X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceI.java;h=2f3e92580756a8a839ad4e6af97d9194e81d6ddd;hb=2b4cc5fb6217217761b4a8bd2529e51b4775a57d;hp=38ae3721db1e9ef8715feea6694dc2e14461a0cd;hpb=70f9c4700f20a8fa57ed7eb974277d8bad0723c2;p=jalview.git

diff --git a/src/jalview/datamodel/SequenceI.java b/src/jalview/datamodel/SequenceI.java
index 38ae372..2f3e925 100755
--- a/src/jalview/datamodel/SequenceI.java
+++ b/src/jalview/datamodel/SequenceI.java
@@ -20,18 +20,22 @@
  */
 package jalview.datamodel;
 
+import jalview.datamodel.features.SequenceFeaturesI;
+
+import java.util.BitSet;
 import java.util.List;
 import java.util.Vector;
 
 import fr.orsay.lri.varna.models.rna.RNA;
 
 /**
- * DOCUMENT ME!
+ * Methods for manipulating a sequence, its metadata and related annotation in
+ * an alignment or dataset.
  * 
  * @author $author$
  * @version $Revision$
  */
-public interface SequenceI
+public interface SequenceI extends ASequenceI
 {
   /**
    * Set the display name for the sequence
@@ -115,9 +119,9 @@ public interface SequenceI
   public String getSequenceAsString(int start, int end);
 
   /**
-   * Get the sequence as a character array
+   * Answers a copy of the sequence as a character array
    * 
-   * @return seqeunce and any gaps
+   * @return
    */
   public char[] getSequence();
 
@@ -173,7 +177,7 @@ public interface SequenceI
   public String getDescription();
 
   /**
-   * Return the alignment column for a sequence position
+   * Return the alignment column (from 1..) for a sequence position
    * 
    * @param pos
    *          lying from start to end
@@ -188,16 +192,28 @@ public interface SequenceI
   public int findIndex(int pos);
 
   /**
-   * Returns the sequence position for an alignment position
+   * Returns the sequence position for an alignment (column) position. If at a
+   * gap, returns the position of the next residue to the right. If beyond the
+   * end of the sequence, returns 1 more than the last residue position.
    * 
    * @param i
    *          column index in alignment (from 0..<length)
    * 
-   * @return residue number for residue (left of and) nearest ith column
+   * @return
    */
   public int findPosition(int i);
 
   /**
+   * Returns the from-to sequence positions (start..) for the given column
+   * positions (1..), or null if no residues are included in the range
+   * 
+   * @param fromColum
+   * @param toColumn
+   * @return
+   */
+  public Range findPositions(int fromColum, int toColumn);
+
+  /**
    * Returns an int array where indices correspond to each residue in the
    * sequence and the element value gives its position in the alignment
    * 
@@ -216,6 +232,15 @@ public interface SequenceI
   public int[] findPositionMap();
 
   /**
+   * Answers true if the sequence is composed of amino acid characters. Note
+   * that implementations may use heuristic methods which are not guaranteed to
+   * give the biologically 'right' answer.
+   * 
+   * @return
+   */
+  public boolean isProtein();
+
+  /**
    * Delete a range of aligned sequence columns, creating a new dataset sequence
    * if necessary and adjusting start and end positions accordingly.
    * 
@@ -230,35 +255,47 @@ public interface SequenceI
    * DOCUMENT ME!
    * 
    * @param i
-   *          DOCUMENT ME!
+   *          alignment column number
    * @param c
-   *          DOCUMENT ME!
+   *          character to insert
    */
   public void insertCharAt(int i, char c);
 
   /**
-   * DOCUMENT ME!
+   * insert given character at alignment column position
+   * 
    * @param position
-   *          DOCUMENT ME!
+   *          alignment column number
+   * @param count
+   *          length of insert
    * @param ch
-   *          DOCUMENT ME!
+   *          character to insert
    */
   public void insertCharAt(int position, int count, char ch);
 
   /**
-   * DOCUMENT ME!
+   * Answers a list of all sequence features associated with this sequence. The
+   * list may be held by the sequence's dataset sequence if that is defined.
    * 
-   * @return DOCUMENT ME!
+   * @return
    */
-  public SequenceFeature[] getSequenceFeatures();
+  public List<SequenceFeature> getSequenceFeatures();
 
   /**
-   * DOCUMENT ME!
+   * Answers the object holding features for the sequence
    * 
-   * @param v
-   *          DOCUMENT ME!
+   * @return
    */
-  public void setSequenceFeatures(SequenceFeature[] features);
+  SequenceFeaturesI getFeatures();
+
+  /**
+   * Replaces the sequence features associated with this sequence with the given
+   * features. If this sequence has a dataset sequence, then this method will
+   * update the dataset sequence's features instead.
+   * 
+   * @param features
+   */
+  public void setSequenceFeatures(List<SequenceFeature> features);
 
   /**
    * DOCUMENT ME!
@@ -273,14 +310,21 @@ public interface SequenceI
    * 
    * @return DOCUMENT ME!
    */
-  public Vector<PDBEntry> getPDBId();
+  public Vector<PDBEntry> getAllPDBEntries();
 
   /**
-   * add entry to the vector of PDBIds, if it isn't in the list already
+   * Adds the entry to the *normalised* list of PDBIds.
+   * 
+   * If a PDBEntry is passed with the same entry.getID() string as one already
+   * in the list, or one is added that appears to be the same but has a chain ID
+   * appended, then the existing PDBEntry will be updated with the new
+   * attributes instead, unless the entries have distinct chain codes or
+   * associated structure files.
    * 
    * @param entry
+   * @return true if the entry was added, false if updated
    */
-  public void addPDBId(PDBEntry entry);
+  public boolean addPDBId(PDBEntry entry);
 
   /**
    * update the list of PDBEntrys to include any DBRefEntrys citing structural
@@ -294,9 +338,17 @@ public interface SequenceI
 
   public void setVamsasId(String id);
 
-  public void setDBRef(DBRefEntry[] dbs);
+  /**
+   * set the array of Database references for the sequence.
+   * 
+   * @param dbs
+   * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
+   *             set are not normalised.
+   */
+  @Deprecated
+  public void setDBRefs(DBRefEntry[] dbs);
 
-  public DBRefEntry[] getDBRef();
+  public DBRefEntry[] getDBRefs();
 
   /**
    * add the given entry to the list of DBRefs for this sequence, or replace a
@@ -306,7 +358,14 @@ public interface SequenceI
    */
   public void addDBRef(DBRefEntry entry);
 
-  public void addSequenceFeature(SequenceFeature sf);
+  /**
+   * Adds the given sequence feature and returns true, or returns false if it is
+   * already present on the sequence, or if the feature type is null.
+   * 
+   * @param sf
+   * @return
+   */
+  public boolean addSequenceFeature(SequenceFeature sf);
 
   public void deleteFeature(SequenceFeature sf);
 
@@ -381,8 +440,8 @@ public interface SequenceI
   /**
    * Transfer any database references or annotation from entry under a sequence
    * mapping. <br/>
-   * <strong>Note: DOES NOT transfer sequence associated alignment
-   * annotation </strong><br/>
+   * <strong>Note: DOES NOT transfer sequence associated alignment annotation
+   * </strong><br/>
    * 
    * @param entry
    * @param mp
@@ -391,17 +450,6 @@ public interface SequenceI
   public void transferAnnotation(SequenceI entry, Mapping mp);
 
   /**
-   * @param index
-   *          The sequence index in the MSA
-   */
-  public void setIndex(int index);
-
-  /**
-   * @return The index of the sequence in the alignment
-   */
-  public int getIndex();
-
-  /**
    * @return The RNA of the sequence in the alignment
    */
 
@@ -419,4 +467,61 @@ public interface SequenceI
    */
   public List<int[]> getInsertions();
 
+  /**
+   * Given a pdbId String, return the equivalent PDBEntry if available in the
+   * given sequence
+   * 
+   * @param pdbId
+   * @return
+   */
+  public PDBEntry getPDBEntry(String pdbId);
+
+  /**
+   * Get all primary database/accessions for this sequence's data. These
+   * DBRefEntry are expected to resolve to a valid record in the associated
+   * external database, either directly or via a provided 1:1 Mapping.
+   * 
+   * @return just the primary references (if any) for this sequence, or an empty
+   *         list
+   */
+  public List<DBRefEntry> getPrimaryDBRefs();
+
+  /**
+   * Returns a (possibly empty) list of sequence features that overlap the given
+   * alignment column range, optionally restricted to one or more specified
+   * feature types. If the range is all gaps, then features which enclose it are
+   * included (but not contact features).
+   * 
+   * @param fromCol
+   *          start column of range inclusive (1..)
+   * @param toCol
+   *          end column of range inclusive (1..)
+   * @param types
+   *          optional feature types to restrict results to
+   * @return
+   */
+  List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
+
+  /**
+   * Method to call to indicate that the sequence (characters or alignment/gaps)
+   * has been modified. Provided to allow any cursors on residue/column
+   * positions to be invalidated.
+   */
+  void sequenceChanged();
+  
+  /**
+   * 
+   * @return BitSet corresponding to index [0,length) where Comparison.isGap()
+   *         returns true.
+   */
+  BitSet getInsertionsAsBits();
+
+  /**
+   * Replaces every occurrence of c1 in the sequence with c2 and returns the
+   * number of characters changed
+   * 
+   * @param c1
+   * @param c2
+   */
+  public int replace(char c1, char c2);
 }