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);
46 * Get the display name
48 public String getName();
51 * Set start position of first non-gapped symbol in sequence
56 public void setStart(int start);
59 * get start position of first non-gapped residue in sequence
63 public int getStart();
66 * get the displayed id of the sequence
68 * @return true means the id will be returned in the form
69 * DisplayName/Start-End
71 public String getDisplayId(boolean jvsuffix);
74 * set end position for last residue in sequence
78 public void setEnd(int end);
81 * get end position for last residue in sequence getEnd()>getStart() unless
82 * sequence only consists of gap characters
89 * @return length of sequence including gaps
92 public int getLength();
95 * Replace the sequence with the given string
100 public void setSequence(String sequence);
103 * @return sequence as string
105 public String getSequenceAsString();
108 * get a range on the sequence as a string
111 * position relative to start of sequence including gaps (from 0)
113 * position relative to start of sequence including gaps (from 0)
115 * @return String containing all gap and symbols in specified range
117 public String getSequenceAsString(int start, int end);
120 * Get the sequence as a character array
122 * @return seqeunce and any gaps
124 public char[] getSequence();
127 * get stretch of sequence characters in an array
130 * absolute index into getSequence()
132 * exclusive index of last position in segment to be returned.
134 * @return char[max(0,end-start)];
136 public char[] getSequence(int start, int end);
139 * create a new sequence object with a subsequence of this one but sharing the
140 * same dataset sequence
143 * int index for start position (base 0, inclusive)
145 * int index for end position (base 0, exclusive)
148 * @note implementations may use getSequence to get the sequence data
150 public SequenceI getSubSequence(int start, int end);
153 * get the i'th character in this sequence's local reference frame (ie from
154 * 0-number of characters lying from start-end)
158 * @return character or ' '
160 public char getCharAt(int i);
168 public void setDescription(String desc);
173 * @return DOCUMENT ME!
175 public String getDescription();
178 * Return the alignment column for a sequence position
181 * lying from start to end
183 * @return aligned column for residue (0 if residue is upstream from
184 * alignment, -1 if residue is downstream from alignment) note.
185 * Sequence object returns sequence.getEnd() for positions upstream
186 * currently. TODO: change sequence for
187 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
190 public int findIndex(int pos);
193 * Returns the sequence position for an alignment position.
196 * column index in alignment (from 0..<length)
198 * @return TODO: JAL-2562 - residue number for residue (left of and) nearest
201 public int findPosition(int i);
204 * Returns an int array where indices correspond to each residue in the
205 * sequence and the element value gives its position in the alignment
207 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
208 * residues in SequenceI object
210 public int[] gapMap();
213 * Returns an int array where indices correspond to each position in sequence
214 * char array and the element value gives the result of findPosition for that
215 * index in the sequence.
217 * @return int[SequenceI.getLength()]
219 public int[] findPositionMap();
222 * Answers true if the sequence is composed of amino acid characters. Note
223 * that implementations may use heuristic methods which are not guaranteed to
224 * give the biologically 'right' answer.
228 public boolean isProtein();
231 * Delete a range of aligned sequence columns, creating a new dataset sequence
232 * if necessary and adjusting start and end positions accordingly.
235 * first column in range to delete (inclusive)
237 * last column in range to delete (exclusive)
239 public void deleteChars(int i, int j);
245 * alignment column number
247 * character to insert
249 public void insertCharAt(int i, char c);
252 * insert given character at alignment column position
255 * alignment column number
259 * character to insert
261 public void insertCharAt(int position, int count, char ch);
264 * Gets array holding sequence features associated with this sequence. The
265 * array may be held by the sequence's dataset sequence if that is defined.
267 * @return hard reference to array
269 public SequenceFeature[] getSequenceFeatures();
272 * Replaces the array of sequence features associated with this sequence with
273 * a new array reference. If this sequence has a dataset sequence, then this
274 * method will update the dataset sequence's feature array
277 * New array of sequence features
279 public void setSequenceFeatures(SequenceFeature[] features);
287 public void setPDBId(Vector<PDBEntry> ids);
292 * @return DOCUMENT ME!
294 public Vector<PDBEntry> getAllPDBEntries();
297 * Adds the entry to the *normalised* list of PDBIds.
299 * If a PDBEntry is passed with the same entry.getID() string as one already
300 * in the list, or one is added that appears to be the same but has a chain ID
301 * appended, then the existing PDBEntry will be updated with the new
302 * attributes instead, unless the entries have distinct chain codes or
303 * associated structure files.
306 * @return true if the entry was added, false if updated
308 public boolean addPDBId(PDBEntry entry);
311 * update the list of PDBEntrys to include any DBRefEntrys citing structural
314 * @return true if PDBEntry list was modified
316 public boolean updatePDBIds();
318 public String getVamsasId();
320 public void setVamsasId(String id);
323 * set the array of Database references for the sequence.
326 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
327 * set are not normalised.
330 public void setDBRefs(DBRefEntry[] dbs);
332 public DBRefEntry[] getDBRefs();
335 * add the given entry to the list of DBRefs for this sequence, or replace a
336 * similar one if entry contains a map object and the existing one doesnt.
340 public void addDBRef(DBRefEntry entry);
343 * Adds the given sequence feature and returns true, or returns false if it is
344 * already present on the sequence
349 public boolean addSequenceFeature(SequenceFeature sf);
351 public void deleteFeature(SequenceFeature sf);
353 public void setDatasetSequence(SequenceI seq);
355 public SequenceI getDatasetSequence();
358 * Returns a new array containing this sequence's annotations, or null.
360 public AlignmentAnnotation[] getAnnotation();
363 * Returns true if this sequence has the given annotation (by object
366 public boolean hasAnnotation(AlignmentAnnotation ann);
369 * Add the given annotation, if not already added, and set its sequence ref to
370 * be this sequence. Does nothing if this sequence's annotations already
371 * include this annotation (by identical object reference).
373 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
375 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
378 * Derive a sequence (using this one's dataset or as the dataset)
380 * @return duplicate sequence with valid dataset sequence
382 public SequenceI deriveSequence();
385 * set the array of associated AlignmentAnnotation for this sequenceI
389 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
392 * Get one or more alignment annotations with a particular label.
395 * string which each returned annotation must have as a label.
396 * @return null or array of annotations.
398 public AlignmentAnnotation[] getAnnotation(String label);
401 * Returns a (possibly empty) list of any annotations that match on given
402 * calcId (source) and label (type). Null values do not match.
407 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
411 * create a new dataset sequence (if necessary) for this sequence and sets
412 * this sequence to refer to it. This call will move any features or
413 * references on the sequence onto the dataset. It will also make a duplicate
414 * of existing annotation rows for the dataset sequence, rather than relocate
415 * them in order to preserve external references (since 2.8.2).
417 * @return dataset sequence for this sequence
419 public SequenceI createDatasetSequence();
422 * Transfer any database references or annotation from entry under a sequence
424 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
429 * null or mapping from entry's numbering to local start/end
431 public void transferAnnotation(SequenceI entry, Mapping mp);
435 * The sequence index in the MSA
437 public void setIndex(int index);
440 * @return The index of the sequence in the alignment
442 public int getIndex();
445 * @return The RNA of the sequence in the alignment
454 public void setRNA(RNA rna);
458 * @return list of insertions (gap characters) in sequence
460 public List<int[]> getInsertions();
463 * Given a pdbId String, return the equivalent PDBEntry if available in the
469 public PDBEntry getPDBEntry(String pdbId);
472 * Get all primary database/accessions for this sequence's data. These
473 * DBRefEntry are expected to resolve to a valid record in the associated
474 * external database, either directly or via a provided 1:1 Mapping.
476 * @return just the primary references (if any) for this sequence, or an empty
479 public List<DBRefEntry> getPrimaryDBRefs();
483 * @return BitSet corresponding to index [0,length) where Comparison.isGap()
486 BitSet getInsertionsAsBits();