Merge pull request #366 from genomic-medicine-sweden/chromograph

add chromograph

CHANGELOG.md

@@ -7,11 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
-- Add `public_aws_ecr` profile for using AWS ECR public gallery images
-- GATK's ShiftFasta to generate all the files required for mitochondrial analysis
-- Feature to calculate CADD scores for indels
-- HmtNote to annotate mitochondria
-- MT del script to detect mitochondrial deltions
+- Add `public_aws_ecr` profile for using AWS ECR public gallery images [#360](https://github.com/nf-core/raredisease/pull/360)
+- GATK's ShiftFasta to generate all the files required for mitochondrial analysis [#354](https://github.com/nf-core/raredisease/pull/354)
+- Feature to calculate CADD scores for indels [#325](https://github.com/nf-core/raredisease/pull/325)
+- HmtNote to annotate mitochondria [#355](https://github.com/nf-core/raredisease/pull/355)
+- MT del script to detect mitochondrial deletions [#349](https://github.com/nf-core/raredisease/pull/349)
+- eKLIPse to identify large mitochondrial deletions [#365](https://github.com/nf-core/raredisease/pull/365)
+- UPD+Chromograph to identify and visualize UPD sites and regions in the chromosomes [#364](https://github.com/nf-core/raredisease/pull/364) and [#366](https://github.com/nf-core/raredisease/pull/366)
 
 ## v1.0.0 - [2023-06-01]
 

README.md

@@ -61,6 +61,8 @@ On release, automated continuous integration tests run the pipeline on a full-si
 - [vcfanno](https://github.com/brentp/vcfanno)
 - [CADD](https://cadd.gs.washington.edu/)
 - [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html)
+- [UPD](https://github.com/bjhall/upd)
+- [Chromograph](https://github.com/Clinical-Genomics/chromograph)
 
 **6. Annotation - SV:**
 
@@ -139,7 +141,7 @@ For more details about the output files and reports, please refer to the
 
 nf-core/raredisease was written in a collaboration between the Clinical Genomics nodes in Sweden, with major contributions from [Ramprasad Neethiraj](https://github.com/ramprasadn), [Anders Jemt](https://github.com/jemten), [Lucia Pena Perez](https://github.com/Lucpen), and [Mei Wu](https://github.com/projectoriented) at Clinical Genomics Stockholm.
 
-Additional contributors were [Sima Rahimi](https://github.com/sima-r), [Gwenna Breton](https://github.com/Gwennid) and [Emma Västerviga](https://github.com/EmmaCAndersson) (Clinical Genomics Gothenburg); [Lauri Mesilaakso](https://github.com/ljmesi) (Clinical Genomics Linköping); [Subazini Thankaswamy Kosalai](https://github.com/sysbiocoder) (Clinical Genomics Örebro); [Annick Renevey](https://github.com/rannick) and [Peter Pruisscher](https://github.com/peterpru) (Clinical Genomics Stockholm); [Ryan Kennedy](https://github.com/ryanjameskennedy) (Clinical Genomics Lund); and [Lucas Taniguti](https://github.com/lmtani).
+Additional contributors were [Sima Rahimi](https://github.com/sima-r), [Gwenna Breton](https://github.com/Gwennid) and [Emma Västerviga](https://github.com/EmmaCAndersson) (Clinical Genomics Gothenburg); [Halfdan Rydbeck](https://github.com/hrydbeck) and [Lauri Mesilaakso](https://github.com/ljmesi) (Clinical Genomics Linköping); [Subazini Thankaswamy Kosalai](https://github.com/sysbiocoder) (Clinical Genomics Örebro); [Annick Renevey](https://github.com/rannick) and [Peter Pruisscher](https://github.com/peterpru) (Clinical Genomics Stockholm); [Ryan Kennedy](https://github.com/ryanjameskennedy) (Clinical Genomics Lund); and [Lucas Taniguti](https://github.com/lmtani).
 
 We thank the nf-core community for their extensive assistance in the development of this pipeline.
 

conf/modules/annotate_snvs.config

@@ -48,7 +48,31 @@ process {
 
     withName: '.*ANNOTATE_SNVS:UPD_REGIONS' {
         ext.prefix = { "${meta.id}_rohann_vcfanno_upd_regions" }
-        ext.args = {"--af-tag GNOMADAF --proband ${meta.upd_child} --mother ${meta.mother} --father ${meta.father} regions"}
+        ext.args = {"--af-tag GNOMADAF --proband ${meta.upd_child} --mother ${meta.mother} --father ${meta.father} regions --min-size 5 --min-sites 1"}
+        ext.when = { !(workflow.profile.tokenize(',').intersect(['test', 'test_one_sample']).size() >= 1) || workflow.stubRun }
+    }
+
+    withName: '.*ANNOTATE_SNVS:CHROMOGRAPH_SITES' {
+        ext.prefix = { "${meta7.id}_rohann_vcfanno_upd_sites_chromograph" }
+        ext.args = { "--euploid" }
+        tag =  {"${meta7.id}"}
+        publishDir = [
+            path: { "${params.outdir}/annotate_snv" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: '.*ANNOTATE_SNVS:CHROMOGRAPH_REGIONS' {
+        ext.prefix = { "${meta6.id}_rohann_vcfanno_upd_regions_chromograph" }
+        ext.args = { '--euploid' }
+        ext.when = { !(workflow.profile.tokenize(',').intersect(['test', 'test_one_sample']).size() >= 1) || workflow.stubRun }
+        tag =  {"${meta6.id}"}
+        publishDir = [
+            path: { "${params.outdir}/annotate_snv" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
     }
 
     withName: '.*ANNOTATE_SNVS:BCFTOOLS_VIEW' {

docs/output.md

@@ -42,6 +42,8 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
   - [vcfanno](#vcfanno)
   - [CADD](#cadd)
   - [VEP](#vep)
+  - [UPD](#upd)
+  - [Chromograph](#chromograph)
 - [Annotation - SV](#annotation---sv)
   - [SVDB query](#svdb-query)
   - [VEP](#vep-1)
@@ -331,6 +333,24 @@ Based on VEP annotations, custom scripts used by the pipeline further annotate e
 
 </details>
 
+#### UPD
+
+[UPD](https://github.com/bjhall/upd) calls regions of uniparental disomy from germline exome/wgs trios. Output from UPD is passed to chromograph for making plots.
+
+#### Chromograph
+
+[Chromograph](https://github.com/Clinical-Genomics/chromograph) is a python package to create PNG images from genetics data such as BED and WIG files.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `annotate_snv/*sites_chromograph`
+  - `<case_id>_rohann_vcfanno_upd_sites_<chr#>.png`: file containing a plot showing upd sites across chromosomes.
+- `annotate_snv/*regions_chromograph`
+  - `<case_id>_rohann_vcfanno_upd_regions_<chr#>.png`: file containing a plot showing upd regions across chromosomes.
+
+</details>
+
 ### Annotation - SV
 
 #### SVDB query
@@ -407,10 +427,6 @@ We recommend using vcfanno to annotate SNVs with precomputed CADD scores (files
 
 </details>
 
-### Call UPD regions
-
-[UPD](https://github.com/bjhall/upd) calls regions of uniparental disomy from germline exome/wgs trios. Output from UPD is passed to chromograph for making plots.
-
 ### Rank variants and filtering
 
 #### GENMOD

modules.json

@@ -70,6 +70,11 @@
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
                         "installed_by": ["modules"]
                     },
+                    "chromograph": {
+                        "branch": "master",
+                        "git_sha": "aad210ba51500be029740d088b4b4827f6f41509",
+                        "installed_by": ["modules"]
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",

subworkflows/local/annotate_snvs.nf

@@ -9,6 +9,8 @@ include { BCFTOOLS_VIEW                         } from '../../modules/nf-core/bc
 include { RHOCALL_ANNOTATE                      } from '../../modules/nf-core/rhocall/annotate/main'
 include { UPD as UPD_SITES                      } from '../../modules/nf-core/upd/main'
 include { UPD as UPD_REGIONS                    } from '../../modules/nf-core/upd/main'
+include { CHROMOGRAPH as CHROMOGRAPH_SITES      } from '../../modules/nf-core/chromograph/main'
+include { CHROMOGRAPH as CHROMOGRAPH_REGIONS    } from '../../modules/nf-core/chromograph/main'
 include { ENSEMBLVEP as ENSEMBLVEP_SNV          } from '../../modules/local/ensemblvep/main'
 include { TABIX_BGZIPTABIX as ZIP_TABIX_ROHCALL } from '../../modules/nf-core/tabix/bgziptabix/main'
 include { TABIX_BGZIPTABIX as ZIP_TABIX_VCFANNO } from '../../modules/nf-core/tabix/bgziptabix/main'
@@ -66,10 +68,11 @@ workflow ANNOTATE_SNVS {
             .flatten()
             .buffer (size: 2)
             .set { ch_upd_in }
-
-        UPD_SITES(ch_upd_in)
 
+        UPD_SITES(ch_upd_in)
         UPD_REGIONS(ch_upd_in)
+        CHROMOGRAPH_SITES([[],[]], [[],[]], [[],[]], [[],[]], [[],[]], [[],[]], UPD_SITES.out.bed)
+        CHROMOGRAPH_REGIONS([[],[]], [[],[]], [[],[]], [[],[]], [[],[]], UPD_REGIONS.out.bed, [[],[]])
 
         ZIP_TABIX_VCFANNO (VCFANNO.out.vcf)
 
@@ -150,6 +153,8 @@ workflow ANNOTATE_SNVS {
         ch_versions = ch_versions.mix(VCFANNO.out.versions)
         ch_versions = ch_versions.mix(UPD_SITES.out.versions)
         ch_versions = ch_versions.mix(UPD_REGIONS.out.versions)
+        ch_versions = ch_versions.mix(CHROMOGRAPH_SITES.out.versions)
+        ch_versions = ch_versions.mix(CHROMOGRAPH_REGIONS.out.versions)
         ch_versions = ch_versions.mix(ZIP_TABIX_VCFANNO.out.versions)
         ch_versions = ch_versions.mix(BCFTOOLS_VIEW.out.versions)
         ch_versions = ch_versions.mix(TABIX_BCFTOOLS_VIEW.out.versions)