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.api.DBRefEntryI;
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();
223 * @return true if sequence is composed of amino acid characters
225 public boolean isProtein();
228 * Delete a range of aligned sequence columns, creating a new dataset sequence
229 * if necessary and adjusting start and end positions accordingly.
232 * first column in range to delete (inclusive)
234 * last column in range to delete (exclusive)
236 public void deleteChars(int i, int j);
242 * alignment column number
244 * character to insert
246 public void insertCharAt(int i, char c);
249 * insert given character at alignment column position
252 * alignment column number
256 * character to insert
258 public void insertCharAt(int position, int count, char ch);
261 * Gets array holding sequence features associated with this sequence. The
262 * array may be held by the sequence's dataset sequence if that is defined.
264 * @return hard reference to array
266 public SequenceFeature[] getSequenceFeatures();
269 * Replaces the array of sequence features associated with this sequence with
270 * a new array reference. If this sequence has a dataset sequence, then this
271 * method will update the dataset sequence's feature array
274 * New array of sequence features
276 public void setSequenceFeatures(SequenceFeature[] features);
284 public void setPDBId(Vector<PDBEntry> ids);
289 * @return DOCUMENT ME!
291 public Vector<PDBEntry> getAllPDBEntries();
294 * add entry to the vector of PDBIds, if it isn't in the list already
298 public void addPDBId(PDBEntry entry);
301 * update the list of PDBEntrys to include any DBRefEntrys citing structural
304 * @return true if PDBEntry list was modified
306 public boolean updatePDBIds();
308 public String getVamsasId();
310 public void setVamsasId(String id);
312 public void setDBRefs(DBRefEntry[] dbs);
314 public DBRefEntry[] getDBRefs();
317 * add the given entry to the list of DBRefs for this sequence, or replace a
318 * similar one if entry contains a map object and the existing one doesnt.
322 public void addDBRef(DBRefEntry entry);
324 public void addSequenceFeature(SequenceFeature sf);
326 public void deleteFeature(SequenceFeature sf);
328 public void setDatasetSequence(SequenceI seq);
330 public SequenceI getDatasetSequence();
333 * Returns a new array containing this sequence's annotations, or null.
335 public AlignmentAnnotation[] getAnnotation();
338 * Returns true if this sequence has the given annotation (by object
341 public boolean hasAnnotation(AlignmentAnnotation ann);
344 * Add the given annotation, if not already added, and set its sequence ref to
345 * be this sequence. Does nothing if this sequence's annotations already
346 * include this annotation (by identical object reference).
348 public void addAlignmentAnnotation(AlignmentAnnotation annotation);
350 public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
353 * Derive a sequence (using this one's dataset or as the dataset)
355 * @return duplicate sequence with valid dataset sequence
357 public SequenceI deriveSequence();
360 * set the array of associated AlignmentAnnotation for this sequenceI
364 public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
367 * Get one or more alignment annotations with a particular label.
370 * string which each returned annotation must have as a label.
371 * @return null or array of annotations.
373 public AlignmentAnnotation[] getAnnotation(String label);
376 * Returns a (possibly empty) list of any annotations that match on given
377 * calcId (source) and label (type). Null values do not match.
382 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
386 * create a new dataset sequence (if necessary) for this sequence and sets
387 * this sequence to refer to it. This call will move any features or
388 * references on the sequence onto the dataset. It will also make a duplicate
389 * of existing annotation rows for the dataset sequence, rather than relocate
390 * them in order to preserve external references (since 2.8.2).
392 * @return dataset sequence for this sequence
394 public SequenceI createDatasetSequence();
397 * Transfer any database references or annotation from entry under a sequence
399 * <strong>Note: DOES NOT transfer sequence associated alignment annotation
404 * null or mapping from entry's numbering to local start/end
406 public void transferAnnotation(SequenceI entry, Mapping mp);
410 * The sequence index in the MSA
412 public void setIndex(int index);
415 * @return The index of the sequence in the alignment
417 public int getIndex();
420 * @return The RNA of the sequence in the alignment
429 public void setRNA(RNA rna);
433 * @return list of insertions (gap characters) in sequence
435 public List<int[]> getInsertions();
438 * Given a pdbId String, return the equivalent PDBEntry if available in the
444 public PDBEntry getPDBEntry(String pdbId);
447 * Set the distinct source database, and accession number from which a
448 * sequence and its start-end data were derived from. This is very important
449 * for SIFTS mappings and must be set prior to performing SIFTS mapping.
452 * the source dbRef for the sequence
454 public void setSourceDBRef(DBRefEntryI dbRef);
457 * Get the distinct source database, and accession number from which a
458 * sequence and its start-end data were derived from.
462 public DBRefEntryI getSourceDBRef();