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

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

diff --git a/src/jalview/ext/ensembl/EnsemblCdna.java b/src/jalview/ext/ensembl/EnsemblCdna.java
index d4d1c08..7384327 100644 (file)
--- a/src/jalview/ext/ensembl/EnsemblCdna.java
+++ b/src/jalview/ext/ensembl/EnsemblCdna.java
@@ -1,18 +1,53 @@
+/*
+ * 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.SequenceOntologyFactory;
 import jalview.io.gff.SequenceOntologyI;
 
+import java.util.ArrayList;
 import java.util.List;
 
 import com.stevesoft.pat.Regex;
 
+/**
+ * A client to fetch CDNA sequence from Ensembl (i.e. that part of the genomic
+ * sequence that is transcribed to RNA, but not necessarily translated to
+ * protein)
+ * 
+ * @author gmcarstairs
+ *
+ */
 public class EnsemblCdna extends EnsemblSeqProxy
 {
-  // TODO modify to accept other species e.g. ENSMUSPnnn
-  private static final Regex ACCESSION_REGEX = new Regex("((ENST|ENSG|CCDS)[0-9.]{3,})");
-  
+  /*
+   * accepts ENST or ENSTG with 11 digits
+   * or ENSMUST or similar for other species
+   * or CCDSnnnnn.nn with at least 3 digits
+   */
+  private static final Regex ACCESSION_REGEX = new Regex(
+          "(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
+
   /*
    * fetch exon features on genomic sequence (to identify the cdna regions)
    * and cds and variation features (to retain)
@@ -21,11 +56,24 @@ public class EnsemblCdna extends EnsemblSeqProxy
       EnsemblFeatureType.exon, EnsemblFeatureType.cds,
       EnsemblFeatureType.variation };
 
+  /**
+   * Default constructor (to use rest.ensembl.org)
+   */
   public EnsemblCdna()
   {
     super();
   }
 
+  /**
+   * Constructor given the target domain to fetch data from
+   * 
+   * @param d
+   */
+  public EnsemblCdna(String d)
+  {
+    super(d);
+  }
+
   @Override
   public String getDbName()
   {
@@ -65,31 +113,37 @@ public class EnsemblCdna extends EnsemblSeqProxy
   }
 
   /**
-   * Answers true if the sequence feature type is 'exon' (or a subtype of exon
-   * in the Sequence Ontology), and the Parent of the feature is the transcript
-   * we are retrieving
+   * Answers a list of sequence features (if any) whose type is 'exon' (or a
+   * subtype of exon in the Sequence Ontology), and whose Parent is the
+   * transcript we are retrieving
    */
   @Override
-  protected boolean identifiesSequence(SequenceFeature sf, String accId)
+  protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
+          String accId)
   {
-    if (SequenceOntologyFactory.getInstance().isA(sf.getType(),
-            SequenceOntologyI.EXON))
+    List<SequenceFeature> result = new ArrayList<>();
+    List<SequenceFeature> sfs = seq.getFeatures()
+            .getFeaturesByOntology(SequenceOntologyI.EXON);
+    for (SequenceFeature sf : sfs)
     {
       String parentFeature = (String) sf.getValue(PARENT);
       if (("transcript:" + accId).equals(parentFeature))
       {
-        return true;
+        result.add(sf);
       }
     }
-    return false;
+
+    return result;
   }
 
+  /**
+   * Parameter object_type=Transcaript added to ensure cdna and not peptide is
+   * returned (JAL-2529)
+   */
   @Override
-  protected List<String> getCrossReferenceDatabases()
+  protected String getObjectType()
   {
-    return super.getCrossReferenceDatabases();
-    // 30/01/16 also found Vega_transcript, OTTT, ENS_LRG_transcript, UCSC,
-    // HGNC_trans_name, RefSeq_mRNA, RefSeq_mRNA_predicted
+    return OBJECT_TYPE_TRANSCRIPT;
   }
 
 }