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;
24 import jalview.util.StringUtils;
26 import java.util.ArrayList;
27 import java.util.Enumeration;
28 import java.util.List;
29 import java.util.Vector;
31 import fr.orsay.lri.varna.models.rna.RNA;
35 * Implements the SequenceI interface for a char[] based sequence object.
40 public class Sequence implements SequenceI
42 SequenceI datasetSequence;
46 private char[] sequence;
63 * This annotation is displayed below the alignment but the positions are tied
64 * to the residues of this sequence
66 * TODO: change to List<>
68 Vector<AlignmentAnnotation> annotation;
71 * The index of the sequence in a MSA
75 /** array of sequence features - may not be null for a valid sequence object */
76 public SequenceFeature[] sequenceFeatures;
79 * Creates a new Sequence object.
84 * string to form a possibly gapped sequence out of
86 * first position of non-gap residue in the sequence
88 * last position of ungapped residues (nearly always only used for
91 public Sequence(String name, String sequence, int start, int end)
94 this.sequence = sequence.toCharArray();
101 public Sequence(String name, char[] sequence, int start, int end)
104 this.sequence = sequence;
111 com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex(
112 "[/][0-9]{1,}[-][0-9]{1,}$");
114 com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex("[0-9]{1,}$");
121 .println("POSSIBLE IMPLEMENTATION ERROR: null sequence name passed to constructor.");
124 // Does sequence have the /start-end signiature?
125 if (limitrx.search(name))
127 name = limitrx.left();
128 endrx.search(limitrx.stringMatched());
129 setStart(Integer.parseInt(limitrx.stringMatched().substring(1,
130 endrx.matchedFrom() - 1)));
131 setEnd(Integer.parseInt(endrx.stringMatched()));
135 void checkValidRange()
138 // http://issues.jalview.org/browse/JAL-774?focusedCommentId=11239&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-11239
141 for (int j = 0; j < sequence.length; j++)
143 if (!jalview.util.Comparison.isGap(sequence[j]))
162 * Creates a new Sequence object.
169 public Sequence(String name, String sequence)
171 this(name, sequence, 1, -1);
175 * Creates a new Sequence object with new features, DBRefEntries,
176 * AlignmentAnnotations, and PDBIds but inherits any existing dataset sequence
182 public Sequence(SequenceI seq)
184 this(seq, seq.getAnnotation());
188 * Create a new sequence object with new features, DBRefEntries, and PDBIds
189 * but inherits any existing dataset sequence reference, and duplicate of any
190 * annotation that is present in the given annotation array.
193 * the sequence to be copied
194 * @param alAnnotation
195 * an array of annotation including some associated with seq
197 public Sequence(SequenceI seq, AlignmentAnnotation[] alAnnotation)
199 this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd());
200 description = seq.getDescription();
201 if (seq.getSequenceFeatures() != null)
203 SequenceFeature[] sf = seq.getSequenceFeatures();
204 for (int i = 0; i < sf.length; i++)
206 addSequenceFeature(new SequenceFeature(sf[i]));
209 setDatasetSequence(seq.getDatasetSequence());
210 if (datasetSequence == null && seq.getDBRef() != null)
212 // only copy DBRefs if we really are a dataset sequence
213 DBRefEntry[] dbr = seq.getDBRef();
214 for (int i = 0; i < dbr.length; i++)
216 addDBRef(new DBRefEntry(dbr[i]));
219 if (seq.getAnnotation() != null)
221 AlignmentAnnotation[] sqann = seq.getAnnotation();
222 for (int i = 0; i < sqann.length; i++)
224 if (sqann[i] == null)
228 boolean found = (alAnnotation == null);
231 for (int apos = 0; !found && apos < alAnnotation.length; apos++)
233 found = (alAnnotation[apos] == sqann[i]);
238 // only copy the given annotation
239 AlignmentAnnotation newann = new AlignmentAnnotation(sqann[i]);
240 addAlignmentAnnotation(newann);
244 if (seq.getPDBId() != null)
246 Vector ids = seq.getPDBId();
247 Enumeration e = ids.elements();
248 while (e.hasMoreElements())
250 this.addPDBId(new PDBEntry((PDBEntry) e.nextElement()));
261 public void setSequenceFeatures(SequenceFeature[] features)
263 sequenceFeatures = features;
266 public synchronized void addSequenceFeature(SequenceFeature sf)
268 if (sequenceFeatures == null)
270 sequenceFeatures = new SequenceFeature[0];
273 for (int i = 0; i < sequenceFeatures.length; i++)
275 if (sequenceFeatures[i].equals(sf))
281 SequenceFeature[] temp = new SequenceFeature[sequenceFeatures.length + 1];
282 System.arraycopy(sequenceFeatures, 0, temp, 0, sequenceFeatures.length);
283 temp[sequenceFeatures.length] = sf;
285 sequenceFeatures = temp;
288 public void deleteFeature(SequenceFeature sf)
290 if (sequenceFeatures == null)
296 for (index = 0; index < sequenceFeatures.length; index++)
298 if (sequenceFeatures[index].equals(sf))
304 if (index == sequenceFeatures.length)
309 int sfLength = sequenceFeatures.length;
312 sequenceFeatures = null;
316 SequenceFeature[] temp = new SequenceFeature[sfLength - 1];
317 System.arraycopy(sequenceFeatures, 0, temp, 0, index);
319 if (index < sfLength)
321 System.arraycopy(sequenceFeatures, index + 1, temp, index,
322 sequenceFeatures.length - index - 1);
325 sequenceFeatures = temp;
332 * @return DOCUMENT ME!
334 public SequenceFeature[] getSequenceFeatures()
336 return sequenceFeatures;
339 public void addPDBId(PDBEntry entry)
343 pdbIds = new Vector();
345 if (!pdbIds.contains(entry))
347 pdbIds.addElement(entry);
357 public void setPDBId(Vector id)
365 * @return DOCUMENT ME!
367 public Vector getPDBId()
375 * @return DOCUMENT ME!
377 public String getDisplayId(boolean jvsuffix)
379 StringBuffer result = new StringBuffer(name);
382 result.append("/" + start + "-" + end);
385 return result.toString();
394 public void setName(String name)
403 * @return DOCUMENT ME!
405 public String getName()
416 public void setStart(int start)
424 * @return DOCUMENT ME!
426 public int getStart()
437 public void setEnd(int end)
445 * @return DOCUMENT ME!
455 * @return DOCUMENT ME!
457 public int getLength()
459 return this.sequence.length;
468 public void setSequence(String seq)
470 this.sequence = seq.toCharArray();
474 public String getSequenceAsString()
476 return new String(sequence);
479 public String getSequenceAsString(int start, int end)
481 return new String(getSequence(start, end));
484 public char[] getSequence()
492 * @see jalview.datamodel.SequenceI#getSequence(int, int)
494 public char[] getSequence(int start, int end)
500 // JBPNote - left to user to pad the result here (TODO:Decide on this
502 if (start >= sequence.length)
507 if (end >= sequence.length)
509 end = sequence.length;
512 char[] reply = new char[end - start];
513 System.arraycopy(sequence, start, reply, 0, end - start);
519 public SequenceI getSubSequence(int start, int end)
525 char[] seq = getSequence(start, end);
530 int nstart = findPosition(start);
531 int nend = findPosition(end) - 1;
532 // JBPNote - this is an incomplete copy.
533 SequenceI nseq = new Sequence(this.getName(), seq, nstart, nend);
534 nseq.setDescription(description);
535 if (datasetSequence != null)
537 nseq.setDatasetSequence(datasetSequence);
541 nseq.setDatasetSequence(this);
552 * @return DOCUMENT ME!
554 public char getCharAt(int i)
556 if (i < sequence.length)
572 public void setDescription(String desc)
574 this.description = desc;
580 * @return DOCUMENT ME!
582 public String getDescription()
584 return this.description;
590 * @see jalview.datamodel.SequenceI#findIndex(int)
592 public int findIndex(int pos)
594 // returns the alignment position for a residue
597 // Rely on end being at least as long as the length of the sequence.
598 while ((i < sequence.length) && (j <= end) && (j <= pos))
600 if (!jalview.util.Comparison.isGap(sequence[i]))
608 if ((j == end) && (j < pos))
619 * Returns the (1-based) residue position for a (0-based) alignment position
622 * column index in alignment (from 0..<length)
624 * @return residue number for residue (left of and) nearest ith column
627 public int findPosition(int i)
631 int seqlen = sequence.length;
632 while ((j < i) && (j < seqlen))
634 if (!jalview.util.Comparison.isGap(sequence[j]))
646 * Returns an int array where indices correspond to each residue in the
647 * sequence and the element value gives its position in the alignment
649 * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
650 * residues in SequenceI object
652 public int[] gapMap()
654 String seq = jalview.analysis.AlignSeq.extractGaps(
655 jalview.util.Comparison.GapChars, new String(sequence));
656 int[] map = new int[seq.length()];
660 while (j < sequence.length)
662 if (!jalview.util.Comparison.isGap(sequence[j]))
676 * @see jalview.datamodel.SequenceI#findPositionMap()
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 * Delete sequence characters from position 'from' (inclusive) to 'to'
699 * (exclusive). The end range is limited to the length of the sequence. If the
700 * start position is out of range, do nothing.
702 * @see jalview.datamodel.SequenceI#deleteChars(int, int)
705 public void deleteChars(int from, int to)
707 if (from >= sequence.length)
711 if (to > sequence.length)
713 to = sequence.length;
715 char[] tmp = StringUtils.deleteChars(sequence, from, to);
717 recreateDatasetAfterDeletions(from, to);
722 * Reconstruct the dataset sequence, if necessary, after deletion of columns
723 * in the aligned sequence.
726 * start column of deletions (zero-based, inclusive)
728 * end column of deletions (exclusive)
730 protected boolean recreateDatasetAfterDeletions(int from, int to)
732 boolean created = false;
733 boolean createNewDs = false;
734 int newstart = start, newend = end;
735 // TODO: take a look at the new dataset creation validation method below -
736 // this could become time consuming for large sequences - consider making it
738 for (int s = from; s < to; s++)
740 if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23)
748 int sindex = findIndex(start) - 1;
751 // delete characters including start of sequence
752 newstart = findPosition(to);
753 break; // don't need to search for any more residue characters.
757 // delete characters after start.
758 int eindex = findIndex(end) - 1;
761 // delete characters at end of sequence
762 newend = findPosition(from - 1);
763 break; // don't need to search for any more residue characters.
768 newend--; // decrease end position by one for the deleted residue
769 // and search further
775 // deletion occured in the middle of the sequence
776 if (createNewDs && this.datasetSequence != null)
778 // construct a new sequence
779 Sequence ds = new Sequence(datasetSequence);
780 // TODO: remove any non-inheritable properties ?
781 // TODO: create a sequence mapping (since there is a relation here ?)
782 ds.deleteChars(from, to);
783 datasetSequence = ds;
792 public void insertCharAt(int i, char c)
794 insertCharAt(i, 1, c);
798 public void insertCharAt(int pos, int count, char c)
800 sequence = StringUtils.insertCharAt(sequence, pos, count, c);
803 public String getVamsasId()
808 public void setVamsasId(String id)
813 public void setDBRef(DBRefEntry[] dbref)
818 public DBRefEntry[] getDBRef()
820 if (dbrefs == null && datasetSequence != null
821 && this != datasetSequence)
823 return datasetSequence.getDBRef();
828 public void addDBRef(DBRefEntry entry)
832 dbrefs = new DBRefEntry[0];
835 int i, iSize = dbrefs.length;
837 for (i = 0; i < iSize; i++)
839 if (dbrefs[i].equalRef(entry))
841 if (entry.getMap() != null)
843 if (dbrefs[i].getMap() == null)
845 // overwrite with 'superior' entry that contains a mapping.
853 DBRefEntry[] temp = new DBRefEntry[iSize + 1];
854 System.arraycopy(dbrefs, 0, temp, 0, iSize);
855 temp[temp.length - 1] = entry;
860 public void setDatasetSequence(SequenceI seq)
862 datasetSequence = seq;
865 public SequenceI getDatasetSequence()
867 return datasetSequence;
871 * Returns a new array containing this sequence's annotations, or null.
873 public AlignmentAnnotation[] getAnnotation()
875 return annotation == null ? null : annotation
876 .toArray(new AlignmentAnnotation[annotation.size()]);
880 * Returns true if this sequence has the given annotation (by object
884 public boolean hasAnnotation(AlignmentAnnotation ann)
886 return annotation == null ? false : annotation.contains(ann);
890 * Add the given annotation, if not already added, and set its sequence ref to
891 * be this sequence. Does nothing if this sequence's annotations already
892 * include this annotation (by identical object reference).
894 public void addAlignmentAnnotation(AlignmentAnnotation annotation)
896 if (this.annotation == null)
898 this.annotation = new Vector();
900 if (!this.annotation.contains(annotation))
902 this.annotation.addElement(annotation);
904 annotation.setSequenceRef(this);
907 public void removeAlignmentAnnotation(AlignmentAnnotation annotation)
909 if (this.annotation != null)
911 this.annotation.removeElement(annotation);
912 if (this.annotation.size() == 0)
914 this.annotation = null;
920 * test if this is a valid candidate for another sequence's dataset sequence.
923 private boolean isValidDatasetSequence()
925 if (datasetSequence != null)
929 for (int i = 0; i < sequence.length; i++)
931 if (jalview.util.Comparison.isGap(sequence[i]))
942 * @see jalview.datamodel.SequenceI#deriveSequence()
944 public SequenceI deriveSequence()
946 SequenceI seq = new Sequence(this);
947 if (datasetSequence != null)
949 // duplicate current sequence with same dataset
950 seq.setDatasetSequence(datasetSequence);
954 if (isValidDatasetSequence())
956 // Use this as dataset sequence
957 seq.setDatasetSequence(this);
961 // Create a new, valid dataset sequence
963 ds.setSequence(AlignSeq.extractGaps(
964 jalview.util.Comparison.GapChars, new String(sequence)));
965 setDatasetSequence(ds);
966 ds.setSequenceFeatures(getSequenceFeatures());
967 seq = this; // and return this sequence as the derived sequence.
976 * @see jalview.datamodel.SequenceI#createDatasetSequence()
978 public SequenceI createDatasetSequence()
980 if (datasetSequence == null)
982 datasetSequence = new Sequence(getName(), AlignSeq.extractGaps(
983 jalview.util.Comparison.GapChars, getSequenceAsString()),
984 getStart(), getEnd());
985 datasetSequence.setSequenceFeatures(getSequenceFeatures());
986 datasetSequence.setDescription(getDescription());
987 setSequenceFeatures(null);
988 // move database references onto dataset sequence
989 datasetSequence.setDBRef(getDBRef());
991 datasetSequence.setPDBId(getPDBId());
993 datasetSequence.updatePDBIds();
994 if (annotation != null)
996 for (AlignmentAnnotation aa : annotation)
998 AlignmentAnnotation _aa = new AlignmentAnnotation(aa);
999 _aa.sequenceRef = datasetSequence;
1000 _aa.adjustForAlignment(); // uses annotation's own record of
1001 // sequence-column mapping
1002 datasetSequence.addAlignmentAnnotation(_aa);
1006 return datasetSequence;
1013 * jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[]
1016 public void setAlignmentAnnotation(AlignmentAnnotation[] annotations)
1018 if (annotation != null)
1020 annotation.removeAllElements();
1022 if (annotations != null)
1024 for (int i = 0; i < annotations.length; i++)
1026 if (annotations[i] != null)
1028 addAlignmentAnnotation(annotations[i]);
1037 * @see jalview.datamodel.SequenceI#getAnnotation(java.lang.String)
1039 public AlignmentAnnotation[] getAnnotation(String label)
1041 if (annotation == null || annotation.size() == 0)
1046 Vector subset = new Vector();
1047 Enumeration e = annotation.elements();
1048 while (e.hasMoreElements())
1050 AlignmentAnnotation ann = (AlignmentAnnotation) e.nextElement();
1051 if (ann.label != null && ann.label.equals(label))
1053 subset.addElement(ann);
1056 if (subset.size() == 0)
1060 AlignmentAnnotation[] anns = new AlignmentAnnotation[subset.size()];
1062 e = subset.elements();
1063 while (e.hasMoreElements())
1065 anns[i++] = (AlignmentAnnotation) e.nextElement();
1067 subset.removeAllElements();
1071 public boolean updatePDBIds()
1073 if (datasetSequence != null)
1075 // TODO: could merge DBRefs
1076 return datasetSequence.updatePDBIds();
1078 if (dbrefs == null || dbrefs.length == 0)
1082 Vector newpdb = new Vector();
1083 for (int i = 0; i < dbrefs.length; i++)
1085 if (DBRefSource.PDB.equals(dbrefs[i].getSource()))
1087 PDBEntry pdbe = new PDBEntry();
1088 pdbe.setId(dbrefs[i].getAccessionId());
1089 if (pdbIds == null || pdbIds.size() == 0)
1091 newpdb.addElement(pdbe);
1095 Enumeration en = pdbIds.elements();
1096 boolean matched = false;
1097 while (!matched && en.hasMoreElements())
1099 PDBEntry anentry = (PDBEntry) en.nextElement();
1100 if (anentry.getId().equals(pdbe.getId()))
1107 newpdb.addElement(pdbe);
1112 if (newpdb.size() > 0)
1114 Enumeration en = newpdb.elements();
1115 while (en.hasMoreElements())
1117 addPDBId((PDBEntry) en.nextElement());
1128 * jalview.datamodel.SequenceI#transferAnnotation(jalview.datamodel.SequenceI,
1129 * jalview.datamodel.Mapping)
1131 public void transferAnnotation(SequenceI entry, Mapping mp)
1133 if (datasetSequence != null)
1135 datasetSequence.transferAnnotation(entry, mp);
1138 if (entry.getDatasetSequence() != null)
1140 transferAnnotation(entry.getDatasetSequence(), mp);
1143 // transfer any new features from entry onto sequence
1144 if (entry.getSequenceFeatures() != null)
1147 SequenceFeature[] sfs = entry.getSequenceFeatures();
1148 for (int si = 0; si < sfs.length; si++)
1150 SequenceFeature sf[] = (mp != null) ? mp.locateFeature(sfs[si])
1151 : new SequenceFeature[]
1152 { new SequenceFeature(sfs[si]) };
1153 if (sf != null && sf.length > 0)
1155 for (int sfi = 0; sfi < sf.length; sfi++)
1157 addSequenceFeature(sf[sfi]);
1163 // transfer PDB entries
1164 if (entry.getPDBId() != null)
1166 Enumeration e = entry.getPDBId().elements();
1167 while (e.hasMoreElements())
1169 PDBEntry pdb = (PDBEntry) e.nextElement();
1173 // transfer database references
1174 DBRefEntry[] entryRefs = entry.getDBRef();
1175 if (entryRefs != null)
1177 for (int r = 0; r < entryRefs.length; r++)
1179 DBRefEntry newref = new DBRefEntry(entryRefs[r]);
1180 if (newref.getMap() != null && mp != null)
1182 // remap ref using our local mapping
1184 // we also assume all version string setting is done by dbSourceProxy
1186 * if (!newref.getSource().equalsIgnoreCase(dbSource)) {
1187 * newref.setSource(dbSource); }
1195 * @return The index (zero-based) on this sequence in the MSA. It returns
1196 * {@code -1} if this information is not available.
1198 public int getIndex()
1204 * Defines the position of this sequence in the MSA. Use the value {@code -1}
1205 * if this information is undefined.
1208 * position for this sequence. This value is zero-based (zero for
1209 * this first sequence)
1211 public void setIndex(int value)
1216 public void setRNA(RNA r)
1227 * Returns a (possibly empty) list of any annotations that match on given
1228 * calcId (source) and label (type). Null values do not match.
1234 public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
1237 List<AlignmentAnnotation> result = new ArrayList<AlignmentAnnotation>();
1238 if (this.annotation != null)
1240 for (AlignmentAnnotation ann : annotation)
1242 if (ann.calcId != null && ann.calcId.equals(calcId)
1243 && ann.label != null && ann.label.equals(label))