Remove/small variants (#125)

* remove a reverted change from the changelog

* update metro map

* remove `small_variants` key

Author: nvnieuwk

CHANGELOG.md

@@ -22,14 +22,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 5. Fixed language server errors
 6. Removed the old output publishing code and used the new workflow output definitions instead
 7. Bumped the minimal nextflow version to 25.10.0
-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. 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.
-11. Moved all `wisecondorx` and `qdnaseq` outputs to a separate directory in each sample output.
-12. Bumped all annotation modules to the latest versions
-13. Reworked the annotation structure to a per tool structure. Specify the annotations tools you want to run with `--annotate_tools`. This parameter takes a comma-separated list of tool names (options: `vep`, `vcfanno`, `svannotate`, `strvctvre` or `all` (=> all tools))
-14. Updated to nf-core template v3.5.1
-15. Removed AnnotSV from the pipeline
+8. Changed the `--annotations_filter` parameter to a `--filter` parameter. This parameter takes an argument of `bcftools filter` to filter the resulting VCFs.
+9. Removed the `--delly_sv_types` parameter.
+10. Moved all `wisecondorx` and `qdnaseq` outputs to a separate directory in each sample output.
+11. Bumped all annotation modules to the latest versions
+12. Reworked the annotation structure to a per tool structure. Specify the annotations tools you want to run with `--annotate_tools`. This parameter takes a comma-separated list of tool names (options: `vep`, `vcfanno`, `svannotate`, `strvctvre` or `all` (=> all tools))
+13. Updated to nf-core template v3.5.1
+14. Removed AnnotSV from the pipeline
+15. Removed the `small_variants` field from the samplesheet. Small variant VCFs are no longer used in the pipeline
 
 ### `Fixed`
 

assets/schema_input.json

@@ -31,12 +31,6 @@
                 "format": "file-path",
                 "exists": true
             },
-            "small_variants": {
-                "type": "string",
-                "pattern": "^\\S+\\.vcf(\\.gz)?$",
-                "format": "file-path",
-                "exists": true
-            },
             "sex": {
                 "type": "string",
                 "meta": ["sex"],

docs/images/metro_map.png

@@ -64,7 +64,6 @@ Following table contains all possible values for the samplesheet.
 | `family`         | The family name of the current sample. All samples in the same family will be merged together at the end of the pipeline. Cannot contain spaces              | string | :x:                |
 | `cram`           | Path to the CRAM file to be used by the pipeline for the current sample.                                                                                     | string | :heavy_check_mark: |
 | `crai`           | Path to the CRAM index file                                                                                                                                  | string | :x:                |
-| `small_variants` | A VCF containing the SNV (small nucleotide variants) for the current sample to be used by AnnotSV                                                            | string | :x:                |
 | `sex`            | The sex of the sample to be used by QDNAseq. Sex will be imputed when missing (Options: `male` or `female`)                                                  | string | :x:                |
 
 See following samplesheet for a working example of a samplesheet (used by the `test` profile of the pipeline):

docs/images/metro_map.svg

@@ -96,12 +96,12 @@ workflow PIPELINE_INITIALISATION {
     }
 
     def ch_samplesheet = channel.fromList(samplesheetList)
-        .map { meta, cram, crai, small_variants ->
+        .map { meta, cram, crai ->
             def new_meta = meta + [
                 family:meta.family ?: meta.sample,
                 family_count:family_counts[meta.family] ?: 1
             ]
-            return [ new_meta, cram, crai, small_variants ]
+            return [ new_meta, cram, crai ]
         }
 
     //

docs/parameters.md

@@ -21,7 +21,6 @@ include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_stru
 include { BAM_PREPARE_SAMTOOLS                  } from '../subworkflows/local/bam_prepare_samtools/main'
 include { BAM_SV_CALLING                        } from '../subworkflows/local/bam_sv_calling/main'
 include { BAM_CNV_CALLING                       } from '../subworkflows/local/bam_cnv_calling/main'
-include { VCF_ANNOTATE_VCFANNO                  } from '../subworkflows/local/vcf_annotate_vcfanno/main'
 include { BAM_REPEAT_ESTIMATION_EXPANSIONHUNTER } from '../subworkflows/local/bam_repeat_estimation_expansionhunter/main'
 include { VCF_ANNOTATE                          } from '../subworkflows/local/vcf_annotate/main'
 include { VCF_CONCAT_BCFTOOLS                   } from '../subworkflows/local/vcf_concat_bcftools/main'
@@ -254,71 +253,46 @@ workflow STRUCTURAL {
     // Prepare the inputs
     //
 
-    def ch_deduplicated = ch_samplesheet
-        .map { meta, _cram, _crai, small_variants ->
-            [ meta, small_variants ]
-        }
-        .groupTuple()
-        .map { meta, small_variants ->
-            [ meta, small_variants.find { small_variant -> small_variant != [] } ?: [] ]
-        }
-
     BAM_PREPARE_SAMTOOLS(
-        ch_samplesheet.map { meta, cram, crai, _small_variants ->
-            [ meta, cram, crai ]
-        },
+        ch_samplesheet,
         ch_fasta,
         ch_fai
     )
     ch_versions = ch_versions.mix(BAM_PREPARE_SAMTOOLS.out.versions)
 
     def ch_input_no_sex = BAM_PREPARE_SAMTOOLS.out.crams
-        .join(ch_deduplicated, failOnDuplicate:true, failOnMismatch:true)
 
     //
     // Determine the gender if needed
     //
 
-    def ch_input_sex = channel.empty()
+    def ch_inputs = channel.empty()
     if(callers.intersect(sexCallers)) {
         def ch_samplegender_input = ch_input_no_sex
-            .branch { meta, _cram, _crai, _small_variants ->
+            .branch { meta, _cram, _crai ->
                 sex: meta.sex
                 no_sex: !meta.sex
             }
 
-        def ch_samplegender_multi = ch_samplegender_input.no_sex
-            .multiMap { meta, cram, crai, small_variants ->
-                cram: [ meta, cram, crai ]
-                other: [ meta, small_variants ]
-            }
-
         NGSBITS_SAMPLEGENDER(
-            ch_samplegender_multi.cram,
+            ch_samplegender_input.no_sex,
             ch_fasta,
             ch_fai,
             "xy"
         )
         ch_versions = ch_versions.mix(NGSBITS_SAMPLEGENDER.out.versions.first())
 
-        ch_input_sex = NGSBITS_SAMPLEGENDER.out.tsv
-            .join(ch_samplegender_multi.cram, failOnDuplicate:true, failOnMismatch:true)
-            .join(ch_samplegender_multi.other, failOnDuplicate:true, failOnMismatch:true)
-            .map { meta, tsv, cram, crai, small_variants ->
+        ch_inputs = NGSBITS_SAMPLEGENDER.out.tsv
+            .join(ch_samplegender_input.no_sex, failOnDuplicate:true, failOnMismatch:true)
+            .map { meta, tsv, cram, crai ->
                 def new_meta = meta + [sex:get_sex(tsv, meta.sample)]
-                return [ new_meta, cram, crai, small_variants ]
+                return [ new_meta, cram, crai ]
             }
             .mix(ch_samplegender_input.sex)
     } else {
-        ch_input_sex = ch_input_no_sex
+        ch_inputs = ch_input_no_sex
     }
 
-    def ch_inputs = ch_input_sex
-        .multiMap { meta, cram, crai, small_variants ->
-            crams:          [ meta, cram, crai ]
-            small_variants: [ meta, small_variants ]
-        }
-
     //
     // Call the variants
     //
@@ -330,7 +304,7 @@ workflow STRUCTURAL {
         variant_types.add("sv")
 
         BAM_SV_CALLING(
-            ch_inputs.crams,
+            ch_inputs,
             ch_fasta,
             ch_fai,
             ch_manta_config,
@@ -357,7 +331,7 @@ workflow STRUCTURAL {
         variant_types.add("cnv")
 
         BAM_CNV_CALLING(
-            ch_inputs.crams,
+            ch_inputs,
             ch_fasta,
             ch_fai,
             ch_qdnaseq_male,
@@ -422,7 +396,7 @@ workflow STRUCTURAL {
         count_types += 1
 
         BAM_REPEAT_ESTIMATION_EXPANSIONHUNTER(
-            ch_inputs.crams,
+            ch_inputs,
             ch_fasta,
             ch_fai,
             ch_catalog