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 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 License for more details.
17 * You should have received a copy of the GNU General 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.Hashtable;
24 import java.util.List;
29 * Data structure to hold and manipulate a multiple sequence alignment
31 public interface AlignmentI extends AnnotatedCollectionI
34 * Calculates the number of sequences in an alignment
36 * @return Number of sequences in alignment
42 * Calculates the maximum width of the alignment, including gaps.
44 * @return Greatest sequence length within alignment, or -1 if no sequences
51 * Calculates if this set of sequences (visible and invisible) are all the
54 * @return true if all sequences in alignment are the same length
59 * Calculates if this set of sequences is all the same length
61 * @param includeHidden
62 * optionally exclude hidden sequences from test
63 * @return true if all (or just visible) sequences are the same length
65 boolean isAligned(boolean includeHidden);
68 * Gets sequences as a Synchronized collection
70 * @return All sequences in alignment.
73 List<SequenceI> getSequences();
76 * Gets sequences as a SequenceI[]
78 * @return All sequences in alignment.
80 SequenceI[] getSequencesArray();
83 * Find a specific sequence in this alignment.
86 * Index of required sequence.
88 * @return SequenceI at given index.
90 SequenceI getSequenceAt(int i);
93 * Returns a map of lists of sequences keyed by sequence name.
97 Map<String, List<SequenceI>> getSequencesByName();
100 * Add a new sequence to this alignment.
103 * New sequence will be added at end of alignment.
105 void addSequence(SequenceI seq);
108 * Used to set a particular index of the alignment with the given sequence.
111 * Index of sequence to be updated. if i>length, sequence will be
112 * added to end, with no intervening positions.
114 * New sequence to be inserted. The existing sequence at position i
116 * @return existing sequence (or null if i>current length)
118 SequenceI replaceSequenceAt(int i, SequenceI seq);
121 * Deletes a sequence from the alignment
124 * Sequence to be deleted.
126 void deleteSequence(SequenceI s);
129 * Deletes a sequence from the alignment.
132 * Index of sequence to be deleted.
134 void deleteSequence(int i);
137 * Finds sequence in alignment using sequence name as query.
140 * Id of sequence to search for.
142 * @return Sequence matching query, if found. If not found returns null.
144 SequenceI findName(String name);
146 SequenceI[] findSequenceMatch(String name);
149 * Finds index of a given sequence in the alignment.
152 * Sequence to look for.
154 * @return Index of sequence within the alignment or -1 if not found
156 int findIndex(SequenceI s);
159 * Finds group that given sequence is part of.
162 * Sequence in alignment.
164 * @return First group found for sequence. WARNING : Sequences may be members
165 * of several groups. This method is incomplete.
167 SequenceGroup findGroup(SequenceI s);
170 * Finds all groups that a given sequence is part of.
173 * Sequence in alignment.
175 * @return All groups containing given sequence.
177 SequenceGroup[] findAllGroups(SequenceI s);
180 * Adds a new SequenceGroup to this alignment.
183 * New group to be added.
185 void addGroup(SequenceGroup sg);
188 * Deletes a specific SequenceGroup
191 * Group will be deleted from alignment.
193 void deleteGroup(SequenceGroup g);
196 * Get all the groups associated with this alignment.
198 * @return All groups as a list.
200 List<SequenceGroup> getGroups();
203 * Deletes all groups from this alignment.
205 void deleteAllGroups();
208 * Adds a new AlignmentAnnotation to this alignment
210 * @note Care should be taken to ensure that annotation is at least as wide as
211 * the longest sequence in the alignment for rendering purposes.
213 void addAnnotation(AlignmentAnnotation aa);
216 * moves annotation to a specified index in alignment annotation display stack
219 * the annotation object to be moved
221 * the destination position
223 void setAnnotationIndex(AlignmentAnnotation aa, int index);
226 * Delete all annotations, including auto-calculated if the flag is set true.
227 * Returns true if at least one annotation was deleted, else false.
229 * @param includingAutoCalculated
232 boolean deleteAllAnnotations(boolean includingAutoCalculated);
235 * Deletes a specific AlignmentAnnotation from the alignment, and removes its
236 * reference from any SequenceI or SequenceGroup object's annotation if and
237 * only if aa is contained within the alignment's annotation vector.
238 * Otherwise, it will do nothing.
241 * the annotation to delete
242 * @return true if annotation was deleted from this alignment.
244 boolean deleteAnnotation(AlignmentAnnotation aa);
247 * Deletes a specific AlignmentAnnotation from the alignment, and optionally
248 * removes any reference from any SequenceI or SequenceGroup object's
249 * annotation if and only if aa is contained within the alignment's annotation
250 * vector. Otherwise, it will do nothing.
253 * the annotation to delete
255 * flag indicating if any references should be removed from
256 * annotation - use this if you intend to add the annotation back
258 * @return true if annotation was deleted from this alignment.
260 boolean deleteAnnotation(AlignmentAnnotation aa, boolean unhook);
263 * Get the annotation associated with this alignment (this can be null if no
264 * annotation has ever been created on the alignment)
266 * @return array of AlignmentAnnotation objects
269 AlignmentAnnotation[] getAlignmentAnnotation();
272 * Change the gap character used in this alignment to 'gc'
275 * the new gap character.
277 void setGapCharacter(char gc);
280 * Get the gap character used in this alignment
282 * @return gap character
284 char getGapCharacter();
287 * Test for all nucleotide alignment
289 * @return true if alignment is nucleotide sequence
291 boolean isNucleotide();
294 * Test if alignment contains RNA structure
296 * @return true if RNA structure AligmnentAnnotation was added to alignment
298 boolean hasRNAStructure();
301 * Get the associated dataset for the alignment.
303 * @return Alignment containing dataset sequences or null of this is a
306 AlignmentI getDataset();
309 * Set the associated dataset for the alignment, or create one.
312 * The dataset alignment or null to construct one.
314 void setDataset(AlignmentI dataset);
317 * pads sequences with gaps (to ensure the set looks like an alignment)
319 * @return boolean true if alignment was modified
323 HiddenSequences getHiddenSequences();
326 * Compact representation of alignment
330 CigarArray getCompactAlignment();
333 * Set an arbitrary key value pair for an alignment. Note: both key and value
334 * objects should return a meaningful, human readable response to .toString()
339 void setProperty(Object key, Object value);
342 * Get a named property from the alignment.
345 * @return value of property
347 Object getProperty(Object key);
350 * Get the property hashtable.
352 * @return hashtable of alignment properties (or null if none are defined)
354 Hashtable getProperties();
357 * add a reference to a frame of aligned codons for this alignment
361 void addCodonFrame(AlignedCodonFrame codons);
364 * remove a particular codon frame reference from this alignment
367 * @return true if codon frame was removed.
369 boolean removeCodonFrame(AlignedCodonFrame codons);
372 * get all codon frames associated with this alignment
376 List<AlignedCodonFrame> getCodonFrames();
379 * Set the codon frame mappings (replacing any existing list).
381 void setCodonFrames(List<AlignedCodonFrame> acfs);
384 * get codon frames involving sequenceI
386 List<AlignedCodonFrame> getCodonFrame(SequenceI seq);
389 * find sequence with given name in alignment
394 * true implies that case insensitive matching will <em>also</em> be
396 * @return matched sequence or null
398 SequenceI findName(String token, boolean b);
401 * find next sequence with given name in alignment starting after a given
405 * the sequence after which the search will be started (usually the
406 * result of the last call to findName)
410 * true implies that case insensitive matching will <em>also</em> be
412 * @return matched sequence or null
414 SequenceI findName(SequenceI startAfter, String token, boolean b);
417 * find first sequence in alignment which is involved in the given search
421 * @return -1 or index of sequence in alignment
423 int findIndex(SearchResultsI results);
426 * append sequences and annotation from another alignment object to this one.
427 * Note: this is a straight transfer of object references, and may result in
428 * toappend's dependent data being transformed to fit the alignment (changing
429 * gap characters, etc...). If you are uncertain, use the copy Alignment copy
430 * constructor to create a new version which can be appended without side
434 * - the alignment to be appended.
436 void append(AlignmentI toappend);
439 * Justify the sequences to the left or right by deleting and inserting gaps
440 * before the initial residue or after the terminal residue
443 * true if alignment padded to right, false to justify to left
444 * @return true if alignment was changed TODO: return undo object
446 boolean justify(boolean right);
449 * add given annotation row at given position (0 is start, -1 is end)
454 void addAnnotation(AlignmentAnnotation consensus, int i);
457 * search for or create a specific annotation row on the alignment
460 * name for annotation (must match)
462 * calcId for the annotation (null or must match)
464 * - value of autocalc flag for the annotation
466 * - null or specific sequence reference
468 * - null or specific group reference
470 * - CalcId for the annotation (must match)
472 * @return existing annotation matching the given attributes
474 AlignmentAnnotation findOrCreateAnnotation(String name, String calcId,
475 boolean autoCalc, SequenceI seqRef, SequenceGroup groupRef);
478 * move the given group up or down in the alignment by the given number of
479 * rows. Implementor assumes given group is already present on alignment - no
480 * recalculations are triggered.
487 void moveSelectedSequencesByOne(SequenceGroup sg,
488 Map<SequenceI, SequenceCollectionI> map, boolean up);
491 * validate annotation after an edit and update any alignment state flags
494 * @param alignmentAnnotation
496 void validateAnnotation(AlignmentAnnotation alignmentAnnotation);
499 * Align this alignment the same as the given one. If both of the same type
500 * (nucleotide/protein) then align both identically. If this is nucleotide and
501 * the other is protein, make 3 gaps for each gap in the protein sequences. If
502 * this is protein and the other is nucleotide, insert a gap for each 3 gaps
503 * (or part thereof) between nucleotide bases. Returns the number of mapped
504 * sequences that were realigned .
509 int alignAs(AlignmentI al);
512 * Returns the set of distinct sequence names in the alignment.
516 Set<String> getSequenceNames();
519 * Checks if the alignment has at least one sequence with one non-gaped
524 public boolean hasValidSequence();
527 * Update any mappings to 'virtual' sequences to compatible real ones, if
528 * present in the added sequences. Returns a count of mappings updated.
533 int realiseMappings(List<SequenceI> seqs);
536 * Returns the first AlignedCodonFrame that has a mapping between the given
543 AlignedCodonFrame getMapping(SequenceI mapFrom, SequenceI mapTo);
546 * Calculate the visible start and end index of an alignment. The result is
547 * returned an int array where: int[0] = startIndex, and int[1] = endIndex.
552 public int[] getVisibleStartAndEndIndex(List<int[]> hiddenCols);