JAL-3076 refactor for more efficient scan of 'gene' features

[jalview.git] / src / jalview / ext / ensembl / EnsemblGenome.java

diff --git a/src/jalview/ext/ensembl/EnsemblGenome.java b/src/jalview/ext/ensembl/EnsemblGenome.java
index 8238da0..6684e20 100644 (file)
--- a/src/jalview/ext/ensembl/EnsemblGenome.java
+++ b/src/jalview/ext/ensembl/EnsemblGenome.java
@@ -1,7 +1,40 @@
+/*
+ * 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.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+import jalview.io.gff.SequenceOntologyI;
 
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * A client to fetch genomic sequence from Ensembl
+ * 
+ * TODO: not currently used - delete?
+ * 
+ * @author gmcarstairs
+ *
+ */
 public class EnsemblGenome extends EnsemblSeqProxy
 {
   /*
@@ -10,17 +43,30 @@ public class EnsemblGenome extends EnsemblSeqProxy
    */
   private static final EnsemblFeatureType[] FEATURES_TO_FETCH = {
       EnsemblFeatureType.transcript, EnsemblFeatureType.exon,
-      EnsemblFeatureType.cds /*, EnsemblFeatureType.variation */};
+      EnsemblFeatureType.cds, EnsemblFeatureType.variation };
 
+  /**
+   * Default constructor (to use rest.ensembl.org)
+   */
   public EnsemblGenome()
   {
     super();
   }
 
+  /**
+   * Constructor given the target domain to fetch data from
+   * 
+   * @param d
+   */
+  public EnsemblGenome(String d)
+  {
+    super(d);
+  }
+
   @Override
   public String getDbName()
   {
-    return "ENSEMBL (Genome)";
+    return "ENSEMBL (Genomic)";
   }
 
   @Override
@@ -37,9 +83,10 @@ public class EnsemblGenome extends EnsemblSeqProxy
 
   /**
    * Answers true unless the feature type is 'transcript' (or a sub-type of
-   * transcript in the Sequence Ontology). Transcript features are only
-   * retrieved in order to identify the transcript sequence range, and are
-   * redundant information on the transcript sequence itself.
+   * transcript in the Sequence Ontology), or has a parent other than the given
+   * accession id. Transcript features are only retrieved in order to identify
+   * the transcript sequence range, and are redundant information on the
+   * transcript sequence itself.
    */
   @Override
   protected boolean retainFeature(SequenceFeature sf, String accessionId)
@@ -52,22 +99,32 @@ public class EnsemblGenome extends EnsemblSeqProxy
   }
 
   /**
-   * Answers true if the sequence feature type is 'transcript' (or a subtype of
-   * transcript in the Sequence Ontology), and the ID of the feature is the
-   * transcript we are retrieving
+   * Answers a list of sequence features (if any) whose type is 'transcript' (or
+   * a subtype of transcript in the Sequence Ontology), and whose ID is the
+   * accession we are retrieving.
+   * <p>
+   * Note we also include features of type "NMD_transcript_variant", although
+   * not strictly 'transcript' in the SO, as they used in Ensembl as if they
+   * were.
    */
   @Override
-  protected boolean identifiesSequence(SequenceFeature sf, String accId)
+  protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
+          String accId)
   {
-    if (isTranscript(sf.getType()))
+    List<SequenceFeature> result = new ArrayList<>();
+    List<SequenceFeature> sfs = seq.getFeatures().getFeaturesByOntology(
+            SequenceOntologyI.TRANSCRIPT,
+            SequenceOntologyI.NMD_TRANSCRIPT_VARIANT);
+    for (SequenceFeature sf : sfs)
     {
-      String id = (String) sf.getValue(ID);
+      // NB features as gff use 'ID'; rest services return as 'id'
+      String id = (String) sf.getValue("ID");
       if (("transcript:" + accId).equals(id))
       {
-        return true;
+        result.add(sf);
       }
     }
-    return false;
+    return result;
   }
 
 }