Merge Alteration Counts that have conflicting HugoSymbols for Study V…

src/main/java/org/cbioportal/service/impl/AlterationCountServiceImpl.java

@@ -255,18 +255,18 @@ public Pair<List<CopyNumberCountByGene>, Long> getPatientCnaGeneCounts(List<Mole
     @Override
     public List<AlterationCountByGene> getMutatedGenes(StudyViewFilterContext studyViewFilterContext) {
         var alterationCountByGenes = studyViewRepository.getMutatedGenes(studyViewFilterContext);
-        return populateAlterationCounts(alterationCountByGenes, studyViewFilterContext, AlterationType.MUTATION_EXTENDED);
+        return populateAlterationCounts(combineAlterationCountsWithConflictingHugoSymbols(alterationCountByGenes), studyViewFilterContext, AlterationType.MUTATION_EXTENDED);
     }
 
     public List<CopyNumberCountByGene> getCnaGenes(StudyViewFilterContext studyViewFilterContext) {
         var copyNumberCountByGenes = studyViewRepository.getCnaGenes(studyViewFilterContext);
-        return populateAlterationCounts(copyNumberCountByGenes, studyViewFilterContext, AlterationType.COPY_NUMBER_ALTERATION);
+        return populateAlterationCounts(combineCopyNumberCountsWithConflictingHugoSymbols(copyNumberCountByGenes), studyViewFilterContext, AlterationType.COPY_NUMBER_ALTERATION);
     }
 
     @Override
     public List<AlterationCountByGene> getStructuralVariantGenes(StudyViewFilterContext studyViewFilterContext) {
         var alterationCountByGenes = studyViewRepository.getStructuralVariantGenes(studyViewFilterContext);
-        return populateAlterationCounts(alterationCountByGenes, studyViewFilterContext, AlterationType.STRUCTURAL_VARIANT);
+        return populateAlterationCounts(combineAlterationCountsWithConflictingHugoSymbols(alterationCountByGenes), studyViewFilterContext, AlterationType.STRUCTURAL_VARIANT);
     }
 
     private < T extends AlterationCountByGene> List<T> populateAlterationCounts(@NonNull List<T> alterationCounts,
@@ -294,6 +294,55 @@ private < T extends AlterationCountByGene> List<T> populateAlterationCounts(@Non
         return alterationCounts;
     }
 
+    /**
+     * Combines alteration counts by Hugo gene symbols. If multiple entries exist for the same 
+     * gene symbol, their number of altered cases and total counts are summed up. Returns a 
+     * list of unique AlterationCountByGene objects where each gene symbol is represented only once.
+     * 
+     * This appears in the Data where Genes have similar Hugo Gene Symbols but different Entrez Ids
+     *
+     * @param alterationCounts List of AlterationCountByGene objects, potentially with duplicate gene symbols
+     * @return List of AlterationCountByGene objects with unique gene symbols and combined counts
+     */
+    private List<AlterationCountByGene> combineAlterationCountsWithConflictingHugoSymbols(@NonNull List<AlterationCountByGene> alterationCounts) {
+        Map<String, AlterationCountByGene> alterationCountByGeneMap = new HashMap<>();
+        for (var alterationCount : alterationCounts) {
+            if (alterationCountByGeneMap.containsKey(alterationCount.getHugoGeneSymbol())){
+                AlterationCountByGene toUpdate = alterationCountByGeneMap.get(alterationCount.getHugoGeneSymbol());
+                toUpdate.setNumberOfAlteredCases(toUpdate.getNumberOfAlteredCases() + alterationCount.getNumberOfAlteredCases());
+                toUpdate.setTotalCount(toUpdate.getTotalCount() + alterationCount.getTotalCount());
+            } else {
+                alterationCountByGeneMap.put(alterationCount.getHugoGeneSymbol(), alterationCount);
+            }
+        }
+        return alterationCountByGeneMap.values().stream().toList(); 
+    }
+
+    /**
+     * Combines alteration counts by Hugo gene symbols. If multiple entries exist for the same 
+     * gene symbol, their number of altered cases and total counts are summed up. Returns a 
+     * list of unique AlterationCountByGene objects where each gene symbol is represented only once.
+     *
+     * This appears in the Data where Genes have similar Hugo Gene Symbols but different Entrez Ids.
+     * This is a special case to handle Copy Number Mutations where the Alteration type should be a part of the key
+     *
+     * @param alterationCounts List of CopyNumberCountByGene objects, potentially with duplicate gene symbols
+     * @return List of AlterationCountByGene objects with unique gene symbols and combined counts
+     */
+    private List<CopyNumberCountByGene> combineCopyNumberCountsWithConflictingHugoSymbols(@NonNull List<CopyNumberCountByGene> alterationCounts) {
+        Map<Pair<String, Integer>, CopyNumberCountByGene> alterationCountByGeneMap = new HashMap<>();
+        for (var alterationCount : alterationCounts) {
+            var copyNumberKey = Pair.create(alterationCount.getHugoGeneSymbol(), alterationCount.getAlteration());
+            if (alterationCountByGeneMap.containsKey(copyNumberKey)) {
+                AlterationCountByGene toUpdate = alterationCountByGeneMap.get(copyNumberKey);
+                toUpdate.setNumberOfAlteredCases(toUpdate.getNumberOfAlteredCases() + alterationCount.getNumberOfAlteredCases());
+                toUpdate.setTotalCount(toUpdate.getTotalCount() + alterationCount.getTotalCount());
+            } else {
+                alterationCountByGeneMap.put(copyNumberKey, alterationCount);
+            }
+        }
+        return alterationCountByGeneMap.values().stream().toList();
+    }
 
     private boolean hasGenePanelData(@NonNull Set<String> matchingGenePanelIds) {
         return matchingGenePanelIds.contains(WHOLE_EXOME_SEQUENCING)