Clover icon

jalviewX

  1. Project Clover database Wed Oct 31 2018 15:13:58 GMT
  2. Package jalview.datamodel

File SequenceI.java

 

Code metrics

0
0
0
1
576
80
0
-
-
0
-

Classes

Class Line # Actions
SequenceI 40 0 0 0
-1.0 -
 

Contributing tests

No tests hitting this source file were found.

Source view

1    /*
2    * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3    * Copyright (C) $$Year-Rel$$ The Jalview Authors
4    *
5    * This file is part of Jalview.
6    *
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.
11    *
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.
16    *
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.
20    */
21    package jalview.datamodel;
22   
23    import jalview.datamodel.features.SequenceFeaturesI;
24    import jalview.util.MapList;
25   
26    import java.util.BitSet;
27    import java.util.Iterator;
28    import java.util.List;
29    import java.util.Vector;
30   
31    import fr.orsay.lri.varna.models.rna.RNA;
32   
33    /**
34    * Methods for manipulating a sequence, its metadata and related annotation in
35    * an alignment or dataset.
36    *
37    * @author $author$
38    * @version $Revision$
39    */
 
40    public interface SequenceI extends ASequenceI
41    {
42    /**
43    * Set the display name for the sequence
44    *
45    * @param name
46    */
47    public void setName(String name);
48   
49    /**
50    * Get the display name
51    */
52    public String getName();
53   
54    /**
55    * Set start position of first non-gapped symbol in sequence
56    *
57    * @param start
58    * new start position
59    */
60    public void setStart(int start);
61   
62    /**
63    * get start position of first non-gapped residue in sequence
64    *
65    * @return
66    */
67    public int getStart();
68   
69    /**
70    * get the displayed id of the sequence
71    *
72    * @return true means the id will be returned in the form
73    * DisplayName/Start-End
74    */
75    public String getDisplayId(boolean jvsuffix);
76   
77    /**
78    * set end position for last residue in sequence
79    *
80    * @param end
81    */
82    public void setEnd(int end);
83   
84    /**
85    * get end position for last residue in sequence getEnd()>getStart() unless
86    * sequence only consists of gap characters
87    *
88    * @return
89    */
90    public int getEnd();
91   
92    /**
93    * @return length of sequence including gaps
94    *
95    */
96    public int getLength();
97   
98    /**
99    * Replace the sequence with the given string
100    *
101    * @param sequence
102    * new sequence string
103    */
104    public void setSequence(String sequence);
105   
106    /**
107    * @return sequence as string
108    */
109    public String getSequenceAsString();
110   
111    /**
112    * get a range on the sequence as a string
113    *
114    * @param start
115    * position relative to start of sequence including gaps (from 0)
116    * @param end
117    * position relative to start of sequence including gaps (from 0)
118    *
119    * @return String containing all gap and symbols in specified range
120    */
121    public String getSequenceAsString(int start, int end);
122   
123    /**
124    * Answers a copy of the sequence as a character array
125    *
126    * @return
127    */
128    public char[] getSequence();
129   
130    /**
131    * get stretch of sequence characters in an array
132    *
133    * @param start
134    * absolute index into getSequence()
135    * @param end
136    * exclusive index of last position in segment to be returned.
137    *
138    * @return char[max(0,end-start)];
139    */
140    public char[] getSequence(int start, int end);
141   
142    /**
143    * create a new sequence object with a subsequence of this one but sharing the
144    * same dataset sequence
145    *
146    * @param start
147    * int index for start position (base 0, inclusive)
148    * @param end
149    * int index for end position (base 0, exclusive)
150    *
151    * @return SequenceI
152    * @note implementations may use getSequence to get the sequence data
153    */
154    public SequenceI getSubSequence(int start, int end);
155   
156    /**
157    * get the i'th character in this sequence's local reference frame (ie from
158    * 0-number of characters lying from start-end)
159    *
160    * @param i
161    * index
162    * @return character or ' '
163    */
164    public char getCharAt(int i);
165   
166    /**
167    * DOCUMENT ME!
168    *
169    * @param desc
170    * DOCUMENT ME!
171    */
172    public void setDescription(String desc);
173   
174    /**
175    * DOCUMENT ME!
176    *
177    * @return DOCUMENT ME!
178    */
179    public String getDescription();
180   
181    /**
182    * Return the alignment column (from 1..) for a sequence position
183    *
184    * @param pos
185    * lying from start to end
186    *
187    * @return aligned column for residue (0 if residue is upstream from
188    * alignment, -1 if residue is downstream from alignment) note.
189    * Sequence object returns sequence.getEnd() for positions upstream
190    * currently. TODO: change sequence for
191    * assert(findIndex(seq.getEnd()+1)==-1) and fix incremental bugs
192    *
193    */
194    public int findIndex(int pos);
195   
196    /**
197    * Returns the sequence position for an alignment (column) position. If at a
198    * gap, returns the position of the next residue to the right. If beyond the
199    * end of the sequence, returns 1 more than the last residue position.
200    *
201    * @param i
202    * column index in alignment (from 0..<length)
203    *
204    * @return
205    */
206    public int findPosition(int i);
207   
208    /**
209    * Returns the from-to sequence positions (start..) for the given column
210    * positions (1..), or null if no residues are included in the range
211    *
212    * @param fromColum
213    * @param toColumn
214    * @return
215    */
216    public Range findPositions(int fromColum, int toColumn);
217   
218    /**
219    * Returns an int array where indices correspond to each residue in the
220    * sequence and the element value gives its position in the alignment
221    *
222    * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
223    * residues in SequenceI object
224    */
225    public int[] gapMap();
226   
227    /**
228    * Build a bitset corresponding to sequence gaps
229    *
230    * @return a BitSet where set values correspond to gaps in the sequence
231    */
232    public BitSet gapBitset();
233   
234    /**
235    * Returns an int array where indices correspond to each position in sequence
236    * char array and the element value gives the result of findPosition for that
237    * index in the sequence.
238    *
239    * @return int[SequenceI.getLength()]
240    */
241    public int[] findPositionMap();
242   
243    /**
244    * Answers true if the sequence is composed of amino acid characters. Note
245    * that implementations may use heuristic methods which are not guaranteed to
246    * give the biologically 'right' answer.
247    *
248    * @return
249    */
250    public boolean isProtein();
251   
252    /**
253    * Delete a range of aligned sequence columns, creating a new dataset sequence
254    * if necessary and adjusting start and end positions accordingly.
255    *
256    * @param i
257    * first column in range to delete (inclusive)
258    * @param j
259    * last column in range to delete (exclusive)
260    */
261    public void deleteChars(int i, int j);
262   
263    /**
264    * DOCUMENT ME!
265    *
266    * @param i
267    * alignment column number
268    * @param c
269    * character to insert
270    */
271    public void insertCharAt(int i, char c);
272   
273    /**
274    * insert given character at alignment column position
275    *
276    * @param position
277    * alignment column number
278    * @param count
279    * length of insert
280    * @param ch
281    * character to insert
282    */
283    public void insertCharAt(int position, int count, char ch);
284   
285    /**
286    * Answers a list of all sequence features associated with this sequence. The
287    * list may be held by the sequence's dataset sequence if that is defined.
288    *
289    * @return
290    */
291    public List<SequenceFeature> getSequenceFeatures();
292   
293    /**
294    * Answers the object holding features for the sequence
295    *
296    * @return
297    */
298    SequenceFeaturesI getFeatures();
299   
300    /**
301    * Replaces the sequence features associated with this sequence with the given
302    * features. If this sequence has a dataset sequence, then this method will
303    * update the dataset sequence's features instead.
304    *
305    * @param features
306    */
307    public void setSequenceFeatures(List<SequenceFeature> features);
308   
309    /**
310    * DOCUMENT ME!
311    *
312    * @param id
313    * DOCUMENT ME!
314    */
315    public void setPDBId(Vector<PDBEntry> ids);
316   
317    /**
318    * Returns a list
319    *
320    * @return DOCUMENT ME!
321    */
322    public Vector<PDBEntry> getAllPDBEntries();
323   
324    /**
325    * Adds the entry to the *normalised* list of PDBIds.
326    *
327    * If a PDBEntry is passed with the same entry.getID() string as one already
328    * in the list, or one is added that appears to be the same but has a chain ID
329    * appended, then the existing PDBEntry will be updated with the new
330    * attributes instead, unless the entries have distinct chain codes or
331    * associated structure files.
332    *
333    * @param entry
334    * @return true if the entry was added, false if updated
335    */
336    public boolean addPDBId(PDBEntry entry);
337   
338    /**
339    * update the list of PDBEntrys to include any DBRefEntrys citing structural
340    * databases
341    *
342    * @return true if PDBEntry list was modified
343    */
344    public boolean updatePDBIds();
345   
346    public String getVamsasId();
347   
348    public void setVamsasId(String id);
349   
350    /**
351    * set the array of Database references for the sequence.
352    *
353    * @param dbs
354    * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
355    * set are not normalised.
356    */
357    @Deprecated
358    public void setDBRefs(DBRefEntry[] dbs);
359   
360    public DBRefEntry[] getDBRefs();
361   
362    /**
363    * add the given entry to the list of DBRefs for this sequence, or replace a
364    * similar one if entry contains a map object and the existing one doesnt.
365    *
366    * @param entry
367    */
368    public void addDBRef(DBRefEntry entry);
369   
370    /**
371    * Adds the given sequence feature and returns true, or returns false if it is
372    * already present on the sequence, or if the feature type is null.
373    *
374    * @param sf
375    * @return
376    */
377    public boolean addSequenceFeature(SequenceFeature sf);
378   
379    public void deleteFeature(SequenceFeature sf);
380   
381    public void setDatasetSequence(SequenceI seq);
382   
383    public SequenceI getDatasetSequence();
384   
385    /**
386    * Returns a new array containing this sequence's annotations, or null.
387    */
388    public AlignmentAnnotation[] getAnnotation();
389   
390    /**
391    * Returns true if this sequence has the given annotation (by object
392    * identity).
393    */
394    public boolean hasAnnotation(AlignmentAnnotation ann);
395   
396    /**
397    * Add the given annotation, if not already added, and set its sequence ref to
398    * be this sequence. Does nothing if this sequence's annotations already
399    * include this annotation (by identical object reference).
400    */
401    public void addAlignmentAnnotation(AlignmentAnnotation annotation);
402   
403    public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
404   
405    /**
406    * Derive a sequence (using this one's dataset or as the dataset)
407    *
408    * @return duplicate sequence with valid dataset sequence
409    */
410    public SequenceI deriveSequence();
411   
412    /**
413    * set the array of associated AlignmentAnnotation for this sequenceI
414    *
415    * @param revealed
416    */
417    public void setAlignmentAnnotation(AlignmentAnnotation[] annotation);
418   
419    /**
420    * Get one or more alignment annotations with a particular label.
421    *
422    * @param label
423    * string which each returned annotation must have as a label.
424    * @return null or array of annotations.
425    */
426    public AlignmentAnnotation[] getAnnotation(String label);
427   
428    /**
429    * Returns a (possibly empty) list of any annotations that match on given
430    * calcId (source) and label (type). Null values do not match.
431    *
432    * @param calcId
433    * @param label
434    */
435    public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
436    String label);
437   
438    /**
439    * create a new dataset sequence (if necessary) for this sequence and sets
440    * this sequence to refer to it. This call will move any features or
441    * references on the sequence onto the dataset. It will also make a duplicate
442    * of existing annotation rows for the dataset sequence, rather than relocate
443    * them in order to preserve external references (since 2.8.2).
444    *
445    * @return dataset sequence for this sequence
446    */
447    public SequenceI createDatasetSequence();
448   
449    /**
450    * Transfer any database references or annotation from entry under a sequence
451    * mapping. <br/>
452    * <strong>Note: DOES NOT transfer sequence associated alignment annotation
453    * </strong><br/>
454    *
455    * @param entry
456    * @param mp
457    * null or mapping from entry's numbering to local start/end
458    */
459    public void transferAnnotation(SequenceI entry, Mapping mp);
460   
461    /**
462    * @return The RNA of the sequence in the alignment
463    */
464   
465    public RNA getRNA();
466   
467    /**
468    * @param rna
469    * The RNA.
470    */
471    public void setRNA(RNA rna);
472   
473    /**
474    *
475    * @return list of insertions (gap characters) in sequence
476    */
477    public List<int[]> getInsertions();
478   
479    /**
480    * Given a pdbId String, return the equivalent PDBEntry if available in the
481    * given sequence
482    *
483    * @param pdbId
484    * @return
485    */
486    public PDBEntry getPDBEntry(String pdbId);
487   
488    /**
489    * Get all primary database/accessions for this sequence's data. These
490    * DBRefEntry are expected to resolve to a valid record in the associated
491    * external database, either directly or via a provided 1:1 Mapping.
492    *
493    * @return just the primary references (if any) for this sequence, or an empty
494    * list
495    */
496    public List<DBRefEntry> getPrimaryDBRefs();
497   
498    /**
499    * Returns a (possibly empty) list of sequence features that overlap the given
500    * alignment column range, optionally restricted to one or more specified
501    * feature types. If the range is all gaps, then features which enclose it are
502    * included (but not contact features).
503    *
504    * @param fromCol
505    * start column of range inclusive (1..)
506    * @param toCol
507    * end column of range inclusive (1..)
508    * @param types
509    * optional feature types to restrict results to
510    * @return
511    */
512    List<SequenceFeature> findFeatures(int fromCol, int toCol, String... types);
513   
514    /**
515    * Method to call to indicate that the sequence (characters or alignment/gaps)
516    * has been modified. Provided to allow any cursors on residue/column
517    * positions to be invalidated.
518    */
519    void sequenceChanged();
520   
521    /**
522    *
523    * @return BitSet corresponding to index [0,length) where Comparison.isGap()
524    * returns true.
525    */
526    BitSet getInsertionsAsBits();
527   
528    /**
529    * Replaces every occurrence of c1 in the sequence with c2 and returns the
530    * number of characters changed
531    *
532    * @param c1
533    * @param c2
534    */
535    public int replace(char c1, char c2);
536   
537    /**
538    * Answers the GeneLociI, or null if not known
539    *
540    * @return
541    */
542    GeneLociI getGeneLoci();
543   
544    /**
545    * Sets the mapping to gene loci for the sequence
546    *
547    * @param speciesId
548    * @param assemblyId
549    * @param chromosomeId
550    * @param map
551    */
552    void setGeneLoci(String speciesId, String assemblyId,
553    String chromosomeId, MapList map);
554   
555   
556    /**
557    * Returns the sequence string constructed from the substrings of a sequence
558    * defined by the int[] ranges provided by an iterator. E.g. the iterator
559    * could iterate over all visible regions of the alignment
560    *
561    * @param it
562    * the iterator to use
563    * @return a String corresponding to the sequence
564    */
565    public String getSequenceStringFromIterator(Iterator<int[]> it);
566   
567    /**
568    * Locate the first position in this sequence which is not contained in an
569    * iterator region. If no such position exists, return 0
570    *
571    * @param it
572    * iterator over regions
573    * @return first residue not contained in regions
574    */
575    public int firstResidueOutsideIterator(Iterator<int[]> it);
576    }