X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblProtein.java;h=0280f1613a16c6f17ed32b44ac345364ebd56685;hb=a4f2a7f356b8edab17a9a5bb6f2e71a1419792a9;hp=8f23984d9f12759498d4ae93381cb35cdcc1cc31;hpb=46b2bc114452c0e30463214b3e82eb0a5c98d23f;p=jalview.git

diff --git a/src/jalview/ext/ensembl/EnsemblProtein.java b/src/jalview/ext/ensembl/EnsemblProtein.java
index 8f23984..0280f16 100644
--- a/src/jalview/ext/ensembl/EnsemblProtein.java
+++ b/src/jalview/ext/ensembl/EnsemblProtein.java
@@ -1,27 +1,68 @@
+/*
+ * 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.AlignmentI;
 import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
 
-import java.util.Arrays;
+import java.util.ArrayList;
 import java.util.List;
 
 import com.stevesoft.pat.Regex;
 
+/**
+ * A client to fetch protein translated sequence for an Ensembl identifier
+ * 
+ * @author gmcarstairs
+ *
+ */
 public class EnsemblProtein extends EnsemblSeqProxy
 {
-  // TODO modify to accept other species e.g. ENSMUSPnnn
+  /*
+   * accepts ENSP with 11 digits
+   * or ENSMUSP or similar for other species
+   * or CCDSnnnnn.nn with at least 3 digits
+   */
   private static final Regex ACCESSION_REGEX = new Regex(
-          "((ENSP|CCDS)[0-9.]{3,})");
-
-  private static final List<String> CROSSREFS = Arrays.asList(new String[] {
-      "PDB", "Uniprot/SPTREMBL", "Uniprot/SWISSPROT" });
+          "(ENS([A-Z]{3}|)P[0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
 
+  /**
+   * Default constructor (to use rest.ensembl.org)
+   */
   public EnsemblProtein()
   {
     super();
   }
 
+  /**
+   * Constructor given the target domain to fetch data from
+   * 
+   * @param d
+   */
+  public EnsemblProtein(String d)
+  {
+    super(d);
+  }
+
   @Override
   public String getDbName()
   {
@@ -69,22 +110,40 @@ public class EnsemblProtein extends EnsemblSeqProxy
   }
 
   @Override
-  protected boolean identifiesSequence(SequenceFeature sf, String accId)
+  protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
+          String accId)
   {
-    // not applicable - protein sequence is not a 'subset' of genomic sequence
-    return false;
+    return new ArrayList<>();
   }
 
   @Override
-  protected List<String> getCrossReferenceDatabases()
+  public Regex getAccessionValidator()
   {
-    return CROSSREFS;
+    return ACCESSION_REGEX;
   }
 
+  /**
+   * Returns an accession id for a query, including conversion of ENST* to
+   * ENSP*. This supports querying for the protein sequence for a transcript
+   * (ENST identifier) and returning the ENSP identifier.
+   */
   @Override
-  public Regex getAccessionValidator()
+  public String getAccessionIdFromQuery(String query)
   {
-    return ACCESSION_REGEX;
+    String accId = super.getAccessionIdFromQuery(query);
+
+    /*
+     * ensure last character before (11) digits is P
+     * ENST00000288602 -> ENSP00000288602
+     * ENSMUST00000288602 -> ENSMUSP00000288602
+     */
+    if (accId != null && accId.length() >= 12)
+    {
+      char[] chars = accId.toCharArray();
+      chars[chars.length - 12] = 'P';
+      accId = new String(chars);
+    }
+    return accId;
   }
 
 }