2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.1)
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 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
17 * The Jalview Authors are detailed in the 'AUTHORS' file.
19 package jalview.datamodel;
21 import jalview.analysis.AlignSeq;
23 import java.util.Enumeration;
24 import java.util.Vector;
28 * Implements the SequenceI interface for a char[] based sequence object.
33 public class Sequence implements SequenceI
35 SequenceI datasetSequence;
39 private char[] sequence;
54 * This annotation is displayed below the alignment but the positions are tied
55 * to the residues of this sequence
60 * The index of the sequence in a MSA
64 /** array of seuqence features - may not be null for a valid sequence object */
65 public SequenceFeature[] sequenceFeatures;
68 * Creates a new Sequence object.
73 * string to form a possibly gapped sequence out of
75 * first position of non-gap residue in the sequence
77 * last position of ungapped residues (nearly always only used for
80 public Sequence(String name, String sequence, int start, int end)
83 this.sequence = sequence.toCharArray();
90 public Sequence(String name, char[] sequence, int start, int end)
93 this.sequence = sequence;
100 com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex(
101 "[/][0-9]{1,}[-][0-9]{1,}$");
103 com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex("[0-9]{1,}$");
110 .println("POSSIBLE IMPLEMENTATION ERROR: null sequence name passed to constructor.");
113 // Does sequence have the /start-end signiature?
114 if (limitrx.search(name))
116 name = limitrx.left();
117 endrx.search(limitrx.stringMatched());
118 setStart(Integer.parseInt(limitrx.stringMatched().substring(1,
119 endrx.matchedFrom() - 1)));
120 setEnd(Integer.parseInt(endrx.stringMatched()));
124 void checkValidRange()
127 // http://issues.jalview.org/browse/JAL-774?focusedCommentId=11239&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-11239
130 for (int j = 0; j < sequence.length; j++)
132 if (!jalview.util.Comparison.isGap(sequence[j]))
151 * Creates a new Sequence object.
158 public Sequence(String name, String sequence)
160 this(name, sequence, 1, -1);
164 * Creates a new Sequence object with new features, DBRefEntries,
165 * AlignmentAnnotations, and PDBIds but inherits any existing dataset sequence
171 public Sequence(SequenceI seq)
173 this(seq, seq.getAnnotation());
177 * Create a new sequence object with new features, DBRefEntries, and PDBIds
178 * but inherits any existing dataset sequence reference, and duplicate of any
179 * annotation that is present in the given annotation array.
182 * the sequence to be copied
183 * @param alAnnotation
184 * an array of annotation including some associated with seq
186 public Sequence(SequenceI seq, AlignmentAnnotation[] alAnnotation)
188 this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd());
189 description = seq.getDescription();
190 if (seq.getSequenceFeatures() != null)
192 SequenceFeature[] sf = seq.getSequenceFeatures();
193 for (int i = 0; i < sf.length; i++)
195 addSequenceFeature(new SequenceFeature(sf[i]));
198 setDatasetSequence(seq.getDatasetSequence());
199 if (datasetSequence == null && seq.getDBRef() != null)
201 // only copy DBRefs if we really are a dataset sequence
202 DBRefEntry[] dbr = seq.getDBRef();
203 for (int i = 0; i < dbr.length; i++)
205 addDBRef(new DBRefEntry(dbr[i]));
208 if (seq.getAnnotation() != null)
210 AlignmentAnnotation[] sqann = seq.getAnnotation();
211 for (int i = 0; i < sqann.length; i++)
213 if (sqann[i] == null)
217 boolean found = (alAnnotation == null);
220 for (int apos = 0; !found && apos < alAnnotation.length; apos++)
222 found = (alAnnotation[apos] == sqann[i]);
227 // only copy the given annotation
228 AlignmentAnnotation newann = new AlignmentAnnotation(sqann[i]);
229 addAlignmentAnnotation(newann);
233 if (seq.getPDBId() != null)
235 Vector ids = seq.getPDBId();
236 Enumeration e = ids.elements();
237 while (e.hasMoreElements())
239 this.addPDBId(new PDBEntry((PDBEntry) e.nextElement()));
250 public void setSequenceFeatures(SequenceFeature[] features)
252 sequenceFeatures = features;
255 public synchronized void addSequenceFeature(SequenceFeature sf)
257 if (sequenceFeatures == null)
259 sequenceFeatures = new SequenceFeature[0];
262 for (int i = 0; i < sequenceFeatures.length; i++)
264 if (sequenceFeatures[i].equals(sf))
270 SequenceFeature[] temp = new SequenceFeature[sequenceFeatures.length + 1];
271 System.arraycopy(sequenceFeatures, 0, temp, 0, sequenceFeatures.length);
272 temp[sequenceFeatures.length] = sf;
274 sequenceFeatures = temp;
277 public void deleteFeature(SequenceFeature sf)
279 if (sequenceFeatures == null)
285 for (index = 0; index < sequenceFeatures.length; index++)
287 if (sequenceFeatures[index].equals(sf))
293 if (index == sequenceFeatures.length)
298 int sfLength = sequenceFeatures.length;
301 sequenceFeatures = null;
305 SequenceFeature[] temp = new SequenceFeature[sfLength - 1];
306 System.arraycopy(sequenceFeatures, 0, temp, 0, index);
308 if (index < sfLength)
310 System.arraycopy(sequenceFeatures, index + 1, temp, index,
311 sequenceFeatures.length - index - 1);
314 sequenceFeatures = temp;
321 * @return DOCUMENT ME!
323 public SequenceFeature[] getSequenceFeatures()
325 return sequenceFeatures;
328 public void addPDBId(PDBEntry entry)
332 pdbIds = new Vector();
334 if (!pdbIds.contains(entry))
336 pdbIds.addElement(entry);
346 public void setPDBId(Vector id)
354 * @return DOCUMENT ME!
356 public Vector getPDBId()
364 * @return DOCUMENT ME!
366 public String getDisplayId(boolean jvsuffix)
368 StringBuffer result = new StringBuffer(name);
371 result.append("/" + start + "-" + end);
374 return result.toString();
383 public void setName(String name)
392 * @return DOCUMENT ME!
394 public String getName()
405 public void setStart(int start)
413 * @return DOCUMENT ME!
415 public int getStart()
426 public void setEnd(int end)
434 * @return DOCUMENT ME!
444 * @return DOCUMENT ME!
446 public int getLength()
448 return this.sequence.length;
457 public void setSequence(String seq)
459 this.sequence = seq.toCharArray();
463 public String getSequenceAsString()
465 return new String(sequence);
468 public String getSequenceAsString(int start, int end)
470 return new String(getSequence(start, end));
473 public char[] getSequence()
481 * @see jalview.datamodel.SequenceI#getSequence(int, int)
483 public char[] getSequence(int start, int end)
487 // JBPNote - left to user to pad the result here (TODO:Decide on this
489 if (start >= sequence.length)
494 if (end >= sequence.length)
496 end = sequence.length;
499 char[] reply = new char[end - start];
500 System.arraycopy(sequence, start, reply, 0, end - start);
506 * make a new Sequence object from start to end (including gaps) over this
515 public SequenceI getSubSequence(int start, int end)
521 char[] seq = getSequence(start, end);
526 int nstart = findPosition(start);
527 int nend = findPosition(end) - 1;
528 // JBPNote - this is an incomplete copy.
529 SequenceI nseq = new Sequence(this.getName(), seq, nstart, nend);
530 nseq.setDescription(description);
531 if (datasetSequence != null)
533 nseq.setDatasetSequence(datasetSequence);
537 nseq.setDatasetSequence(this);
548 * @return DOCUMENT ME!
550 public char getCharAt(int i)
552 if (i < sequence.length)
568 public void setDescription(String desc)
570 this.description = desc;
576 * @return DOCUMENT ME!
578 public String getDescription()
580 return this.description;
586 * @see jalview.datamodel.SequenceI#findIndex(int)
588 public int findIndex(int pos)
590 // returns the alignment position for a residue
593 // Rely on end being at least as long as the length of the sequence.
594 while ((i < sequence.length) && (j <= end) && (j <= pos))
596 if (!jalview.util.Comparison.isGap(sequence[i]))
604 if ((j == end) && (j < pos))
615 * Returns the sequence position for an alignment position
618 * column index in alignment (from 1)
620 * @return residue number for residue (left of and) nearest ith column
622 public int findPosition(int i)
626 int seqlen = sequence.length;
627 while ((j < i) && (j < seqlen))
629 if (!jalview.util.Comparison.isGap(sequence[j]))
641 * Returns an int array where indices correspond to each residue in the
642 * sequence and the element value gives its position in the alignment
644 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
645 * residues in SequenceI object
647 public int[] gapMap()
649 String seq = jalview.analysis.AlignSeq.extractGaps(
650 jalview.util.Comparison.GapChars, new String(sequence));
651 int[] map = new int[seq.length()];
655 while (j < sequence.length)
657 if (!jalview.util.Comparison.isGap(sequence[j]))
671 * @see jalview.datamodel.SequenceI#findPositionMap()
673 public int[] findPositionMap()
675 int map[] = new int[sequence.length];
678 int seqlen = sequence.length;
682 if (!jalview.util.Comparison.isGap(sequence[j]))
695 * @see jalview.datamodel.SequenceI#deleteChars(int, int)
697 public void deleteChars(int i, int j)
699 int newstart = start, newend = end;
700 if (i >= sequence.length)
707 if (j >= sequence.length)
710 System.arraycopy(sequence, 0, tmp, 0, i);
715 tmp = new char[sequence.length - j + i];
716 System.arraycopy(sequence, 0, tmp, 0, i);
717 System.arraycopy(sequence, j, tmp, i, sequence.length - j);
719 boolean createNewDs = false;
720 // TODO: take a look at the new dataset creation validation method below -
721 // this could become time comsuming for large sequences - consider making it
723 for (int s = i; s < j; s++)
725 if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23)
733 int sindex = findIndex(start) - 1;
736 // delete characters including start of sequence
737 newstart = findPosition(j);
738 break; // don't need to search for any more residue characters.
742 // delete characters after start.
743 int eindex = findIndex(end) - 1;
746 // delete characters at end of sequence
747 newend = findPosition(i - 1);
748 break; // don't need to search for any more residue characters.
753 newend--; // decrease end position by one for the deleted residue
754 // and search further
760 // deletion occured in the middle of the sequence
761 if (createNewDs && this.datasetSequence != null)
763 // construct a new sequence
764 Sequence ds = new Sequence(datasetSequence);
765 // TODO: remove any non-inheritable properties ?
766 // TODO: create a sequence mapping (since there is a relation here ?)
767 ds.deleteChars(i, j);
768 datasetSequence = ds;
785 public void insertCharAt(int i, int length, char c)
787 char[] tmp = new char[sequence.length + length];
789 if (i >= sequence.length)
791 System.arraycopy(sequence, 0, tmp, 0, sequence.length);
796 System.arraycopy(sequence, 0, tmp, 0, i);
806 if (i < sequence.length)
808 System.arraycopy(sequence, i, tmp, index, sequence.length - i);
814 public void insertCharAt(int i, char c)
816 insertCharAt(i, 1, c);
819 public String getVamsasId()
824 public void setVamsasId(String id)
829 public void setDBRef(DBRefEntry[] dbref)
834 public DBRefEntry[] getDBRef()
836 if (dbrefs == null && datasetSequence != null
837 && this != datasetSequence)
839 return datasetSequence.getDBRef();
844 public void addDBRef(DBRefEntry entry)
848 dbrefs = new DBRefEntry[0];
851 int i, iSize = dbrefs.length;
853 for (i = 0; i < iSize; i++)
855 if (dbrefs[i].equalRef(entry))
857 if (entry.getMap() != null)
859 if (dbrefs[i].getMap() == null)
861 // overwrite with 'superior' entry that contains a mapping.
869 DBRefEntry[] temp = new DBRefEntry[iSize + 1];
870 System.arraycopy(dbrefs, 0, temp, 0, iSize);
871 temp[temp.length - 1] = entry;
876 public void setDatasetSequence(SequenceI seq)
878 datasetSequence = seq;
881 public SequenceI getDatasetSequence()
883 return datasetSequence;
886 public AlignmentAnnotation[] getAnnotation()
888 if (annotation == null)
893 AlignmentAnnotation[] ret = new AlignmentAnnotation[annotation.size()];
894 for (int r = 0; r < ret.length; r++)
896 ret[r] = (AlignmentAnnotation) annotation.elementAt(r);
902 public void addAlignmentAnnotation(AlignmentAnnotation annotation)
904 if (this.annotation == null)
906 this.annotation = new Vector();
908 if (!this.annotation.contains(annotation))
910 this.annotation.addElement(annotation);
912 annotation.setSequenceRef(this);
915 public void removeAlignmentAnnotation(AlignmentAnnotation annotation)
917 if (this.annotation != null)
919 this.annotation.removeElement(annotation);
920 if (this.annotation.size() == 0)
921 this.annotation = null;
926 * test if this is a valid candidate for another sequence's dataset sequence.
929 private boolean isValidDatasetSequence()
931 if (datasetSequence != null)
935 for (int i = 0; i < sequence.length; i++)
937 if (jalview.util.Comparison.isGap(sequence[i]))
948 * @see jalview.datamodel.SequenceI#deriveSequence()
950 public SequenceI deriveSequence()
952 SequenceI seq = new Sequence(this);
953 if (datasetSequence != null)
955 // duplicate current sequence with same dataset
956 seq.setDatasetSequence(datasetSequence);
960 if (isValidDatasetSequence())
962 // Use this as dataset sequence
963 seq.setDatasetSequence(this);
967 // Create a new, valid dataset sequence
969 ds.setSequence(AlignSeq.extractGaps(
970 jalview.util.Comparison.GapChars, new String(sequence)));
971 setDatasetSequence(ds);
972 ds.setSequenceFeatures(getSequenceFeatures());
973 seq = this; // and return this sequence as the derived sequence.
982 * @see jalview.datamodel.SequenceI#createDatasetSequence()
984 public SequenceI createDatasetSequence()
986 if (datasetSequence == null)
988 datasetSequence = new Sequence(getName(), AlignSeq.extractGaps(
989 jalview.util.Comparison.GapChars, getSequenceAsString()),
990 getStart(), getEnd());
991 datasetSequence.setSequenceFeatures(getSequenceFeatures());
992 datasetSequence.setDescription(getDescription());
993 setSequenceFeatures(null);
994 // move database references onto dataset sequence
995 datasetSequence.setDBRef(getDBRef());
997 datasetSequence.setPDBId(getPDBId());
999 datasetSequence.updatePDBIds();
1000 if (annotation != null)
1002 Vector<AlignmentAnnotation> _annot = annotation;
1004 for (AlignmentAnnotation aa : _annot)
1006 aa.sequenceRef = datasetSequence;
1007 aa.adjustForAlignment(); // uses annotation's own record of
1008 // sequence-column mapping
1009 datasetSequence.addAlignmentAnnotation(aa);
1013 return datasetSequence;
1020 * jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[]
1023 public void setAlignmentAnnotation(AlignmentAnnotation[] annotations)
1025 if (annotation != null)
1027 annotation.removeAllElements();
1029 if (annotations != null)
1031 for (int i = 0; i < annotations.length; i++)
1033 if (annotations[i] != null)
1034 addAlignmentAnnotation(annotations[i]);
1042 * @see jalview.datamodel.SequenceI#getAnnotation(java.lang.String)
1044 public AlignmentAnnotation[] getAnnotation(String label)
1046 if (annotation == null || annotation.size() == 0)
1051 Vector subset = new Vector();
1052 Enumeration e = annotation.elements();
1053 while (e.hasMoreElements())
1055 AlignmentAnnotation ann = (AlignmentAnnotation) e.nextElement();
1056 if (ann.label != null && ann.label.equals(label))
1058 subset.addElement(ann);
1061 if (subset.size() == 0)
1065 AlignmentAnnotation[] anns = new AlignmentAnnotation[subset.size()];
1067 e = subset.elements();
1068 while (e.hasMoreElements())
1070 anns[i++] = (AlignmentAnnotation) e.nextElement();
1072 subset.removeAllElements();
1076 public boolean updatePDBIds()
1078 if (datasetSequence != null)
1080 // TODO: could merge DBRefs
1081 return datasetSequence.updatePDBIds();
1083 if (dbrefs == null || dbrefs.length == 0)
1087 Vector newpdb = new Vector();
1088 for (int i = 0; i < dbrefs.length; i++)
1090 if (DBRefSource.PDB.equals(dbrefs[i].getSource()))
1092 PDBEntry pdbe = new PDBEntry();
1093 pdbe.setId(dbrefs[i].getAccessionId());
1094 if (pdbIds == null || pdbIds.size() == 0)
1096 newpdb.addElement(pdbe);
1100 Enumeration en = pdbIds.elements();
1101 boolean matched = false;
1102 while (!matched && en.hasMoreElements())
1104 PDBEntry anentry = (PDBEntry) en.nextElement();
1105 if (anentry.getId().equals(pdbe.getId()))
1112 newpdb.addElement(pdbe);
1117 if (newpdb.size() > 0)
1119 Enumeration en = newpdb.elements();
1120 while (en.hasMoreElements())
1122 addPDBId((PDBEntry) en.nextElement());
1133 * jalview.datamodel.SequenceI#transferAnnotation(jalview.datamodel.SequenceI,
1134 * jalview.datamodel.Mapping)
1136 public void transferAnnotation(SequenceI entry, Mapping mp)
1138 if (datasetSequence != null)
1140 datasetSequence.transferAnnotation(entry, mp);
1143 if (entry.getDatasetSequence() != null)
1145 transferAnnotation(entry.getDatasetSequence(), mp);
1148 // transfer any new features from entry onto sequence
1149 if (entry.getSequenceFeatures() != null)
1152 SequenceFeature[] sfs = entry.getSequenceFeatures();
1153 for (int si = 0; si < sfs.length; si++)
1155 SequenceFeature sf[] = (mp != null) ? mp.locateFeature(sfs[si])
1156 : new SequenceFeature[]
1157 { new SequenceFeature(sfs[si]) };
1158 if (sf != null && sf.length > 0)
1160 for (int sfi = 0; sfi < sf.length; sfi++)
1162 addSequenceFeature(sf[sfi]);
1168 // transfer PDB entries
1169 if (entry.getPDBId() != null)
1171 Enumeration e = entry.getPDBId().elements();
1172 while (e.hasMoreElements())
1174 PDBEntry pdb = (PDBEntry) e.nextElement();
1178 // transfer database references
1179 DBRefEntry[] entryRefs = entry.getDBRef();
1180 if (entryRefs != null)
1182 for (int r = 0; r < entryRefs.length; r++)
1184 DBRefEntry newref = new DBRefEntry(entryRefs[r]);
1185 if (newref.getMap() != null && mp != null)
1187 // remap ref using our local mapping
1189 // we also assume all version string setting is done by dbSourceProxy
1191 * if (!newref.getSource().equalsIgnoreCase(dbSource)) {
1192 * newref.setSource(dbSource); }
1200 * @return The index (zero-based) on this sequence in the MSA. It returns
1201 * {@code -1} if this information is not available.
1203 public int getIndex()
1209 * Defines the position of this sequence in the MSA. Use the value {@code -1}
1210 * if this information is undefined.
1213 * position for this sequence. This value is zero-based (zero for
1214 * this first sequence)
1216 public void setIndex(int value)