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.List;
25 import java.util.Vector;
27 import fr.orsay.lri.varna.models.rna.RNA;
30 * Methods for manipulating a sequence, its metadata and related annotation in
31 * an alignment or dataset.
36 public interface SequenceI extends ASequenceI
39 * Set the display name for the sequence
43 public void setName(String name);
45 public HiddenMarkovModel getHMM();
47 public void setHMM(HiddenMarkovModel hmm);
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 * position relative to start of sequence including gaps (from 0)
117 * position relative to start of sequence including gaps (from 0)
119 * @return String containing all gap and symbols in specified range
121 public String getSequenceAsString(int start, int end);
124 * Get the sequence as a character array
126 * @return seqeunce and any gaps
128 public char[] getSequence();
131 * get stretch of sequence characters in an array
134 * absolute index into getSequence()
136 * exclusive index of last position in segment to be returned.
138 * @return char[max(0,end-start)];
140 public char[] getSequence(int start, int end);
143 * create a new sequence object with a subsequence of this one but sharing the
144 * same dataset sequence
147 * int index for start position (base 0, inclusive)
149 * int index for end position (base 0, exclusive)
152 * @note implementations may use getSequence to get the sequence data
154 public SequenceI getSubSequence(int start, int end);
157 * get the i'th character in this sequence's local reference frame (ie from
158 * 0-number of characters lying from start-end)
162 * @return character or ' '
164 public char getCharAt(int i);
172 public void setDescription(String desc);
177 * @return DOCUMENT ME!
179 public String getDescription();
182 * Return the alignment column for a sequence position
185 * lying from start to end
187 * @return aligned column for residue (0 if residue is upstream from
188 * alignment, -1 if residue is downstream from alignment) note.
189 * Sequence object returns sequence.getEnd() for positions upstream
190 * currently. TODO: change sequence for
191 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
194 public int findIndex(int pos);
197 * Returns the sequence position for an alignment position.
200 * column index in alignment (from 0..<length)
202 * @return TODO: JAL-2562 - residue number for residue (left of and) nearest
205 public int findPosition(int i);
208 * Returns an int array where indices correspond to each residue in the
209 * sequence and the element value gives its position in the alignment
211 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
212 * residues in SequenceI object
214 public int[] gapMap();
217 * Returns an int array where indices correspond to each position in sequence
218 * char array and the element value gives the result of findPosition for that
219 * index in the sequence.
221 * @return int[SequenceI.getLength()]
223 public int[] findPositionMap();
226 * Answers true if the sequence is composed of amino acid characters. Note
227 * that implementations may use heuristic methods which are not guaranteed to
228 * give the biologically 'right' answer.
232 public boolean isProtein();
235 * Delete a range of aligned sequence columns, creating a new dataset sequence
236 * if necessary and adjusting start and end positions accordingly.
239 * first column in range to delete (inclusive)
241 * last column in range to delete (exclusive)
243 public void deleteChars(int i, int j);
249 * alignment column number
251 * character to insert
253 public void insertCharAt(int i, char c);
256 * insert given character at alignment column position
259 * alignment column number
263 * character to insert
265 public void insertCharAt(int position, int count, char ch);
268 * Gets array holding sequence features associated with this sequence. The
269 * array may be held by the sequence's dataset sequence if that is defined.
271 * @return hard reference to array
273 public SequenceFeature[] getSequenceFeatures();
276 * Replaces the array of sequence features associated with this sequence with
277 * a new array reference. If this sequence has a dataset sequence, then this
278 * method will update the dataset sequence's feature array
281 * New array of sequence features
283 public void setSequenceFeatures(SequenceFeature[] features);
291 public void setPDBId(Vector<PDBEntry> ids);
296 * @return DOCUMENT ME!
298 public Vector<PDBEntry> getAllPDBEntries();
301 * Adds the entry to the *normalised* list of PDBIds.
303 * If a PDBEntry is passed with the same entry.getID() string as one already
304 * in the list, or one is added that appears to be the same but has a chain ID
305 * appended, then the existing PDBEntry will be updated with the new
306 * attributes instead, unless the entries have distinct chain codes or
307 * associated structure files.
310 * @return true if the entry was added, false if updated
312 public boolean addPDBId(PDBEntry entry);
315 * update the list of PDBEntrys to include any DBRefEntrys citing structural
318 * @return true if PDBEntry list was modified
320 public boolean updatePDBIds();
322 public String getVamsasId();
324 public void setVamsasId(String id);
327 * set the array of Database references for the sequence.
330 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
331 * set are not normalised.
334 public void setDBRefs(DBRefEntry[] dbs);
336 public DBRefEntry[] getDBRefs();
339 * add the given entry to the list of DBRefs for this sequence, or replace a
340 * similar one if entry contains a map object and the existing one doesnt.
344 public void addDBRef(DBRefEntry entry);
347 * Adds the given sequence feature and returns true, or returns false if it is
348 * already present on the sequence
353 public boolean addSequenceFeature(SequenceFeature sf);
355 public void deleteFeature(SequenceFeature sf);
357 public void setDatasetSequence(SequenceI seq);
359 public SequenceI getDatasetSequence();
362 * Returns a new array containing this sequence's annotations, or null.
364 public AlignmentAnnotation[] getAnnotation();
367 * Returns true if this sequence has the given annotation (by object
370 public boolean hasAnnotation(AlignmentAnnotation ann);
373 * Add the given annotation, if not already added, and set its sequence ref to
374 * be this sequence. Does nothing if this sequence's annotations already
375 * include this annotation (by identical object reference).
377 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
379 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
382 * Derive a sequence (using this one's dataset or as the dataset)
384 * @return duplicate sequence with valid dataset sequence
386 public SequenceI deriveSequence();
389 * set the array of associated AlignmentAnnotation for this sequenceI
393 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
396 * Get one or more alignment annotations with a particular label.
399 * string which each returned annotation must have as a label.
400 * @return null or array of annotations.
402 public AlignmentAnnotation[] getAnnotation(String label);
405 * Returns a (possibly empty) list of any annotations that match on given
406 * calcId (source) and label (type). Null values do not match.
411 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
415 * create a new dataset sequence (if necessary) for this sequence and sets
416 * this sequence to refer to it. This call will move any features or
417 * references on the sequence onto the dataset. It will also make a duplicate
418 * of existing annotation rows for the dataset sequence, rather than relocate
419 * them in order to preserve external references (since 2.8.2).
421 * @return dataset sequence for this sequence
423 public SequenceI createDatasetSequence();
426 * Transfer any database references or annotation from entry under a sequence
428 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
433 * null or mapping from entry's numbering to local start/end
435 public void transferAnnotation(SequenceI entry, Mapping mp);
439 * The sequence index in the MSA
441 public void setIndex(int index);
444 * @return The index of the sequence in the alignment
446 public int getIndex();
449 * @return The RNA of the sequence in the alignment
458 public void setRNA(RNA rna);
462 * @return list of insertions (gap characters) in sequence
464 public List<int[]> getInsertions();
467 * Given a pdbId String, return the equivalent PDBEntry if available in the
473 public PDBEntry getPDBEntry(String pdbId);
476 * Get all primary database/accessions for this sequence's data. These
477 * DBRefEntry are expected to resolve to a valid record in the associated
478 * external database, either directly or via a provided 1:1 Mapping.
480 * @return just the primary references (if any) for this sequence, or an empty
483 public List<DBRefEntry> getPrimaryDBRefs();
485 public void updateHMMMapping();
487 boolean isHMMConsensusSequence();
489 void setIsHMMConsensusSequence(boolean isHMMConsensusSequence);
491 boolean hasHMMAnnotation();
493 void setHasInfo(boolean status);
495 int getPreviousPosition();
497 void setPreviousPosition(int previousPosition);
501 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
504 BitSet getInsertionsAsBits();