lower allowable nubmer of variants qc check to 3 milliion from 10 million in array imputation qc wdl

Author: Jose Soto

pipelines/wdl/arrays/imputation_beagle/ImputationBeagle.changelog.md

@@ -1,3 +1,8 @@
+# 2.5.1
+2026-2-04 (Date of Last Commit)
+
+* Update input_qc_version to 1.2.5 to match the latest changes in InputQC wdl.
+
 # 2.5.0
 2026-01-27 (Date of Last Commit)
 

pipelines/wdl/arrays/imputation_beagle/ImputationBeagle.wdl

@@ -5,8 +5,8 @@ import "../../../../tasks/wdl/ImputationTasks.wdl" as tasks
 import "../../../../tasks/wdl/ImputationBeagleTasks.wdl" as beagleTasks
 
 workflow ImputationBeagle {
-  String pipeline_version = "2.5.0"
-  String input_qc_version = "1.2.5"
+  String pipeline_version = "2.5.1"
+  String input_qc_version = "1.3.0"
   String quota_consumed_version = "1.1.0"
 
   input {

pipelines/wdl/arrays/imputation_beagle/input_qc/ArrayImputationQC.changelog.md

@@ -1,3 +1,8 @@
+# 1.3.0
+2026-02-04 (Date of Last Commit)
+
+* Lower variant number check to 3 million from 10 million to further prevent whole genome inputs from being submitted
+
 # 1.2.5
 2025-12-23 (Date of Last Commit)
 

pipelines/wdl/arrays/imputation_beagle/input_qc/ArrayImputationQC.wdl

@@ -4,7 +4,7 @@ import "../../../../../tasks/wdl/ImputationBeagleQcTasks.wdl" as tasks
 
 workflow InputQC {
     # if this changes, update the input_qc_version value in ImputationBeagle.wdl
-    String pipeline_version = "1.2.5"
+    String pipeline_version = "1.3.0"
 
 
     input {

pipelines/wdl/arrays/imputation_beagle/input_qc/test_inputs/Plumbing/NA12878_wgs_chr20_qc_fails_too_many_records.json

@@ -1,5 +1,5 @@
 {
-    "ArrayImputationQC.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation_beagle/input_qc/scientific/vcfs/NA12878.annotated.chr20.g.vcf.gz",
+    "ArrayImputationQC.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation_beagle/input_qc/scientific/vcfs/NA12878.annotated.chr20_over_three_million_sites.g.vcf.gz",
     "ArrayImputationQC.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
     "ArrayImputationQC.reference_panel_path_prefix": "gs://broad-gotc-test-storage/imputation_beagle/scientific/1000G_HGDP_no_singletons_reference_panel/hgdp.tgp.gwaspy.AN_added.bcf.ac2",
     "ArrayImputationQC.contigs": ["this_contig_is_not_in_inputs_1", "this_contig_is_not_in_inputs_2", "this_contig_is_not_in_inputs_3"],

tasks/wdl/ImputationBeagleQcTasks.wdl

@@ -18,14 +18,14 @@ task QcChecks {
         # create empty qc messages file
         touch qc_messages.txt
 
-        # check for a large number of variants in input vcf and exit if greater than 10 million
+        # check for a large number of variants in input vcf and exit if greater than 3 million
         line_count=$(bcftools stats ~{vcf_input}  | grep "number of records:" | awk '{print $6}')
-        if [ "$line_count" -gt 10000000 ]; then
-            echo "Greater than 10 million variants found in the input VCF." >> qc_messages.txt
+        if [ "$line_count" -gt 3000000 ]; then
+            echo "Greater than 3 million variants found in the input VCF." >> qc_messages.txt
             echo "false" > passes_qc.txt
             exit 0
         else
-            echo "Less than or equal to 10 million variants found in input VCF."
+            echo "$line_count variants found in input VCF."
         fi
 
         # grab header from vcf