JAL-2525 put in missing "transcript" feature type
[jalview.git] / src / jalview / ext / ensembl / EnsemblGene.java
index 50e1032..2d4d61a 100644 (file)
@@ -1,3 +1,23 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ * 
+ * This file is part of Jalview.
+ * 
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License 
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *  
+ * Jalview is distributed in the hope that it will be useful, but 
+ * WITHOUT ANY WARRANTY; without even the implied warranty 
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR 
+ * PURPOSE.  See the GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
 package jalview.ext.ensembl;
 
 import jalview.api.FeatureColourI;
@@ -6,6 +26,7 @@ import jalview.datamodel.AlignmentI;
 import jalview.datamodel.Sequence;
 import jalview.datamodel.SequenceFeature;
 import jalview.datamodel.SequenceI;
+import jalview.datamodel.features.SequenceFeatures;
 import jalview.io.gff.SequenceOntologyFactory;
 import jalview.io.gff.SequenceOntologyI;
 import jalview.schemes.FeatureColour;
@@ -118,7 +139,10 @@ public class EnsemblGene extends EnsemblSeqProxy
        * fetch the gene sequence(s) with features and xrefs
        */
       AlignmentI geneAlignment = super.getSequenceRecords(geneId);
-
+      if (geneAlignment == null)
+      {
+        continue;
+      }
       if (geneAlignment.getHeight() == 1)
       {
         getTranscripts(geneAlignment, geneId);
@@ -244,23 +268,20 @@ public class EnsemblGene extends EnsemblSeqProxy
    */
   protected void clearGeneFeatures(SequenceI gene)
   {
-    SequenceFeature[] sfs = gene.getSequenceFeatures();
-    if (sfs != null)
+    /*
+     * Note we include NMD_transcript_variant here because it behaves like 
+     * 'transcript' in Ensembl, although strictly speaking it is not 
+     * (it is a sub-type of sequence_variant)    
+     */
+    String[] soTerms = new String[] {
+        SequenceOntologyI.NMD_TRANSCRIPT_VARIANT,
+        SequenceOntologyI.TRANSCRIPT, SequenceOntologyI.EXON,
+        SequenceOntologyI.CDS };
+    List<SequenceFeature> sfs = gene.getFeatures().getFeaturesByOntology(
+            soTerms);
+    for (SequenceFeature sf : sfs)
     {
-      SequenceOntologyI so = SequenceOntologyFactory.getInstance();
-      List<SequenceFeature> filtered = new ArrayList<SequenceFeature>();
-      for (SequenceFeature sf : sfs)
-      {
-        String type = sf.getType();
-        if (!isTranscript(type) && !so.isA(type, SequenceOntologyI.EXON)
-                && !so.isA(type, SequenceOntologyI.CDS))
-        {
-          filtered.add(sf);
-        }
-      }
-      gene.setSequenceFeatures(filtered
-              .toArray(new SequenceFeature[filtered
-              .size()]));
+      gene.deleteFeature(sf);
     }
   }
 
@@ -310,6 +331,7 @@ public class EnsemblGene extends EnsemblSeqProxy
     {
       splices = findFeatures(gene, SequenceOntologyI.CDS, parentId);
     }
+    SequenceFeatures.sortFeatures(splices, true);
 
     int transcriptLength = 0;
     final char[] geneChars = gene.getSequence();
@@ -359,7 +381,7 @@ public class EnsemblGene extends EnsemblSeqProxy
     mapTo.add(new int[] { 1, transcriptLength });
     MapList mapping = new MapList(mappedFrom, mapTo, 1, 1);
     EnsemblCdna cdna = new EnsemblCdna(getDomain());
-    cdna.transferFeatures(gene.getSequenceFeatures(),
+    cdna.transferFeatures(gene.getFeatures().getPositionalFeatures(),
             transcript.getDatasetSequence(), mapping, parentId);
 
     /*
@@ -400,19 +422,18 @@ public class EnsemblGene extends EnsemblSeqProxy
     List<SequenceFeature> transcriptFeatures = new ArrayList<SequenceFeature>();
 
     String parentIdentifier = GENE_PREFIX + accId;
-    SequenceFeature[] sfs = geneSequence.getSequenceFeatures();
+    // todo optimise here by transcript type!
+    List<SequenceFeature> sfs = geneSequence.getFeatures()
+            .getPositionalFeatures();
 
-    if (sfs != null)
+    for (SequenceFeature sf : sfs)
     {
-      for (SequenceFeature sf : sfs)
+      if (isTranscript(sf.getType()))
       {
-        if (isTranscript(sf.getType()))
+        String parent = (String) sf.getValue(PARENT);
+        if (parentIdentifier.equals(parent))
         {
-          String parent = (String) sf.getValue(PARENT);
-          if (parentIdentifier.equals(parent))
-          {
-            transcriptFeatures.add(sf);
-          }
+          transcriptFeatures.add(sf);
         }
       }
     }
@@ -526,6 +547,7 @@ public class EnsemblGene extends EnsemblSeqProxy
     return new FeatureSettingsAdapter()
     {
       SequenceOntologyI so = SequenceOntologyFactory.getInstance();
+
       @Override
       public boolean isFeatureDisplayed(String type)
       {