2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.datamodel;
23 import jalview.datamodel.features.SequenceFeaturesI;
24 import jalview.util.MapList;
26 import java.util.BitSet;
27 import java.util.Iterator;
28 import java.util.List;
29 import java.util.Vector;
31 import fr.orsay.lri.varna.models.rna.RNA;
34 * Methods for manipulating a sequence, its metadata and related annotation in
35 * an alignment or dataset.
40 public interface SequenceI extends ASequenceI
43 * Set the display name for the sequence
47 public void setName(String name);
50 * Get the display name
52 public String getName();
55 * Set start position of first non-gapped symbol in sequence
60 public void setStart(int start);
63 * get start position of first non-gapped residue in sequence
67 public int getStart();
70 * get the displayed id of the sequence
72 * @return true means the id will be returned in the form
73 * DisplayName/Start-End
75 public String getDisplayId(boolean jvsuffix);
78 * set end position for last residue in sequence
82 public void setEnd(int end);
85 * get end position for last residue in sequence getEnd()>getStart() unless
86 * sequence only consists of gap characters
93 * @return length of sequence including gaps
96 public int getLength();
99 * Replace the sequence with the given string
102 * new sequence string
104 public void setSequence(String sequence);
107 * @return sequence as string
109 public String getSequenceAsString();
112 * get a range on the sequence as a string
115 * position relative to start of sequence including gaps (from 0)
117 * position relative to start of sequence including gaps (from 0)
119 * @return String containing all gap and symbols in specified range
121 public String getSequenceAsString(int start, int end);
124 * Answers a copy of the sequence as a character array
128 public char[] getSequence();
131 * get stretch of sequence characters in an array
134 * absolute index into getSequence()
136 * exclusive index of last position in segment to be returned.
138 * @return char[max(0,end-start)];
140 public char[] getSequence(int start, int end);
143 * create a new sequence object with a subsequence of this one but sharing the
144 * same dataset sequence
147 * int index for start position (base 0, inclusive)
149 * int index for end position (base 0, exclusive)
152 * @note implementations may use getSequence to get the sequence data
154 public SequenceI getSubSequence(int start, int end);
157 * get the i'th character in this sequence's local reference frame (ie from
158 * 0-number of characters lying from start-end)
162 * @return character or ' '
164 public char getCharAt(int i);
172 public void setDescription(String desc);
177 * @return DOCUMENT ME!
179 public String getDescription();
182 * Return the alignment column (from 1..) for a sequence position
185 * lying from start to end
187 * @return aligned column for residue (0 if residue is upstream from
188 * alignment, -1 if residue is downstream from alignment) note.
189 * Sequence object returns sequence.getEnd() for positions upstream
190 * currently. TODO: change sequence for
191 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
194 public int findIndex(int pos);
197 * Returns the sequence position for an alignment (column) position. If at a
198 * gap, returns the position of the next residue to the right. If beyond the
199 * end of the sequence, returns 1 more than the last residue position.
202 * column index in alignment (from 0..<length)
206 public int findPosition(int i);
209 * Returns the sequence positions for first and last residues lying within the
210 * given column positions [fromColum,toColumn] (where columns are numbered
211 * from 1), or null if no residues are included in the range
214 * - first column base 1
216 * - last column, base 1
219 public Range findPositions(int fromColum, int toColumn);
222 * Returns an int array where indices correspond to each residue in the
223 * sequence and the element value gives its position in the alignment
225 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
226 * residues in SequenceI object
228 public int[] gapMap();
231 * Build a bitset corresponding to sequence gaps
233 * @return a BitSet where set values correspond to gaps in the sequence
235 public BitSet gapBitset();
238 * Returns an int array where indices correspond to each position in sequence
239 * char array and the element value gives the result of findPosition for that
240 * index in the sequence.
242 * @return int[SequenceI.getLength()]
244 public int[] findPositionMap();
247 * Answers true if the sequence is composed of amino acid characters. Note
248 * that implementations may use heuristic methods which are not guaranteed to
249 * give the biologically 'right' answer.
253 public boolean isProtein();
256 * Delete a range of aligned sequence columns, creating a new dataset sequence
257 * if necessary and adjusting start and end positions accordingly.
260 * first column in range to delete (inclusive)
262 * last column in range to delete (exclusive)
264 public void deleteChars(int i, int j);
270 * alignment column number
272 * character to insert
274 public void insertCharAt(int i, char c);
277 * insert given character at alignment column position
280 * alignment column number
284 * character to insert
286 public void insertCharAt(int position, int count, char ch);
289 * Answers a list of all sequence features associated with this sequence. The
290 * list may be held by the sequence's dataset sequence if that is defined.
294 public List<SequenceFeature> getSequenceFeatures();
297 * Answers the object holding features for the sequence
301 SequenceFeaturesI getFeatures();
304 * Replaces the sequence features associated with this sequence with the given
305 * features. If this sequence has a dataset sequence, then this method will
306 * update the dataset sequence's features instead.
310 public void setSequenceFeatures(List<SequenceFeature> features);
318 public void setPDBId(Vector<PDBEntry> ids);
323 * @return DOCUMENT ME!
325 public Vector<PDBEntry> getAllPDBEntries();
328 * Adds the entry to the *normalised* list of PDBIds.
330 * If a PDBEntry is passed with the same entry.getID() string as one already
331 * in the list, or one is added that appears to be the same but has a chain ID
332 * appended, then the existing PDBEntry will be updated with the new
333 * attributes instead, unless the entries have distinct chain codes or
334 * associated structure files.
337 * @return true if the entry was added, false if updated
339 public boolean addPDBId(PDBEntry entry);
342 * update the list of PDBEntrys to include any DBRefEntrys citing structural
345 * @return true if PDBEntry list was modified
347 public boolean updatePDBIds();
349 public String getVamsasId();
351 public void setVamsasId(String id);
354 * set the array of Database references for the sequence.
357 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
358 * set are not normalised.
361 public void setDBRefs(DBRefEntry[] dbs);
363 public DBRefEntry[] getDBRefs();
366 * add the given entry to the list of DBRefs for this sequence, or replace a
367 * similar one if entry contains a map object and the existing one doesnt.
371 public void addDBRef(DBRefEntry entry);
374 * Adds the given sequence feature and returns true, or returns false if it is
375 * already present on the sequence, or if the feature type is null.
380 public boolean addSequenceFeature(SequenceFeature sf);
382 public void deleteFeature(SequenceFeature sf);
384 public void setDatasetSequence(SequenceI seq);
386 public SequenceI getDatasetSequence();
389 * Returns a new array containing this sequence's annotations, or null.
391 public AlignmentAnnotation[] getAnnotation();
394 * Returns true if this sequence has the given annotation (by object
397 public boolean hasAnnotation(AlignmentAnnotation ann);
400 * Add the given annotation, if not already added, and set its sequence ref to
401 * be this sequence. Does nothing if this sequence's annotations already
402 * include this annotation (by identical object reference).
404 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
406 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
409 * Derive a sequence (using this one's dataset or as the dataset)
411 * @return duplicate sequence with valid dataset sequence
413 public SequenceI deriveSequence();
416 * set the array of associated AlignmentAnnotation for this sequenceI
420 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
423 * Get one or more alignment annotations with a particular label.
426 * string which each returned annotation must have as a label.
427 * @return null or array of annotations.
429 public AlignmentAnnotation[] getAnnotation(String label);
432 * Returns a (possibly empty) list of any annotations that match on given
433 * calcId (source) and label (type). Null values do not match.
438 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
442 * create a new dataset sequence (if necessary) for this sequence and sets
443 * this sequence to refer to it. This call will move any features or
444 * references on the sequence onto the dataset. It will also make a duplicate
445 * of existing annotation rows for the dataset sequence, rather than relocate
446 * them in order to preserve external references (since 2.8.2).
448 * @return dataset sequence for this sequence
450 public SequenceI createDatasetSequence();
453 * Transfer any database references or annotation from entry under a sequence
455 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
460 * null or mapping from entry's numbering to local start/end
462 public void transferAnnotation(SequenceI entry, Mapping mp);
465 * @return The RNA of the sequence in the alignment
474 public void setRNA(RNA rna);
478 * @return list of insertions (gap characters) in sequence
480 public List<int[]> getInsertions();
483 * Given a pdbId String, return the equivalent PDBEntry if available in the
489 public PDBEntry getPDBEntry(String pdbId);
492 * Get all primary database/accessions for this sequence's data. These
493 * DBRefEntry are expected to resolve to a valid record in the associated
494 * external database, either directly or via a provided 1:1 Mapping.
496 * @return just the primary references (if any) for this sequence, or an empty
499 public List<DBRefEntry> getPrimaryDBRefs();
502 * Returns a (possibly empty) list of sequence features that overlap the given
503 * alignment column range, optionally restricted to one or more specified
504 * feature types. If the range is all gaps, then features which enclose it are
505 * included (but not contact features).
508 * start column of range inclusive (1..)
510 * end column of range inclusive (1..)
512 * optional feature types to restrict results to
515 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
518 * Method to call to indicate that the sequence (characters or alignment/gaps)
519 * has been modified. Provided to allow any cursors on residue/column
520 * positions to be invalidated.
522 void sequenceChanged();
526 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
529 BitSet getInsertionsAsBits();
532 * Replaces every occurrence of c1 in the sequence with c2 and returns the
533 * number of characters changed
538 public int replace(char c1, char c2);
541 * Answers the GeneLociI, or null if not known
545 GeneLociI getGeneLoci();
548 * Sets the mapping to gene loci for the sequence
552 * @param chromosomeId
555 void setGeneLoci(String speciesId, String assemblyId,
556 String chromosomeId, MapList map);
560 * Returns the sequence string constructed from the substrings of a sequence
561 * defined by the int[] ranges provided by an iterator. E.g. the iterator
562 * could iterate over all visible regions of the alignment
565 * the iterator to use
566 * @return a String corresponding to the sequence
568 public String getSequenceStringFromIterator(Iterator<int[]> it);
571 * Locate the first position in this sequence which is not contained in an
572 * iterator region. If no such position exists, return 0
575 * iterator over regions
576 * @return first residue not contained in regions
578 public int firstResidueOutsideIterator(Iterator<int[]> it);