ workflow {
         params.species,
         params.vep_assembly,
         params.vep_cache_version,
-        params.annotations_filter,
+        params.filter,
         params.outdir
     )
     //

diff --git a/nextflow.config b/nextflow.config
@@ -20,7 +20,7 @@ params {
     cnv_callers_support             = 1
     annotate                        = false
     concat_output                   = false
-    annotations_filter              = null
+    filter                          = null
     bedpe                           = false
 
     // Delly parameters

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -331,9 +331,9 @@
                     "type": "boolean",
                     "description": "Also output a concatenated VCF with all variant types analysed included."
                 },
-                "annotations_filter": {
+                "filter": {
                     "type": "string",
-                    "description": "The filter arguments to use after annotating.",
+                    "description": "The filter options to perform on SV and CNV VCF files as postprocessing",
                     "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": {

diff --git a/subworkflows/local/vcf_annotate_vcfanno/main.nf b/subworkflows/local/vcf_annotate_vcfanno/main.nf
@@ -11,7 +11,6 @@ workflow VCF_ANNOTATE_VCFANNO {
         ch_sample_specific_resources            // channel: [optional]  [ val(meta), path(vcf), path(tbi) ] Files containing resources that are sample-specific
         ch_vcfanno_lua                          // channel: [optional]  [ path(lua) ] => The lua script to influence VCFanno
         val_vcfanno_resources                   // list:    [optional]  [ path(file1, file2, file3...) ] => The extra VCFanno files
-        filter                                  // string:  [optional]  => A filter pattern to use after annotating
         vcfanno_toml                            // file:    [optional]  => A vcfanno TOML config
         default_vcfanno_tomls                   // list:    [mandatory] => A list of default vcfanno configs to be concatenated with the input TOML
         annotate                                // boolean: [mandatory] => Whether or not to run the full annotation or only the specified annotations
@@ -31,7 +30,7 @@ workflow VCF_ANNOTATE_VCFANNO {
         }
         ch_vcfanno_input = ch_vcfs.join(ch_collected_specific_resources, failOnMismatch:true, failOnDuplicate:true)
     } else {
-        ch_vcfanno_toml = Channel.fromPath(vcfanno_toml)
+        ch_vcfanno_toml = Channel.fromPath(vcfanno_toml).collect()
         ch_vcfanno_input = ch_vcfs.map { meta, vcf, tbi ->
             [ meta, vcf, tbi, [] ]
         }
@@ -45,19 +44,7 @@ workflow VCF_ANNOTATE_VCFANNO {
     )
     ch_versions = ch_versions.mix(VCFANNO.out.versions)
 
-    def ch_vcfanno_output = VCFANNO.out.vcf.join(VCFANNO.out.tbi, failOnDuplicate:true, failOnMismatch:true)
-
-    def ch_annotated_vcfs = Channel.empty()
-    if(filter) {
-        BCFTOOLS_FILTER(
-            ch_vcfanno_output
-        )
-        ch_versions = ch_versions.mix(BCFTOOLS_FILTER.out.versions.first())
-
-        ch_annotated_vcfs = BCFTOOLS_FILTER.out.vcf.join(BCFTOOLS_FILTER.out.tbi, failOnDuplicate:true, failOnMismatch:true)
-    } else {
-        ch_annotated_vcfs = ch_vcfanno_output
-    }
+    def ch_annotated_vcfs = VCFANNO.out.vcf.join(VCFANNO.out.tbi, failOnDuplicate:true, failOnMismatch:true)
 
     emit:
     vcfs            = ch_annotated_vcfs  // channel: [ val(meta), path(vcf), path(tbi) ]

diff --git a/tests/subworkflows/local/vcf_annotate_vcfanno/main.nf.test b/tests/subworkflows/local/vcf_annotate_vcfanno/main.nf.test
@@ -10,57 +10,9 @@ nextflow_workflow {
 
     options "-stub"
 
-    test("homo_sapiens - no_filter, annotate") {
+    test("homo_sapiens - annotate") {
 
         when {
-            params {
-                annotations_filter = null
-            }
-            workflow {
-                """
-                def meta = [id:"test", sample:"test", sex:"male", family: "test1", family_count:1, hpo:[], variant_type:'sv']
-                input[0] = Channel.of([
-                    meta,
-                    file(params.sv_vcf1, checkIfExists:true),
-                    file(params.sv_tbi1, checkIfExists:true)
-                ])
-                input[1] = Channel.of([
-                    meta,
-                    [],
-                    []
-                ])
-                input[2] = []
-                input[3] = []
-                input[4] = params.annotations_filter
-                input[5] = []
-                input[6] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)
-                input[7] = true
-                """
-            }
-        }
-
-        then {
-            assertAll(
-                { assert workflow.success },
-                { assert snapshot(
-                    workflow.out.collectEntries { key, value ->
-                        if(key.matches("^\\d+\$") || key.matches('versions')) {
-                            return null
-                        }
-                        return [ key, value ]
-                    }.findAll { it != null }
-                ).match() }
-            )
-        }
-
-    }
-
-    test("homo_sapiens - filter, no_annotate") {
-
-        when {
-            params {
-                annotations_filter = "-i FILTER='PASS'"
-            }
             workflow {
                 """
                 def meta = [id:"test", sample:"test", sex:"male", family: "test1", family_count:1, hpo:[], variant_type:'sv']
@@ -76,10 +28,9 @@ nextflow_workflow {
                 ])
                 input[2] = []
                 input[3] = []
-                input[4] = params.annotations_filter
-                input[5] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)[0]
-                input[6] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)
-                input[7] = false
+                input[4] = []
+                input[5] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)
+                input[6] = true
                 """
             }
         }
@@ -100,12 +51,9 @@ nextflow_workflow {
 
     }
 
-    test("homo_sapiens - filter, annotate") {
+    test("homo_sapiens - no_annotate") {
 
         when {
-            params {
-                annotations_filter = null
-            }
             workflow {
                 """
                 def meta = [id:"test", sample:"test", sex:"male", family: "test1", family_count:1, hpo:[], variant_type:'sv']
@@ -121,10 +69,9 @@ nextflow_workflow {
                 ])
                 input[2] = []
                 input[3] = []
-                input[4] = params.annotations_filter
-                input[5] = []
-                input[6] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)
-                input[7] = true
+                input[4] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)[0]
+                input[5] = files("\${params.vcfanno_tomls}/*.toml", checkIfExists:true)
+                input[6] = false
                 """
             }
         }

diff --git a/tests/subworkflows/local/vcf_annotate_vcfanno/main.nf.test.snap b/tests/subworkflows/local/vcf_annotate_vcfanno/main.nf.test.snap
@@ -1,33 +1,5 @@
 {
-    "homo_sapiens - filter, no_annotate": {
-        "content": [
-            {
-                "vcfs": [
-                    [
-                        {
-                            "id": "test",
-                            "sample": "test",
-                            "sex": "male",
-                            "family": "test1",
-                            "family_count": 1,
-                            "hpo": [
-
-                            ],
-                            "variant_type": "sv"
-                        },
-                        "test.sv.filtered.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940",
-                        "test.sv.filtered.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ]
-            }
-        ],
-        "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.10.4"
-        },
-        "timestamp": "2025-02-10T16:55:00.763124808"
-    },
-    "homo_sapiens - filter, annotate": {
+    "homo_sapiens - no_annotate": {
         "content": [
             {
                 "vcfs": [
@@ -53,9 +25,9 @@
             "nf-test": "0.9.1",
             "nextflow": "24.10.4"
         },
-        "timestamp": "2025-02-10T16:55:09.970621986"
+        "timestamp": "2025-02-12T14:07:01.425728203"
     },
-    "homo_sapiens - no_filter, annotate": {
+    "homo_sapiens - annotate": {
         "content": [
             {
                 "vcfs": [
@@ -81,6 +53,6 @@
             "nf-test": "0.9.1",
             "nextflow": "24.10.4"
         },
-        "timestamp": "2025-02-10T16:54:50.521405941"
+        "timestamp": "2025-02-12T14:06:51.583328891"
     }
 }
diff --git a/workflows/structural.nf b/workflows/structural.nf
@@ -43,6 +43,7 @@ include { ANNOTSV_INSTALLANNOTATIONS        } from '../modules/nf-core/annotsv/i
 include { UNTAR as UNTAR_ANNOTSV            } from '../modules/nf-core/untar/main'
 include { UNTAR as UNTAR_BWA                } from '../modules/nf-core/untar/main'
 include { NGSBITS_SAMPLEGENDER              } from '../modules/nf-core/ngsbits/samplegender/main'
+include { BCFTOOLS_FILTER                   } from '../modules/nf-core/bcftools/filter/main'
 include { SVTOOLS_VCFTOBEDPE                } from '../modules/nf-core/svtools/vcftobedpe/main'
 include { MULTIQC                           } from '../modules/nf-core/multiqc/main'
 
@@ -95,7 +96,7 @@ workflow STRUCTURAL {
     species                     // The species to be used by VEP
     vep_assembly                // The genome assembly to be downloaded for VEP
     vep_cache_version           // The version of the VEP cache to use
-    annotations_filter          // The filter pattern to use after annotation
+    filter                      // The filter pattern to use after annotation
     outdir                      // The output directory of the pipeline
 
     main:
@@ -409,22 +410,33 @@ workflow STRUCTURAL {
         ch_annotation_output    = ch_annotation_input
     }
 
-    def ch_outputs = Channel.empty()
+    def ch_vcfanno_output = Channel.empty()
     if(annotate || vcfanno_toml) {
         VCF_ANNOTATE_VCFANNO(
             ch_annotation_output,
             ch_annotsv_vcfs,
             ch_vcfanno_lua,
             val_vcfanno_resources,
-            annotations_filter,
             val_vcfanno_toml,
             val_default_vcfanno_tomls,
             annotate
         )
         ch_versions = ch_versions.mix(VCF_ANNOTATE_VCFANNO.out.versions)
-        ch_outputs  = ch_outputs.mix(VCF_ANNOTATE_VCFANNO.out.vcfs)
+        ch_vcfanno_output  = VCF_ANNOTATE_VCFANNO.out.vcfs
+    } else {
+        ch_vcfanno_output  = ch_annotation_input
+    }
+
+    def ch_outputs = Channel.empty()
+    if(filter) {
+        BCFTOOLS_FILTER(
+            ch_vcfanno_output
+        )
+        def ch_filter_output = BCFTOOLS_FILTER.out.vcf.join(BCFTOOLS_FILTER.out.tbi, failOnMismatch:true, failOnDuplicate:true)
+        ch_outputs = ch_outputs.mix(ch_filter_output)
+        ch_versions = ch_versions.mix(BCFTOOLS_FILTER.out.versions)
     } else {
-        ch_outputs  = ch_outputs.mix(ch_annotation_input)
+        ch_outputs = ch_outputs.mix(ch_vcfanno_output)
     }
 
     //