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.List;
26 import java.util.Vector;
28 import fr.orsay.lri.varna.models.rna.RNA;
31 * Methods for manipulating a sequence, its metadata and related annotation in
32 * an alignment or dataset.
37 public interface SequenceI extends ASequenceI
40 * Set the display name for the sequence
44 public void setName(String name);
47 * Get the display name
49 public String getName();
52 * Set start position of first non-gapped symbol in sequence
57 public void setStart(int start);
60 * get start position of first non-gapped residue in sequence
64 public int getStart();
67 * get the displayed id of the sequence
69 * @return true means the id will be returned in the form
70 * DisplayName/Start-End
72 public String getDisplayId(boolean jvsuffix);
75 * set end position for last residue in sequence
79 public void setEnd(int end);
82 * get end position for last residue in sequence getEnd()>getStart() unless
83 * sequence only consists of gap characters
90 * @return length of sequence including gaps
93 public int getLength();
96 * Replace the sequence with the given string
101 public void setSequence(String sequence);
104 * @return sequence as string
106 public String getSequenceAsString();
109 * get a range on the sequence as a string
112 * position relative to start of sequence including gaps (from 0)
114 * position relative to start of sequence including gaps (from 0)
116 * @return String containing all gap and symbols in specified range
118 public String getSequenceAsString(int start, int end);
121 * Get the sequence as a character array
123 * @return seqeunce and any gaps
125 public char[] getSequence();
128 * get stretch of sequence characters in an array
131 * absolute index into getSequence()
133 * exclusive index of last position in segment to be returned.
135 * @return char[max(0,end-start)];
137 public char[] getSequence(int start, int end);
140 * create a new sequence object with a subsequence of this one but sharing the
141 * same dataset sequence
144 * int index for start position (base 0, inclusive)
146 * int index for end position (base 0, exclusive)
149 * @note implementations may use getSequence to get the sequence data
151 public SequenceI getSubSequence(int start, int end);
154 * get the i'th character in this sequence's local reference frame (ie from
155 * 0-number of characters lying from start-end)
159 * @return character or ' '
161 public char getCharAt(int i);
169 public void setDescription(String desc);
174 * @return DOCUMENT ME!
176 public String getDescription();
179 * Return the alignment column for a sequence position
182 * lying from start to end
184 * @return aligned column for residue (0 if residue is upstream from
185 * alignment, -1 if residue is downstream from alignment) note.
186 * Sequence object returns sequence.getEnd() for positions upstream
187 * currently. TODO: change sequence for
188 * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
191 public int findIndex(int pos);
194 * Returns the sequence position for an alignment position
197 * column index in alignment (from 0..<length)
199 * @return residue number for residue (left of and) nearest ith column
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 * Answers a list of all sequence features associated with this sequence. The
265 * list may be held by the sequence's dataset sequence if that is defined.
267 * @return hard reference to array
269 public List<SequenceFeature> getSequenceFeatures();
272 * Answers the object holding features for the sequence
276 SequenceFeaturesI getFeatures();
279 * Replaces the sequence features associated with this sequence with the given
280 * features. If this sequence has a dataset sequence, then this method will
281 * update the dataset sequence's features instead.
285 public void setSequenceFeatures(List<SequenceFeature> features);
293 public void setPDBId(Vector<PDBEntry> ids);
298 * @return DOCUMENT ME!
300 public Vector<PDBEntry> getAllPDBEntries();
303 * Adds the entry to the *normalised* list of PDBIds.
305 * If a PDBEntry is passed with the same entry.getID() string as one already
306 * in the list, or one is added that appears to be the same but has a chain ID
307 * appended, then the existing PDBEntry will be updated with the new
308 * attributes instead, unless the entries have distinct chain codes or
309 * associated structure files.
312 * @return true if the entry was added, false if updated
314 public boolean addPDBId(PDBEntry entry);
317 * update the list of PDBEntrys to include any DBRefEntrys citing structural
320 * @return true if PDBEntry list was modified
322 public boolean updatePDBIds();
324 public String getVamsasId();
326 public void setVamsasId(String id);
329 * set the array of Database references for the sequence.
332 * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
333 * set are not normalised.
336 public void setDBRefs(DBRefEntry[] dbs);
338 public DBRefEntry[] getDBRefs();
341 * add the given entry to the list of DBRefs for this sequence, or replace a
342 * similar one if entry contains a map object and the existing one doesnt.
346 public void addDBRef(DBRefEntry entry);
349 * Adds the given sequence feature and returns true, or returns false if it is
350 * already present on the sequence, or if the feature type is null.
355 public boolean addSequenceFeature(SequenceFeature sf);
357 public void deleteFeature(SequenceFeature sf);
359 public void setDatasetSequence(SequenceI seq);
361 public SequenceI getDatasetSequence();
364 * Returns a new array containing this sequence's annotations, or null.
366 public AlignmentAnnotation[] getAnnotation();
369 * Returns true if this sequence has the given annotation (by object
372 public boolean hasAnnotation(AlignmentAnnotation ann);
375 * Add the given annotation, if not already added, and set its sequence ref to
376 * be this sequence. Does nothing if this sequence's annotations already
377 * include this annotation (by identical object reference).
379 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
381 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
384 * Derive a sequence (using this one's dataset or as the dataset)
386 * @return duplicate sequence with valid dataset sequence
388 public SequenceI deriveSequence();
391 * set the array of associated AlignmentAnnotation for this sequenceI
395 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
398 * Get one or more alignment annotations with a particular label.
401 * string which each returned annotation must have as a label.
402 * @return null or array of annotations.
404 public AlignmentAnnotation[] getAnnotation(String label);
407 * Returns a (possibly empty) list of any annotations that match on given
408 * calcId (source) and label (type). Null values do not match.
413 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
417 * create a new dataset sequence (if necessary) for this sequence and sets
418 * this sequence to refer to it. This call will move any features or
419 * references on the sequence onto the dataset. It will also make a duplicate
420 * of existing annotation rows for the dataset sequence, rather than relocate
421 * them in order to preserve external references (since 2.8.2).
423 * @return dataset sequence for this sequence
425 public SequenceI createDatasetSequence();
428 * Transfer any database references or annotation from entry under a sequence
430 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
435 * null or mapping from entry's numbering to local start/end
437 public void transferAnnotation(SequenceI entry, Mapping mp);
441 * The sequence index in the MSA
443 public void setIndex(int index);
446 * @return The index of the sequence in the alignment
448 public int getIndex();
451 * @return The RNA of the sequence in the alignment
460 public void setRNA(RNA rna);
464 * @return list of insertions (gap characters) in sequence
466 public List<int[]> getInsertions();
469 * Given a pdbId String, return the equivalent PDBEntry if available in the
475 public PDBEntry getPDBEntry(String pdbId);
478 * Get all primary database/accessions for this sequence's data. These
479 * DBRefEntry are expected to resolve to a valid record in the associated
480 * external database, either directly or via a provided 1:1 Mapping.
482 * @return just the primary references (if any) for this sequence, or an empty
485 public List<DBRefEntry> getPrimaryDBRefs();
488 * Returns a (possibly empty) list of sequence features that overlap the range
489 * from-to (inclusive), optionally restricted to one or more specified feature
497 List<SequenceFeature> findFeatures(int from, int to, String... types);