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, excluding hidden
37 * @return Number of sequences in alignment
42 * Calculates the number of sequences in an alignment, including hidden
45 * @return Number of sequences in alignment
47 int getAbsoluteHeight();
51 * Calculates the maximum width of the alignment, including gaps.
53 * @return Greatest sequence length within alignment, or -1 if no sequences
60 * Calculates if this set of sequences (visible and invisible) are all the
63 * @return true if all sequences in alignment are the same length
68 * Calculates if this set of sequences is all the same length
70 * @param includeHidden
71 * optionally exclude hidden sequences from test
72 * @return true if all (or just visible) sequences are the same length
74 boolean isAligned(boolean includeHidden);
77 * Answers if the sequence at alignmentIndex is hidden
79 * @param alignmentIndex
81 * @return true if the sequence is hidden
83 boolean isHidden(int alignmentIndex);
86 * Gets sequences as a Synchronized collection
88 * @return All sequences in alignment.
91 List<SequenceI> getSequences();
94 * Gets sequences as a SequenceI[]
96 * @return All sequences in alignment.
98 SequenceI[] getSequencesArray();
101 * Find a specific sequence in this alignment.
104 * Index of required sequence.
106 * @return SequenceI at given index.
108 SequenceI getSequenceAt(int i);
111 * Find a specific sequence in this alignment.
114 * Index of required sequence in full alignment, i.e. if all columns
117 * @return SequenceI at given index.
119 SequenceI getSequenceAtAbsoluteIndex(int i);
122 * Returns a map of lists of sequences keyed by sequence name.
126 Map<String, List<SequenceI>> getSequencesByName();
129 * Add a new sequence to this alignment.
132 * New sequence will be added at end of alignment.
134 void addSequence(SequenceI seq);
137 * Used to set a particular index of the alignment with the given sequence.
140 * Index of sequence to be updated. if i>length, sequence will be
141 * added to end, with no intervening positions.
143 * New sequence to be inserted. The existing sequence at position i
145 * @return existing sequence (or null if i>current length)
147 SequenceI replaceSequenceAt(int i, SequenceI seq);
150 * Deletes a sequence from the alignment
153 * Sequence to be deleted.
155 void deleteSequence(SequenceI s);
158 * Deletes a sequence from the alignment.
161 * Index of sequence to be deleted.
163 void deleteSequence(int i);
166 * Finds sequence in alignment using sequence name as query.
169 * Id of sequence to search for.
171 * @return Sequence matching query, if found. If not found returns null.
173 SequenceI findName(String name);
175 SequenceI[] findSequenceMatch(String name);
178 * Finds index of a given sequence in the alignment.
181 * Sequence to look for.
183 * @return Index of sequence within the alignment or -1 if not found
185 int findIndex(SequenceI s);
188 * Returns the first group (in the order in which groups were added) that
189 * includes the given sequence instance and aligned position (base 0), or null
193 * - must be contained in the alignment (not a dataset sequence)
198 SequenceGroup findGroup(SequenceI seq, int position);
201 * Finds all groups that a given sequence is part of.
204 * Sequence in alignment.
206 * @return All groups containing given sequence.
208 SequenceGroup[] findAllGroups(SequenceI s);
211 * Adds a new SequenceGroup to this alignment.
214 * New group to be added.
216 void addGroup(SequenceGroup sg);
219 * Deletes a specific SequenceGroup
222 * Group will be deleted from alignment.
224 void deleteGroup(SequenceGroup g);
227 * Get all the groups associated with this alignment.
229 * @return All groups as a list.
231 List<SequenceGroup> getGroups();
234 * Deletes all groups from this alignment.
236 void deleteAllGroups();
239 * Adds a new AlignmentAnnotation to this alignment
241 * @note Care should be taken to ensure that annotation is at least as wide as
242 * the longest sequence in the alignment for rendering purposes.
244 void addAnnotation(AlignmentAnnotation aa);
247 * moves annotation to a specified index in alignment annotation display stack
250 * the annotation object to be moved
252 * the destination position
254 void setAnnotationIndex(AlignmentAnnotation aa, int index);
257 * Delete all annotations, including auto-calculated if the flag is set true.
258 * Returns true if at least one annotation was deleted, else false.
260 * @param includingAutoCalculated
263 boolean deleteAllAnnotations(boolean includingAutoCalculated);
266 * Deletes a specific AlignmentAnnotation from the alignment, and removes its
267 * reference from any SequenceI or SequenceGroup object's annotation if and
268 * only if aa is contained within the alignment's annotation vector.
269 * Otherwise, it will do nothing.
272 * the annotation to delete
273 * @return true if annotation was deleted from this alignment.
275 boolean deleteAnnotation(AlignmentAnnotation aa);
278 * Deletes a specific AlignmentAnnotation from the alignment, and optionally
279 * removes any reference from any SequenceI or SequenceGroup object's
280 * annotation if and only if aa is contained within the alignment's annotation
281 * vector. Otherwise, it will do nothing.
284 * the annotation to delete
286 * flag indicating if any references should be removed from
287 * annotation - use this if you intend to add the annotation back
289 * @return true if annotation was deleted from this alignment.
291 boolean deleteAnnotation(AlignmentAnnotation aa, boolean unhook);
294 * Get the annotation associated with this alignment (this can be null if no
295 * annotation has ever been created on the alignment)
297 * @return array of AlignmentAnnotation objects
300 AlignmentAnnotation[] getAlignmentAnnotation();
303 * Change the gap character used in this alignment to 'gc'
306 * the new gap character.
308 void setGapCharacter(char gc);
311 * Get the gap character used in this alignment
313 * @return gap character
315 char getGapCharacter();
318 * Test if alignment contains RNA structure
320 * @return true if RNA structure AligmnentAnnotation was added to alignment
322 boolean hasRNAStructure();
325 * Get the associated dataset for the alignment.
327 * @return Alignment containing dataset sequences or null of this is a
330 AlignmentI getDataset();
333 * Set the associated dataset for the alignment, or create one.
336 * The dataset alignment or null to construct one.
338 void setDataset(AlignmentI dataset);
341 * pads sequences with gaps (to ensure the set looks like an alignment)
343 * @return boolean true if alignment was modified
347 HiddenSequences getHiddenSequences();
350 * Compact representation of alignment
354 CigarArray getCompactAlignment();
357 * Set an arbitrary key value pair for an alignment. Note: both key and value
358 * objects should return a meaningful, human readable response to .toString()
363 void setProperty(Object key, Object value);
366 * Get a named property from the alignment.
369 * @return value of property
371 Object getProperty(Object key);
374 * Get the property hashtable.
376 * @return hashtable of alignment properties (or null if none are defined)
378 Hashtable getProperties();
381 * add a reference to a frame of aligned codons for this alignment
385 void addCodonFrame(AlignedCodonFrame codons);
388 * remove a particular codon frame reference from this alignment
391 * @return true if codon frame was removed.
393 boolean removeCodonFrame(AlignedCodonFrame codons);
396 * get all codon frames associated with this alignment
400 List<AlignedCodonFrame> getCodonFrames();
403 * Set the codon frame mappings (replacing any existing list).
405 void setCodonFrames(List<AlignedCodonFrame> acfs);
408 * get codon frames involving sequenceI
410 List<AlignedCodonFrame> getCodonFrame(SequenceI seq);
413 * find sequence with given name in alignment
418 * true implies that case insensitive matching will <em>also</em> be
420 * @return matched sequence or null
422 SequenceI findName(String token, boolean b);
425 * find next sequence with given name in alignment starting after a given
429 * the sequence after which the search will be started (usually the
430 * result of the last call to findName)
434 * true implies that case insensitive matching will <em>also</em> be
436 * @return matched sequence or null
438 SequenceI findName(SequenceI startAfter, String token, boolean b);
441 * find first sequence in alignment which is involved in the given search
445 * @return -1 or index of sequence in alignment
447 int findIndex(SearchResultsI results);
450 * append sequences and annotation from another alignment object to this one.
451 * Note: this is a straight transfer of object references, and may result in
452 * toappend's dependent data being transformed to fit the alignment (changing
453 * gap characters, etc...). If you are uncertain, use the copy Alignment copy
454 * constructor to create a new version which can be appended without side
458 * - the alignment to be appended.
460 void append(AlignmentI toappend);
463 * Justify the sequences to the left or right by deleting and inserting gaps
464 * before the initial residue or after the terminal residue
467 * true if alignment padded to right, false to justify to left
468 * @return true if alignment was changed TODO: return undo object
470 boolean justify(boolean right);
473 * add given annotation row at given position (0 is start, -1 is end)
478 void addAnnotation(AlignmentAnnotation consensus, int i);
481 * search for or create a specific annotation row on the alignment
484 * name for annotation (must match)
486 * calcId for the annotation (null or must match)
488 * - value of autocalc flag for the annotation
490 * - null or specific sequence reference
492 * - null or specific group reference
494 * - CalcId for the annotation (must match)
496 * @return existing annotation matching the given attributes
498 AlignmentAnnotation findOrCreateAnnotation(String name, String calcId,
499 boolean autoCalc, SequenceI seqRef, SequenceGroup groupRef);
502 * move the given group up or down in the alignment by the given number of
503 * rows. Implementor assumes given group is already present on alignment - no
504 * recalculations are triggered.
511 void moveSelectedSequencesByOne(SequenceGroup sg,
512 Map<SequenceI, SequenceCollectionI> map, boolean up);
515 * validate annotation after an edit and update any alignment state flags
518 * @param alignmentAnnotation
520 void validateAnnotation(AlignmentAnnotation alignmentAnnotation);
523 * Align this alignment the same as the given one. If both of the same type
524 * (nucleotide/protein) then align both identically. If this is nucleotide and
525 * the other is protein, make 3 gaps for each gap in the protein sequences. If
526 * this is protein and the other is nucleotide, insert a gap for each 3 gaps
527 * (or part thereof) between nucleotide bases. Returns the number of mapped
528 * sequences that were realigned .
533 int alignAs(AlignmentI al);
536 * Returns the set of distinct sequence names in the alignment.
540 Set<String> getSequenceNames();
543 * Checks if the alignment has at least one sequence with one non-gaped
548 public boolean hasValidSequence();
551 * Update any mappings to 'virtual' sequences to compatible real ones, if
552 * present in the added sequences. Returns a count of mappings updated.
557 int realiseMappings(List<SequenceI> seqs);
560 * Returns the first AlignedCodonFrame that has a mapping between the given
567 AlignedCodonFrame getMapping(SequenceI mapFrom, SequenceI mapTo);
570 * Calculate the visible start and end index of an alignment. The result is
571 * returned an int array where: int[0] = startIndex, and int[1] = endIndex.
576 public int[] getVisibleStartAndEndIndex(List<int[]> hiddenCols);