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.Iterator;
27 import java.util.List;
28 import java.util.Vector;
30 import fr.orsay.lri.varna.models.rna.RNA;
33 * Methods for manipulating a sequence, its metadata and related annotation in
34 * an alignment or dataset.
39 public interface SequenceI extends ASequenceI
42 * Set the display name for the sequence
46 public void setName(String name);
49 * Get the display name
51 public String getName();
54 * Set start position of first non-gapped symbol in sequence
59 public void setStart(int start);
62 * get start position of first non-gapped residue in sequence
66 public int getStart();
69 * get the displayed id of the sequence
71 * @return true means the id will be returned in the form
72 * DisplayName/Start-End
74 public String getDisplayId(boolean jvsuffix);
77 * set end position for last residue in sequence
81 public void setEnd(int end);
84 * get end position for last residue in sequence getEnd()>getStart() unless
85 * sequence only consists of gap characters
92 * @return length of sequence including gaps
95 public int getLength();
98 * Replace the sequence with the given string
101 * new sequence string
103 public void setSequence(String sequence);
106 * @return sequence as string
108 public String getSequenceAsString();
111 * get a range on the sequence as a string
114 * position relative to start of sequence including gaps (from 0)
116 * position relative to start of sequence including gaps (from 0)
118 * @return String containing all gap and symbols in specified range
120 public String getSequenceAsString(int start, int end);
123 * Answers a copy of the sequence as a character array
127 public char[] getSequence();
130 * get stretch of sequence characters in an array
133 * absolute index into getSequence()
135 * exclusive index of last position in segment to be returned.
137 * @return char[max(0,end-start)];
139 public char[] getSequence(int start, int end);
142 * create a new sequence object with a subsequence of this one but sharing the
143 * same dataset sequence
146 * int index for start position (base 0, inclusive)
148 * int index for end position (base 0, exclusive)
151 * @note implementations may use getSequence to get the sequence data
153 public SequenceI getSubSequence(int start, int end);
156 * get the i'th character in this sequence's local reference frame (ie from
157 * 0-number of characters lying from start-end)
161 * @return character or ' '
163 public char getCharAt(int i);
171 public void setDescription(String desc);
176 * @return DOCUMENT ME!
178 public String getDescription();
181 * Return the alignment column (from 1..) for a sequence position
184 * lying from start to end
186 * @return aligned column for residue (0 if residue is upstream from
187 * alignment, -1 if residue is downstream from alignment) note.
188 * Sequence object returns sequence.getEnd() for positions upstream
189 * currently. TODO: change sequence for
190 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
193 public int findIndex(int pos);
196 * Returns the sequence position for an alignment (column) position. If at a
197 * gap, returns the position of the next residue to the right. If beyond the
198 * end of the sequence, returns 1 more than the last residue position.
201 * column index in alignment (from 0..<length)
205 public int findPosition(int i);
208 * Returns the from-to sequence positions (start..) for the given column
209 * positions (1..), or null if no residues are included in the range
215 public Range findPositions(int fromColum, int toColumn);
218 * Returns an int array where indices correspond to each residue in the
219 * sequence and the element value gives its position in the alignment
221 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
222 * residues in SequenceI object
224 public int[] gapMap();
227 * Build a bitset corresponding to sequence gaps
229 * @return a BitSet where set values correspond to gaps in the sequence
231 public BitSet gapBitset();
234 * Returns an int array where indices correspond to each position in sequence
235 * char array and the element value gives the result of findPosition for that
236 * index in the sequence.
238 * @return int[SequenceI.getLength()]
240 public int[] findPositionMap();
243 * Answers true if the sequence is composed of amino acid characters. Note
244 * that implementations may use heuristic methods which are not guaranteed to
245 * give the biologically 'right' answer.
249 public boolean isProtein();
252 * Delete a range of aligned sequence columns, creating a new dataset sequence
253 * if necessary and adjusting start and end positions accordingly.
256 * first column in range to delete (inclusive)
258 * last column in range to delete (exclusive)
260 public void deleteChars(int i, int j);
266 * alignment column number
268 * character to insert
270 public void insertCharAt(int i, char c);
273 * insert given character at alignment column position
276 * alignment column number
280 * character to insert
282 public void insertCharAt(int position, int count, char ch);
285 * Answers a list of all sequence features associated with this sequence. The
286 * list may be held by the sequence's dataset sequence if that is defined.
290 public List<SequenceFeature> getSequenceFeatures();
293 * Answers the object holding features for the sequence
297 SequenceFeaturesI getFeatures();
300 * Replaces the sequence features associated with this sequence with the given
301 * features. If this sequence has a dataset sequence, then this method will
302 * update the dataset sequence's features instead.
306 public void setSequenceFeatures(List<SequenceFeature> features);
314 public void setPDBId(Vector<PDBEntry> ids);
319 * @return DOCUMENT ME!
321 public Vector<PDBEntry> getAllPDBEntries();
324 * Adds the entry to the *normalised* list of PDBIds.
326 * If a PDBEntry is passed with the same entry.getID() string as one already
327 * in the list, or one is added that appears to be the same but has a chain ID
328 * appended, then the existing PDBEntry will be updated with the new
329 * attributes instead, unless the entries have distinct chain codes or
330 * associated structure files.
333 * @return true if the entry was added, false if updated
335 public boolean addPDBId(PDBEntry entry);
338 * update the list of PDBEntrys to include any DBRefEntrys citing structural
341 * @return true if PDBEntry list was modified
343 public boolean updatePDBIds();
345 public String getVamsasId();
347 public void setVamsasId(String id);
350 * set the array of Database references for the sequence.
353 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
354 * set are not normalised.
357 public void setDBRefs(DBRefEntry[] dbs);
359 public DBRefEntry[] getDBRefs();
362 * add the given entry to the list of DBRefs for this sequence, or replace a
363 * similar one if entry contains a map object and the existing one doesnt.
367 public void addDBRef(DBRefEntry entry);
370 * Adds the given sequence feature and returns true, or returns false if it is
371 * already present on the sequence, or if the feature type is null.
376 public boolean addSequenceFeature(SequenceFeature sf);
378 public void deleteFeature(SequenceFeature sf);
380 public void setDatasetSequence(SequenceI seq);
382 public SequenceI getDatasetSequence();
385 * Returns a new array containing this sequence's annotations, or null.
387 public AlignmentAnnotation[] getAnnotation();
390 * Returns true if this sequence has the given annotation (by object
393 public boolean hasAnnotation(AlignmentAnnotation ann);
396 * Add the given annotation, if not already added, and set its sequence ref to
397 * be this sequence. Does nothing if this sequence's annotations already
398 * include this annotation (by identical object reference).
400 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
402 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
405 * Derive a sequence (using this one's dataset or as the dataset)
407 * @return duplicate sequence with valid dataset sequence
409 public SequenceI deriveSequence();
412 * set the array of associated AlignmentAnnotation for this sequenceI
416 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
419 * Get one or more alignment annotations with a particular label.
422 * string which each returned annotation must have as a label.
423 * @return null or array of annotations.
425 public AlignmentAnnotation[] getAnnotation(String label);
428 * Returns a (possibly empty) list of any annotations that match on given
429 * calcId (source) and label (type). Null values do not match.
434 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
438 * create a new dataset sequence (if necessary) for this sequence and sets
439 * this sequence to refer to it. This call will move any features or
440 * references on the sequence onto the dataset. It will also make a duplicate
441 * of existing annotation rows for the dataset sequence, rather than relocate
442 * them in order to preserve external references (since 2.8.2).
444 * @return dataset sequence for this sequence
446 public SequenceI createDatasetSequence();
449 * Transfer any database references or annotation from entry under a sequence
451 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
456 * null or mapping from entry's numbering to local start/end
458 public void transferAnnotation(SequenceI entry, Mapping mp);
461 * @return The RNA of the sequence in the alignment
470 public void setRNA(RNA rna);
474 * @return list of insertions (gap characters) in sequence
476 public List<int[]> getInsertions();
479 * Given a pdbId String, return the equivalent PDBEntry if available in the
485 public PDBEntry getPDBEntry(String pdbId);
488 * Get all primary database/accessions for this sequence's data. These
489 * DBRefEntry are expected to resolve to a valid record in the associated
490 * external database, either directly or via a provided 1:1 Mapping.
492 * @return just the primary references (if any) for this sequence, or an empty
495 public List<DBRefEntry> getPrimaryDBRefs();
498 * Returns a (possibly empty) list of sequence features that overlap the given
499 * alignment column range, optionally restricted to one or more specified
500 * feature types. If the range is all gaps, then features which enclose it are
501 * included (but not contact features).
504 * start column of range inclusive (1..)
506 * end column of range inclusive (1..)
508 * optional feature types to restrict results to
511 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
514 * Method to call to indicate that the sequence (characters or alignment/gaps)
515 * has been modified. Provided to allow any cursors on residue/column
516 * positions to be invalidated.
518 void sequenceChanged();
522 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
525 BitSet getInsertionsAsBits();
528 * Replaces every occurrence of c1 in the sequence with c2 and returns the
529 * number of characters changed
534 public int replace(char c1, char c2);
537 * Returns the sequence string constructed from the substrings of a sequence
538 * defined by the int[] ranges provided by an iterator. E.g. the iterator
539 * could iterate over all visible regions of the alignment
542 * the iterator to use
543 * @return a String corresponding to the sequence
545 public String getSequenceStringFromIterator(Iterator<int[]> it);
548 * Locate the first position in this sequence which is not contained in an
549 * iterator region. If no such position exists, return 0
552 * iterator over regions
553 * @return first residue not contained in regions
555 public int firstResidueOutsideIterator(Iterator<int[]> it);