BioSem release 1.1.9.

Release #30.
JULIELab · Nov 24, 2022 · f6a81f4 · f6a81f4
1 parent e756e07
commit f6a81f4
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 2 deletions.
diff --git a/biosem-event-extractor/pom.xml b/biosem-event-extractor/pom.xml
@@ -172,5 +172,5 @@
         </license>
     </licenses>
     <url>http://www.ncbi.nlm.nih.gov/pubmed/22859502</url>
-    <version>1.1.8</version>
+    <version>1.1.9</version>
 </project>
diff --git a/biosem-event-extractor/src/relations/EventExtraction.java b/biosem-event-extractor/src/relations/EventExtraction.java
@@ -2156,6 +2156,11 @@ public void initSentence(String id) {
 		out = analyzer.analyze(id);
 		trg_ID = analyzer.proList.size(); // trg ID follows number of protein +1
 											// ;
+		// In case of predicted proteins that have been merged with gold genes, the 1:1 relation between the number
+		// of proteins and their IDs gets lost. Obtain the highest protein ID to avoid ID clashes.
+		OptionalInt maxGeneIdNumber = analyzer.proList.stream().map(prot -> prot.tid).mapToInt(tid -> Integer.parseInt(tid.substring(1))).max();
+		if (maxGeneIdNumber.isPresent())
+			trg_ID = maxGeneIdNumber.getAsInt() + 1;
 		evt_ID = 0;// reset new Event list
 	}
 

diff --git a/biosem-event-extractor/src/utils/SentenceSplitter.java b/biosem-event-extractor/src/utils/SentenceSplitter.java
@@ -35,7 +35,7 @@ public static List<BioSemSentence> spliter(String str) {
 		Chunking chunks = SENTENCE_CHUNKER.chunk(cc, 0, cc.length);
 		Set<Chunk> ls = chunks.chunkSet();
 		if (ls.size() < 1) {
-			System.out.println("No sentence found.");
+			System.out.println("No sentence found in input '" + str + "'.");
 			return list;
 		}
 		String sub_sen = chunks.charSequence().toString();