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.List;
24 import java.util.Vector;
26 import fr.orsay.lri.varna.models.rna.RNA;
29 * Methods for manipulating a sequence, its metadata and related annotation in
30 * an alignment or dataset.
35 public interface SequenceI extends ASequenceI
38 * Set the display name for the sequence
42 public void setName(String name);
44 public HiddenMarkovModel getHMM();
46 public void setHMM(HiddenMarkovModel hmm);
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 * Get the sequence as a character array
125 * @return seqeunce and any gaps
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 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 position.
199 * column index in alignment (from 0..<length)
201 * @return TODO: JAL-2562 - residue number for residue (left of and) nearest
204 public int findPosition(int i);
207 * Returns an int array where indices correspond to each residue in the
208 * sequence and the element value gives its position in the alignment
210 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
211 * residues in SequenceI object
213 public int[] gapMap();
216 * Returns an int array where indices correspond to each position in sequence
217 * char array and the element value gives the result of findPosition for that
218 * index in the sequence.
220 * @return int[SequenceI.getLength()]
222 public int[] findPositionMap();
225 * Answers true if the sequence is composed of amino acid characters. Note
226 * that implementations may use heuristic methods which are not guaranteed to
227 * give the biologically 'right' answer.
231 public boolean isProtein();
234 * Delete a range of aligned sequence columns, creating a new dataset sequence
235 * if necessary and adjusting start and end positions accordingly.
238 * first column in range to delete (inclusive)
240 * last column in range to delete (exclusive)
242 public void deleteChars(int i, int j);
248 * alignment column number
250 * character to insert
252 public void insertCharAt(int i, char c);
255 * insert given character at alignment column position
258 * alignment column number
262 * character to insert
264 public void insertCharAt(int position, int count, char ch);
267 * Gets array holding sequence features associated with this sequence. The
268 * array may be held by the sequence's dataset sequence if that is defined.
270 * @return hard reference to array
272 public SequenceFeature[] getSequenceFeatures();
275 * Replaces the array of sequence features associated with this sequence with
276 * a new array reference. If this sequence has a dataset sequence, then this
277 * method will update the dataset sequence's feature array
280 * New array of sequence features
282 public void setSequenceFeatures(SequenceFeature[] features);
290 public void setPDBId(Vector<PDBEntry> ids);
295 * @return DOCUMENT ME!
297 public Vector<PDBEntry> getAllPDBEntries();
300 * Adds the entry to the *normalised* list of PDBIds.
302 * If a PDBEntry is passed with the same entry.getID() string as one already
303 * in the list, or one is added that appears to be the same but has a chain ID
304 * appended, then the existing PDBEntry will be updated with the new
305 * attributes instead, unless the entries have distinct chain codes or
306 * associated structure files.
309 * @return true if the entry was added, false if updated
311 public boolean addPDBId(PDBEntry entry);
314 * update the list of PDBEntrys to include any DBRefEntrys citing structural
317 * @return true if PDBEntry list was modified
319 public boolean updatePDBIds();
321 public String getVamsasId();
323 public void setVamsasId(String id);
326 * set the array of Database references for the sequence.
329 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
330 * set are not normalised.
333 public void setDBRefs(DBRefEntry[] dbs);
335 public DBRefEntry[] getDBRefs();
338 * add the given entry to the list of DBRefs for this sequence, or replace a
339 * similar one if entry contains a map object and the existing one doesnt.
343 public void addDBRef(DBRefEntry entry);
346 * Adds the given sequence feature and returns true, or returns false if it is
347 * already present on the sequence
352 public boolean addSequenceFeature(SequenceFeature sf);
354 public void deleteFeature(SequenceFeature sf);
356 public void setDatasetSequence(SequenceI seq);
358 public SequenceI getDatasetSequence();
361 * Returns a new array containing this sequence's annotations, or null.
363 public AlignmentAnnotation[] getAnnotation();
366 * Returns true if this sequence has the given annotation (by object
369 public boolean hasAnnotation(AlignmentAnnotation ann);
372 * Add the given annotation, if not already added, and set its sequence ref to
373 * be this sequence. Does nothing if this sequence's annotations already
374 * include this annotation (by identical object reference).
376 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
378 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
381 * Derive a sequence (using this one's dataset or as the dataset)
383 * @return duplicate sequence with valid dataset sequence
385 public SequenceI deriveSequence();
388 * set the array of associated AlignmentAnnotation for this sequenceI
392 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
395 * Get one or more alignment annotations with a particular label.
398 * string which each returned annotation must have as a label.
399 * @return null or array of annotations.
401 public AlignmentAnnotation[] getAnnotation(String label);
404 * Returns a (possibly empty) list of any annotations that match on given
405 * calcId (source) and label (type). Null values do not match.
410 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
414 * create a new dataset sequence (if necessary) for this sequence and sets
415 * this sequence to refer to it. This call will move any features or
416 * references on the sequence onto the dataset. It will also make a duplicate
417 * of existing annotation rows for the dataset sequence, rather than relocate
418 * them in order to preserve external references (since 2.8.2).
420 * @return dataset sequence for this sequence
422 public SequenceI createDatasetSequence();
425 * Transfer any database references or annotation from entry under a sequence
427 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
432 * null or mapping from entry's numbering to local start/end
434 public void transferAnnotation(SequenceI entry, Mapping mp);
438 * The sequence index in the MSA
440 public void setIndex(int index);
443 * @return The index of the sequence in the alignment
445 public int getIndex();
448 * @return The RNA of the sequence in the alignment
457 public void setRNA(RNA rna);
461 * @return list of insertions (gap characters) in sequence
463 public List<int[]> getInsertions();
466 * Given a pdbId String, return the equivalent PDBEntry if available in the
472 public PDBEntry getPDBEntry(String pdbId);
475 * Get all primary database/accessions for this sequence's data. These
476 * DBRefEntry are expected to resolve to a valid record in the associated
477 * external database, either directly or via a provided 1:1 Mapping.
479 * @return just the primary references (if any) for this sequence, or an empty
482 public List<DBRefEntry> getPrimaryDBRefs();
484 public void updateHMMMapping();
486 boolean isHMMConsensusSequence();
488 void setIsHMMConsensusSequence(boolean isHMMConsensusSequence);