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;
25 import java.util.BitSet;
26 import java.util.List;
27 import java.util.Vector;
29 import fr.orsay.lri.varna.models.rna.RNA;
32 * Methods for manipulating a sequence, its metadata and related annotation in
33 * an alignment or dataset.
38 public interface SequenceI extends ASequenceI
41 * Set the display name for the sequence
45 public void setName(String name);
48 * Get the display name
50 public String getName();
53 * Set start position of first non-gapped symbol in sequence
58 public void setStart(int start);
61 * get start position of first non-gapped residue in sequence
65 public int getStart();
68 * get the displayed id of the sequence
70 * @return true means the id will be returned in the form
71 * DisplayName/Start-End
73 public String getDisplayId(boolean jvsuffix);
76 * set end position for last residue in sequence
80 public void setEnd(int end);
83 * get end position for last residue in sequence getEnd()>getStart() unless
84 * sequence only consists of gap characters
91 * @return length of sequence including gaps
94 public int getLength();
97 * Replace the sequence with the given string
100 * new sequence string
102 public void setSequence(String sequence);
105 * @return sequence as string
107 public String getSequenceAsString();
110 * get a range on the sequence as a string
113 * position relative to start of sequence including gaps (from 0)
115 * position relative to start of sequence including gaps (from 0)
117 * @return String containing all gap and symbols in specified range
119 public String getSequenceAsString(int start, int end);
122 * Answers a copy of the sequence as a character array
126 public char[] getSequence();
129 * get stretch of sequence characters in an array
132 * absolute index into getSequence()
134 * exclusive index of last position in segment to be returned.
136 * @return char[max(0,end-start)];
138 public char[] getSequence(int start, int end);
141 * create a new sequence object with a subsequence of this one but sharing the
142 * same dataset sequence
145 * int index for start position (base 0, inclusive)
147 * int index for end position (base 0, exclusive)
150 * @note implementations may use getSequence to get the sequence data
152 public SequenceI getSubSequence(int start, int end);
155 * get the i'th character in this sequence's local reference frame (ie from
156 * 0-number of characters lying from start-end)
160 * @return character or ' '
162 public char getCharAt(int i);
170 public void setDescription(String desc);
175 * @return DOCUMENT ME!
177 public String getDescription();
180 * Return the alignment column (from 1..) for a sequence position
183 * lying from start to end
185 * @return aligned column for residue (0 if residue is upstream from
186 * alignment, -1 if residue is downstream from alignment) note.
187 * Sequence object returns sequence.getEnd() for positions upstream
188 * currently. TODO: change sequence for
189 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
192 public int findIndex(int pos);
195 * Returns the sequence position for an alignment position.
198 * column index in alignment (from 0..<length)
200 * @return TODO: JAL-2562 - residue number for residue (left of and) nearest
203 public int findPosition(int i);
206 * Returns the from-to sequence positions (start..) for the given column
207 * positions (1..), or null if no residues are included in the range
213 public Range findPositions(int fromColum, int toColumn);
216 * Returns an int array where indices correspond to each residue in the
217 * sequence and the element value gives its position in the alignment
219 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
220 * residues in SequenceI object
222 public int[] gapMap();
225 * Build a bitset corresponding to sequence gaps
227 * @return a BitSet where set values correspond to gaps in the sequence
229 public BitSet gapBitset();
232 * Returns an int array where indices correspond to each position in sequence
233 * char array and the element value gives the result of findPosition for that
234 * index in the sequence.
236 * @return int[SequenceI.getLength()]
238 public int[] findPositionMap();
241 * Answers true if the sequence is composed of amino acid characters. Note
242 * that implementations may use heuristic methods which are not guaranteed to
243 * give the biologically 'right' answer.
247 public boolean isProtein();
250 * Delete a range of aligned sequence columns, creating a new dataset sequence
251 * if necessary and adjusting start and end positions accordingly.
254 * first column in range to delete (inclusive)
256 * last column in range to delete (exclusive)
258 public void deleteChars(int i, int j);
264 * alignment column number
266 * character to insert
268 public void insertCharAt(int i, char c);
271 * insert given character at alignment column position
274 * alignment column number
278 * character to insert
280 public void insertCharAt(int position, int count, char ch);
283 * Answers a list of all sequence features associated with this sequence. The
284 * list may be held by the sequence's dataset sequence if that is defined.
288 public List<SequenceFeature> getSequenceFeatures();
291 * Answers the object holding features for the sequence
295 SequenceFeaturesI getFeatures();
298 * Replaces the sequence features associated with this sequence with the given
299 * features. If this sequence has a dataset sequence, then this method will
300 * update the dataset sequence's features instead.
304 public void setSequenceFeatures(List<SequenceFeature> features);
312 public void setPDBId(Vector<PDBEntry> ids);
317 * @return DOCUMENT ME!
319 public Vector<PDBEntry> getAllPDBEntries();
322 * Adds the entry to the *normalised* list of PDBIds.
324 * If a PDBEntry is passed with the same entry.getID() string as one already
325 * in the list, or one is added that appears to be the same but has a chain ID
326 * appended, then the existing PDBEntry will be updated with the new
327 * attributes instead, unless the entries have distinct chain codes or
328 * associated structure files.
331 * @return true if the entry was added, false if updated
333 public boolean addPDBId(PDBEntry entry);
336 * update the list of PDBEntrys to include any DBRefEntrys citing structural
339 * @return true if PDBEntry list was modified
341 public boolean updatePDBIds();
343 public String getVamsasId();
345 public void setVamsasId(String id);
348 * set the array of Database references for the sequence.
351 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
352 * set are not normalised.
355 public void setDBRefs(DBRefEntry[] dbs);
357 public DBRefEntry[] getDBRefs();
360 * add the given entry to the list of DBRefs for this sequence, or replace a
361 * similar one if entry contains a map object and the existing one doesnt.
365 public void addDBRef(DBRefEntry entry);
368 * Adds the given sequence feature and returns true, or returns false if it is
369 * already present on the sequence, or if the feature type is null.
374 public boolean addSequenceFeature(SequenceFeature sf);
376 public void deleteFeature(SequenceFeature sf);
378 public void setDatasetSequence(SequenceI seq);
380 public SequenceI getDatasetSequence();
383 * Returns a new array containing this sequence's annotations, or null.
385 public AlignmentAnnotation[] getAnnotation();
388 * Returns true if this sequence has the given annotation (by object
391 public boolean hasAnnotation(AlignmentAnnotation ann);
394 * Add the given annotation, if not already added, and set its sequence ref to
395 * be this sequence. Does nothing if this sequence's annotations already
396 * include this annotation (by identical object reference).
398 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
400 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
403 * Derive a sequence (using this one's dataset or as the dataset)
405 * @return duplicate sequence with valid dataset sequence
407 public SequenceI deriveSequence();
410 * set the array of associated AlignmentAnnotation for this sequenceI
414 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
417 * Get one or more alignment annotations with a particular label.
420 * string which each returned annotation must have as a label.
421 * @return null or array of annotations.
423 public AlignmentAnnotation[] getAnnotation(String label);
426 * Returns a (possibly empty) list of any annotations that match on given
427 * calcId (source) and label (type). Null values do not match.
432 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
436 * create a new dataset sequence (if necessary) for this sequence and sets
437 * this sequence to refer to it. This call will move any features or
438 * references on the sequence onto the dataset. It will also make a duplicate
439 * of existing annotation rows for the dataset sequence, rather than relocate
440 * them in order to preserve external references (since 2.8.2).
442 * @return dataset sequence for this sequence
444 public SequenceI createDatasetSequence();
447 * Transfer any database references or annotation from entry under a sequence
449 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
454 * null or mapping from entry's numbering to local start/end
456 public void transferAnnotation(SequenceI entry, Mapping mp);
460 * The sequence index in the MSA
462 public void setIndex(int index);
465 * @return The index of the sequence in the alignment
467 public int getIndex();
470 * @return The RNA of the sequence in the alignment
479 public void setRNA(RNA rna);
483 * @return list of insertions (gap characters) in sequence
485 public List<int[]> getInsertions();
488 * Given a pdbId String, return the equivalent PDBEntry if available in the
494 public PDBEntry getPDBEntry(String pdbId);
497 * Get all primary database/accessions for this sequence's data. These
498 * DBRefEntry are expected to resolve to a valid record in the associated
499 * external database, either directly or via a provided 1:1 Mapping.
501 * @return just the primary references (if any) for this sequence, or an empty
504 public List<DBRefEntry> getPrimaryDBRefs();
507 * Returns a (possibly empty) list of sequence features that overlap the given
508 * alignment column range, optionally restricted to one or more specified
509 * feature types. If the range is all gaps, then features which enclose it are
510 * included (but not contact features).
513 * start column of range inclusive (1..)
515 * end column of range inclusive (1..)
517 * optional feature types to restrict results to
520 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
523 * Method to call to indicate that the sequence (characters or alignment/gaps)
524 * has been modified. Provided to allow any cursors on residue/column
525 * positions to be invalidated.
527 void sequenceChanged();
531 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
534 BitSet getInsertionsAsBits();
537 * Replaces every occurrence of c1 in the sequence with c2 and returns the
538 * number of characters changed
543 public int replace(char c1, char c2);