From d2ebecbfce3b524049db1122edb63be791629131 Mon Sep 17 00:00:00 2001
From: Bec Asch <rsasch@users.noreply.github.com>
Date: Fri, 25 Feb 2022 11:49:47 -0500
Subject: [PATCH] Additional tweaks for GvsExtractCohortFromSampleNames
 [VS-283] (#7698)

---
 .dockstore.yml                                |  6 ++---
 .../variantstore/wdl/GvsExtractCallset.wdl    |  3 ++-
 .../wdl/GvsExtractCohortFromSampleNames.wdl   | 26 ++++++++++++++++---
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/.dockstore.yml b/.dockstore.yml
index ecfbda0a172..a567b086e8d 100644
--- a/.dockstore.yml
+++ b/.dockstore.yml
@@ -91,7 +91,7 @@ workflows:
          - ah_var_store
          - rsa_split_intervals_part_2
          - kc_cluster_vqsr
-         - kc_quoting_bug         
+         - kc_quoting_bug
    - name: GvsCreateAltAllele
      subclass: WDL
      primaryDescriptorPath: /scripts/variantstore/wdl/GvsCreateAltAllele.wdl
@@ -101,7 +101,7 @@ workflows:
        branches:
          - master
          - ah_var_store
-         - kc_quoting_bug         
+         - kc_quoting_bug
    - name: GvsCreateTables
      subclass: WDL
      primaryDescriptorPath: /scripts/variantstore/wdl/GvsCreateTables.wdl
@@ -178,7 +178,7 @@ workflows:
        branches:
          - master
          - ah_var_store
-         - rsa_wire_cohort_wdl
+         - rsa_cohort_wdl_fixes
    - name: MitochondriaPipeline
      subclass: WDL
      primaryDescriptorPath: /scripts/mitochondria_m2_wdl/MitochondriaPipeline.wdl
diff --git a/scripts/variantstore/wdl/GvsExtractCallset.wdl b/scripts/variantstore/wdl/GvsExtractCallset.wdl
index 06106bfd747..3306c0c5535 100644
--- a/scripts/variantstore/wdl/GvsExtractCallset.wdl
+++ b/scripts/variantstore/wdl/GvsExtractCallset.wdl
@@ -72,7 +72,8 @@ workflow GvsExtractCallset {
           output_gcs_dir = output_gcs_dir,
           split_intervals_disk_size_override = split_intervals_disk_size_override,
           split_intervals_mem_override = split_intervals_mem_override,
-          service_account_json_path = service_account_json_path
+          service_account_json_path = service_account_json_path,
+          gatk_override = gatk_override
     }
 
     call Utils.GetBQTablesMaxLastModifiedTimestamp {
diff --git a/scripts/variantstore/wdl/GvsExtractCohortFromSampleNames.wdl b/scripts/variantstore/wdl/GvsExtractCohortFromSampleNames.wdl
index 46fa87986aa..19285e85d49 100644
--- a/scripts/variantstore/wdl/GvsExtractCohortFromSampleNames.wdl
+++ b/scripts/variantstore/wdl/GvsExtractCohortFromSampleNames.wdl
@@ -12,6 +12,7 @@ workflow GvsExtractCohortFromSampleNames {
     String query_project
     String gvs_project
     String gvs_dataset
+    String cohort_table_prefix
 
     # not using the defaults in GvsPrepareCallset because we're using pre created datasets defined by the caller
     String fq_gvs_extraction_destination_dataset
@@ -19,6 +20,7 @@ workflow GvsExtractCohortFromSampleNames {
 
     String extraction_uuid
     String? output_gcs_dir
+    String? service_account_json_path
 
     # Extract parameters
     File wgs_intervals
@@ -40,12 +42,17 @@ workflow GvsExtractCohortFromSampleNames {
     Float? snps_truth_sensitivity_filter_level_override
     Float? indels_truth_sensitivity_filter_level_override
 
+    Int? extract_preemptible_override
+    Int? extract_maxretries_override
+    Int? split_intervals_disk_size_override
+    Int? split_intervals_mem_override
+
     File? gatk_override
   }
 
   call GvsPrepareCallset.GvsPrepareCallset {
     input:
-      destination_cohort_table_prefix = extraction_uuid,
+      destination_cohort_table_prefix = cohort_table_prefix,
       sample_names_to_extract         = cohort_sample_names,
       data_project                    = gvs_project,
       query_labels                    = ["extraction_uuid=~{extraction_uuid}"],
@@ -54,7 +61,8 @@ workflow GvsExtractCohortFromSampleNames {
       fq_petvet_dataset               = "~{gvs_project}.~{gvs_dataset}",
       fq_sample_mapping_table         = "~{gvs_project}.~{gvs_dataset}.sample_info",
       fq_temp_table_dataset           = fq_gvs_extraction_temp_tables_dataset,
-      fq_destination_dataset          = fq_gvs_extraction_destination_dataset
+      fq_destination_dataset          = fq_gvs_extraction_destination_dataset,
+      service_account_json_path       = service_account_json_path
   }
 
   call GvsExtractCallset.GvsExtractCallset {
@@ -62,7 +70,7 @@ workflow GvsExtractCohortFromSampleNames {
       data_project = gvs_project,
       query_project = query_project,
       default_dataset = gvs_dataset,
-      extract_table_prefix = extraction_uuid,
+      extract_table_prefix = cohort_table_prefix,
 
       wgs_intervals = wgs_intervals,
       scatter_count = scatter_count,
@@ -78,7 +86,17 @@ workflow GvsExtractCohortFromSampleNames {
 
       output_file_base_name = output_file_base_name,
       output_gcs_dir = output_gcs_dir,
-      gatk_override = gatk_override
+      service_account_json_path = service_account_json_path,
+      gatk_override = gatk_override,
+      fq_samples_to_extract_table = "~{GvsPrepareCallset.fq_cohort_extract_table_prefix}__SAMPLES",
+      fq_ranges_cohort_vet_extract_table = "~{GvsPrepareCallset.fq_cohort_extract_table_prefix}__VET_DATA",
+      fq_ranges_cohort_ref_extract_table = "~{GvsPrepareCallset.fq_cohort_extract_table_prefix}__REF_DATA",
+
+      extract_preemptible_override = extract_preemptible_override,
+      extract_maxretries_override = extract_maxretries_override,
+      split_intervals_disk_size_override = split_intervals_disk_size_override,
+      split_intervals_mem_override = split_intervals_mem_override
+
   }
 
   output {