2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
3 * Copyright (C) 2014 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.analysis.AlignSeq;
25 import java.util.ArrayList;
26 import java.util.Enumeration;
27 import java.util.List;
28 import java.util.Vector;
30 import fr.orsay.lri.varna.models.rna.RNA;
34 * Implements the SequenceI interface for a char[] based sequence object.
39 public class Sequence implements SequenceI
41 SequenceI datasetSequence;
45 private char[] sequence;
62 * This annotation is displayed below the alignment but the positions are tied
63 * to the residues of this sequence
65 * TODO: change to List<>
67 Vector<AlignmentAnnotation> annotation;
70 * The index of the sequence in a MSA
74 /** array of sequence features - may not be null for a valid sequence object */
75 public SequenceFeature[] sequenceFeatures;
78 * Creates a new Sequence object.
83 * string to form a possibly gapped sequence out of
85 * first position of non-gap residue in the sequence
87 * last position of ungapped residues (nearly always only used for
90 public Sequence(String name, String sequence, int start, int end)
93 this.sequence = sequence.toCharArray();
100 public Sequence(String name, char[] sequence, int start, int end)
103 this.sequence = sequence;
110 com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex(
111 "[/][0-9]{1,}[-][0-9]{1,}$");
113 com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex("[0-9]{1,}$");
120 .println("POSSIBLE IMPLEMENTATION ERROR: null sequence name passed to constructor.");
123 // Does sequence have the /start-end signiature?
124 if (limitrx.search(name))
126 name = limitrx.left();
127 endrx.search(limitrx.stringMatched());
128 setStart(Integer.parseInt(limitrx.stringMatched().substring(1,
129 endrx.matchedFrom() - 1)));
130 setEnd(Integer.parseInt(endrx.stringMatched()));
134 void checkValidRange()
137 // http://issues.jalview.org/browse/JAL-774?focusedCommentId=11239&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-11239
140 for (int j = 0; j < sequence.length; j++)
142 if (!jalview.util.Comparison.isGap(sequence[j]))
161 * Creates a new Sequence object.
168 public Sequence(String name, String sequence)
170 this(name, sequence, 1, -1);
174 * Creates a new Sequence object with new features, DBRefEntries,
175 * AlignmentAnnotations, and PDBIds but inherits any existing dataset sequence
181 public Sequence(SequenceI seq)
183 this(seq, seq.getAnnotation());
187 * Create a new sequence object with new features, DBRefEntries, and PDBIds
188 * but inherits any existing dataset sequence reference, and duplicate of any
189 * annotation that is present in the given annotation array.
192 * the sequence to be copied
193 * @param alAnnotation
194 * an array of annotation including some associated with seq
196 public Sequence(SequenceI seq, AlignmentAnnotation[] alAnnotation)
198 this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd());
199 description = seq.getDescription();
200 if (seq.getSequenceFeatures() != null)
202 SequenceFeature[] sf = seq.getSequenceFeatures();
203 for (int i = 0; i < sf.length; i++)
205 addSequenceFeature(new SequenceFeature(sf[i]));
208 setDatasetSequence(seq.getDatasetSequence());
209 if (datasetSequence == null && seq.getDBRef() != null)
211 // only copy DBRefs if we really are a dataset sequence
212 DBRefEntry[] dbr = seq.getDBRef();
213 for (int i = 0; i < dbr.length; i++)
215 addDBRef(new DBRefEntry(dbr[i]));
218 if (seq.getAnnotation() != null)
220 AlignmentAnnotation[] sqann = seq.getAnnotation();
221 for (int i = 0; i < sqann.length; i++)
223 if (sqann[i] == null)
227 boolean found = (alAnnotation == null);
230 for (int apos = 0; !found && apos < alAnnotation.length; apos++)
232 found = (alAnnotation[apos] == sqann[i]);
237 // only copy the given annotation
238 AlignmentAnnotation newann = new AlignmentAnnotation(sqann[i]);
239 addAlignmentAnnotation(newann);
243 if (seq.getPDBId() != null)
245 Vector ids = seq.getPDBId();
246 Enumeration e = ids.elements();
247 while (e.hasMoreElements())
249 this.addPDBId(new PDBEntry((PDBEntry) e.nextElement()));
260 public void setSequenceFeatures(SequenceFeature[] features)
262 sequenceFeatures = features;
265 public synchronized void addSequenceFeature(SequenceFeature sf)
267 if (sequenceFeatures == null)
269 sequenceFeatures = new SequenceFeature[0];
272 for (int i = 0; i < sequenceFeatures.length; i++)
274 if (sequenceFeatures[i].equals(sf))
280 SequenceFeature[] temp = new SequenceFeature[sequenceFeatures.length + 1];
281 System.arraycopy(sequenceFeatures, 0, temp, 0, sequenceFeatures.length);
282 temp[sequenceFeatures.length] = sf;
284 sequenceFeatures = temp;
287 public void deleteFeature(SequenceFeature sf)
289 if (sequenceFeatures == null)
295 for (index = 0; index < sequenceFeatures.length; index++)
297 if (sequenceFeatures[index].equals(sf))
303 if (index == sequenceFeatures.length)
308 int sfLength = sequenceFeatures.length;
311 sequenceFeatures = null;
315 SequenceFeature[] temp = new SequenceFeature[sfLength - 1];
316 System.arraycopy(sequenceFeatures, 0, temp, 0, index);
318 if (index < sfLength)
320 System.arraycopy(sequenceFeatures, index + 1, temp, index,
321 sequenceFeatures.length - index - 1);
324 sequenceFeatures = temp;
329 * Returns the sequence features (if any), looking first on the sequence, then
330 * on its dataset sequence, and so on until a non-null value is found (or
331 * none). This supports retrieval of sequence features stored on the sequence
332 * (as in the applet) or on the dataset sequence (as in the Desktop version).
336 public SequenceFeature[] getSequenceFeatures()
338 SequenceFeature[] features = sequenceFeatures;
340 SequenceI seq = this;
341 int count = 0; // failsafe against loop in sequence.datasetsequence...
342 while (features == null && seq.getDatasetSequence() != null
345 seq = seq.getDatasetSequence();
346 features = ((Sequence) seq).sequenceFeatures;
351 public void addPDBId(PDBEntry entry)
355 pdbIds = new Vector();
357 if (!pdbIds.contains(entry))
359 pdbIds.addElement(entry);
369 public void setPDBId(Vector id)
377 * @return DOCUMENT ME!
379 public Vector getPDBId()
387 * @return DOCUMENT ME!
389 public String getDisplayId(boolean jvsuffix)
391 StringBuffer result = new StringBuffer(name);
394 result.append("/" + start + "-" + end);
397 return result.toString();
406 public void setName(String name)
415 * @return DOCUMENT ME!
417 public String getName()
428 public void setStart(int start)
436 * @return DOCUMENT ME!
438 public int getStart()
449 public void setEnd(int end)
457 * @return DOCUMENT ME!
467 * @return DOCUMENT ME!
469 public int getLength()
471 return this.sequence.length;
480 public void setSequence(String seq)
482 this.sequence = seq.toCharArray();
486 public String getSequenceAsString()
488 return new String(sequence);
491 public String getSequenceAsString(int start, int end)
493 return new String(getSequence(start, end));
496 public char[] getSequence()
504 * @see jalview.datamodel.SequenceI#getSequence(int, int)
506 public char[] getSequence(int start, int end)
512 // JBPNote - left to user to pad the result here (TODO:Decide on this
514 if (start >= sequence.length)
519 if (end >= sequence.length)
521 end = sequence.length;
524 char[] reply = new char[end - start];
525 System.arraycopy(sequence, start, reply, 0, end - start);
531 public SequenceI getSubSequence(int start, int end)
537 char[] seq = getSequence(start, end);
542 int nstart = findPosition(start);
543 int nend = findPosition(end) - 1;
544 // JBPNote - this is an incomplete copy.
545 SequenceI nseq = new Sequence(this.getName(), seq, nstart, nend);
546 nseq.setDescription(description);
547 if (datasetSequence != null)
549 nseq.setDatasetSequence(datasetSequence);
553 nseq.setDatasetSequence(this);
564 * @return DOCUMENT ME!
566 public char getCharAt(int i)
568 if (i < sequence.length)
584 public void setDescription(String desc)
586 this.description = desc;
592 * @return DOCUMENT ME!
594 public String getDescription()
596 return this.description;
602 * @see jalview.datamodel.SequenceI#findIndex(int)
604 public int findIndex(int pos)
606 // returns the alignment position for a residue
609 // Rely on end being at least as long as the length of the sequence.
610 while ((i < sequence.length) && (j <= end) && (j <= pos))
612 if (!jalview.util.Comparison.isGap(sequence[i]))
620 if ((j == end) && (j < pos))
631 public int findPosition(int i)
635 int seqlen = sequence.length;
636 while ((j < i) && (j < seqlen))
638 if (!jalview.util.Comparison.isGap(sequence[j]))
650 * Returns an int array where indices correspond to each residue in the
651 * sequence and the element value gives its position in the alignment
653 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
654 * residues in SequenceI object
656 public int[] gapMap()
658 String seq = jalview.analysis.AlignSeq.extractGaps(
659 jalview.util.Comparison.GapChars, new String(sequence));
660 int[] map = new int[seq.length()];
664 while (j < sequence.length)
666 if (!jalview.util.Comparison.isGap(sequence[j]))
678 public int[] findPositionMap()
680 int map[] = new int[sequence.length];
683 int seqlen = sequence.length;
687 if (!jalview.util.Comparison.isGap(sequence[j]))
698 public List<int[]> getInsertions()
700 ArrayList<int[]> map = new ArrayList<int[]>();
701 int lastj = -1, j = 0;
703 int seqlen = sequence.length;
706 if (jalview.util.Comparison.isGap(sequence[j]))
734 public void deleteChars(int i, int j)
736 int newstart = start, newend = end;
737 if (i >= sequence.length)
744 if (j >= sequence.length)
747 System.arraycopy(sequence, 0, tmp, 0, i);
752 tmp = new char[sequence.length - j + i];
753 System.arraycopy(sequence, 0, tmp, 0, i);
754 System.arraycopy(sequence, j, tmp, i, sequence.length - j);
756 boolean createNewDs = false;
757 // TODO: take a look at the new dataset creation validation method below -
758 // this could become time comsuming for large sequences - consider making it
760 for (int s = i; s < j; s++)
762 if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23)
770 int sindex = findIndex(start) - 1;
773 // delete characters including start of sequence
774 newstart = findPosition(j);
775 break; // don't need to search for any more residue characters.
779 // delete characters after start.
780 int eindex = findIndex(end) - 1;
783 // delete characters at end of sequence
784 newend = findPosition(i - 1);
785 break; // don't need to search for any more residue characters.
790 newend--; // decrease end position by one for the deleted residue
791 // and search further
797 // deletion occured in the middle of the sequence
798 if (createNewDs && this.datasetSequence != null)
800 // construct a new sequence
801 Sequence ds = new Sequence(datasetSequence);
802 // TODO: remove any non-inheritable properties ?
803 // TODO: create a sequence mapping (since there is a relation here ?)
804 ds.deleteChars(i, j);
805 datasetSequence = ds;
813 public void insertCharAt(int i, int length, char c)
815 char[] tmp = new char[sequence.length + length];
817 if (i >= sequence.length)
819 System.arraycopy(sequence, 0, tmp, 0, sequence.length);
824 System.arraycopy(sequence, 0, tmp, 0, i);
834 if (i < sequence.length)
836 System.arraycopy(sequence, i, tmp, index, sequence.length - i);
843 public void insertCharAt(int i, char c)
845 insertCharAt(i, 1, c);
849 public String getVamsasId()
855 public void setVamsasId(String id)
861 public void setDBRef(DBRefEntry[] dbref)
867 public DBRefEntry[] getDBRef()
869 if (dbrefs == null && datasetSequence != null
870 && this != datasetSequence)
872 return datasetSequence.getDBRef();
878 public void addDBRef(DBRefEntry entry)
882 dbrefs = new DBRefEntry[0];
885 int i, iSize = dbrefs.length;
887 for (i = 0; i < iSize; i++)
889 if (dbrefs[i].equalRef(entry))
891 if (entry.getMap() != null)
893 if (dbrefs[i].getMap() == null)
895 // overwrite with 'superior' entry that contains a mapping.
903 DBRefEntry[] temp = new DBRefEntry[iSize + 1];
904 System.arraycopy(dbrefs, 0, temp, 0, iSize);
905 temp[temp.length - 1] = entry;
911 public void setDatasetSequence(SequenceI seq)
913 datasetSequence = seq;
917 public SequenceI getDatasetSequence()
919 return datasetSequence;
923 public AlignmentAnnotation[] getAnnotation()
925 return annotation == null ? null : annotation
926 .toArray(new AlignmentAnnotation[annotation.size()]);
931 public boolean hasAnnotation(AlignmentAnnotation ann)
933 return annotation == null ? false : annotation.contains(ann);
937 public void addAlignmentAnnotation(AlignmentAnnotation annotation)
939 if (this.annotation == null)
941 this.annotation = new Vector();
943 if (!this.annotation.contains(annotation))
945 this.annotation.addElement(annotation);
947 annotation.setSequenceRef(this);
950 public void removeAlignmentAnnotation(AlignmentAnnotation annotation)
952 if (this.annotation != null)
954 this.annotation.removeElement(annotation);
955 if (this.annotation.size() == 0)
957 this.annotation = null;
963 * test if this is a valid candidate for another sequence's dataset sequence.
966 private boolean isValidDatasetSequence()
968 if (datasetSequence != null)
972 for (int i = 0; i < sequence.length; i++)
974 if (jalview.util.Comparison.isGap(sequence[i]))
983 public SequenceI deriveSequence()
985 SequenceI seq = new Sequence(this);
986 if (datasetSequence != null)
988 // duplicate current sequence with same dataset
989 seq.setDatasetSequence(datasetSequence);
993 if (isValidDatasetSequence())
995 // Use this as dataset sequence
996 seq.setDatasetSequence(this);
1000 // Create a new, valid dataset sequence
1002 ds.setSequence(AlignSeq.extractGaps(
1003 jalview.util.Comparison.GapChars, new String(sequence)));
1004 setDatasetSequence(ds);
1005 ds.setSequenceFeatures(getSequenceFeatures());
1006 seq = this; // and return this sequence as the derived sequence.
1015 * @see jalview.datamodel.SequenceI#createDatasetSequence()
1017 public SequenceI createDatasetSequence()
1019 if (datasetSequence == null)
1021 datasetSequence = new Sequence(getName(), AlignSeq.extractGaps(
1022 jalview.util.Comparison.GapChars, getSequenceAsString()),
1023 getStart(), getEnd());
1024 datasetSequence.setSequenceFeatures(getSequenceFeatures());
1025 datasetSequence.setDescription(getDescription());
1026 setSequenceFeatures(null);
1027 // move database references onto dataset sequence
1028 datasetSequence.setDBRef(getDBRef());
1030 datasetSequence.setPDBId(getPDBId());
1032 datasetSequence.updatePDBIds();
1033 if (annotation != null)
1035 for (AlignmentAnnotation aa : annotation)
1037 AlignmentAnnotation _aa = new AlignmentAnnotation(aa);
1038 _aa.sequenceRef = datasetSequence;
1039 _aa.adjustForAlignment(); // uses annotation's own record of
1040 // sequence-column mapping
1041 datasetSequence.addAlignmentAnnotation(_aa);
1045 return datasetSequence;
1052 * jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[]
1055 public void setAlignmentAnnotation(AlignmentAnnotation[] annotations)
1057 if (annotation != null)
1059 annotation.removeAllElements();
1061 if (annotations != null)
1063 for (int i = 0; i < annotations.length; i++)
1065 if (annotations[i] != null)
1067 addAlignmentAnnotation(annotations[i]);
1074 public AlignmentAnnotation[] getAnnotation(String label)
1076 if (annotation == null || annotation.size() == 0)
1081 Vector subset = new Vector();
1082 Enumeration e = annotation.elements();
1083 while (e.hasMoreElements())
1085 AlignmentAnnotation ann = (AlignmentAnnotation) e.nextElement();
1086 if (ann.label != null && ann.label.equals(label))
1088 subset.addElement(ann);
1091 if (subset.size() == 0)
1095 AlignmentAnnotation[] anns = new AlignmentAnnotation[subset.size()];
1097 e = subset.elements();
1098 while (e.hasMoreElements())
1100 anns[i++] = (AlignmentAnnotation) e.nextElement();
1102 subset.removeAllElements();
1107 public boolean updatePDBIds()
1109 if (datasetSequence != null)
1111 // TODO: could merge DBRefs
1112 return datasetSequence.updatePDBIds();
1114 if (dbrefs == null || dbrefs.length == 0)
1118 Vector newpdb = new Vector();
1119 for (int i = 0; i < dbrefs.length; i++)
1121 if (DBRefSource.PDB.equals(dbrefs[i].getSource()))
1123 PDBEntry pdbe = new PDBEntry();
1124 pdbe.setId(dbrefs[i].getAccessionId());
1125 if (pdbIds == null || pdbIds.size() == 0)
1127 newpdb.addElement(pdbe);
1131 Enumeration en = pdbIds.elements();
1132 boolean matched = false;
1133 while (!matched && en.hasMoreElements())
1135 PDBEntry anentry = (PDBEntry) en.nextElement();
1136 if (anentry.getId().equals(pdbe.getId()))
1143 newpdb.addElement(pdbe);
1148 if (newpdb.size() > 0)
1150 Enumeration en = newpdb.elements();
1151 while (en.hasMoreElements())
1153 addPDBId((PDBEntry) en.nextElement());
1161 public void transferAnnotation(SequenceI entry, Mapping mp)
1163 if (datasetSequence != null)
1165 datasetSequence.transferAnnotation(entry, mp);
1168 if (entry.getDatasetSequence() != null)
1170 transferAnnotation(entry.getDatasetSequence(), mp);
1173 // transfer any new features from entry onto sequence
1174 if (entry.getSequenceFeatures() != null)
1177 SequenceFeature[] sfs = entry.getSequenceFeatures();
1178 for (int si = 0; si < sfs.length; si++)
1180 SequenceFeature sf[] = (mp != null) ? mp.locateFeature(sfs[si])
1181 : new SequenceFeature[]
1182 { new SequenceFeature(sfs[si]) };
1183 if (sf != null && sf.length > 0)
1185 for (int sfi = 0; sfi < sf.length; sfi++)
1187 addSequenceFeature(sf[sfi]);
1193 // transfer PDB entries
1194 if (entry.getPDBId() != null)
1196 Enumeration e = entry.getPDBId().elements();
1197 while (e.hasMoreElements())
1199 PDBEntry pdb = (PDBEntry) e.nextElement();
1203 // transfer database references
1204 DBRefEntry[] entryRefs = entry.getDBRef();
1205 if (entryRefs != null)
1207 for (int r = 0; r < entryRefs.length; r++)
1209 DBRefEntry newref = new DBRefEntry(entryRefs[r]);
1210 if (newref.getMap() != null && mp != null)
1212 // remap ref using our local mapping
1214 // we also assume all version string setting is done by dbSourceProxy
1216 * if (!newref.getSource().equalsIgnoreCase(dbSource)) {
1217 * newref.setSource(dbSource); }
1225 * @return The index (zero-based) on this sequence in the MSA. It returns
1226 * {@code -1} if this information is not available.
1228 public int getIndex()
1234 * Defines the position of this sequence in the MSA. Use the value {@code -1}
1235 * if this information is undefined.
1238 * position for this sequence. This value is zero-based (zero for
1239 * this first sequence)
1241 public void setIndex(int value)
1246 public void setRNA(RNA r)
1257 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
1260 List<AlignmentAnnotation> result = new ArrayList<AlignmentAnnotation>();
1261 if (this.annotation != null) {
1262 for (AlignmentAnnotation ann : annotation) {
1263 if (ann.calcId != null && ann.calcId.equals(calcId)
1264 && ann.label != null && ann.label.equals(label))