config variant search with vid as primary id

ui/src/criteria/filterableGroup.tsx

@@ -1054,7 +1054,7 @@ function generateFilters(
         filterType: tanagra.FilterFilterTypeEnum.Attribute,
         filterUnion: {
           attributeFilter: {
-            attribute: "variant_id",
+            attribute: "id",
             operator: tanagra.AttributeFilterOperatorEnum.Equals,
             values: [literalFromDataValue(query)],
           },

underlay/src/main/java/bio/terra/tanagra/filterbuilder/impl/core/FilterableGroupFilterBuilder.java

@@ -181,7 +181,7 @@ private static EntityFilter generateFilterForQuery(
           underlay, entity, entity.getAttribute("rs_number"), NaryOperator.IN, List.of(literal));
     } else if (query.matches("[0-9]+-[0-9]+-[A-Z]+-[A-Z]+")) {
       return new AttributeFilter(
-          underlay, entity, entity.getAttribute("variant_id"), BinaryOperator.EQUALS, literal);
+          underlay, entity, entity.getAttribute("id"), BinaryOperator.EQUALS, literal);
     } else {
       return new TextSearchFilter(
           underlay, entity, TextSearchOperator.EXACT_MATCH, query, entity.getAttribute("gene"));

underlay/src/main/resources/config/criteria/aouCT/criteriaselector/variant/selector.json

@@ -0,0 +1,15 @@
+{
+  "name": "tanagra-variant",
+  "displayName": "SNP/Indel Variant",
+  "isEnabledForCohorts": true,
+  "isEnabledForDataFeatureSets": false,
+  "display": {
+    "category": "Genomics",
+    "tags": null
+  },
+  "filterBuilder": "core.FilterableGroupFilterBuilder",
+  "plugin": "filterableGroup",
+  "pluginConfig": null,
+  "pluginConfigFile": "variant.json",
+  "modifiers": null
+}

underlay/src/main/resources/config/criteria/aouCT/criteriaselector/variant/variant.json

@@ -0,0 +1,81 @@
+{
+  "columns": [
+    {
+      "key": "id",
+      "widthString": "100%",
+      "title": "Variant id"
+    },
+    {
+      "key": "gene",
+      "widthDouble": 100,
+      "title": "Gene"
+    },
+    {
+      "key": "rs_number",
+      "widthDouble": 100,
+      "title": "RS number"
+    },
+    {
+      "key": "consequence",
+      "widthDouble": 100,
+      "title": "Consequence"
+    },
+    {
+      "key": "clinvar_significance",
+      "widthDouble": 100,
+      "title": "ClinVar significance"
+    },
+    {
+      "key": "protein_change",
+      "widthDouble": 100,
+      "title": "Protein change"
+    },
+    {
+      "key": "allele_count",
+      "widthDouble": 100,
+      "title": "Allele count"
+    },
+    {
+      "key": "allele_number",
+      "widthDouble": 100,
+      "title": "Allele number"
+    },
+    {
+      "key": "allele_frequency",
+      "widthDouble": 100,
+      "title": "Allele frequency"
+    },
+    {
+      "key": "t_item_count",
+      "widthDouble": 150,
+      "title": "Participant count"
+    }
+  ],
+  "entityGroup": "variantPerson",
+  "valueConfigs": [
+    {
+      "attribute": "gene",
+      "title": "Gene"
+    },
+    {
+      "attribute": "consequence",
+      "title": "Consequence"
+    },
+    {
+      "attribute": "clinvar_significance",
+      "title": "ClinVar significance"
+    },
+    {
+      "attribute": "allele_count",
+      "title": "Allele count"
+    },
+    {
+      "attribute": "allele_number",
+      "title": "Allele number"
+    },
+    {
+      "attribute": "allele_frequency",
+      "title": "Allele frequency"
+    }
+  ]
+}

underlay/src/main/resources/config/datamapping/aouCT/entity/variant/all.sql

@@ -0,0 +1,47 @@
+WITH sorted_transcripts AS (
+    SELECT vid,
+           consequence,
+           aa_change,
+           contig,
+           position,
+           ref_allele,
+           alt_allele,
+           dbsnp_rsid,
+           transcript,
+           dna_change_in_transcript,
+           clinvar_classification,
+           gvs_all_ac,
+           gvs_all_an,
+           gvs_all_af,
+           ROW_NUMBER() OVER(PARTITION BY vid ORDER BY CASE ARRAY_TO_STRING(consequence, ', ')
+                   WHEN 'upstream_gene_variant'
+                       THEN 4
+                   WHEN 'downstream_gene_variant'
+                       THEN 5
+                   ELSE 1
+                   END
+                   ASC
+                  )  AS row_number
+    FROM `${omopDataset}.prep_vat`
+    WHERE is_canonical_transcript OR transcript IS NULL
+    ORDER BY vid, row_number),
+     genes AS (
+         SELECT vid, ARRAY_TO_STRING(ARRAY_AGG(DISTINCT gene_symbol IGNORE NULLS ORDER BY gene_symbol), ', ') AS genes
+         FROM `${omopDataset}.prep_vat`
+         GROUP BY vid
+     )
+SELECT
+    sorted_transcripts.vid,
+    genes.genes as gene_symbol,
+    sorted_transcripts.dbsnp_rsid,
+    sorted_transcripts.consequence,
+    sorted_transcripts.aa_change,
+    sorted_transcripts.clinvar_classification,
+    sorted_transcripts.gvs_all_ac,
+    sorted_transcripts.gvs_all_an,
+    sorted_transcripts.gvs_all_af,
+    sorted_transcripts.contig,
+    sorted_transcripts.position
+FROM sorted_transcripts, genes
+WHERE genes.vid = sorted_transcripts.vid
+  AND (sorted_transcripts.row_number =1 or sorted_transcripts.transcript is NULL)

underlay/src/main/resources/config/datamapping/aouCT/entity/variant/entity.json

@@ -0,0 +1,22 @@
+{
+  "name": "variant",
+  "allInstancesSqlFile": "all.sql",
+  "attributes": [
+    { "name": "id", "dataType": "STRING", "valueFieldName": "vid" },
+    { "name": "gene", "dataType": "STRING", "valueFieldName": "gene_symbol", "isComputeDisplayHint": true },
+    { "name": "rs_number", "dataType": "STRING", "isDataTypeRepeated": true, "valueFieldName": "dbsnp_rsid" },
+    { "name": "consequence", "dataType": "STRING", "isDataTypeRepeated":  true, "isComputeDisplayHint": true },
+    { "name": "protein_change", "dataType": "STRING", "valueFieldName": "aa_change" },
+    { "name": "clinvar_significance", "dataType": "STRING", "isDataTypeRepeated":  true, "valueFieldName": "clinvar_classification", "isComputeDisplayHint": true },
+    { "name": "allele_count", "dataType": "INT64", "valueFieldName": "gvs_all_ac", "isComputeDisplayHint": true },
+    { "name": "allele_number", "dataType": "INT64", "valueFieldName": "gvs_all_an", "isComputeDisplayHint": true },
+    { "name": "allele_frequency", "dataType": "DOUBLE", "valueFieldName": "gvs_all_af", "isComputeDisplayHint": true },
+    { "name": "contig", "dataType": "STRING" },
+    { "name": "position", "dataType": "INT64" }
+  ],
+  "idAttribute": "id",
+  "textSearch": {
+    "attributes": [ "id", "gene", "rs_number" ]
+  },
+  "optimizeGroupByAttributes": [ "id" ]
+}

underlay/src/main/resources/config/datamapping/aouCT/entitygroup/variantPerson/entityGroup.json

@@ -0,0 +1,14 @@
+{
+  "name": "variantPerson",
+  "groupEntity": "variant",
+  "itemsEntity": "person",
+  "idPairsSqlFile":  "idPairs.sql",
+  "useSourceIdPairsSql": true,
+  "groupEntityIdFieldName": "id",
+  "itemsEntityIdFieldName": "flattened_person_id",
+  "rollupCountsSql": {
+    "sqlFile": "rollupCounts.sql",
+    "entityIdFieldName": "id",
+    "rollupCountFieldName": "num_persons"
+  }
+}

underlay/src/main/resources/config/datamapping/aouCT/entitygroup/variantPerson/idPairs.sql

@@ -0,0 +1,3 @@
+SELECT DISTINCT vid as id, flattened_person_id
+FROM `${omopDataset}.cb_variant_to_person`
+CROSS JOIN UNNEST(person_ids) AS flattened_person_id

underlay/src/main/resources/config/datamapping/aouCT/entitygroup/variantPerson/rollupCounts.sql

@@ -0,0 +1,2 @@
+SELECT vid as id, ARRAY_LENGTH(person_ids) AS num_persons
+FROM (SELECT DISTINCT vid, person_ids FROM `${omopDataset}.cb_variant_to_person`)

underlay/src/main/resources/config/underlay/aouSC2023Q3R2/underlay.json

@@ -58,7 +58,9 @@
     "aouRT/surveySocialDeterminantsOfHealth",
     "aouRT/surveyCovidVaccine",
     "aouRT/surveyCope",
-    "aouRT/surveyOccurrence"
+    "aouRT/surveyOccurrence",
+
+    "aouCT/variant"
   ],
   "groupItemsEntityGroups": [
     "aouRT/brandIngredientConcept",
@@ -77,7 +79,9 @@
     "aouRT/weightPerson",
     "aouRT/bmiPerson",
     "aouRT/waistCircumferencePerson",
-    "aouRT/hipCircumferencePerson"
+    "aouRT/hipCircumferencePerson",
+
+    "aouCT/variantPerson"
   ],
   "criteriaOccurrenceEntityGroups": [
     "aouRT/conditionPerson",
@@ -144,6 +148,7 @@
     "aouCT/longReadWGS",
     "aouCT/globalDiversityArray",
     "aouCT/structuralVariants",
+    "aouCT/variant",
     "aouRT/bloodPressure",
     "aouRT/heartRate",
     "aouRT/height",

underlay/src/test/java/bio/terra/tanagra/filterbuilder/FilterableGroupFilterBuilderTest.java

@@ -143,7 +143,7 @@ void selectAllQueryFilter() {
     EntityFilter cohortFilter = filterBuilder.buildForCohort(underlay, List.of(selectionData));
     assertEquals(expectedCohortFilter, cohortFilter);
 
-    // query format: variant_id ("[0-9]+-[0-9]+-[A-Z]+-[A-Z]+")
+    // query format: id ("[0-9]+-[0-9]+-[A-Z]+-[A-Z]+")
     query = "12-34-AB-CD";
     data =
         FilterableGroup.newBuilder()
@@ -155,7 +155,7 @@ void selectAllQueryFilter() {
         new AttributeFilter(
             underlay,
             entity_variant,
-            entity_variant.getAttribute("variant_id"),
+            entity_variant.getAttribute("id"),
             BinaryOperator.EQUALS,
             Literal.forString(query));
     expectedSubFilter =