update changelog

.github/workflows/render-puml.yaml

@@ -13,7 +13,7 @@ jobs:
 
     steps:
       - name: Generate PUML diagrams
-        uses: uclahs-cds/[email protected].0
+        uses: uclahs-cds/[email protected].1
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           ghcr-username: ${{ github.actor }}

CHANGELOG.md

@@ -10,9 +10,19 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 ## [Unreleased]
 ### Added
 - Add workflow for genotyping from GVCFs
-
 ### Changed
+- Standardize description
 - Update GATK to 4.5.0.0
+
+---
+
+## [10.0.1] - 2024-04-15
+### Changed
+- Replace workflow diagram with PlantUML version
+- Update PlantUML action to v1.0.1
+### Fixed
+- Resolve intervals before splitting to allow for index discovery
+
 ---
 
 ## [10.0.0] - 2024-03-08

README.md

@@ -18,6 +18,8 @@ This pipeline takes BAMs and corresponding indices from [recalibrate-BAM](https:
 
 ## How To Run
 
+**Requirements**: Currently supported Nextflow versions: `v23.04.2`
+
 **The pipeline is currently configured to run on a SINGLE NODE mode with normal only, tumor only, normal-tumor paired, or multiple normal and tumor samples.**
 
 1. Update the params section of the .config file ([Example config](config/template.config)).
@@ -42,7 +44,7 @@ python submit_nextflow_pipeline.py \
 
 ## Flow Diagram
 
-![call-gSNP flow diagram](call-gSNP-DSL2.png)
+![call-gSNP flow diagram](docs/call-gsnp-flow.svg)
 
 ---
 

docs/call-gsnp-flow.puml

@@ -0,0 +1,87 @@
+@startuml
+
+skinparam ConditionEndStyle hline
+
+start
+
+if (Explicit intervals?) is (Yes) then
+    :==run_SplitIntervals_GATK
+    ----
+    Split reference genome into up
+    to **scatter_count** interval lists,
+    without subdividing any of the
+    input intervals;
+else (No)
+    :==run_SplitIntervals_GATK
+    ----
+    Split reference genome into
+    **scatter_count** interval lists;
+endif
+
+split
+
+:==run_HaplotypeCallerVCF_GATK
+----
+Generate VCFs for each split interval
+using HaplotypeCaller;
+
+:==run_MergeVcfs_Picard_VCF
+----
+Merge raw variants into whole VCF file;
+
+#palegreen:Per-sample raw VCF + index files>
+
+partition "Recalibrate Variants" {
+
+:==run_VariantRecalibratorSNP_GATK
+----
+Generate Variant Quality Score Recalibration
+(VQSR) table for SNPs;
+
+:==run_ApplyVQSR_GATK_SNP
+----
+Filter SNPs based on VQSR table;
+
+:==run_VariantRecalibratorINDEL_GATK
+----
+Generate VQSR table for INDELs;
+
+:==run_ApplyVQSR_GATK_INDEL
+----
+Filter INDELs based on VQSR table;
+
+}
+
+#palegreen:SNP and INDEL recalibrated
+variants + index files>
+
+:==filter_gSNP_GATK
+----
+Filter ambiguous variants with
+customized Perl script;
+
+#palegreen:Filtered germline
+variants + index files>
+
+detach
+
+split again
+
+:==run_HaplotypeCallerGVCF_GATK
+----
+Generate GVCFs for each split interval
+using HaplotypeCaller;
+
+:==run_MergeVcfs_Picard_GVCF
+----
+Merge raw variants into whole GVCF file;
+
+#palegreen:Per-sample GVCF + index files>
+
+detach
+
+endsplit
+
+
+@enduml
+

metadata.yaml

@@ -1,6 +1,6 @@
 ---
 category: "pipeline"
-description: "GATK pipeline for calling germline variants"
+description: "Nextflow pipeline to call germline short variants using GATK"
 maintainers: "Boutros Lab Infrastructure <[email protected]>"
 languages: ["Nextflow", "Docker"]
 dependencies: ["Java", "Nextflow", "Docker"]

module/split-intervals.nf

@@ -42,7 +42,7 @@ process run_SplitIntervals_GATK {
     set -euo pipefail
     gatk SplitIntervals \
         -R ${reference} \
-        -L ${intervals} \
+        -L "\$(realpath ${intervals})" \
         --scatter-count ${params.scatter_count} \
         ${subdivision_mode} \
         ${params.split_intervals_extra_args} \

nextflow.config

@@ -5,5 +5,5 @@ manifest {
     name = 'call-gSNP'
     author = ["Yash Patel", "Shu Tao", "Stefan Eng"]
     description = 'Nextflow pipeline to call germline short variants in single or normal-tumour paired mode'
-    version = '10.0.0'
+    version = '10.0.1'
 }