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;
32 import intervalstore.api.IntervalI;
35 * Methods for manipulating a sequence, its metadata and related annotation in
36 * an alignment or dataset.
41 public interface SequenceI extends ASequenceI
44 * Set the display name for the sequence
48 public void setName(String name);
51 * Get the display name
53 public String getName();
56 * Set start position of first non-gapped symbol in sequence
61 public void setStart(int start);
64 * get start position of first non-gapped residue in sequence
68 public int getStart();
71 * get the displayed id of the sequence
73 * @return true means the id will be returned in the form
74 * DisplayName/Start-End
76 public String getDisplayId(boolean jvsuffix);
79 * set end position for last residue in sequence
83 public void setEnd(int end);
86 * get end position for last residue in sequence getEnd()>getStart() unless
87 * sequence only consists of gap characters
94 * @return length of sequence including gaps
97 public int getLength();
100 * Replace the sequence with the given string
103 * new sequence string
105 public void setSequence(String sequence);
108 * @return sequence as string
110 public String getSequenceAsString();
113 * get a range on the sequence as a string
116 * position relative to start of sequence including gaps (from 0)
118 * position relative to start of sequence including gaps (from 0)
120 * @return String containing all gap and symbols in specified range
122 public String getSequenceAsString(int start, int end);
125 * Answers a copy of the sequence as a character array
129 public char[] getSequence();
132 * get stretch of sequence characters in an array
135 * absolute index into getSequence()
137 * exclusive index of last position in segment to be returned.
139 * @return char[max(0,end-start)];
141 public char[] getSequence(int start, int end);
144 * create a new sequence object with a subsequence of this one but sharing the
145 * same dataset sequence
148 * int index for start position (base 0, inclusive)
150 * int index for end position (base 0, exclusive)
153 * @note implementations may use getSequence to get the sequence data
155 public SequenceI getSubSequence(int start, int end);
158 * get the i'th character in this sequence's local reference frame (ie from
159 * 0-number of characters lying from start-end)
163 * @return character or ' '
165 public char getCharAt(int i);
173 public void setDescription(String desc);
178 * @return DOCUMENT ME!
180 public String getDescription();
183 * Return the alignment column (from 1..) for a sequence position
186 * lying from start to end
188 * @return aligned column for residue (0 if residue is upstream from
189 * alignment, -1 if residue is downstream from alignment) note.
190 * Sequence object returns sequence.getEnd() for positions upstream
191 * currently. TODO: change sequence for
192 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
195 public int findIndex(int pos);
198 * Returns the sequence position for an alignment (column) position. If at a
199 * gap, returns the position of the next residue to the right. If beyond the
200 * end of the sequence, returns 1 more than the last residue position.
203 * column index in alignment (from 0..<length)
207 public int findPosition(int i);
210 * Returns the from-to sequence positions (start..) for the given column
211 * positions (1..), or null if no residues are included in the range
217 public IntervalI findPositions(int fromColum, int toColumn);
220 * Returns an int array where indices correspond to each residue in the
221 * sequence and the element value gives its position in the alignment
223 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
224 * residues in SequenceI object
226 public int[] gapMap();
229 * Build a bitset corresponding to sequence gaps
231 * @return a BitSet where set values correspond to gaps in the sequence
233 public BitSet gapBitset();
236 * Returns an int array where indices correspond to each position in sequence
237 * char array and the element value gives the result of findPosition for that
238 * index in the sequence.
240 * @return int[SequenceI.getLength()]
242 public int[] findPositionMap();
245 * Answers true if the sequence is composed of amino acid characters. Note
246 * that implementations may use heuristic methods which are not guaranteed to
247 * give the biologically 'right' answer.
251 public boolean isProtein();
254 * Delete a range of aligned sequence columns, creating a new dataset sequence
255 * if necessary and adjusting start and end positions accordingly.
258 * first column in range to delete (inclusive)
260 * last column in range to delete (exclusive)
262 public void deleteChars(int i, int j);
268 * alignment column number
270 * character to insert
272 public void insertCharAt(int i, char c);
275 * insert given character at alignment column position
278 * alignment column number
282 * character to insert
284 public void insertCharAt(int position, int count, char ch);
287 * Answers a list of all sequence features associated with this sequence. The
288 * list may be held by the sequence's dataset sequence if that is defined.
292 public List<SequenceFeature> getSequenceFeatures();
295 * Answers the object holding features for the sequence
299 SequenceFeaturesI getFeatures();
302 * Replaces the sequence features associated with this sequence with the given
303 * features. If this sequence has a dataset sequence, then this method will
304 * update the dataset sequence's features instead.
308 public void setSequenceFeatures(List<SequenceFeature> features);
316 public void setPDBId(Vector<PDBEntry> ids);
321 * @return DOCUMENT ME!
323 public Vector<PDBEntry> getAllPDBEntries();
326 * Adds the entry to the *normalised* list of PDBIds.
328 * If a PDBEntry is passed with the same entry.getID() string as one already
329 * in the list, or one is added that appears to be the same but has a chain ID
330 * appended, then the existing PDBEntry will be updated with the new
331 * attributes instead, unless the entries have distinct chain codes or
332 * associated structure files.
335 * @return true if the entry was added, false if updated
337 public boolean addPDBId(PDBEntry entry);
340 * update the list of PDBEntrys to include any DBRefEntrys citing structural
343 * @return true if PDBEntry list was modified
345 public boolean updatePDBIds();
347 public String getVamsasId();
349 public void setVamsasId(String id);
352 * set the array of Database references for the sequence.
355 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
356 * set are not normalised.
359 public void setDBRefs(DBRefEntry[] dbs);
361 public DBRefEntry[] getDBRefs();
364 * add the given entry to the list of DBRefs for this sequence, or replace a
365 * similar one if entry contains a map object and the existing one doesnt.
369 public void addDBRef(DBRefEntry entry);
372 * Adds the given sequence feature and returns true, or returns false if it is
373 * already present on the sequence, or if the feature type is null.
378 public boolean addSequenceFeature(SequenceFeature sf);
380 public void deleteFeature(SequenceFeature sf);
382 public void setDatasetSequence(SequenceI seq);
384 public SequenceI getDatasetSequence();
387 * Returns a new array containing this sequence's annotations, or null.
389 public AlignmentAnnotation[] getAnnotation();
392 * Returns true if this sequence has the given annotation (by object
395 public boolean hasAnnotation(AlignmentAnnotation ann);
398 * Add the given annotation, if not already added, and set its sequence ref to
399 * be this sequence. Does nothing if this sequence's annotations already
400 * include this annotation (by identical object reference).
402 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
404 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
407 * Derive a sequence (using this one's dataset or as the dataset)
409 * @return duplicate sequence with valid dataset sequence
411 public SequenceI deriveSequence();
414 * set the array of associated AlignmentAnnotation for this sequenceI
418 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
421 * Get one or more alignment annotations with a particular label.
424 * string which each returned annotation must have as a label.
425 * @return null or array of annotations.
427 public AlignmentAnnotation[] getAnnotation(String label);
430 * Returns a (possibly empty) list of any annotations that match on given
431 * calcId (source) and label (type). Null values do not match.
436 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
440 * create a new dataset sequence (if necessary) for this sequence and sets
441 * this sequence to refer to it. This call will move any features or
442 * references on the sequence onto the dataset. It will also make a duplicate
443 * of existing annotation rows for the dataset sequence, rather than relocate
444 * them in order to preserve external references (since 2.8.2).
446 * @return dataset sequence for this sequence
448 public SequenceI createDatasetSequence();
451 * Transfer any database references or annotation from entry under a sequence
453 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
458 * null or mapping from entry's numbering to local start/end
460 public void transferAnnotation(SequenceI entry, Mapping mp);
463 * @return The RNA of the sequence in the alignment
472 public void setRNA(RNA rna);
476 * @return list of insertions (gap characters) in sequence
478 public List<int[]> getInsertions();
481 * Given a pdbId String, return the equivalent PDBEntry if available in the
487 public PDBEntry getPDBEntry(String pdbId);
490 * Get all primary database/accessions for this sequence's data. These
491 * DBRefEntry are expected to resolve to a valid record in the associated
492 * external database, either directly or via a provided 1:1 Mapping.
494 * @return just the primary references (if any) for this sequence, or an empty
497 public List<DBRefEntry> getPrimaryDBRefs();
500 * Returns a (possibly empty) list of sequence features that overlap the given
501 * alignment column range, optionally restricted to one or more specified
502 * feature types. If the range is all gaps, then features which enclose it are
503 * included (but not contact features).
506 * start column of range inclusive (1..)
508 * end column of range inclusive (1..)
510 * optional feature types to restrict results to
513 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
516 * Method to call to indicate that the sequence (characters or alignment/gaps)
517 * has been modified. Provided to allow any cursors on residue/column
518 * positions to be invalidated.
520 void sequenceChanged();
524 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
527 BitSet getInsertionsAsBits();
530 * Replaces every occurrence of c1 in the sequence with c2 and returns the
531 * number of characters changed
536 public int replace(char c1, char c2);
539 * Answers the GeneLociI, or null if not known
543 GeneLociI getGeneLoci();
546 * Sets the mapping to gene loci for the sequence
550 * @param chromosomeId
553 void setGeneLoci(String speciesId, String assemblyId,
554 String chromosomeId, MapList map);
558 * Returns the sequence string constructed from the substrings of a sequence
559 * defined by the int[] ranges provided by an iterator. E.g. the iterator
560 * could iterate over all visible regions of the alignment
563 * the iterator to use
564 * @return a String corresponding to the sequence
566 public String getSequenceStringFromIterator(Iterator<int[]> it);
569 * Locate the first position in this sequence which is not contained in an
570 * iterator region. If no such position exists, return 0
573 * iterator over regions
574 * @return first residue not contained in regions
576 public int firstResidueOutsideIterator(Iterator<int[]> it);