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);
49 public HiddenMarkovModel getHMM();
51 public void setHMM(HiddenMarkovModel hmm);
54 * Get the display name
56 public String getName();
59 * Set start position of first non-gapped symbol in sequence
64 public void setStart(int start);
67 * get start position of first non-gapped residue in sequence
71 public int getStart();
74 * get the displayed id of the sequence
76 * @return true means the id will be returned in the form
77 * DisplayName/Start-End
79 public String getDisplayId(boolean jvsuffix);
82 * set end position for last residue in sequence
86 public void setEnd(int end);
89 * get end position for last residue in sequence getEnd()>getStart() unless
90 * sequence only consists of gap characters
97 * @return length of sequence including gaps
100 public int getLength();
103 * Replace the sequence with the given string
106 * new sequence string
108 public void setSequence(String sequence);
111 * @return sequence as string
113 public String getSequenceAsString();
116 * get a range on the sequence as a string
119 * position relative to start of sequence including gaps (from 0)
121 * position relative to start of sequence including gaps (from 0)
123 * @return String containing all gap and symbols in specified range
125 public String getSequenceAsString(int start, int end);
128 * Answers a copy of the sequence as a character array
132 public char[] getSequence();
135 * get stretch of sequence characters in an array
138 * absolute index into getSequence()
140 * exclusive index of last position in segment to be returned.
142 * @return char[max(0,end-start)];
144 public char[] getSequence(int start, int end);
147 * create a new sequence object with a subsequence of this one but sharing the
148 * same dataset sequence
151 * int index for start position (base 0, inclusive)
153 * int index for end position (base 0, exclusive)
156 * @note implementations may use getSequence to get the sequence data
158 public SequenceI getSubSequence(int start, int end);
161 * get the i'th character in this sequence's local reference frame (ie from
162 * 0-number of characters lying from start-end)
166 * @return character or ' '
168 public char getCharAt(int i);
176 public void setDescription(String desc);
181 * @return DOCUMENT ME!
183 public String getDescription();
186 * Return the alignment column (from 1..) for a sequence position
189 * lying from start to end
191 * @return aligned column for residue (0 if residue is upstream from
192 * alignment, -1 if residue is downstream from alignment) note.
193 * Sequence object returns sequence.getEnd() for positions upstream
194 * currently. TODO: change sequence for
195 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
198 public int findIndex(int pos);
201 * Returns the sequence position for an alignment (column) position. If at a
202 * gap, returns the position of the next residue to the right. If beyond the
203 * end of the sequence, returns 1 more than the last residue position.
206 * column index in alignment (from 0..<length)
210 public int findPosition(int i);
213 * Returns the from-to sequence positions (start..) for the given column
214 * positions (1..), or null if no residues are included in the range
220 public Range findPositions(int fromColum, int toColumn);
223 * Returns an int array where indices correspond to each residue in the
224 * sequence and the element value gives its position in the alignment
226 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
227 * residues in SequenceI object
229 public int[] gapMap();
232 * Build a bitset corresponding to sequence gaps
234 * @return a BitSet where set values correspond to gaps in the sequence
236 public BitSet gapBitset();
239 * Returns an int array where indices correspond to each position in sequence
240 * char array and the element value gives the result of findPosition for that
241 * index in the sequence.
243 * @return int[SequenceI.getLength()]
245 public int[] findPositionMap();
248 * Answers true if the sequence is composed of amino acid characters. Note
249 * that implementations may use heuristic methods which are not guaranteed to
250 * give the biologically 'right' answer.
254 public boolean isProtein();
257 * Delete a range of aligned sequence columns, creating a new dataset sequence
258 * if necessary and adjusting start and end positions accordingly.
261 * first column in range to delete (inclusive)
263 * last column in range to delete (exclusive)
265 public void deleteChars(int i, int j);
271 * alignment column number
273 * character to insert
275 public void insertCharAt(int i, char c);
278 * insert given character at alignment column position
281 * alignment column number
285 * character to insert
287 public void insertCharAt(int position, int count, char ch);
290 * Answers a list of all sequence features associated with this sequence. The
291 * list may be held by the sequence's dataset sequence if that is defined.
295 public List<SequenceFeature> getSequenceFeatures();
298 * Answers the object holding features for the sequence
302 SequenceFeaturesI getFeatures();
305 * Replaces the sequence features associated with this sequence with the given
306 * features. If this sequence has a dataset sequence, then this method will
307 * update the dataset sequence's features instead.
311 public void setSequenceFeatures(List<SequenceFeature> features);
319 public void setPDBId(Vector<PDBEntry> ids);
324 * @return DOCUMENT ME!
326 public Vector<PDBEntry> getAllPDBEntries();
329 * Adds the entry to the *normalised* list of PDBIds.
331 * If a PDBEntry is passed with the same entry.getID() string as one already
332 * in the list, or one is added that appears to be the same but has a chain ID
333 * appended, then the existing PDBEntry will be updated with the new
334 * attributes instead, unless the entries have distinct chain codes or
335 * associated structure files.
338 * @return true if the entry was added, false if updated
340 public boolean addPDBId(PDBEntry entry);
343 * update the list of PDBEntrys to include any DBRefEntrys citing structural
346 * @return true if PDBEntry list was modified
348 public boolean updatePDBIds();
350 public String getVamsasId();
352 public void setVamsasId(String id);
355 * set the array of Database references for the sequence.
358 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
359 * set are not normalised.
362 public void setDBRefs(DBRefEntry[] dbs);
364 public DBRefEntry[] getDBRefs();
367 * add the given entry to the list of DBRefs for this sequence, or replace a
368 * similar one if entry contains a map object and the existing one doesnt.
372 public void addDBRef(DBRefEntry entry);
375 * Adds the given sequence feature and returns true, or returns false if it is
376 * already present on the sequence, or if the feature type is null.
381 public boolean addSequenceFeature(SequenceFeature sf);
383 public void deleteFeature(SequenceFeature sf);
385 public void setDatasetSequence(SequenceI seq);
387 public SequenceI getDatasetSequence();
390 * Returns a new array containing this sequence's annotations, or null.
392 public AlignmentAnnotation[] getAnnotation();
395 * Returns true if this sequence has the given annotation (by object
398 public boolean hasAnnotation(AlignmentAnnotation ann);
401 * Add the given annotation, if not already added, and set its sequence ref to
402 * be this sequence. Does nothing if this sequence's annotations already
403 * include this annotation (by identical object reference).
405 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
407 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
410 * Derive a sequence (using this one's dataset or as the dataset)
412 * @return duplicate sequence with valid dataset sequence
414 public SequenceI deriveSequence();
417 * set the array of associated AlignmentAnnotation for this sequenceI
421 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
424 * Get one or more alignment annotations with a particular label.
427 * string which each returned annotation must have as a label.
428 * @return null or array of annotations.
430 public AlignmentAnnotation[] getAnnotation(String label);
433 * Returns a (possibly empty) list of any annotations that match on given
434 * calcId (source) and label (type). Null values do not match.
439 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
443 * create a new dataset sequence (if necessary) for this sequence and sets
444 * this sequence to refer to it. This call will move any features or
445 * references on the sequence onto the dataset. It will also make a duplicate
446 * of existing annotation rows for the dataset sequence, rather than relocate
447 * them in order to preserve external references (since 2.8.2).
449 * @return dataset sequence for this sequence
451 public SequenceI createDatasetSequence();
454 * Transfer any database references or annotation from entry under a sequence
456 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
461 * null or mapping from entry's numbering to local start/end
463 public void transferAnnotation(SequenceI entry, Mapping mp);
466 * @return The RNA of the sequence in the alignment
475 public void setRNA(RNA rna);
479 * @return list of insertions (gap characters) in sequence
481 public List<int[]> getInsertions();
484 * Given a pdbId String, return the equivalent PDBEntry if available in the
490 public PDBEntry getPDBEntry(String pdbId);
493 * Get all primary database/accessions for this sequence's data. These
494 * DBRefEntry are expected to resolve to a valid record in the associated
495 * external database, either directly or via a provided 1:1 Mapping.
497 * @return just the primary references (if any) for this sequence, or an empty
500 public List<DBRefEntry> getPrimaryDBRefs();
503 * Answers true if the sequence has annotation for Hidden Markov Model
504 * information content, else false
506 boolean hasHMMAnnotation();
509 * Returns a (possibly empty) list of sequence features that overlap the given
510 * alignment column range, optionally restricted to one or more specified
511 * feature types. If the range is all gaps, then features which enclose it are
512 * included (but not contact features).
515 * start column of range inclusive (1..)
517 * end column of range inclusive (1..)
519 * optional feature types to restrict results to
522 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
525 * Method to call to indicate that the sequence (characters or alignment/gaps)
526 * has been modified. Provided to allow any cursors on residue/column
527 * positions to be invalidated.
529 void sequenceChanged();
533 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
536 BitSet getInsertionsAsBits();
539 * Replaces every occurrence of c1 in the sequence with c2 and returns the
540 * number of characters changed
545 int replace(char c1, char c2);
548 * Answers the GeneLociI, or null if not known
552 GeneLociI getGeneLoci();
555 * Sets the mapping to gene loci for the sequence
559 * @param chromosomeId
562 void setGeneLoci(String speciesId, String assemblyId,
563 String chromosomeId, MapList map);
567 * Returns the sequence string constructed from the substrings of a sequence
568 * defined by the int[] ranges provided by an iterator. E.g. the iterator
569 * could iterate over all visible regions of the alignment
572 * the iterator to use
573 * @return a String corresponding to the sequence
575 String getSequenceStringFromIterator(Iterator<int[]> it);
578 * Locate the first position in this sequence which is not contained in an
579 * iterator region. If no such position exists, return 0
582 * iterator over regions
583 * @return first residue not contained in regions
585 int firstResidueOutsideIterator(Iterator<int[]> it);
588 * Answers true if this sequence has an associated Hidden Markov Model
592 boolean hasHMMProfile();