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.Sequence.DBModList;
24 import jalview.datamodel.features.SequenceFeaturesI;
25 import jalview.util.MapList;
26 import jalview.ws.params.InvalidArgumentException;
28 import java.awt.Color;
29 import java.util.BitSet;
30 import java.util.Iterator;
31 import java.util.List;
32 import java.util.Vector;
34 import fr.orsay.lri.varna.models.rna.RNA;
37 * Methods for manipulating a sequence, its metadata and related annotation in
38 * an alignment or dataset.
43 public interface SequenceI extends ASequenceI
46 * Set the display name for the sequence
50 public void setName(String name);
53 * Get the display name
55 public String getName();
58 * Set start position of first non-gapped symbol in sequence
63 public void setStart(int start);
66 * get start position of first non-gapped residue in sequence
70 public int getStart();
73 * get the displayed id of the sequence
75 * @return true means the id will be returned in the form
76 * DisplayName/Start-End
78 public String getDisplayId(boolean jvsuffix);
81 * set end position for last residue in sequence
85 public void setEnd(int end);
88 * get end position for last residue in sequence getEnd()>getStart() unless
89 * sequence only consists of gap characters
96 * @return length of sequence including gaps
99 public int getLength();
102 * Replace the sequence with the given string
105 * new sequence string
107 public void setSequence(String sequence);
110 * @return sequence as string
112 public String getSequenceAsString();
115 * get a range on the sequence as a string
118 * (inclusive) position relative to start of sequence including gaps
121 * (exclusive) position relative to start of sequence including gaps
124 * @return String containing all gap and symbols in specified range
126 public String getSequenceAsString(int start, int end);
129 * Answers a copy of the sequence as a character array
133 public char[] getSequence();
136 * get stretch of sequence characters in an array
139 * absolute index into getSequence()
141 * exclusive index of last position in segment to be returned.
143 * @return char[max(0,end-start)];
145 public char[] getSequence(int start, int end);
148 * create a new sequence object with a subsequence of this one but sharing the
149 * same dataset sequence
152 * int index for start position (base 0, inclusive)
154 * int index for end position (base 0, exclusive)
157 * @note implementations may use getSequence to get the sequence data
159 public SequenceI getSubSequence(int start, int end);
162 * get the i'th character in this sequence's local reference frame (ie from
163 * 0-number of characters lying from start-end)
167 * @return character or ' '
169 public char getCharAt(int i);
177 public void setDescription(String desc);
182 * @return DOCUMENT ME!
184 public String getDescription();
187 * Return the alignment column (from 1..) for a sequence position
190 * lying from start to end
192 * @return aligned column for residue (0 if residue is upstream from
193 * alignment, -1 if residue is downstream from alignment) note.
194 * Sequence object returns sequence.getEnd() for positions upstream
195 * currently. TODO: change sequence for
196 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
199 public int findIndex(int pos);
202 * Returns the sequence position for an alignment (column) position. If at a
203 * gap, returns the position of the next residue to the right. If beyond the
204 * end of the sequence, returns 1 more than the last residue position.
207 * column index in alignment (from 0..<length)
211 public int findPosition(int i);
214 * Returns the sequence positions for first and last residues lying within the
215 * given column positions [fromColum,toColumn] (where columns are numbered
216 * from 1), or null if no residues are included in the range
219 * - first column base 1
221 * - last column, base 1
224 public ContiguousI findPositions(int fromColum, int toColumn);
227 * Returns an int array where indices correspond to each residue in the
228 * sequence and the element value gives its position in the alignment
230 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
231 * residues in SequenceI object
233 public int[] gapMap();
236 * Build a bitset corresponding to sequence gaps
238 * @return a BitSet where set values correspond to gaps in the sequence
240 public BitSet gapBitset();
243 * Returns an int array where indices correspond to each position in sequence
244 * char array and the element value gives the result of findPosition for that
245 * index in the sequence.
247 * @return int[SequenceI.getLength()]
249 public int[] findPositionMap();
252 * Answers true if the sequence is composed of amino acid characters. Note
253 * that implementations may use heuristic methods which are not guaranteed to
254 * give the biologically 'right' answer.
258 public boolean isProtein();
261 * Delete a range of aligned sequence columns, creating a new dataset sequence
262 * if necessary and adjusting start and end positions accordingly.
265 * first column in range to delete (inclusive)
267 * last column in range to delete (exclusive)
269 public void deleteChars(int i, int j);
275 * alignment column number
277 * character to insert
279 public void insertCharAt(int i, char c);
282 * insert given character at alignment column position
285 * alignment column number
289 * character to insert
291 public void insertCharAt(int position, int count, char ch);
294 * Answers a list of all sequence features associated with this sequence. The
295 * list may be held by the sequence's dataset sequence if that is defined.
299 public List<SequenceFeature> getSequenceFeatures();
302 * Answers the object holding features for the sequence
306 SequenceFeaturesI getFeatures();
309 * Replaces the sequence features associated with this sequence with the given
310 * features. If this sequence has a dataset sequence, then this method will
311 * update the dataset sequence's features instead.
315 public void setSequenceFeatures(List<SequenceFeature> features);
323 public void setPDBId(Vector<PDBEntry> ids);
328 * @return DOCUMENT ME!
330 public Vector<PDBEntry> getAllPDBEntries();
333 * Adds the entry to the *normalised* list of PDBIds.
335 * If a PDBEntry is passed with the same entry.getID() string as one already
336 * in the list, or one is added that appears to be the same but has a chain ID
337 * appended, then the existing PDBEntry will be updated with the new
338 * attributes instead, unless the entries have distinct chain codes or
339 * associated structure files.
342 * @return true if the entry was added, false if updated
344 public boolean addPDBId(PDBEntry entry);
347 * update the list of PDBEntrys to include any DBRefEntrys citing structural
350 * @return true if PDBEntry list was modified
352 public boolean updatePDBIds();
354 public String getVamsasId();
356 public void setVamsasId(String id);
359 * set the array of Database references for the sequence.
361 * BH 2019.02.04 changes param to DBModlist
364 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
365 * set are not normalised.
366 * @throws InvalidArgumentException if the is not one created by Sequence itself
369 public void setDBRefs(DBModList<DBRefEntry> dbs);
371 public DBModList<DBRefEntry> getDBRefs();
374 * add the given entry to the list of DBRefs for this sequence, or replace a
375 * similar one if entry contains a map object and the existing one doesnt.
379 public void addDBRef(DBRefEntry entry);
382 * Adds the given sequence feature and returns true, or returns false if it is
383 * already present on the sequence, or if the feature type is null.
388 public boolean addSequenceFeature(SequenceFeature sf);
390 public void deleteFeature(SequenceFeature sf);
392 public void setDatasetSequence(SequenceI seq);
394 public SequenceI getDatasetSequence();
397 * Returns a new array containing this sequence's annotations, or null.
399 public AlignmentAnnotation[] getAnnotation();
402 * Returns true if this sequence has the given annotation (by object
405 public boolean hasAnnotation(AlignmentAnnotation ann);
408 * Add the given annotation, if not already added, and set its sequence ref to
409 * be this sequence. Does nothing if this sequence's annotations already
410 * include this annotation (by identical object reference).
412 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
414 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
417 * Derive a sequence (using this one's dataset or as the dataset)
419 * @return duplicate sequence with valid dataset sequence
421 public SequenceI deriveSequence();
424 * set the array of associated AlignmentAnnotation for this sequenceI
428 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
431 * Get one or more alignment annotations with a particular label.
434 * string which each returned annotation must have as a label.
435 * @return null or array of annotations.
437 public AlignmentAnnotation[] getAnnotation(String label);
440 * Returns a (possibly empty) list of any annotations that match on given
441 * calcId (source) and label (type). Null values do not match.
446 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
450 * create a new dataset sequence (if necessary) for this sequence and sets
451 * this sequence to refer to it. This call will move any features or
452 * references on the sequence onto the dataset. It will also make a duplicate
453 * of existing annotation rows for the dataset sequence, rather than relocate
454 * them in order to preserve external references (since 2.8.2).
456 * @return dataset sequence for this sequence
458 public SequenceI createDatasetSequence();
461 * Transfer any database references or annotation from entry under a sequence
463 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
468 * null or mapping from entry's numbering to local start/end
470 public void transferAnnotation(SequenceI entry, Mapping mp);
473 * @return The RNA of the sequence in the alignment
482 public void setRNA(RNA rna);
486 * @return list of insertions (gap characters) in sequence
488 public List<int[]> getInsertions();
491 * Given a pdbId String, return the equivalent PDBEntry if available in the
497 public PDBEntry getPDBEntry(String pdbId);
500 * Get all primary database/accessions for this sequence's data. These
501 * DBRefEntry are expected to resolve to a valid record in the associated
502 * external database, either directly or via a provided 1:1 Mapping.
504 * @return just the primary references (if any) for this sequence, or an empty
507 public List<DBRefEntry> getPrimaryDBRefs();
510 * Returns a (possibly empty) list of sequence features that overlap the given
511 * alignment column range, optionally restricted to one or more specified
512 * feature types. If the range is all gaps, then features which enclose it are
513 * included (but not contact features).
516 * start column of range inclusive (1..)
518 * end column of range inclusive (1..)
520 * optional feature types to restrict results to
523 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
526 * Method to call to indicate that the sequence (characters or alignment/gaps)
527 * has been modified. Provided to allow any cursors on residue/column
528 * positions to be invalidated.
530 void sequenceChanged();
534 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
537 BitSet getInsertionsAsBits();
540 * Replaces every occurrence of c1 in the sequence with c2 and returns the
541 * number of characters changed
546 public int replace(char c1, char c2);
549 * Answers the GeneLociI, or null if not known
553 GeneLociI getGeneLoci();
556 * Sets the mapping to gene loci for the sequence
560 * @param chromosomeId
563 void setGeneLoci(String speciesId, String assemblyId,
564 String chromosomeId, MapList map);
568 * Returns the sequence string constructed from the substrings of a sequence
569 * defined by the int[] ranges provided by an iterator. E.g. the iterator
570 * could iterate over all visible regions of the alignment
573 * the iterator to use
574 * @return a String corresponding to the sequence
576 public String getSequenceStringFromIterator(Iterator<int[]> it);
579 * Locate the first position in this sequence which is not contained in an
580 * iterator region. If no such position exists, return 0
583 * iterator over regions
584 * @return first residue not contained in regions
586 public int firstResidueOutsideIterator(Iterator<int[]> it);
588 public Color getColor(int i);
590 public Color setColor(int i, Color c);
592 public void resetColors();