Add protein start+end and add consequence

oncokb · Sep 3, 2024 · b0219ab · b0219ab
1 parent f43db10
commit b0219ab
Show file tree

Hide file tree

Showing 4 changed files with 48 additions and 16 deletions.
diff --git a/src/main/java/org/mskcc/oncokb/curation/domain/enumeration/CNAConsequence.java b/src/main/java/org/mskcc/oncokb/curation/domain/enumeration/CNAConsequence.java
@@ -1,9 +1,9 @@
 package org.mskcc.oncokb.curation.domain.enumeration;
 
 public enum CNAConsequence {
-    AMPLIFICATION,
-    DELETION,
-    GAIN,
-    LOSS,
-    UNKNOWN,
+    CNA_AMPLIFICATION,
+    CNA_DELETION,
+    CNA_GAIN,
+    CNA_LOSS,
+    CNA_UNKNOWN,
 }
diff --git a/src/main/java/org/mskcc/oncokb/curation/domain/enumeration/SVConsequence.java b/src/main/java/org/mskcc/oncokb/curation/domain/enumeration/SVConsequence.java
@@ -1,11 +1,11 @@
 package org.mskcc.oncokb.curation.domain.enumeration;
 
 public enum SVConsequence {
-    DELETION,
-    TRANSLOCATION,
-    DUPLICATION,
-    INSERTION,
-    INVERSION,
-    FUSION,
-    UNKNOWN,
+    SV_DELETION,
+    SV_TRANSLOCATION,
+    SV_DUPLICATION,
+    SV_INSERTION,
+    SV_INVERSION,
+    SV_FUSION,
+    SV_UNKNOWN,
 }
diff --git a/src/main/java/org/mskcc/oncokb/curation/service/MainService.java b/src/main/java/org/mskcc/oncokb/curation/service/MainService.java
@@ -293,13 +293,26 @@ public AlterationAnnotationStatus annotateAlteration(ReferenceGenome referenceGe
                 List<String> problematicExonAlts = new ArrayList<>();
                 for (String exonAlterationString : Arrays.asList(alteration.getAlteration().split("\\s*\\+\\s*"))) {
                     Integer exonNumber = Integer.parseInt(exonAlterationString.replaceAll("\\D*", ""));
-                    if (exonNumber > 0 && exonNumber < proteinExons.size()) {
+                    if (exonNumber > 0 && exonNumber < proteinExons.size() + 1) {
                         overlap.add(proteinExons.get(exonNumber - 1));
                     } else {
                         problematicExonAlts.add(exonAlterationString);
                     }
                 }
                 if (problematicExonAlts.isEmpty()) {
+                    overlap.sort(Comparator.comparingInt(ProteinExonDTO::getExon));
+                    Boolean isConsecutiveExonRange =
+                        overlap
+                            .stream()
+                            .map(ProteinExonDTO::getExon)
+                            .reduce((prev, curr) -> (curr - prev == 1) ? curr : Integer.MIN_VALUE)
+                            .orElse(Integer.MIN_VALUE) !=
+                        Integer.MIN_VALUE;
+                    if (isConsecutiveExonRange && overlap.size() > 0) {
+                        alteration.setStart(overlap.get(0).getRange().getStart());
+                        alteration.setEnd(overlap.get(overlap.size() - 1).getRange().getEnd());
+                    }
+
                     annotationDTO.setExons(overlap);
                 } else {
                     StringBuilder sb = new StringBuilder();

diff --git a/src/main/java/org/mskcc/oncokb/curation/util/AlterationUtils.java b/src/main/java/org/mskcc/oncokb/curation/util/AlterationUtils.java
@@ -28,7 +28,7 @@ private Alteration parseFusion(String alteration) {
         Alteration alt = new Alteration();
 
         Consequence consequence = new Consequence();
-        consequence.setTerm(SVConsequence.FUSION.name());
+        consequence.setTerm(SVConsequence.SV_FUSION.name());
         alt.setType(AlterationType.STRUCTURAL_VARIANT);
         alt.setConsequence(consequence);
 
@@ -52,7 +52,7 @@ private Alteration parseFusion(String alteration) {
     }
 
     private Alteration parseCopyNumberAlteration(String alteration) {
-        CNAConsequence cnaTerm = CNAConsequence.UNKNOWN;
+        CNAConsequence cnaTerm = CNAConsequence.CNA_UNKNOWN;
 
         Optional<CNAConsequence> cnaConsequenceOptional = getCNAConsequence(alteration);
         if (cnaConsequenceOptional.isPresent()) {
@@ -96,19 +96,38 @@ private Alteration parseGenomicChange(String genomicChange) {
     private Alteration parseExonAlteration(String alteration) {
         Alteration alt = new Alteration();
         Consequence consequence = new Consequence();
-        consequence.setTerm(UNKNOWN.name());
+        consequence.setTerm(SVConsequence.SV_UNKNOWN.name());
         alt.setType(AlterationType.STRUCTURAL_VARIANT);
         alt.setConsequence(consequence);
 
         Pattern pattern = Pattern.compile(EXON_ALT_REGEX);
         Matcher matcher = pattern.matcher(alteration);
         List<String> splitResults = new ArrayList<>();
+        Set<String> consequenceTermSet = new HashSet<>();
 
         while (matcher.find()) {
             String startExonStr = matcher.group(1); // The start exon number
             String endExonStr = matcher.group(3); // The end exon number (if present)
             String consequenceTerm = matcher.group(4); // consequence term
 
+            switch (consequenceTerm.toLowerCase()) {
+                case "insertion":
+                    consequence.setTerm(SVConsequence.SV_INSERTION.name());
+                    break;
+                case "duplication":
+                    consequence.setTerm(SVConsequence.SV_DUPLICATION.name());
+                    break;
+                case "deletion":
+                    consequence.setTerm(SVConsequence.SV_DELETION.name());
+                default:
+                    break;
+            }
+
+            consequenceTermSet.add(consequenceTerm);
+            if (consequenceTermSet.size() > 0) {
+                consequence.setTerm(SVConsequence.SV_UNKNOWN.name());
+            }
+
             int startExon = Integer.parseInt(startExonStr);
             int endExon = (endExonStr != null) ? Integer.parseInt(endExonStr) : startExon;