Fix alteration filter SQL (#11853)

onursumer · web-flow · commit c7cfc7420cdc · 2026-01-05T15:12:11.000-05:00
* fix driver filter SQL

* fix custom annotation filters for getStructuralVariantGenes sql

* allow filtering structural variants by mutation status filter

* apply cna filters when tier options selected

* update derived table version to 1.0.6
diff --git a/pom.xml b/pom.xml
@@ -31,7 +31,7 @@
     <frontend.version>v6.4.3</frontend.version>
     <!-- THIS SHOULD BE KEPT IN SYNC TO VERSION IN CGDS.SQL -->
     <db.version>2.14.5</db.version>
-    <derived_table.version>1.0.3</derived_table.version>
+    <derived_table.version>1.0.6</derived_table.version>
 
     <!-- Version properties for dependencies that should have same version. -->
     <!-- The rest can be set in the dependencyManagement section -->
diff --git a/src/main/java/org/cbioportal/legacy/persistence/helper/AlterationFilterHelper.java b/src/main/java/org/cbioportal/legacy/persistence/helper/AlterationFilterHelper.java
@@ -150,6 +150,7 @@ public boolean shouldApplyMutationAlterationFilter() {
 
   public boolean shouldApplyCnaAlterationFilter() {
     return isSomeDriverAnnotationsSelected()
+        || isSomeTierOptionsSelected()
         || mappedCnaTypes.hasNone()
         || (!mappedCnaTypes.hasNone() && !mappedCnaTypes.hasAll());
   }
diff --git a/src/main/resources/db-scripts/clickhouse/clickhouse.sql b/src/main/resources/db-scripts/clickhouse/clickhouse.sql
@@ -1,4 +1,4 @@
--- version 1.0.5 of derived table schema and data definition
+-- version 1.0.6 of derived table schema and data definition
 -- when making updates:
 --     increment the version number here
 --     update pom.xml with the new version number
@@ -167,7 +167,9 @@ CREATE TABLE IF NOT EXISTS genomic_event_derived
     mutation_type             LowCardinality(String),
     mutation_status           LowCardinality(String),
     driver_filter             LowCardinality(String),
+    driver_filter_annotation  String,
     driver_tiers_filter       LowCardinality(String),
+    driver_tiers_filter_annotation String,
     cna_alteration            Nullable(Int8),
     cna_cytoband              String,
     sv_event_info             String,
@@ -188,8 +190,10 @@ SELECT concat(cs.cancer_study_identifier, '_', sample.stable_id) AS sample_uniqu
        me.protein_change                                         AS mutation_variant,
        me.mutation_type                                          AS mutation_type,
        mutation.mutation_status                                  AS mutation_status,
-       'NA'                                                      AS driver_filter,
-       'NA'                                                      AS drivet_tiers_filter,
+       ada.driver_filter                                         AS driver_filter,
+       ada.driver_filter_annotation                              AS driver_filter_annotation,
+       ada.driver_tiers_filter                                   AS driver_tiers_filter,
+       ada.driver_tiers_filter_annotation                        AS driver_tiers_filter_annotation,
        NULL                                                      AS cna_alteration,
        ''                                                        AS cna_cytoband,
        ''                                                        AS sv_event_info,
@@ -207,7 +211,8 @@ FROM mutation
          INNER JOIN cancer_study cs ON g.cancer_study_id = cs.cancer_study_id
          INNER JOIN sample ON mutation.sample_id = sample.internal_id
          INNER JOIN patient on sample.patient_id = patient.internal_id
-         LEFT JOIN gene ON mutation.entrez_gene_id = gene.entrez_gene_id;
+         LEFT JOIN gene ON mutation.entrez_gene_id = gene.entrez_gene_id
+         LEFT JOIN alteration_driver_annotation ada ON (mutation.genetic_profile_id = alteration_driver_annotation.genetic_profile_id) AND (mutation.sample_id = alteration_driver_annotation.sample_id) AND (mutation.mutation_event_id = alteration_driver_annotation.alteration_event_id);
 
 INSERT INTO genomic_event_derived
 -- Insert CNA Genes
@@ -221,8 +226,10 @@ SELECT concat(cs.cancer_study_identifier, '_', sample.stable_id) AS sample_uniqu
        'NA'                                                      AS mutation_variant,
        'NA'                                                      AS mutation_type,
        'NA'                                                      AS mutation_status,
-       'NA'                                                      AS driver_filter,
-       'NA'                                                      AS drivet_tiers_filter,
+       ada.driver_filter                                         AS driver_filter,
+       ada.driver_filter_annotation                              AS driver_filter_annotation,
+       ada.driver_tiers_filter                                   AS driver_tiers_filter,
+       ada.driver_tiers_filter_annotation                        AS driver_tiers_filter_annotation,
        ce.alteration                                             AS cna_alteration,
        rgg.cytoband                                              AS cna_cytoband,
        ''                                                        AS sv_event_info,
@@ -240,7 +247,9 @@ FROM cna_event ce
          INNER JOIN sample ON sce.sample_id = sample.internal_id
          INNER JOIN patient on sample.patient_id = patient.internal_id
          INNER JOIN gene ON ce.entrez_gene_id = gene.entrez_gene_id
-         INNER JOIN reference_genome_gene rgg ON rgg.entrez_gene_id = ce.entrez_gene_id AND rgg.reference_genome_id = cs.reference_genome_id;
+         INNER JOIN reference_genome_gene rgg ON rgg.entrez_gene_id = ce.entrez_gene_id AND rgg.reference_genome_id = cs.reference_genome_id
+         LEFT JOIN alteration_driver_annotation ada ON (sce.genetic_profile_id = ada.genetic_profile_id) AND (sce.sample_id = ada.sample_id) AND (sce.cna_event_id = ada.alteration_event_id);
+
 
 INSERT INTO genomic_event_derived
 -- Insert Structural Variants Site1
@@ -253,9 +262,11 @@ SELECT concat(cs.cancer_study_identifier, '_', s.stable_id) AS sample_unique_id,
        'structural_variant'                                 AS variant_type,
        'NA'                                                 AS mutation_variant,
        'NA'                                                 AS mutation_type,
-       'NA'                                                 AS mutation_status,
-       'NA'                                                 AS driver_filter,
-       'NA'                                                 AS drivet_tiers_filter,
+       sv.sv_status                                         AS mutation_status,
+       ada.driver_filter                                    AS driver_filter,
+       ada.driver_filter_annotation                         AS driver_filter_annotation,
+       ada.driver_tiers_filter                              AS driver_tiers_filter,
+       ada.driver_tiers_filter_annotation                   AS driver_tiers_filter_annotation,
        NULL                                                 AS cna_alteration,
        ''                                                   AS cna_cytoband,
        event_info                                           AS sv_event_info,
@@ -271,7 +282,10 @@ FROM structural_variant sv
          INNER JOIN cancer_study cs ON gp.cancer_study_id = cs.cancer_study_id
          INNER JOIN gene ON sv.site1_entrez_gene_id = gene.entrez_gene_id
          INNER JOIN sample_profile ON s.internal_id = sample_profile.sample_id AND sample_profile.genetic_profile_id = sv.genetic_profile_id
-         LEFT JOIN gene_panel ON sample_profile.panel_id = gene_panel.internal_id;
+         LEFT JOIN gene_panel ON sample_profile.panel_id = gene_panel.internal_id
+         LEFT JOIN alteration_driver_annotation ada ON (sv.genetic_profile_id = ada.genetic_profile_id) AND (sv.sample_id = ada.sample_id) AND (sv.internal_id = ada.alteration_event_id);
+
+
 
 INSERT INTO genomic_event_derived
 -- Insert Structural Variants Site2
@@ -284,9 +298,11 @@ SELECT concat(cs.cancer_study_identifier, '_', s.stable_id) AS sample_unique_id,
        'structural_variant'                                 AS variant_type,
        'NA'                                                 AS mutation_variant,
        'NA'                                                 AS mutation_type,
-       'NA'                                                 AS mutation_status,
-       'NA'                                                 AS driver_filter,
-       'NA'                                                 AS drivet_tiers_filter,
+       sv.sv_status                                         AS mutation_status,
+       ada.driver_filter                                    AS driver_filter,
+       ada.driver_filter_annotation                         AS driver_filter_annotation,
+       ada.driver_tiers_filter                              AS driver_tiers_filter,
+       ada.driver_tiers_filter_annotation                   AS driver_tiers_filter_annotation,
        NULL                                                 AS cna_alteration,
        ''                                                   AS cna_cytoband,
        event_info                                           AS sv_event_info,
@@ -303,9 +319,10 @@ FROM structural_variant sv
          INNER JOIN gene ON sv.site2_entrez_gene_id = gene.entrez_gene_id
          INNER JOIN sample_profile ON s.internal_id = sample_profile.sample_id AND sample_profile.genetic_profile_id = sv.genetic_profile_id
          LEFT JOIN gene_panel ON sample_profile.panel_id = gene_panel.internal_id
+         LEFT JOIN alteration_driver_annotation ada ON (sv.genetic_profile_id = ada.genetic_profile_id) AND (sv.sample_id = ada.sample_id) AND (sv.internal_id = ada.alteration_event_id)
 WHERE
         sv.site2_entrez_gene_id != sv.site1_entrez_gene_id
-   OR sv.site1_entrez_gene_id IS NULL;
+            OR sv.site1_entrez_gene_id IS NULL;
 
 CREATE TABLE IF NOT EXISTS clinical_data_derived
 (
diff --git a/src/main/resources/mappers/clickhouse/alteration/ClickhouseAlterationMapper.xml b/src/main/resources/mappers/clickhouse/alteration/ClickhouseAlterationMapper.xml
@@ -73,6 +73,8 @@
             <include
                 refid="org.cbioportal.infrastructure.repository.clickhouse.studyview.ClickhouseStudyViewFilterMapper.applyStudyViewFilterUsingSampleId"
             />
+            <include refid="whereCustomAnnotations" />
+            <include refid="whereMutationStatus" />
         </where>
         GROUP BY entrez_gene_id, hugo_gene_symbol
     </select>

Original file line number	Diff line number	Diff line change
`@@ -150,6 +150,7 @@ public boolean shouldApplyMutationAlterationFilter() {`
`150`	`150`
`151`	`151`	`public boolean shouldApplyCnaAlterationFilter() {`
`152`	`152`	`return isSomeDriverAnnotationsSelected()`
	`153`	`+ \|\| isSomeTierOptionsSelected()`
`153`	`154`	`\|\| mappedCnaTypes.hasNone()`
`154`	`155`	`\|\| (!mappedCnaTypes.hasNone() && !mappedCnaTypes.hasAll());`
`155`	`156`	`}`