Merge pull request #256 from nf-cmgg/dev

Release PR 1.9.2

.github/workflows/ci.yml

@@ -25,7 +25,7 @@ jobs:
       matrix:
         NXF_VER:
           - "24.10.0"
-          - "latest-everything"
+          - "latest-stable"
         filter:
           - "process"
           - "workflow"

.nf-core.yml

@@ -2,32 +2,32 @@ bump_version:
 lint:
   actions_ci: false
   files_exist:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-germline_logo_light.png
-  - docs/images/nf-core-germline_logo_light.png
-  - docs/images/nf-core-germline_logo_dark.png
-  - .github/ISSUE_TEMPLATE/config.yml
-  - .github/workflows/awstest.yml
-  - .github/workflows/awsfulltest.yml
-  - .github/workflows/template_version_comment.yml
-  - docs/README.md
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-germline_logo_light.png
+    - docs/images/nf-core-germline_logo_light.png
+    - docs/images/nf-core-germline_logo_dark.png
+    - .github/ISSUE_TEMPLATE/config.yml
+    - .github/workflows/awstest.yml
+    - .github/workflows/awsfulltest.yml
+    - .github/workflows/template_version_comment.yml
+    - docs/README.md
   files_unchanged:
-  - .github/CONTRIBUTING.md
-  - .github/PULL_REQUEST_TEMPLATE.md
-  - .github/workflows/branch.yml
-  - .github/workflows/linting_comment.yml
-  - .github/workflows/linting.yml
-  - CODE_OF_CONDUCT.md
-  - .github/ISSUE_TEMPLATE/bug_report.yml
-  - .prettierignore
+    - .github/CONTRIBUTING.md
+    - .github/PULL_REQUEST_TEMPLATE.md
+    - .github/workflows/branch.yml
+    - .github/workflows/linting_comment.yml
+    - .github/workflows/linting.yml
+    - CODE_OF_CONDUCT.md
+    - .github/ISSUE_TEMPLATE/bug_report.yml
+    - .prettierignore
   multiqc_config:
-  - report_comment
+    - report_comment
   nextflow_config:
-  - custom_config
-  - manifest.name
-  - manifest.homePage
-  - validation.help.afterText
-  - validation.summary.afterText
+    - custom_config
+    - manifest.name
+    - manifest.homePage
+    - validation.help.afterText
+    - validation.summary.afterText
   subworkflow_changes: false
 nf_core_version: 3.0.2
 repository_type: pipeline
@@ -41,6 +41,6 @@ template:
   org: nf-cmgg
   outdir: .
   skip_features:
-  - fastqc
-  - is_nfcore
-  version: 1.9.1
+    - fastqc
+    - is_nfcore
+  version: 1.9.2

CHANGELOG.md

@@ -3,6 +3,13 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.9.2 - New Nieuwkerke - [January 22 2025]
+
+## Changes
+
+1. The pipeline now also outputs the per-base coverage BED file generated by mosdepth per sample
+2. Add the `--disable_hc_dict_validation` parameter that disables sequence dictionary validation in HaplotypeCaller
+
 ## v1.9.1 - Nice Nieuwkerke - [January 16 2025]
 
 ### Changes

conf/modules.config

@@ -44,7 +44,7 @@ process {
 
     withName: "^.*CRAM_PREPARE_SAMTOOLS_BEDTOOLS:MOSDEPTH\$" {
         ext.args = [
-            "--quantize 0:1:${params.min_callable_coverage - 1}: --mapq 1 --flag 1804 --no-per-base",
+            "--quantize 0:1:${params.min_callable_coverage - 1}: --mapq 1 --flag 1804",
             params.mosdepth_slow ? "" : "--fast-mode"
         ].join(" ")
     }
@@ -79,7 +79,8 @@ process {
                 '-GQB 10 -GQB 20 -GQB 30 -GQB 40 -GQB 50 -GQB 60 -GQB 70 -GQB 80 -GQB 90',
                 '-G StandardAnnotation -G StandardHCAnnotation -G AS_StandardAnnotation',
                 params.dragstr ? '--dragen-mode' : '',
-                params.hc_phasing ? '' : '--do-not-run-physical-phasing'
+                params.hc_phasing ? '' : '--do-not-run-physical-phasing',
+                params.disable_hc_dict_validation ? '--disable-sequence-dictionary-validation' : ''
             ].join(" ")
         }
     }

conf/seqplorer.config

@@ -5,18 +5,19 @@
 */
 
 params {
-    filter              = true
-    normalize           = true
-    gemini              = true
+    filter                      = true
+    normalize                   = true
+    gemini                      = true
+    disable_hc_dict_validation  = true
 
-    vcfanno             = true
-    annotate            = true
-    vep_merged          = true
-    vep_spliceai        = true
-    vep_mastermind      = true
-    vep_eog             = true
-    vep_spliceregion    = true
+    vcfanno                     = true
+    annotate                    = true
+    vep_merged                  = true
+    vep_spliceai                = true
+    vep_mastermind              = true
+    vep_eog                     = true
+    vep_spliceregion            = true
 
-    vcfanno_config      = "https://raw.githubusercontent.com/CenterForMedicalGeneticsGhent/nf-cmgg-configs/main/conf/Hsapiens/vcfanno/cmgg_vcfanno.toml"
-    vcfanno_resources   = "${params.genomes_base}/Hsapiens/GRCh38/variation/dbscSNV-1.1/dbscSNV.txt.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/dbscSNV-1.1/dbscSNV.txt.gz.tbi;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/exomes/r2.2.1/gnomad_exomes.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/exomes/r2.2.1/gnomad_exomes.vcf.gz.csi;${params.genomes_base}/Hsapiens/GRCh38/variation/clinvar/clinvar_20221119.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/clinvar/clinvar_20221119.vcf.gz.tbi;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/genomes/r3.1.2/gnomad_genomes.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/genomes/r3.1.2/gnomad_genomes.vcf.gz.csi;${params.genomes_base}/Hsapiens/GRCh38/variation/dbNSFP-4.3/dbNSFP4.3a_grch38.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/dbNSFP-4.3/dbNSFP4.3a_grch38.gz.tbi"
+    vcfanno_config              = "https://raw.githubusercontent.com/CenterForMedicalGeneticsGhent/nf-cmgg-configs/main/conf/Hsapiens/vcfanno/cmgg_vcfanno.toml"
+    vcfanno_resources           = "${params.genomes_base}/Hsapiens/GRCh38/variation/dbscSNV-1.1/dbscSNV.txt.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/dbscSNV-1.1/dbscSNV.txt.gz.tbi;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/exomes/r2.2.1/gnomad_exomes.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/exomes/r2.2.1/gnomad_exomes.vcf.gz.csi;${params.genomes_base}/Hsapiens/GRCh38/variation/clinvar/clinvar_20221119.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/clinvar/clinvar_20221119.vcf.gz.tbi;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/genomes/r3.1.2/gnomad_genomes.vcf.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/gnomAD/genomes/r3.1.2/gnomad_genomes.vcf.gz.csi;${params.genomes_base}/Hsapiens/GRCh38/variation/dbNSFP-4.3/dbNSFP4.3a_grch38.gz;${params.genomes_base}/Hsapiens/GRCh38/variation/dbNSFP-4.3/dbNSFP4.3a_grch38.gz.tbi"
 }

docs/output.md

@@ -34,6 +34,8 @@ To explain the structure of the output directory, a simple example run consistin
 │   │   ├── sample1.<caller>.bcftools_stats.txt #(17)!
 │   │   ├── sample1.<caller>.g.vcf.gz #(18)!
 │   │   ├── sample1.<caller>.g.vcf.gz.tbi #(19)!
+│   │   ├── sample1.per-base.bed.gz #(33)!
+│   │   ├── sample1.per-base.bed.gz.csi #(34)!
 │   │   └── validation #(20)!
 │   │       └── <caller> #(21)!
 │   │           ├── ... #(22)!
@@ -118,3 +120,7 @@ To explain the structure of the output directory, a simple example run consistin
 31. This file contains a list of all tools used in the pipeline and their versions
 
 32. The samplesheet used to run this pipeline run
+
+33. The per-base coverage BED file generated by Mosdepth
+
+34. The index of the per-base coverage BED file generated by Mosdepth

main.nf

@@ -99,10 +99,6 @@ workflow {
         if(!(caller in GlobalVariables.availableCallers)) { error("\"${caller}\" is not a supported callers please use one or more of these instead: ${GlobalVariables.availableCallers}")}
     }
 
-    if (params.output_suffix && callers.size() > 1) {
-        error("Cannot use --output_suffix with more than one caller")
-    }
-
     /*
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
         CONFIG FILES
@@ -219,6 +215,7 @@ workflow {
     publish:
     ch_gvcfs_out >> 'gvcfs'
     GERMLINE.out.single_beds >> 'single_beds'
+    GERMLINE.out.perbase_beds >> 'perbase_beds'
     GERMLINE.out.validation >> 'validation'
     GERMLINE.out.gvcf_reports >> 'gvcf_reports'
     GERMLINE.out.genomicsdb >> 'genomicsdb'
@@ -245,6 +242,14 @@ output {
     'single_beds' {
         path { meta, _bed -> { _file -> "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.bed" } }
     }
+    'perbase_beds' {
+        path { meta, bed, _csi -> { file ->
+            if(file == bed.name) {
+                return "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.per-base.bed.gz"
+            }
+            return "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.per-base.bed.gz.csi"
+        } }
+    }
     'validation' {
         path { meta, _report -> { file -> "${meta.family}/${meta.id}_${params.unique_out}/validation/${meta.caller}/${file}" } }
     }

nextflow.config

@@ -41,6 +41,7 @@ params {
     mosdepth_slow              = false
     merge_distance             = 100000
     updio_common_cnvs          = null
+    disable_hc_dict_validation = false
 
     // VEP plugins to use
     vep_dbnsfp                 = false
@@ -276,7 +277,7 @@ manifest {
     description     = """A nextflow pipeline for calling and annotating small germline variants from short DNA reads for WES and WGS data"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=24.10.0'
-    version         = '1.9.1'
+    version         = '1.9.2'
     doi             = ''
 }
 

nextflow_schema.json

@@ -331,6 +331,10 @@
                     "type": "string",
                     "description": "Don't change this value",
                     "hidden": true
+                },
+                "disable_hc_dict_validation": {
+                    "type": "boolean",
+                    "description": "Disable the sequence dictionary validation in HaplotypeCaller"
                 }
             }
         },

subworkflows/local/cram_prepare_samtools_bedtools/main.nf

@@ -151,6 +151,8 @@ workflow CRAM_PREPARE_SAMTOOLS_BEDTOOLS {
         ch_fasta
     )
     ch_versions = ch_versions.mix(MOSDEPTH.out.versions.first())
+    def ch_perbase_beds = MOSDEPTH.out.per_base_bed
+        .join(MOSDEPTH.out.per_base_csi, failOnMismatch: true, failOnDuplicate:true)
 
     def ch_beds_to_filter = ch_ready_rois
         .join(MOSDEPTH.out.quantized_bed, failOnDuplicate:true, failOnMismatch:true)
@@ -181,9 +183,10 @@ workflow CRAM_PREPARE_SAMTOOLS_BEDTOOLS {
         .mix(BEDTOOLS_INTERSECT.out.intersect)
 
     emit:
-    ready_crams = ch_ready_crams    // [ val(meta), path(cram), path(crai) ]
-    ready_bams  = ch_ready_bams     // [ val(meta), path(bam), path(bai) ]
-    ready_beds  = ch_ready_beds     // [ val(meta), path(bed) ]
-    versions    = ch_versions       // [ path(versions) ]
-    reports     = ch_reports        // [ path(reports) ]
+    ready_crams  = ch_ready_crams    // [ val(meta), path(cram), path(crai) ]
+    ready_bams   = ch_ready_bams     // [ val(meta), path(bam), path(bai) ]
+    ready_beds   = ch_ready_beds     // [ val(meta), path(bed) ]
+    perbase_beds = ch_perbase_beds   // [ val(meta), path(bed), path(csi) ]
+    versions     = ch_versions       // [ path(versions) ]
+    reports      = ch_reports        // [ path(reports) ]
 }

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

@@ -48,6 +48,7 @@ nextflow_workflow {
                         [ it[0], "${file(it[1]).name},readsMD5:${bam(it[1]).getReadsMD5()}", file(it[2]).name ]
                     },
                     workflow.out.ready_beds,
+                    workflow.out.perbase_beds,
                     workflow.out.reports
                 ).match() }
             )
@@ -95,6 +96,7 @@ nextflow_workflow {
                         [ it[0], "${file(it[1]).name},readsMD5:${bam(it[1]).getReadsMD5()}", file(it[2]).name ]
                     },
                     workflow.out.ready_beds,
+                    workflow.out.perbase_beds,
                     workflow.out.reports
                 ).match() }
             )
@@ -142,6 +144,7 @@ nextflow_workflow {
                         [ it[0], "${file(it[1]).name},readsMD5:${bam(it[1]).getReadsMD5()}", file(it[2]).name ]
                     },
                     workflow.out.ready_beds,
+                    workflow.out.perbase_beds,
                     workflow.out.reports
                 ).match() }
             )
@@ -196,6 +199,7 @@ nextflow_workflow {
                         [ it[0], "${file(it[1]).name},readsMD5:${bam(it[1]).getReadsMD5()}", file(it[2]).name ]
                     },
                     workflow.out.ready_beds,
+                    workflow.out.perbase_beds,
                     workflow.out.reports
                 ).match() }
             )

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

@@ -39,15 +39,28 @@
                     "NA24143.intersect.bed:md5,b87069698afefb15282d069e56110046"
                 ]
             ],
+            [
+                [
+                    {
+                        "id": "NA24143",
+                        "sample": "NA24143",
+                        "family": "Ashkenazim",
+                        "family_samples": "NA24143",
+                        "duplicate_count": 1
+                    },
+                    "NA24143.per-base.bed.gz:md5,2f773324021d6d1b18c87af240d1a18f",
+                    "NA24143.per-base.bed.gz.csi:md5,fe996e285822f6126adcdca8b7517058"
+                ]
+            ],
             [
 
             ]
         ],
         "meta": {
             "nf-test": "0.9.1",
-            "nextflow": "24.10.0"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-11-14T16:07:03.620603158"
+        "timestamp": "2025-01-22T13:39:12.575142149"
     },
     "cram_prepare_samtools_bedtools - default - WES": {
         "content": [
@@ -79,15 +92,28 @@
                     "NA24143.intersect.bed:md5,b87069698afefb15282d069e56110046"
                 ]
             ],
+            [
+                [
+                    {
+                        "id": "NA24143",
+                        "sample": "NA24143",
+                        "family": "Ashkenazim",
+                        "family_samples": "NA24143",
+                        "duplicate_count": 1
+                    },
+                    "NA24143.per-base.bed.gz:md5,2f773324021d6d1b18c87af240d1a18f",
+                    "NA24143.per-base.bed.gz.csi:md5,fe996e285822f6126adcdca8b7517058"
+                ]
+            ],
             [
 
             ]
         ],
         "meta": {
             "nf-test": "0.9.1",
-            "nextflow": "24.10.0"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-11-14T16:07:24.688580575"
+        "timestamp": "2025-01-22T13:39:30.958080052"
     },
     "cram_prepare_samtools_bedtools - default - WGS": {
         "content": [
@@ -119,15 +145,28 @@
                     "NA24143.filter.bed:md5,85a5568a6976ed455caa712991b30ac2"
                 ]
             ],
+            [
+                [
+                    {
+                        "id": "NA24143",
+                        "sample": "NA24143",
+                        "family": "Ashkenazim",
+                        "family_samples": "NA24143",
+                        "duplicate_count": 1
+                    },
+                    "NA24143.per-base.bed.gz:md5,2f773324021d6d1b18c87af240d1a18f",
+                    "NA24143.per-base.bed.gz.csi:md5,fe996e285822f6126adcdca8b7517058"
+                ]
+            ],
             [
 
             ]
         ],
         "meta": {
             "nf-test": "0.9.1",
-            "nextflow": "24.10.0"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-11-14T16:06:42.311563291"
+        "timestamp": "2025-01-22T13:38:51.625657423"
     },
     "cram_prepare_samtools_bedtools - default - merge": {
         "content": [
@@ -169,14 +208,27 @@
                     "NA24143.intersect.bed:md5,b87069698afefb15282d069e56110046"
                 ]
             ],
+            [
+                [
+                    {
+                        "id": "NA24143",
+                        "sample": "NA24143",
+                        "family": "Ashkenazim",
+                        "family_samples": "NA24143",
+                        "duplicate_count": 2
+                    },
+                    "NA24143.per-base.bed.gz:md5,85e799ea056ba8d127115e012adcbe7a",
+                    "NA24143.per-base.bed.gz.csi:md5,3f40731dbdbef353385d04f51feb43b3"
+                ]
+            ],
             [
 
             ]
         ],
         "meta": {
             "nf-test": "0.9.1",
-            "nextflow": "24.10.0"
+            "nextflow": "24.10.3"
         },
-        "timestamp": "2024-11-14T16:08:20.712943795"
+        "timestamp": "2025-01-22T13:40:12.40700375"
     }
 }