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 java.util.BitSet;
24 import java.util.Iterator;
25 import java.util.List;
26 import java.util.Vector;
28 import fr.orsay.lri.varna.models.rna.RNA;
29 import jalview.datamodel.Sequence.DBModList;
30 import jalview.datamodel.features.SequenceFeaturesI;
31 import jalview.util.MapList;
32 import jalview.ws.params.InvalidArgumentException;
35 * Methods for manipulating a sequence, its metadata and related annotation in
36 * an alignment or dataset.
41 public interface SequenceI extends ASequenceI, ContactMapHolderI
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 * (inclusive) position relative to start of sequence including gaps
119 * (exclusive) position relative to start of sequence including gaps
122 * @return String containing all gap and symbols in specified range
124 public String getSequenceAsString(int start, int end);
127 * Answers a copy of the sequence as a character array
131 public char[] getSequence();
134 * get stretch of sequence characters in an array
137 * absolute index into getSequence()
139 * exclusive index of last position in segment to be returned.
141 * @return char[max(0,end-start)];
143 public char[] getSequence(int start, int end);
146 * create a new sequence object with a subsequence of this one but sharing the
147 * same dataset sequence
150 * int index for start position (base 0, inclusive)
152 * int index for end position (base 0, exclusive)
155 * @note implementations may use getSequence to get the sequence data
157 public SequenceI getSubSequence(int start, int end);
160 * get the i'th character in this sequence's local reference frame (ie from
161 * 0-number of characters lying from start-end)
165 * @return character or ' '
167 public char getCharAt(int i);
175 public void setDescription(String desc);
180 * @return DOCUMENT ME!
182 public String getDescription();
185 * Return the alignment column (from 1..) for a sequence position
188 * lying from start to end
190 * @return aligned column for residue (0 if residue is upstream from
191 * alignment, -1 if residue is downstream from alignment) note.
192 * Sequence object returns sequence.getEnd() for positions upstream
193 * currently. TODO: change sequence for
194 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
197 public int findIndex(int pos);
200 * Returns the sequence position for an alignment (column) position. If at a
201 * gap, returns the position of the next residue to the right. If beyond the
202 * end of the sequence, returns 1 more than the last residue position.
205 * column index in alignment (from 0..<length)
209 public int findPosition(int i);
212 * Returns the sequence positions for first and last residues lying within the
213 * given column positions [fromColum,toColumn] (where columns are numbered
214 * from 1), or null if no residues are included in the range
217 * - first column base 1
219 * - last column, base 1
222 public ContiguousI findPositions(int fromColum, int toColumn);
225 * Returns an int array where indices correspond to each residue in the
226 * sequence and the element value gives its position in the alignment
228 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
229 * residues in SequenceI object
231 public int[] gapMap();
234 * Build a bitset corresponding to sequence gaps
236 * @return a BitSet where set values correspond to gaps in the sequence
238 public BitSet gapBitset();
241 * Returns an int array where indices correspond to each position in sequence
242 * char array and the element value gives the result of findPosition for that
243 * index in the sequence.
245 * @return int[SequenceI.getLength()]
247 public int[] findPositionMap();
250 * Answers true if the sequence is composed of amino acid characters. Note
251 * that implementations may use heuristic methods which are not guaranteed to
252 * give the biologically 'right' answer.
256 public boolean isProtein();
259 * Delete a range of aligned sequence columns, creating a new dataset sequence
260 * if necessary and adjusting start and end positions accordingly.
263 * first column in range to delete (inclusive)
265 * last column in range to delete (exclusive)
267 public void deleteChars(int i, int j);
273 * alignment column number
275 * character to insert
277 public void insertCharAt(int i, char c);
280 * insert given character at alignment column position
283 * alignment column number
287 * character to insert
289 public void insertCharAt(int position, int count, char ch);
292 * Answers a list of all sequence features associated with this sequence. The
293 * list may be held by the sequence's dataset sequence if that is defined.
297 public List<SequenceFeature> getSequenceFeatures();
300 * Answers the object holding features for the sequence
304 SequenceFeaturesI getFeatures();
307 * Replaces the sequence features associated with this sequence with the given
308 * features. If this sequence has a dataset sequence, then this method will
309 * update the dataset sequence's features instead.
313 public void setSequenceFeatures(List<SequenceFeature> features);
321 public void setPDBId(Vector<PDBEntry> ids);
326 * @return DOCUMENT ME!
328 public Vector<PDBEntry> getAllPDBEntries();
331 * Adds the entry to the *normalised* list of PDBIds.
333 * If a PDBEntry is passed with the same entry.getID() string as one already
334 * in the list, or one is added that appears to be the same but has a chain ID
335 * appended, then the existing PDBEntry will be updated with the new
336 * attributes instead, unless the entries have distinct chain codes or
337 * associated structure files.
340 * @return true if the entry was added, false if updated
342 public boolean addPDBId(PDBEntry entry);
345 * update the list of PDBEntrys to include any DBRefEntrys citing structural
348 * @return true if PDBEntry list was modified
350 public boolean updatePDBIds();
352 public String getVamsasId();
354 public void setVamsasId(String id);
357 * set the array of Database references for the sequence.
359 * BH 2019.02.04 changes param to DBModlist
362 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
363 * set are not normalised.
364 * @throws InvalidArgumentException
365 * 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);
389 public void deleteFeature(SequenceFeature sf);
391 public void setDatasetSequence(SequenceI seq);
393 public SequenceI getDatasetSequence();
396 * Returns a new array containing this sequence's annotations, or null.
398 public AlignmentAnnotation[] getAnnotation();
401 * Returns true if this sequence has the given annotation (by object
404 public boolean hasAnnotation(AlignmentAnnotation ann);
407 * Add the given annotation, if not already added, and set its sequence ref to
408 * be this sequence. Does nothing if this sequence's annotations already
409 * include this annotation (by identical object reference).
411 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
413 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
416 * Derive a sequence (using this one's dataset or as the dataset)
418 * @return duplicate sequence and any annotation present with valid dataset
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 * Returns a (possibly empty) list of any annotations that match on given
451 * calcId (source), label (type) and description (observation instance). Null
452 * values do not match.
458 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
459 String label, String description);
462 * create a new dataset sequence (if necessary) for this sequence and sets
463 * this sequence to refer to it. This call will move any features or
464 * references on the sequence onto the dataset. It will also make a duplicate
465 * of existing annotation rows for the dataset sequence, rather than relocate
466 * them in order to preserve external references (since 2.8.2).
468 * @return dataset sequence for this sequence
470 public SequenceI createDatasetSequence();
473 * Transfer any database references or annotation from entry under a sequence
475 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
480 * null or mapping from entry's numbering to local start/end
482 public void transferAnnotation(SequenceI entry, Mapping mp);
485 * @return The RNA of the sequence in the alignment
494 public void setRNA(RNA rna);
498 * @return list of insertions (gap characters) in sequence
500 public List<int[]> getInsertions();
503 * Given a pdbId String, return the equivalent PDBEntry if available in the
509 public PDBEntry getPDBEntry(String pdbId);
512 * Get all primary database/accessions for this sequence's data. These
513 * DBRefEntry are expected to resolve to a valid record in the associated
514 * external database, either directly or via a provided 1:1 Mapping.
516 * @return just the primary references (if any) for this sequence, or an empty
519 public List<DBRefEntry> getPrimaryDBRefs();
522 * Returns a (possibly empty) list of sequence features that overlap the given
523 * alignment column range, optionally restricted to one or more specified
524 * feature types. If the range is all gaps, then features which enclose it are
525 * included (but not contact features).
528 * start column of range inclusive (1..)
530 * end column of range inclusive (1..)
532 * optional feature types to restrict results to
535 List<SequenceFeature> findFeatures(int fromCol, int toCol,
539 * Method to call to indicate that the sequence (characters or alignment/gaps)
540 * has been modified. Provided to allow any cursors on residue/column
541 * positions to be invalidated.
543 void sequenceChanged();
547 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
550 BitSet getInsertionsAsBits();
553 * Replaces every occurrence of c1 in the sequence with c2 and returns the
554 * number of characters changed
559 public int replace(char c1, char c2);
562 * Answers the GeneLociI, or null if not known
566 GeneLociI getGeneLoci();
569 * Sets the mapping to gene loci for the sequence
573 * @param chromosomeId
576 void setGeneLoci(String speciesId, String assemblyId, String chromosomeId,
580 * Returns the sequence string constructed from the substrings of a sequence
581 * defined by the int[] ranges provided by an iterator. E.g. the iterator
582 * could iterate over all visible regions of the alignment
585 * the iterator to use
586 * @return a String corresponding to the sequence
588 public String getSequenceStringFromIterator(Iterator<int[]> it);
591 * Locate the first position in this sequence which is not contained in an
592 * iterator region. If no such position exists, return 0
595 * iterator over regions
596 * @return first residue not contained in regions
598 public int firstResidueOutsideIterator(Iterator<int[]> it);
600 public void addContactListFor(AlignmentAnnotation annotation,