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.util.BitSet;
29 import java.util.Iterator;
30 import java.util.List;
31 import java.util.Vector;
33 import fr.orsay.lri.varna.models.rna.RNA;
36 * Methods for manipulating a sequence, its metadata and related annotation in
37 * an alignment or dataset.
42 public interface SequenceI extends ASequenceI
45 * Set the display name for the sequence
49 public void setName(String name);
51 public HiddenMarkovModel getHMM();
53 public void setHMM(HiddenMarkovModel hmm);
55 * Get the display name
57 public String getName();
60 * Set start position of first non-gapped symbol in sequence
65 public void setStart(int start);
68 * get start position of first non-gapped residue in sequence
72 public int getStart();
75 * get the displayed id of the sequence
77 * @return true means the id will be returned in the form
78 * DisplayName/Start-End
80 public String getDisplayId(boolean jvsuffix);
83 * set end position for last residue in sequence
87 public void setEnd(int end);
90 * get end position for last residue in sequence getEnd()>getStart() unless
91 * sequence only consists of gap characters
98 * @return length of sequence including gaps
101 public int getLength();
104 * Replace the sequence with the given string
107 * new sequence string
109 public void setSequence(String sequence);
112 * @return sequence as string
114 public String getSequenceAsString();
117 * get a range on the sequence as a string
120 * (inclusive) position relative to start of sequence including gaps
123 * (exclusive) position relative to start of sequence including gaps
126 * @return String containing all gap and symbols in specified range
128 public String getSequenceAsString(int start, int end);
131 * Answers a copy of the sequence as a character array
135 public char[] getSequence();
138 * get stretch of sequence characters in an array
141 * absolute index into getSequence()
143 * exclusive index of last position in segment to be returned.
145 * @return char[max(0,end-start)];
147 public char[] getSequence(int start, int end);
150 * create a new sequence object with a subsequence of this one but sharing the
151 * same dataset sequence
154 * int index for start position (base 0, inclusive)
156 * int index for end position (base 0, exclusive)
159 * @note implementations may use getSequence to get the sequence data
161 public SequenceI getSubSequence(int start, int end);
164 * get the i'th character in this sequence's local reference frame (ie from
165 * 0-number of characters lying from start-end)
169 * @return character or ' '
171 public char getCharAt(int i);
179 public void setDescription(String desc);
184 * @return DOCUMENT ME!
186 public String getDescription();
189 * Return the alignment column (from 1..) for a sequence position
192 * lying from start to end
194 * @return aligned column for residue (0 if residue is upstream from
195 * alignment, -1 if residue is downstream from alignment) note.
196 * Sequence object returns sequence.getEnd() for positions upstream
197 * currently. TODO: change sequence for
198 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
201 public int findIndex(int pos);
204 * Returns the sequence position for an alignment (column) position. If at a
205 * gap, returns the position of the next residue to the right. If beyond the
206 * end of the sequence, returns 1 more than the last residue position.
209 * column index in alignment (from 0..<length)
213 public int findPosition(int i);
216 * Returns the sequence positions for first and last residues lying within the
217 * given column positions [fromColum,toColumn] (where columns are numbered
218 * from 1), or null if no residues are included in the range
221 * - first column base 1. (0 and negative positions are rounded up)
223 * - last column, base 1
224 * @return null if fromColum>toColumn
226 public ContiguousI findPositions(int fromColum, int toColumn);
229 * Returns an int array where indices correspond to each residue in the
230 * sequence and the element value gives its position in the alignment
232 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
233 * residues in SequenceI object
235 public int[] gapMap();
238 * Build a bitset corresponding to sequence gaps
240 * @return a BitSet where set values correspond to gaps in the sequence
242 public BitSet gapBitset();
245 * Returns an int array where indices correspond to each position in sequence
246 * char array and the element value gives the result of findPosition for that
247 * index in the sequence.
249 * @return int[SequenceI.getLength()]
251 public int[] findPositionMap();
254 * Answers true if the sequence is composed of amino acid characters. Note
255 * that implementations may use heuristic methods which are not guaranteed to
256 * give the biologically 'right' answer.
260 public boolean isProtein();
263 * Delete a range of aligned sequence columns, creating a new dataset sequence
264 * if necessary and adjusting start and end positions accordingly.
267 * first column in range to delete (inclusive)
269 * last column in range to delete (exclusive)
271 public void deleteChars(int i, int j);
277 * alignment column number
279 * character to insert
281 public void insertCharAt(int i, char c);
284 * insert given character at alignment column position
287 * alignment column number
291 * character to insert
293 public void insertCharAt(int position, int count, char ch);
296 * Answers a list of all sequence features associated with this sequence. The
297 * list may be held by the sequence's dataset sequence if that is defined.
301 public List<SequenceFeature> getSequenceFeatures();
304 * Answers the object holding features for the sequence
308 SequenceFeaturesI getFeatures();
311 * Replaces the sequence features associated with this sequence with the given
312 * features. If this sequence has a dataset sequence, then this method will
313 * update the dataset sequence's features instead.
317 public void setSequenceFeatures(List<SequenceFeature> features);
325 public void setPDBId(Vector<PDBEntry> ids);
330 * @return DOCUMENT ME!
332 public Vector<PDBEntry> getAllPDBEntries();
335 * Adds the entry to the *normalised* list of PDBIds.
337 * If a PDBEntry is passed with the same entry.getID() string as one already
338 * in the list, or one is added that appears to be the same but has a chain ID
339 * appended, then the existing PDBEntry will be updated with the new
340 * attributes instead, unless the entries have distinct chain codes or
341 * associated structure files.
344 * @return true if the entry was added, false if updated
346 public boolean addPDBId(PDBEntry entry);
349 * update the list of PDBEntrys to include any DBRefEntrys citing structural
352 * @return true if PDBEntry list was modified
354 public boolean updatePDBIds();
356 public String getVamsasId();
358 public void setVamsasId(String id);
361 * set the array of Database references for the sequence.
363 * BH 2019.02.04 changes param to DBModlist
366 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
367 * set are not normalised.
368 * @throws InvalidArgumentException if the is not one created by Sequence itself
371 public void setDBRefs(DBModList<DBRefEntry> dbs);
373 public DBModList<DBRefEntry> getDBRefs();
376 * add the given entry to the list of DBRefs for this sequence, or replace a
377 * similar one if entry contains a map object and the existing one doesnt.
381 public void addDBRef(DBRefEntry entry);
384 * Adds the given sequence feature and returns true, or returns false if it is
385 * already present on the sequence, or if the feature type is null.
390 public boolean addSequenceFeature(SequenceFeature sf);
392 public void deleteFeature(SequenceFeature sf);
394 public void setDatasetSequence(SequenceI seq);
396 public SequenceI getDatasetSequence();
399 * Returns a new array containing this sequence's annotations, or null.
401 public AlignmentAnnotation[] getAnnotation();
404 * Returns true if this sequence has the given annotation (by object
407 public boolean hasAnnotation(AlignmentAnnotation ann);
410 * Add the given annotation, if not already added, and set its sequence ref to
411 * be this sequence. Does nothing if this sequence's annotations already
412 * include this annotation (by identical object reference).
414 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
416 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
419 * Derive a sequence (using this one's dataset or as the dataset)
421 * @return duplicate sequence with valid dataset sequence
423 public SequenceI deriveSequence();
426 * set the array of associated AlignmentAnnotation for this sequenceI
430 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
433 * Get one or more alignment annotations with a particular label.
436 * string which each returned annotation must have as a label.
437 * @return null or array of annotations.
439 public AlignmentAnnotation[] getAnnotation(String label);
442 * Returns a (possibly empty) list of any annotations that match on given
443 * calcId (source) and label (type). Null values do not match.
448 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
452 * Returns a (possibly empty) list of any annotations that match on given
453 * calcId (source), label (type) and description (observation instance).
454 * Null values do not match.
460 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
461 String label, String description);
463 * create a new dataset sequence (if necessary) for this sequence and sets
464 * this sequence to refer to it. This call will move any features or
465 * references on the sequence onto the dataset. It will also make a duplicate
466 * of existing annotation rows for the dataset sequence, rather than relocate
467 * them in order to preserve external references (since 2.8.2).
469 * @return dataset sequence for this sequence
471 public SequenceI createDatasetSequence();
474 * Transfer any database references or annotation from entry under a sequence
476 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
481 * null or mapping from entry's numbering to local start/end
483 public void transferAnnotation(SequenceI entry, Mapping mp);
486 * @return The RNA of the sequence in the alignment
495 public void setRNA(RNA rna);
499 * @return list of insertions (gap characters) in sequence
501 public List<int[]> getInsertions();
504 * Given a pdbId String, return the equivalent PDBEntry if available in the
510 public PDBEntry getPDBEntry(String pdbId);
513 * Get all primary database/accessions for this sequence's data. These
514 * DBRefEntry are expected to resolve to a valid record in the associated
515 * external database, either directly or via a provided 1:1 Mapping.
517 * @return just the primary references (if any) for this sequence, or an empty
520 public List<DBRefEntry> getPrimaryDBRefs();
522 * Answers true if the sequence has annotation for Hidden Markov Model
523 * information content, else false
525 boolean hasHMMAnnotation();
528 * Returns a (possibly empty) list of sequence features that overlap the given
529 * alignment column range, optionally restricted to one or more specified
530 * feature types. If the range is all gaps, then features which enclose it are
531 * included (but not contact features).
534 * start column of range inclusive (1..)
536 * end column of range inclusive (1..)
538 * optional feature types to restrict results to
541 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
544 * Method to call to indicate that the sequence (characters or alignment/gaps)
545 * has been modified. Provided to allow any cursors on residue/column
546 * positions to be invalidated.
548 void sequenceChanged();
552 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
555 BitSet getInsertionsAsBits();
558 * Replaces every occurrence of c1 in the sequence with c2 and returns the
559 * number of characters changed
564 public int replace(char c1, char c2);
567 * Answers the GeneLociI, or null if not known
571 GeneLociI getGeneLoci();
574 * Sets the mapping to gene loci for the sequence
578 * @param chromosomeId
581 void setGeneLoci(String speciesId, String assemblyId,
582 String chromosomeId, MapList map);
586 * Returns the sequence string constructed from the substrings of a sequence
587 * defined by the int[] ranges provided by an iterator. E.g. the iterator
588 * could iterate over all visible regions of the alignment
591 * the iterator to use
592 * @return a String corresponding to the sequence
594 public String getSequenceStringFromIterator(Iterator<int[]> it);
597 * Locate the first position in this sequence which is not contained in an
598 * iterator region. If no such position exists, return 0
601 * iterator over regions
602 * @return first residue not contained in regions
604 public int firstResidueOutsideIterator(Iterator<int[]> it);
608 * Answers true if this sequence has an associated Hidden Markov Model
612 boolean hasHMMProfile();