/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * 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.
*
*/
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
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
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);
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
public int findIndex(int pos);
/**
- * Returns the sequence position for an alignment position
+ * Returns the sequence position for an alignment position.
*
* @param i
* column index in alignment (from 0..<length)
*
- * @return residue number for residue (left of and) nearest ith column
+ * @return TODO: JAL-2562 - residue number for residue (left of and) nearest
+ * ith column
*/
public int findPosition(int i);
/**
+ * Returns the range of sequence positions included in the given alignment
+ * position range. If no positions are included (the range is entirely gaps),
+ * then returns null.
+ *
+ * <pre>
+ * Example:
+ * >Seq/8-13
+ * ABC--DE-F
+ * findPositions(1, 4) returns Range(9, 9) // B only
+ * findPositions(3, 4) returns null // all gaps
+ * findPositions(2, 6) returns Range(10, 12) // CDE
+ * findPositions(3, 7) returns Range(11,12) // DE
+ * </pre>
+ *
+ * @param fromCol
+ * first aligned column position (base 0, inclusive)
+ * @param toCol
+ * last aligned column position (base 0, inclusive)
+ *
+ * @return
+ */
+ public Range findPositions(int fromCol, int toCol);
+
+ /**
* Returns an int array where indices correspond to each residue in the
* sequence and the element value gives its position in the alignment
*
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);
* 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 hard reference to array
*/
- 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!
* @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
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
*/
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);
/**
* 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
*/
public void setRNA(RNA rna);
+ /**
+ *
+ * @return list of insertions (gap characters) in sequence
+ */
+ 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 range
+ * from-to (inclusive), optionally restricted to one or more specified feature
+ * types
+ *
+ * @param from
+ * @param to
+ * @param types
+ * @return
+ */
+ List<SequenceFeature> findFeatures(int from, int to, 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();
}
git://source.jalview.org / jalview.git / blobdiff