Filter wham-only DELs and scramble-only SVAs in CleanVcf & docs updates (#740)

Author: epiercehoffman

.github/.dockstore.yml

@@ -198,6 +198,15 @@ workflows:
       tags:
         - /.*/
 
+  - subclass: WDL
+    name: VisualizeCnvs
+    primaryDescriptorPath: /wdl/VisualizeCnvs.wdl
+    filters:
+      branches:
+        - main
+      tags:
+        - /.*/
+
   - subclass: WDL
     name: SingleSamplePipeline
     primaryDescriptorPath: /wdl/GATKSVPipelineSingleSample.wdl

README.md

@@ -2,7 +2,7 @@
 
 A structural variation discovery pipeline for Illumina short-read whole-genome sequencing (WGS) data.
 
-For technical documentation on GATK-SV, including how to run the pipeline, please refer to our website.
+For technical documentation on GATK-SV, including how to run the pipeline, please refer to our [website](https://broadinstitute.github.io/gatk-sv/).
 
 ## Repository structure
 * `/carrot`: [Carrot](https://github.com/broadinstitute/carrot) tests

inputs/templates/terra_workspaces/cohort_mode/cohort_mode_workspace_dashboard.md.tmpl

@@ -0,0 +1,10 @@
+{
+  "VisualizeCnvs.vcf_or_bed": "${this.filtered_vcf}",
+  "VisualizeCnvs.prefix": "${this.sample_set_set_id}",
+  "VisualizeCnvs.median_files": "${this.sample_sets.median_cov}",
+  "VisualizeCnvs.rd_files": "${this.sample_sets.merged_bincov}",
+  "VisualizeCnvs.ped_file": "${workspace.cohort_ped_file}",
+  "VisualizeCnvs.min_size": 50000,
+  "VisualizeCnvs.flags": "-s 999999999",
+  "VisualizeCnvs.sv_pipeline_docker": "${workspace.sv_pipeline_docker}"
+}

inputs/templates/terra_workspaces/cohort_mode/samples_1kgp_156.tsv.tmpl

@@ -5,6 +5,6 @@
   "VisualizeCnvs.rd_files": [{{ test_batch.merged_coverage_file | tojson }}],
   "VisualizeCnvs.ped_file": {{ test_batch.ped_file | tojson }},
   "VisualizeCnvs.min_size": 50000,
-  "VisualizeCnvs.flags": "",
+  "VisualizeCnvs.flags": "-s 999999999",
   "VisualizeCnvs.sv_pipeline_docker": {{ dockers.sv_pipeline_docker | tojson }}
 }

inputs/templates/terra_workspaces/cohort_mode/samples_1kgp.tsv.tmpl inputs/templates/terra_workspaces/cohort_mode/samples_1kgp_312.tsv.tmpl

@@ -113,7 +113,7 @@ def main():
     parser.add_argument("-j", "--womtool-jar", help="Path to womtool jar", required=True)
     parser.add_argument("-n", "--num-input-jsons",
                         help="Number of Terra input JSONs expected",
-                        required=False, default=25, type=int)
+                        required=False, default=26, type=int)
     parser.add_argument("--log-level",
                         help="Specify level of logging information, ie. info, warning, error (not case-sensitive)",
                         required=False, default="INFO")

inputs/templates/terra_workspaces/cohort_mode/workflow_configurations/VisualizeCnvs.json.tmpl

@@ -53,6 +53,7 @@ workflow CleanVcfChromosome {
     RuntimeAttr? runtime_override_stitch_fragmented_cnvs
     RuntimeAttr? runtime_override_final_cleanup
     RuntimeAttr? runtime_override_rescue_me_dels
+    RuntimeAttr? runtime_attr_add_high_fp_rate_filters
 
     # Clean vcf 1b
     RuntimeAttr? runtime_attr_override_subset_large_cnvs_1b
@@ -299,9 +300,17 @@ workflow CleanVcfChromosome {
       runtime_attr_override = runtime_override_rescue_me_dels
   }
 
-  call FinalCleanup {
+  call AddHighFDRFilters {
     input:
       vcf=RescueMobileElementDeletions.out,
+      prefix="~{prefix}.high_fdr_filtered",
+      sv_pipeline_docker=sv_pipeline_docker,
+      runtime_attr_override=runtime_attr_add_high_fp_rate_filters
+  }
+
+  call FinalCleanup {
+    input:
+      vcf=AddHighFDRFilters.out,
       contig=contig,
       prefix="~{prefix}.final_cleanup",
       sv_pipeline_docker=sv_pipeline_docker,
@@ -799,6 +808,58 @@ task StitchFragmentedCnvs {
   }
 }
 
+# Add FILTER status for pockets of variants with high FP rate: wham-only DELs and Scramble-only SVAs with HIGH_SR_BACKGROUND
+task AddHighFDRFilters {
+  input {
+    File vcf
+    String prefix
+    String sv_pipeline_docker
+    RuntimeAttr? runtime_attr_override
+  }
+
+  Float input_size = size(vcf, "GiB")
+  RuntimeAttr runtime_default = object {
+    mem_gb: 3.75,
+    disk_gb: ceil(10.0 + input_size * 3.0),
+    cpu_cores: 1,
+    preemptible_tries: 3,
+    max_retries: 1,
+    boot_disk_gb: 10
+  }
+  RuntimeAttr runtime_override = select_first([runtime_attr_override, runtime_default])
+  runtime {
+    memory: "~{select_first([runtime_override.mem_gb, runtime_default.mem_gb])} GB"
+    disks: "local-disk ~{select_first([runtime_override.disk_gb, runtime_default.disk_gb])} HDD"
+    cpu: select_first([runtime_override.cpu_cores, runtime_default.cpu_cores])
+    preemptible: select_first([runtime_override.preemptible_tries, runtime_default.preemptible_tries])
+    maxRetries: select_first([runtime_override.max_retries, runtime_default.max_retries])
+    docker: sv_pipeline_docker
+    bootDiskSizeGb: select_first([runtime_override.boot_disk_gb, runtime_default.boot_disk_gb])
+  }
+
+  command <<<
+    set -euo pipefail
+
+    python <<CODE
+import pysam
+with pysam.VariantFile("~{vcf}", 'r') as fin:
+  header = fin.header
+  header.add_line("##FILTER=<ID=HIGH_ALGORITHM_FDR,Description=\"Categories of variants with low precision including Wham-only deletions and certain Scramble SVAs\">")
+  with pysam.VariantFile("~{prefix}.vcf.gz", 'w', header=header) as fo:
+    for record in fin:
+        if (record.info['ALGORITHMS'] == ('wham',) and record.info['SVTYPE'] == 'DEL') or \
+          (record.info['ALGORITHMS'] == ('scramble',) and record.info['HIGH_SR_BACKGROUND'] and record.alts == ('<INS:ME:SVA>',)):
+            record.filter.add('HIGH_ALGORITHM_FDR')
+        fo.write(record)
+CODE
+  >>>
+
+  output {
+    File out = "~{prefix}.vcf.gz"
+  }
+}
+
+
 
 # Final VCF cleanup
 task FinalCleanup {

inputs/templates/test/VisualizeCnvs/VisualizeCnvs.json.tmpl

@@ -7,6 +7,7 @@
 # Generated files
 .docusaurus
 .cache-loader
+package-lock.json
 
 # Misc
 .DS_Store

scripts/test/terra_validation.py

@@ -29,7 +29,7 @@ Google Cloud Platform (GCP).
 
 # Cromwell Server
 
-There are two option to communicate with a running Cromwell server: 
+There are two options to communicate with a running Cromwell server: 
 [REST API](https://cromwell.readthedocs.io/en/stable/tutorials/ServerMode/), and
 [Cromshell](https://github.com/broadinstitute/cromshell) which is a command line tool
 to interface with a Cromwell server. We recommend using Cromshell due to its simplicity 

wdl/CleanVcfChromosome.wdl

@@ -4,8 +4,8 @@ description: Guide for using GATK-SV
 sidebar_position: 4
 ---
 
-A comprehensive guide for the single-sample calling mode is available in [GATK Best Practices for Structural Variation 
-Discovery on Single Samples](https://gatk.broadinstitute.org/hc/en-us/articles/9022653744283-GATK-Best-Practices-for-Structural-Variation-Discovery-on-Single-Samples).
+A comprehensive guide for the single-sample [calling mode](/docs/gs/calling_modes) is available in 
+[GATK Best Practices for Structural Variation Discovery on Single Samples](https://gatk.broadinstitute.org/hc/en-us/articles/9022653744283-GATK-Best-Practices-for-Structural-Variation-Discovery-on-Single-Samples).
 This material covers basic concepts of structural variant calling, specifics of SV VCF formatting, and 
 advanced troubleshooting that also apply to the joint calling mode as well. This guide is intended to supplement 
 documentation found here.