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);
52 * Get the display name
54 public String getName();
57 * Set start position of first non-gapped symbol in sequence
62 public void setStart(int start);
65 * get start position of first non-gapped residue in sequence
69 public int getStart();
72 * get the displayed id of the sequence
74 * @return true means the id will be returned in the form
75 * DisplayName/Start-End
77 public String getDisplayId(boolean jvsuffix);
80 * set end position for last residue in sequence
84 public void setEnd(int end);
87 * get end position for last residue in sequence getEnd()>getStart() unless
88 * sequence only consists of gap characters
95 * @return length of sequence including gaps
98 public int getLength();
101 * Replace the sequence with the given string
104 * new sequence string
106 public void setSequence(String sequence);
109 * @return sequence as string
111 public String getSequenceAsString();
114 * get a range on the sequence as a string
117 * (inclusive) position relative to start of sequence including gaps
120 * (exclusive) position relative to start of sequence including gaps
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 sequence positions for first and last residues lying within the
214 * given column positions [fromColum,toColumn] (where columns are numbered
215 * from 1), or null if no residues are included in the range
218 * - first column base 1
220 * - last column, base 1
223 public ContiguousI findPositions(int fromColum, int toColumn);
226 * Returns an int array where indices correspond to each residue in the
227 * sequence and the element value gives its position in the alignment
229 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
230 * residues in SequenceI object
232 public int[] gapMap();
235 * Build a bitset corresponding to sequence gaps
237 * @return a BitSet where set values correspond to gaps in the sequence
239 public BitSet gapBitset();
242 * Returns an int array where indices correspond to each position in sequence
243 * char array and the element value gives the result of findPosition for that
244 * index in the sequence.
246 * @return int[SequenceI.getLength()]
248 public int[] findPositionMap();
251 * Answers true if the sequence is composed of amino acid characters. Note
252 * that implementations may use heuristic methods which are not guaranteed to
253 * give the biologically 'right' answer.
257 public boolean isProtein();
260 * Delete a range of aligned sequence columns, creating a new dataset sequence
261 * if necessary and adjusting start and end positions accordingly.
264 * first column in range to delete (inclusive)
266 * last column in range to delete (exclusive)
268 public void deleteChars(int i, int j);
274 * alignment column number
276 * character to insert
278 public void insertCharAt(int i, char c);
281 * insert given character at alignment column position
284 * alignment column number
288 * character to insert
290 public void insertCharAt(int position, int count, char ch);
293 * Answers a list of all sequence features associated with this sequence. The
294 * list may be held by the sequence's dataset sequence if that is defined.
298 public List<SequenceFeature> getSequenceFeatures();
301 * Answers the object holding features for the sequence
305 SequenceFeaturesI getFeatures();
308 * Replaces the sequence features associated with this sequence with the given
309 * features. If this sequence has a dataset sequence, then this method will
310 * update the dataset sequence's features instead.
314 public void setSequenceFeatures(List<SequenceFeature> features);
322 public void setPDBId(Vector<PDBEntry> ids);
327 * @return DOCUMENT ME!
329 public Vector<PDBEntry> getAllPDBEntries();
332 * Adds the entry to the *normalised* list of PDBIds.
334 * If a PDBEntry is passed with the same entry.getID() string as one already
335 * in the list, or one is added that appears to be the same but has a chain ID
336 * appended, then the existing PDBEntry will be updated with the new
337 * attributes instead, unless the entries have distinct chain codes or
338 * associated structure files.
341 * @return true if the entry was added, false if updated
343 public boolean addPDBId(PDBEntry entry);
346 * update the list of PDBEntrys to include any DBRefEntrys citing structural
349 * @return true if PDBEntry list was modified
351 public boolean updatePDBIds();
353 public String getVamsasId();
355 public void setVamsasId(String id);
358 * set the array of Database references for the sequence.
360 * BH 2019.02.04 changes param to DBModlist
363 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
364 * set are not normalised.
365 * @throws InvalidArgumentException if the is not one created by Sequence itself
368 public void setDBRefs(DBModList<DBRefEntry> dbs);
370 public DBModList<DBRefEntry> getDBRefs();
373 * add the given entry to the list of DBRefs for this sequence, or replace a
374 * similar one if entry contains a map object and the existing one doesnt.
378 public void addDBRef(DBRefEntry entry);
381 * Adds the given sequence feature and returns true, or returns false if it is
382 * already present on the sequence, or if the feature type is null.
387 public boolean addSequenceFeature(SequenceFeature sf);
390 * Deletes the feature from the sequence (if found). To be precise, deletes
391 * the first feature {@code f} found where {@code f.equals(sf)}.
395 public void deleteFeature(SequenceFeature sf);
397 public void setDatasetSequence(SequenceI seq);
399 public SequenceI getDatasetSequence();
402 * Returns a new array containing this sequence's annotations, or null.
404 public AlignmentAnnotation[] getAnnotation();
407 * Returns true if this sequence has the given annotation (by object
410 public boolean hasAnnotation(AlignmentAnnotation ann);
413 * Add the given annotation, if not already added, and set its sequence ref to
414 * be this sequence. Does nothing if this sequence's annotations already
415 * include this annotation (by identical object reference).
417 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
419 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
422 * Derive a sequence (using this one's dataset or as the dataset)
424 * @return duplicate sequence with valid dataset sequence
426 public SequenceI deriveSequence();
429 * set the array of associated AlignmentAnnotation for this sequenceI
433 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
436 * Get one or more alignment annotations with a particular label.
439 * string which each returned annotation must have as a label.
440 * @return null or array of annotations.
442 public AlignmentAnnotation[] getAnnotation(String label);
445 * Returns a (possibly empty) list of any annotations that match on given
446 * calcId (source) and label (type). Null values do not match.
451 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
455 * create a new dataset sequence (if necessary) for this sequence and sets
456 * this sequence to refer to it. This call will move any features or
457 * references on the sequence onto the dataset. It will also make a duplicate
458 * of existing annotation rows for the dataset sequence, rather than relocate
459 * them in order to preserve external references (since 2.8.2).
461 * @return dataset sequence for this sequence
463 public SequenceI createDatasetSequence();
466 * Transfer any database references or annotation from entry under a sequence
468 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
473 * null or mapping from entry's numbering to local start/end
475 public void transferAnnotation(SequenceI entry, Mapping mp);
478 * @return The RNA of the sequence in the alignment
487 public void setRNA(RNA rna);
491 * @return list of insertions (gap characters) in sequence
493 public List<int[]> getInsertions();
496 * Given a pdbId String, return the equivalent PDBEntry if available in the
502 public PDBEntry getPDBEntry(String pdbId);
505 * Get all primary database/accessions for this sequence's data. These
506 * DBRefEntry are expected to resolve to a valid record in the associated
507 * external database, either directly or via a provided 1:1 Mapping.
509 * @return just the primary references (if any) for this sequence, or an empty
512 public List<DBRefEntry> getPrimaryDBRefs();
515 * Returns a (possibly empty) list of sequence features that overlap the given
516 * alignment column range, optionally restricted to one or more specified
517 * feature types. If the range is all gaps, then features which enclose it are
518 * included (but not contact features).
521 * start column of range inclusive (1..)
523 * end column of range inclusive (1..)
525 * optional feature types to restrict results to
528 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
531 * Method to call to indicate that the sequence (characters or alignment/gaps)
532 * has been modified. Provided to allow any cursors on residue/column
533 * positions to be invalidated.
535 void sequenceChanged();
539 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
542 BitSet getInsertionsAsBits();
545 * Replaces every occurrence of c1 in the sequence with c2 and returns the
546 * number of characters changed
551 public int replace(char c1, char c2);
554 * Answers the GeneLociI, or null if not known
558 GeneLociI getGeneLoci();
561 * Sets the mapping to gene loci for the sequence
565 * @param chromosomeId
568 void setGeneLoci(String speciesId, String assemblyId,
569 String chromosomeId, MapList map);
573 * Returns the sequence string constructed from the substrings of a sequence
574 * defined by the int[] ranges provided by an iterator. E.g. the iterator
575 * could iterate over all visible regions of the alignment
578 * the iterator to use
579 * @return a String corresponding to the sequence
581 public String getSequenceStringFromIterator(Iterator<int[]> it);
584 * Locate the first position in this sequence which is not contained in an
585 * iterator region. If no such position exists, return 0
588 * iterator over regions
589 * @return first residue not contained in regions
591 public int firstResidueOutsideIterator(Iterator<int[]> it);
594 * Answers a (possibly empty) list of features of the specified type that
595 * overlap the specified column position. If parameter {@code result} is not
596 * null, features are appended to it and the (possibly extended) list is
599 List<SequenceFeature> findFeatures(int column, String type,
600 List<SequenceFeature> result);
603 * Answers true if this store contains at least one feature, else false
607 public boolean hasFeatures(String type);