Now biojava can parse mmcif files with carbohydrates, though it ignores the carbohydrate chains

josemduarte · josemduarte · commit 41c36aef2fa7 · 2020-04-12T22:27:28.000-07:00
diff --git a/biojava-structure/src/main/java/org/biojava/nbio/structure/EntityType.java b/biojava-structure/src/main/java/org/biojava/nbio/structure/EntityType.java
@@ -44,6 +44,18 @@ public enum EntityType {
 	 */
 	POLYMER("polymer"),
 
+	/**
+	 * The 'branched' type use mainly to represent carbohydrates.
+	 * The type was introduced in these versions of the mmcif dictionary:
+	 * 5.101	2012-08-22
+	 * 5.291	2017-09-10
+	 * 5.304	2018-08-01
+	 * The type will only be used for PDB-deposited files from July 2020, as part of
+	 * the carbohydrate remediation project.
+	 * @since 5.4.0
+	 */
+	BRANCHED("branched"),
+
 	/**
 	 * Non-polymeric entities: ligands, metal ions, buffer molecules, etc
 	 */
diff --git a/biojava-structure/src/test/java/org/biojava/nbio/structure/io/TestNonDepositedFiles.java b/biojava-structure/src/test/java/org/biojava/nbio/structure/io/TestNonDepositedFiles.java
@@ -27,6 +27,7 @@
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.InputStreamReader;
+import java.net.URL;
 import java.util.List;
 import java.util.zip.GZIPInputStream;
 
@@ -443,4 +444,28 @@ private static int[] countEntityTypes(List<EntityInfo> entities) {
 		return counts;
 
 	}
+
+	@Test
+	public void testCarbohydrates() throws IOException {
+		// Example carbohydrate remediation file to be released in July 2020
+		URL url = new URL("https://raw.githubusercontent.com/pdbxmmcifwg/carbohydrate-extension/master/examples/models/1B5F-carb.cif");
+		InputStream inStream = url.openStream();
+
+		MMcifParser parser = new SimpleMMcifParser();
+
+		SimpleMMcifConsumer consumer = new SimpleMMcifConsumer();
+		parser.addMMcifConsumer(consumer);
+		parser.parse(new BufferedReader(new InputStreamReader(inStream)));
+
+		Structure structure = consumer.getStructure();
+
+		assertEquals(7, structure.getEntityInfos().size());
+
+		assertEquals(2, structure.getEntityById(1).getChains().size());
+		assertEquals(2, structure.getEntityById(2).getChains().size());
+
+		assertEquals(0, structure.getNonPolyChains().size());
+		assertEquals(4, structure.getPolyChains().size());
+
+	}
 }
