X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceI.java;h=15b61d2b4dcda5be93d6e01f1885aa8bb8b40009;hb=9c8b674e5ab62309b0df090977c8bf8288deb98b;hp=64a57bae376b10bbfbdf36ed1d56233348679118;hpb=ab43013b7e357b84b4abade0dba949668dfb2a0e;p=jalview.git

diff --git a/src/jalview/datamodel/SequenceI.java b/src/jalview/datamodel/SequenceI.java
index 64a57ba..15b61d2 100755
--- a/src/jalview/datamodel/SequenceI.java
+++ b/src/jalview/datamodel/SequenceI.java
@@ -1,6 +1,6 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2b1)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
  * 
  * This file is part of Jalview.
  * 
@@ -20,18 +20,24 @@
  */
 package jalview.datamodel;
 
+import jalview.datamodel.features.SequenceFeaturesI;
+import jalview.util.MapList;
+
+import java.util.BitSet;
+import java.util.Iterator;
 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
@@ -106,18 +112,20 @@ public interface SequenceI
    * get a range on the sequence as a string
    * 
    * @param start
-   *          position relative to start of sequence including gaps (from 0)
+   *          (inclusive) position relative to start of sequence including gaps
+   *          (from 0)
    * @param end
-   *          position relative to start of sequence including gaps (from 0)
+   *          (exclusive) position relative to start of sequence including gaps
+   *          (from 0)
    * 
    * @return String containing all gap and symbols in specified range
    */
   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();
 
@@ -134,12 +142,13 @@ public interface SequenceI
   public char[] getSequence(int start, int end);
 
   /**
-   * create a new sequence object from start to end of this sequence
+   * create a new sequence object with a subsequence of this one but sharing the
+   * same dataset sequence
    * 
    * @param start
-   *          int index for start position
+   *          int index for start position (base 0, inclusive)
    * @param end
-   *          int index for end position
+   *          int index for end position (base 0, exclusive)
    * 
    * @return SequenceI
    * @note implementations may use getSequence to get the sequence data
@@ -147,12 +156,12 @@ public interface SequenceI
   public SequenceI getSubSequence(int start, int end);
 
   /**
-   * DOCUMENT ME!
+   * get the i'th character in this sequence's local reference frame (ie from
+   * 0-number of characters lying from start-end)
    * 
    * @param i
-   *          DOCUMENT ME!
-   * 
-   * @return DOCUMENT ME!
+   *          index
+   * @return character or ' '
    */
   public char getCharAt(int i);
 
@@ -172,8 +181,7 @@ public interface SequenceI
   public String getDescription();
 
   /**
-   * Return the alignment column for a sequence position * Return the alignment
-   * position for a sequence position
+   * Return the alignment column (from 1..) for a sequence position
    * 
    * @param pos
    *          lying from start to end
@@ -188,16 +196,31 @@ 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 sequence positions for first and last residues lying within the
+   * given column positions [fromColum,toColumn] (where columns are numbered
+   * from 1), or null if no residues are included in the range
+   * 
+   * @param fromColum
+   *          - first column base 1
+   * @param toColumn
+   *          - last column, base 1
+   * @return
+   */
+  public ContiguousI 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
    * 
@@ -207,6 +230,13 @@ public interface SequenceI
   public int[] gapMap();
 
   /**
+   * Build a bitset corresponding to sequence gaps
+   * 
+   * @return a BitSet where set values correspond to gaps in the sequence
+   */
+  public BitSet gapBitset();
+
+  /**
    * Returns an int array where indices correspond to each position in sequence
    * char array and the element value gives the result of findPosition for that
    * index in the sequence.
@@ -216,13 +246,22 @@ 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.
    * 
    * @param i
-   *          first column in range to delete
+   *          first column in range to delete (inclusive)
    * @param j
-   *          last column in range to delete
+   *          last column in range to delete (exclusive)
    */
   public void deleteChars(int i, int j);
 
@@ -230,36 +269,47 @@ 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 i
-   *          DOCUMENT ME!
-   * @param c
-   *          DOCUMENT ME!
+   * @param position
+   *          alignment column number
+   * @param count
+   *          length of insert
+   * @param ch
+   *          character to insert
    */
-  public void insertCharAt(int i, int length, char c);
+  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
+   */
+  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(SequenceFeature[] features);
+  public void setSequenceFeatures(List<SequenceFeature> features);
 
   /**
    * DOCUMENT ME!
@@ -267,21 +317,28 @@ public interface SequenceI
    * @param id
    *          DOCUMENT ME!
    */
-  public void setPDBId(Vector ids);
+  public void setPDBId(Vector<PDBEntry> ids);
 
   /**
-   * DOCUMENT ME!
+   * Returns a list
    * 
    * @return DOCUMENT ME!
    */
-  public Vector 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
@@ -295,9 +352,17 @@ 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
@@ -307,7 +372,14 @@ 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);
 
@@ -315,10 +387,22 @@ public interface SequenceI
 
   public SequenceI getDatasetSequence();
 
+  /**
+   * Returns a new array containing this sequence's annotations, or null.
+   */
   public AlignmentAnnotation[] getAnnotation();
 
+  /**
+   * Returns true if this sequence has the given annotation (by object
+   * identity).
+   */
   public boolean hasAnnotation(AlignmentAnnotation ann);
 
+  /**
+   * Add the given annotation, if not already added, and set its sequence ref to
+   * be this sequence. Does nothing if this sequence's annotations already
+   * include this annotation (by identical object reference).
+   */
   public void addAlignmentAnnotation(AlignmentAnnotation annotation);
 
   public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
@@ -347,12 +431,11 @@ public interface SequenceI
   public AlignmentAnnotation[] getAnnotation(String label);
 
   /**
-   * Return a list of any annotations which match the given calcId (source) and
-   * label (type). Null values do not match.
+   * Returns a (possibly empty) list of any annotations that match on given
+   * calcId (source) and label (type). Null values do not match.
    * 
    * @param calcId
    * @param label
-   * @return
    */
   public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
           String label);
@@ -371,8 +454,8 @@ 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
@@ -381,26 +464,118 @@ public interface SequenceI
   public void transferAnnotation(SequenceI entry, Mapping mp);
 
   /**
-   * @param index
-   *          The sequence index in the MSA
+   * @return The RNA of the sequence in the alignment
    */
-  public void setIndex(int index);
+
+  public RNA getRNA();
 
   /**
-   * @return The index of the sequence in the alignment
+   * @param rna
+   *          The RNA.
    */
-  public int getIndex();
+  public void setRNA(RNA rna);
 
   /**
-   * @return The RNA of the sequence in the alignment
+   * 
+   * @return list of insertions (gap characters) in sequence
    */
+  public List<int[]> getInsertions();
 
-  public RNA getRNA();
+  /**
+   * Given a pdbId String, return the equivalent PDBEntry if available in the
+   * given sequence
+   * 
+   * @param pdbId
+   * @return
+   */
+  public PDBEntry getPDBEntry(String pdbId);
 
   /**
-   * @param rna
-   *          The RNA.
+   * 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 void setRNA(RNA rna);
+  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);
+
+  /**
+   * Answers the GeneLociI, or null if not known
+   * 
+   * @return
+   */
+  GeneLociI getGeneLoci();
+
+  /**
+   * Sets the mapping to gene loci for the sequence
+   * 
+   * @param speciesId
+   * @param assemblyId
+   * @param chromosomeId
+   * @param map
+   */
+  void setGeneLoci(String speciesId, String assemblyId,
+          String chromosomeId, MapList map);
+
+
+  /**
+   * Returns the sequence string constructed from the substrings of a sequence
+   * defined by the int[] ranges provided by an iterator. E.g. the iterator
+   * could iterate over all visible regions of the alignment
+   * 
+   * @param it
+   *          the iterator to use
+   * @return a String corresponding to the sequence
+   */
+  public String getSequenceStringFromIterator(Iterator<int[]> it);
+
+  /**
+   * Locate the first position in this sequence which is not contained in an
+   * iterator region. If no such position exists, return 0
+   * 
+   * @param it
+   *          iterator over regions
+   * @return first residue not contained in regions
+   */
+  public int firstResidueOutsideIterator(Iterator<int[]> it);
 }