X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceI.java;h=15b61d2b4dcda5be93d6e01f1885aa8bb8b40009;hb=383fd91269f510b189450fbe174e9c051103c7eb;hp=18f0948d1a1b31130c77290f252a468146364bb3;hpb=bcd69929dba447593c10ed661545751727ad0b77;p=jalview.git diff --git a/src/jalview/datamodel/SequenceI.java b/src/jalview/datamodel/SequenceI.java index 18f0948..15b61d2 100755 --- a/src/jalview/datamodel/SequenceI.java +++ b/src/jalview/datamodel/SequenceI.java @@ -21,7 +21,10 @@ 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; @@ -109,18 +112,20 @@ public interface SequenceI extends ASequenceI * 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(); @@ -191,39 +196,29 @@ public interface SequenceI extends ASequenceI 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.. - * 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 - * - * - * @param fromCol - * first aligned column position (base 0, inclusive) - * @param toCol - * last aligned column position (base 0, inclusive) + * 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 Range findPositions(int fromCol, int toCol); + public ContiguousI findPositions(int fromColum, int toColumn); /** * Returns an int array where indices correspond to each residue in the @@ -235,6 +230,13 @@ public interface SequenceI extends ASequenceI 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. @@ -289,7 +291,7 @@ public interface SequenceI extends ASequenceI * 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 hard reference to array + * @return */ public List getSequenceFeatures(); @@ -462,17 +464,6 @@ public interface SequenceI extends ASequenceI 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 */ @@ -510,16 +501,20 @@ public interface SequenceI extends ASequenceI public List 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 + * 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 from - * @param to + * @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 findFeatures(int from, int to, String... types); + List findFeatures(int fromCol, int toCol, String... types); /** * Method to call to indicate that the sequence (characters or alignment/gaps) @@ -527,4 +522,60 @@ public interface SequenceI extends ASequenceI * 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 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 it); }