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;
34 * Methods for manipulating a sequence, its metadata and related annotation in
35 * an alignment or dataset.
40 public interface SequenceI extends ASequenceI
43 * Set the display name for the sequence
47 public void setName(String name);
50 * Get the display name
52 public String getName();
55 * Set start position of first non-gapped symbol in sequence
60 public void setStart(int start);
63 * get start position of first non-gapped residue in sequence
67 public int getStart();
70 * get the displayed id of the sequence
72 * @return true means the id will be returned in the form
73 * DisplayName/Start-End
75 public String getDisplayId(boolean jvsuffix);
78 * set end position for last residue in sequence
82 public void setEnd(int end);
85 * get end position for last residue in sequence getEnd()>getStart() unless
86 * sequence only consists of gap characters
93 * @return length of sequence including gaps
96 public int getLength();
99 * Replace the sequence with the given string
102 * new sequence string
104 public void setSequence(String sequence);
107 * @return sequence as string
109 public String getSequenceAsString();
112 * get a range on the sequence as a string
115 * (inclusive) position relative to start of sequence including gaps
118 * (exclusive) position relative to start of sequence including gaps
121 * @return String containing all gap and symbols in specified range
123 public String getSequenceAsString(int start, int end);
126 * Answers a copy of the sequence as a character array
130 public char[] getSequence();
133 * get stretch of sequence characters in an array
136 * absolute index into getSequence()
138 * exclusive index of last position in segment to be returned.
140 * @return char[max(0,end-start)];
142 public char[] getSequence(int start, int end);
145 * create a new sequence object with a subsequence of this one but sharing the
146 * same dataset sequence
149 * int index for start position (base 0, inclusive)
151 * int index for end position (base 0, exclusive)
154 * @note implementations may use getSequence to get the sequence data
156 public SequenceI getSubSequence(int start, int end);
159 * get the i'th character in this sequence's local reference frame (ie from
160 * 0-number of characters lying from start-end)
164 * @return character or ' '
166 public char getCharAt(int i);
174 public void setDescription(String desc);
179 * @return DOCUMENT ME!
181 public String getDescription();
184 * Return the alignment column (from 1..) for a sequence position
187 * lying from start to end
189 * @return aligned column for residue (0 if residue is upstream from
190 * alignment, -1 if residue is downstream from alignment) note.
191 * Sequence object returns sequence.getEnd() for positions upstream
192 * currently. TODO: change sequence for
193 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
196 public int findIndex(int pos);
199 * Returns the sequence position for an alignment (column) position. If at a
200 * gap, returns the position of the next residue to the right. If beyond the
201 * end of the sequence, returns 1 more than the last residue position.
204 * column index in alignment (from 0..<length)
208 public int findPosition(int i);
211 * Returns the from-to sequence positions (start..) for the given column
212 * positions (1..), or null if no residues are included in the range
218 public Range findPositions(int fromColum, int toColumn);
221 * Returns an int array where indices correspond to each residue in the
222 * sequence and the element value gives its position in the alignment
224 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
225 * residues in SequenceI object
227 public int[] gapMap();
230 * Build a bitset corresponding to sequence gaps
232 * @return a BitSet where set values correspond to gaps in the sequence
234 public BitSet gapBitset();
237 * Returns an int array where indices correspond to each position in sequence
238 * char array and the element value gives the result of findPosition for that
239 * index in the sequence.
241 * @return int[SequenceI.getLength()]
243 public int[] findPositionMap();
246 * Answers true if the sequence is composed of amino acid characters. Note
247 * that implementations may use heuristic methods which are not guaranteed to
248 * give the biologically 'right' answer.
252 public boolean isProtein();
255 * Delete a range of aligned sequence columns, creating a new dataset sequence
256 * if necessary and adjusting start and end positions accordingly.
259 * first column in range to delete (inclusive)
261 * last column in range to delete (exclusive)
263 public void deleteChars(int i, int j);
269 * alignment column number
271 * character to insert
273 public void insertCharAt(int i, char c);
276 * insert given character at alignment column position
279 * alignment column number
283 * character to insert
285 public void insertCharAt(int position, int count, char ch);
288 * Answers a list of all sequence features associated with this sequence. The
289 * list may be held by the sequence's dataset sequence if that is defined.
293 public List<SequenceFeature> getSequenceFeatures();
296 * Answers the object holding features for the sequence
300 SequenceFeaturesI getFeatures();
303 * Replaces the sequence features associated with this sequence with the given
304 * features. If this sequence has a dataset sequence, then this method will
305 * update the dataset sequence's features instead.
309 public void setSequenceFeatures(List<SequenceFeature> features);
317 public void setPDBId(Vector<PDBEntry> ids);
322 * @return DOCUMENT ME!
324 public Vector<PDBEntry> getAllPDBEntries();
327 * Adds the entry to the *normalised* list of PDBIds.
329 * If a PDBEntry is passed with the same entry.getID() string as one already
330 * in the list, or one is added that appears to be the same but has a chain ID
331 * appended, then the existing PDBEntry will be updated with the new
332 * attributes instead, unless the entries have distinct chain codes or
333 * associated structure files.
336 * @return true if the entry was added, false if updated
338 public boolean addPDBId(PDBEntry entry);
341 * update the list of PDBEntrys to include any DBRefEntrys citing structural
344 * @return true if PDBEntry list was modified
346 public boolean updatePDBIds();
348 public String getVamsasId();
350 public void setVamsasId(String id);
353 * set the array of Database references for the sequence.
356 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
357 * set are not normalised.
360 public void setDBRefs(DBRefEntry[] dbs);
362 public DBRefEntry[] getDBRefs();
365 * add the given entry to the list of DBRefs for this sequence, or replace a
366 * similar one if entry contains a map object and the existing one doesnt.
370 public void addDBRef(DBRefEntry entry);
373 * Adds the given sequence feature and returns true, or returns false if it is
374 * already present on the sequence, or if the feature type is null.
379 public boolean addSequenceFeature(SequenceFeature sf);
381 public void deleteFeature(SequenceFeature sf);
383 public void setDatasetSequence(SequenceI seq);
385 public SequenceI getDatasetSequence();
388 * Returns a new array containing this sequence's annotations, or null.
390 public AlignmentAnnotation[] getAnnotation();
393 * Returns true if this sequence has the given annotation (by object
396 public boolean hasAnnotation(AlignmentAnnotation ann);
399 * Add the given annotation, if not already added, and set its sequence ref to
400 * be this sequence. Does nothing if this sequence's annotations already
401 * include this annotation (by identical object reference).
403 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
405 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
408 * Derive a sequence (using this one's dataset or as the dataset)
410 * @return duplicate sequence with valid dataset sequence
412 public SequenceI deriveSequence();
415 * set the array of associated AlignmentAnnotation for this sequenceI
419 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
422 * Get one or more alignment annotations with a particular label.
425 * string which each returned annotation must have as a label.
426 * @return null or array of annotations.
428 public AlignmentAnnotation[] getAnnotation(String label);
431 * Returns a (possibly empty) list of any annotations that match on given
432 * calcId (source) and label (type). Null values do not match.
437 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
441 * create a new dataset sequence (if necessary) for this sequence and sets
442 * this sequence to refer to it. This call will move any features or
443 * references on the sequence onto the dataset. It will also make a duplicate
444 * of existing annotation rows for the dataset sequence, rather than relocate
445 * them in order to preserve external references (since 2.8.2).
447 * @return dataset sequence for this sequence
449 public SequenceI createDatasetSequence();
452 * Transfer any database references or annotation from entry under a sequence
454 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
459 * null or mapping from entry's numbering to local start/end
461 public void transferAnnotation(SequenceI entry, Mapping mp);
464 * @return The RNA of the sequence in the alignment
473 public void setRNA(RNA rna);
477 * @return list of insertions (gap characters) in sequence
479 public List<int[]> getInsertions();
482 * Given a pdbId String, return the equivalent PDBEntry if available in the
488 public PDBEntry getPDBEntry(String pdbId);
491 * Get all primary database/accessions for this sequence's data. These
492 * DBRefEntry are expected to resolve to a valid record in the associated
493 * external database, either directly or via a provided 1:1 Mapping.
495 * @return just the primary references (if any) for this sequence, or an empty
498 public List<DBRefEntry> getPrimaryDBRefs();
501 * Returns a (possibly empty) list of sequence features that overlap the given
502 * alignment column range, optionally restricted to one or more specified
503 * feature types. If the range is all gaps, then features which enclose it are
504 * included (but not contact features).
507 * start column of range inclusive (1..)
509 * end column of range inclusive (1..)
511 * optional feature types to restrict results to
514 List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
517 * Method to call to indicate that the sequence (characters or alignment/gaps)
518 * has been modified. Provided to allow any cursors on residue/column
519 * positions to be invalidated.
521 void sequenceChanged();
525 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
528 BitSet getInsertionsAsBits();
531 * Replaces every occurrence of c1 in the sequence with c2 and returns the
532 * number of characters changed
537 public int replace(char c1, char c2);
540 * Answers the GeneLociI, or null if not known
544 GeneLociI getGeneLoci();
547 * Sets the mapping to gene loci for the sequence
551 * @param chromosomeId
554 void setGeneLoci(String speciesId, String assemblyId,
555 String chromosomeId, MapList map);
559 * Returns the sequence string constructed from the substrings of a sequence
560 * defined by the int[] ranges provided by an iterator. E.g. the iterator
561 * could iterate over all visible regions of the alignment
564 * the iterator to use
565 * @return a String corresponding to the sequence
567 public String getSequenceStringFromIterator(Iterator<int[]> it);
570 * Locate the first position in this sequence which is not contained in an
571 * iterator region. If no such position exists, return 0
574 * iterator over regions
575 * @return first residue not contained in regions
577 public int firstResidueOutsideIterator(Iterator<int[]> it);