X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblProtein.java;h=97796a5d418a01d6a457cd99a8fc909838e25b14;hb=6fb341da6a316869ba5fc87c146c30d1279f06fa;hp=4cc43ab27adcefb0c6ed5d5e631c7e9483594346;hpb=409fd993c6e32e999b24082aae107a043a590f8f;p=jalview.git

diff --git a/src/jalview/ext/ensembl/EnsemblProtein.java b/src/jalview/ext/ensembl/EnsemblProtein.java
index 4cc43ab..97796a5 100644
--- a/src/jalview/ext/ensembl/EnsemblProtein.java
+++ b/src/jalview/ext/ensembl/EnsemblProtein.java
@@ -1,15 +1,50 @@
 package jalview.ext.ensembl;
 
-import jalview.ext.ensembl.SeqFetcher.EnsemblSeqType;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.SequenceFeature;
 
+import java.util.Arrays;
+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
 {
+  /*
+   * 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(
+          "(ENS([A-Z]{3}|)P[0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
 
+  private static final List<String> CROSSREFS = Arrays.asList(new String[] {
+      "PDB", "Uniprot/SPTREMBL", "Uniprot/SWISSPROT" });
+
+  /**
+   * 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()
   {
@@ -22,6 +57,9 @@ public class EnsemblProtein extends EnsemblSeqProxy
     return EnsemblSeqType.PROTEIN;
   }
 
+  /**
+   * Returns false, as this fetcher does not retrieve DNA sequences.
+   */
   @Override
   public boolean isDnaCoding()
   {
@@ -37,4 +75,63 @@ public class EnsemblProtein extends EnsemblSeqProxy
     return "ENSP00000288602";
   }
 
+  /**
+   * Overrides base class method to do nothing - genomic features are not
+   * applicable to the protein product sequence
+   */
+  @Override
+  protected void addFeaturesAndProduct(String accId, AlignmentI alignment)
+  {
+  }
+
+  @Override
+  protected EnsemblFeatureType[] getFeaturesToFetch()
+  {
+    // not applicable - can't fetch genomic features for a protein sequence
+    return null;
+  }
+
+  @Override
+  protected boolean identifiesSequence(SequenceFeature sf, String accId)
+  {
+    // not applicable - protein sequence is not a 'subset' of genomic sequence
+    return false;
+  }
+
+  @Override
+  protected List<String> getCrossReferenceDatabases()
+  {
+    return CROSSREFS;
+  }
+
+  @Override
+  public Regex getAccessionValidator()
+  {
+    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 String getAccessionIdFromQuery(String query)
+  {
+    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;
+  }
+
 }