X-Git-Url: http://source.jalview.org/gitweb/?p=jalview.git;a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequence.java;h=def9c4735ed2a7f2418eacd6e9a332af48c4872b;hp=635043b6eda8e2b8982dad4dc23132bcddf629bd;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hpb=174230b4233d9ce80f94527768d2cd2f76da11ab diff --git a/src/jalview/datamodel/Sequence.java b/src/jalview/datamodel/Sequence.java index 635043b..def9c47 100755 --- a/src/jalview/datamodel/Sequence.java +++ b/src/jalview/datamodel/Sequence.java @@ -1,778 +1,1324 @@ /* -* Jalview - A Sequence Alignment Editor and Viewer -* Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle -* -* This program is free software; you can redistribute it and/or -* modify it under the terms of the GNU General Public License -* as published by the Free Software Foundation; either version 2 -* of the License, or (at your option) any later version. -* -* This program is distributed in the hope that it will be useful, -* but WITHOUT ANY WARRANTY; without even the implied warranty of -* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -* GNU General Public License for more details. -* -* You should have received a copy of the GNU General Public License -* along with this program; if not, write to the Free Software -* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA -*/ + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9) + * Copyright (C) 2015 The Jalview Authors + * + * This file is part of Jalview. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 + * of the License, or (at your option) any later version. + * + * Jalview is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR + * PURPOSE. See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . + * The Jalview Authors are detailed in the 'AUTHORS' file. + */ package jalview.datamodel; -import java.awt.*; +import jalview.analysis.AlignSeq; +import jalview.util.StringUtils; -import java.util.*; +import java.util.ArrayList; +import java.util.Enumeration; +import java.util.List; +import java.util.Vector; +import fr.orsay.lri.varna.models.rna.RNA; /** - * DOCUMENT ME! - * + * + * Implements the SequenceI interface for a char[] based sequence object. + * * @author $author$ * @version $Revision$ */ -public class Sequence implements SequenceI +public class Sequence extends ASequence implements SequenceI { - SequenceI datasetSequence; - String name; - private String sequence; - String description; - int start; - int end; - Color color = Color.white; - Vector pdbIds; - String vamsasId; - DBRefEntry [] dbrefs; - - /** This annotation is displayed below the alignment but the - * positions are tied to the residues of this sequence */ - Vector annotation; - - /** DOCUMENT ME!! */ - public SequenceFeature [] sequenceFeatures; - - /** This array holds hidden sequences - * of which this sequence is the representitive member of a group - */ - SequenceGroup hiddenSequences; - - /** - * Creates a new Sequence object. - * - * @param name DOCUMENT ME! - * @param sequence DOCUMENT ME! - * @param start DOCUMENT ME! - * @param end DOCUMENT ME! - */ - public Sequence(String name, String sequence, int start, int end) - { - this.name = name; - this.sequence = sequence; - this.start = start; - this.end = end; - - parseId(); - - checkValidRange(); - } - - com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex( - "[/][0-9]{1,}[-][0-9]{1,}$"); - com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex( - "[0-9]{1,}$"); - - void parseId() - { - // Does sequence have the /start-end signiature? - if(limitrx.search(name)) - { - name = limitrx.left(); - endrx.search(limitrx.stringMatched()); - setStart( Integer.parseInt( limitrx.stringMatched().substring(1,endrx.matchedFrom()-1 ))); - setEnd( Integer.parseInt( endrx.stringMatched() )); - } - } - - void checkValidRange() - { - if (end < 1) - { - int endRes = 0; - char ch; - for (int j = 0; j < sequence.length(); j++) - { - ch = sequence.charAt(j); - if (!jalview.util.Comparison.isGap( (ch))) - { - endRes++; - } - } - if (endRes > 0) - { - endRes += start - 1; - } + SequenceI datasetSequence; - this.end = endRes; - } + String name; - } + private char[] sequence; + + String description; + + int start; + + int end; + + Vector pdbIds; + + String vamsasId; - /** - * Creates a new Sequence object. - * - * @param name DOCUMENT ME! - * @param sequence DOCUMENT ME! - */ - public Sequence(String name, String sequence) + DBRefEntry[] dbrefs; + + RNA rna; + + /** + * This annotation is displayed below the alignment but the positions are tied + * to the residues of this sequence + * + * TODO: change to List<> + */ + Vector annotation; + + /** + * The index of the sequence in a MSA + */ + int index = -1; + + /** array of sequence features - may not be null for a valid sequence object */ + public SequenceFeature[] sequenceFeatures; + + /** + * Creates a new Sequence object. + * + * @param name + * display name string + * @param sequence + * string to form a possibly gapped sequence out of + * @param start + * first position of non-gap residue in the sequence + * @param end + * last position of ungapped residues (nearly always only used for + * display purposes) + */ + public Sequence(String name, String sequence, int start, int end) + { + initSeqAndName(name, sequence.toCharArray(), start, end); + } + + public Sequence(String name, char[] sequence, int start, int end) + { + initSeqAndName(name, sequence, start, end); + } + + /** + * Stage 1 constructor - assign name, sequence, and set start and end fields. + * start and end are updated values from name2 if it ends with /start-end + * + * @param name2 + * @param sequence2 + * @param start2 + * @param end2 + */ + protected void initSeqAndName(String name2, char[] sequence2, int start2, + int end2) + { + this.name = name2; + this.sequence = sequence2; + this.start = start2; + this.end = end2; + parseId(); + checkValidRange(); + } + + com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex( + "[/][0-9]{1,}[-][0-9]{1,}$"); + + com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex("[0-9]{1,}$"); + + void parseId() + { + if (name == null) { - this(name, sequence, 1, -1); + System.err + .println("POSSIBLE IMPLEMENTATION ERROR: null sequence name passed to constructor."); + name = ""; } - - /** - * Creates a new Sequence object. - * - * @param seq DOCUMENT ME! - */ - public Sequence(SequenceI seq) + // Does sequence have the /start-end signature? + if (limitrx.search(name)) { - this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd()); + name = limitrx.left(); + endrx.search(limitrx.stringMatched()); + setStart(Integer.parseInt(limitrx.stringMatched().substring(1, + endrx.matchedFrom() - 1))); + setEnd(Integer.parseInt(endrx.stringMatched())); } + } - /** - * DOCUMENT ME! - * - * @param v DOCUMENT ME! - */ - public void setSequenceFeatures(SequenceFeature [] features) + void checkValidRange() + { + // Note: JAL-774 : + // http://issues.jalview.org/browse/JAL-774?focusedCommentId=11239&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-11239 { - sequenceFeatures = features; + int endRes = 0; + for (int j = 0; j < sequence.length; j++) + { + if (!jalview.util.Comparison.isGap(sequence[j])) + { + endRes++; + } + } + if (endRes > 0) + { + endRes += start - 1; + } + + if (end < endRes) + { + end = endRes; + } } - public synchronized void addSequenceFeature(SequenceFeature sf) + } + + /** + * Creates a new Sequence object. + * + * @param name + * DOCUMENT ME! + * @param sequence + * DOCUMENT ME! + */ + public Sequence(String name, String sequence) + { + this(name, sequence, 1, -1); + } + + /** + * Creates a new Sequence object with new features, DBRefEntries, + * AlignmentAnnotations, and PDBIds but inherits any existing dataset sequence + * reference. + * + * @param seq + * DOCUMENT ME! + */ + public Sequence(SequenceI seq) + { + this(seq, seq.getAnnotation()); + } + + /** + * Create a new sequence object with new features, DBRefEntries, and PDBIds + * but inherits any existing dataset sequence reference, and duplicate of any + * annotation that is present in the given annotation array. + * + * @param seq + * the sequence to be copied + * @param alAnnotation + * an array of annotation including some associated with seq + */ + public Sequence(SequenceI seq, AlignmentAnnotation[] alAnnotation) + { + initSeqFrom(seq, alAnnotation); + + } + + protected void initSeqFrom(SequenceI seq, + AlignmentAnnotation[] alAnnotation) + { + initSeqAndName(seq.getName(), seq.getSequence(), seq.getStart(), + seq.getEnd()); + description = seq.getDescription(); + if (seq.getSequenceFeatures() != null) { - if(sequenceFeatures==null) + SequenceFeature[] sf = seq.getSequenceFeatures(); + for (int i = 0; i < sf.length; i++) { - sequenceFeatures = new SequenceFeature[0]; + addSequenceFeature(new SequenceFeature(sf[i])); } - - for(int i=0; i(); } - - /** - * DOCUMENT ME! - * - * @param start DOCUMENT ME! - */ - public void setStart(int start) + if (pdbIds.contains(entry)) { - this.start = start; + updatePDBEntry(pdbIds.get(pdbIds.indexOf(entry)), entry); } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getStart() + else { - return this.start; + pdbIds.addElement(entry); } + } - /** - * DOCUMENT ME! - * - * @param end DOCUMENT ME! - */ - public void setEnd(int end) + private static void updatePDBEntry(PDBEntry oldEntry, PDBEntry newEntry) + { + if (newEntry.getFile() != null) { - this.end = end; + oldEntry.setFile(newEntry.getFile()); } + } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getEnd() + /** + * DOCUMENT ME! + * + * @param id + * DOCUMENT ME! + */ + @Override + public void setPDBId(Vector id) + { + pdbIds = id; + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + @Override + public Vector getAllPDBEntries() + { + return pdbIds; + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getDisplayId(boolean jvsuffix) + { + StringBuffer result = new StringBuffer(name); + if (jvsuffix) { - return this.end; + result.append("/" + start + "-" + end); } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getLength() + return result.toString(); + } + + /** + * DOCUMENT ME! + * + * @param name + * DOCUMENT ME! + */ + public void setName(String name) + { + this.name = name; + this.parseId(); + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getName() + { + return this.name; + } + + /** + * DOCUMENT ME! + * + * @param start + * DOCUMENT ME! + */ + public void setStart(int start) + { + this.start = start; + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getStart() + { + return this.start; + } + + /** + * DOCUMENT ME! + * + * @param end + * DOCUMENT ME! + */ + public void setEnd(int end) + { + this.end = end; + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getEnd() + { + return this.end; + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getLength() + { + return this.sequence.length; + } + + /** + * DOCUMENT ME! + * + * @param seq + * DOCUMENT ME! + */ + public void setSequence(String seq) + { + this.sequence = seq.toCharArray(); + checkValidRange(); + } + + public String getSequenceAsString() + { + return new String(sequence); + } + + public String getSequenceAsString(int start, int end) + { + return new String(getSequence(start, end)); + } + + public char[] getSequence() + { + return sequence; + } + + /* + * (non-Javadoc) + * + * @see jalview.datamodel.SequenceI#getSequence(int, int) + */ + public char[] getSequence(int start, int end) + { + if (start < 0) { - return this.sequence.length(); + start = 0; } - - /** - * DOCUMENT ME! - * - * @param seq DOCUMENT ME! - */ - public void setSequence(String seq) + // JBPNote - left to user to pad the result here (TODO:Decide on this + // policy) + if (start >= sequence.length) { - this.sequence = seq; - checkValidRange(); + return new char[0]; } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public String getSequence() + if (end >= sequence.length) { - return this.sequence; + end = sequence.length; } - /** - * DOCUMENT ME! - * - * @param start DOCUMENT ME! - * @param end DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public String getSequence(int start, int end) - { - // JBPNote - left to user to pad the result here (TODO:Decide on this policy) - if (start >= sequence.length()) - { - return ""; - } + char[] reply = new char[end - start]; + System.arraycopy(sequence, start, reply, 0, end - start); - if (end >= sequence.length()) - { - end = sequence.length(); - } + return reply; + } - return this.sequence.substring(start, end); - } - /** - * make a new Sequence object from start to end (including gaps) over this seqeunce - * @param start int - * @param end int - * @return SequenceI - */ - public SequenceI getSubSequence(int start, int end) { - if (start<0) - start = 0; - String seq = getSequence(start, end); - if (seq=="") - return null; - int nstart = findPosition(start); - int nend=findPosition(end)-1; - // JBPNote - this is an incomplete copy. - SequenceI nseq = new Sequence(this.getName(), seq, nstart, nend); - nseq.setDatasetSequence(getDatasetSequence()); - return nseq; - } - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public char getCharAt(int i) - { - if (i < sequence.length()) - { - return sequence.charAt(i); - } - else - { - return ' '; - } + @Override + public SequenceI getSubSequence(int start, int end) + { + if (start < 0) + { + start = 0; } - - /** - * DOCUMENT ME! - * - * @param desc DOCUMENT ME! - */ - public void setDescription(String desc) + char[] seq = getSequence(start, end); + if (seq.length == 0) { - this.description = desc; + return null; } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public String getDescription() + int nstart = findPosition(start); + int nend = findPosition(end) - 1; + // JBPNote - this is an incomplete copy. + SequenceI nseq = new Sequence(this.getName(), seq, nstart, nend); + nseq.setDescription(description); + if (datasetSequence != null) { - return this.description; + nseq.setDatasetSequence(datasetSequence); } + else + { + nseq.setDatasetSequence(this); + } + return nseq; + } - /** - * DOCUMENT ME! - * - * @param pos DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int findIndex(int pos) + /** + * DOCUMENT ME! + * + * @param i + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public char getCharAt(int i) + { + if (i < sequence.length) + { + return sequence[i]; + } + else { - // returns the alignment position for a residue - int j = start; - int i = 0; + return ' '; + } + } - while ((i < sequence.length()) && (j <= end) && (j <= pos)) - { - if (!jalview.util.Comparison.isGap(sequence.charAt(i))) - { - j++; - } + /** + * DOCUMENT ME! + * + * @param desc + * DOCUMENT ME! + */ + public void setDescription(String desc) + { + this.description = desc; + } - i++; - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getDescription() + { + return this.description; + } - if ((j == end) && (j < pos)) - { - return end + 1; - } - else - { - return i; - } + /* + * (non-Javadoc) + * + * @see jalview.datamodel.SequenceI#findIndex(int) + */ + public int findIndex(int pos) + { + // returns the alignment position for a residue + int j = start; + int i = 0; + // Rely on end being at least as long as the length of the sequence. + while ((i < sequence.length) && (j <= end) && (j <= pos)) + { + if (!jalview.util.Comparison.isGap(sequence[i])) + { + j++; + } + + i++; } - /** - * Returns the sequence position for an alignment position - * - * @param i column index in alignment (from 1) - * - * @return residue number for residue (left of and) nearest ith column - */ - public int findPosition(int i) + if ((j == end) && (j < pos)) { - int j = 0; - int pos = start; - int seqlen=sequence.length(); - while ((j < i) && (j < seqlen)) - { - if (!jalview.util.Comparison.isGap((sequence.charAt(j)))) - { - pos++; - } + return end + 1; + } + else + { + return i; + } + } - j++; - } + @Override + public int findPosition(int i) + { + int j = 0; + int pos = start; + int seqlen = sequence.length; + while ((j < i) && (j < seqlen)) + { + if (!jalview.util.Comparison.isGap(sequence[j])) + { + pos++; + } - return pos; + j++; } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int[] gapMap() - { - // Returns an int array giving the position of each residue in the sequence in the alignment - String seq = jalview.analysis.AlignSeq.extractGaps(jalview.util.Comparison.GapChars, sequence); - int[] map = new int[seq.length()]; - int j = 0; - int p = 0; + return pos; + } - while (j < sequence.length()) - { - if (!jalview.util.Comparison.isGap(sequence.charAt(j))) - { - map[p++] = j; - } + /** + * Returns an int array where indices correspond to each residue in the + * sequence and the element value gives its position in the alignment + * + * @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no + * residues in SequenceI object + */ + public int[] gapMap() + { + String seq = jalview.analysis.AlignSeq.extractGaps( + jalview.util.Comparison.GapChars, new String(sequence)); + int[] map = new int[seq.length()]; + int j = 0; + int p = 0; - j++; - } + while (j < sequence.length) + { + if (!jalview.util.Comparison.isGap(sequence[j])) + { + map[p++] = j; + } - return map; + j++; } - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - */ - public void deleteCharAt(int i) + return map; + } + + @Override + public int[] findPositionMap() + { + int map[] = new int[sequence.length]; + int j = 0; + int pos = start; + int seqlen = sequence.length; + while ((j < seqlen)) { - if (i >= sequence.length()) - { - return; - } + map[j] = pos; + if (!jalview.util.Comparison.isGap(sequence[j])) + { + pos++; + } - sequence = sequence.substring(0, i) + sequence.substring(i + 1); + j++; } + return map; + } - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - * @param j DOCUMENT ME! - */ - public void deleteChars(int i, int j) + @Override + public List getInsertions() + { + ArrayList map = new ArrayList(); + int lastj = -1, j = 0; + int pos = start; + int seqlen = sequence.length; + while ((j < seqlen)) { - if (i >= sequence.length()) - { - return; - } - - if (j >= sequence.length()) + if (jalview.util.Comparison.isGap(sequence[j])) + { + if (lastj == -1) { - sequence = sequence.substring(0, i); + lastj = j; } - else + } + else + { + if (lastj != -1) { - sequence = sequence.substring(0, i) + sequence.substring(j); + map.add(new int[] { lastj, j - 1 }); + lastj = -1; } + } + j++; } + if (lastj != -1) + { + map.add(new int[] { lastj, j - 1 }); + lastj = -1; + } + return map; + } - - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - * @param c DOCUMENT ME! - * @param chop DOCUMENT ME! - */ - public void insertCharAt(int i, char c) + @Override + public void deleteChars(int i, int j) + { + int newstart = start, newend = end; + if (i >= sequence.length || i < 0) { - String tmp = new String(sequence); + return; + } - if (i < sequence.length()) + char[] tmp = StringUtils.deleteChars(sequence, i, j); + boolean createNewDs = false; + // TODO: take a (second look) at the dataset creation validation method for + // the very large sequence case + int eindex = -1, sindex = -1; + boolean ecalc = false, scalc = false; + for (int s = i; s < j; s++) + { + if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23) + { + if (createNewDs) { - sequence = tmp.substring(0, i) + String.valueOf(c) + - tmp.substring(i); + newend--; } else { - // JBPNote : padding char at end of sequence. We'll not get away with this when we insert residues, I bet! - char[] ch = new char[(1 + i) - sequence.length()]; - - for (int j = 0, k = ch.length; j < k; j++) - ch[j] = c; - - sequence = tmp + String.valueOf(ch); + if (!scalc) + { + sindex = findIndex(start) - 1; + scalc = true; + } + if (sindex == s) + { + // delete characters including start of sequence + newstart = findPosition(j); + break; // don't need to search for any more residue characters. + } + else + { + // delete characters after start. + if (!ecalc) + { + eindex = findIndex(end) - 1; + ecalc = true; + } + if (eindex < j) + { + // delete characters at end of sequence + newend = findPosition(i - 1); + break; // don't need to search for any more residue characters. + } + else + { + createNewDs = true; + newend--; // decrease end position by one for the deleted residue + // and search further + } + } } + } } - - /** - * DOCUMENT ME! - * - * @param c DOCUMENT ME! - */ - public void setColor(Color c) + // deletion occured in the middle of the sequence + if (createNewDs && this.datasetSequence != null) { - this.color = c; + // construct a new sequence + Sequence ds = new Sequence(datasetSequence); + // TODO: remove any non-inheritable properties ? + // TODO: create a sequence mapping (since there is a relation here ?) + ds.deleteChars(i, j); + datasetSequence = ds; } + start = newstart; + end = newend; + sequence = tmp; + } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public Color getColor() - { - return color; - } + @Override + public void insertCharAt(int i, int length, char c) + { + char[] tmp = new char[sequence.length + length]; - public String getVamsasId() + if (i >= sequence.length) { - return vamsasId; + System.arraycopy(sequence, 0, tmp, 0, sequence.length); + i = sequence.length; } - - public void setVamsasId(String id) + else { - vamsasId = id; + System.arraycopy(sequence, 0, tmp, 0, i); } - public void setDBRef(DBRefEntry [] dbref) + int index = i; + while (length > 0) { - dbrefs = dbref; + tmp[index++] = c; + length--; } - public DBRefEntry [] getDBRef() + if (i < sequence.length) { - return dbrefs; + System.arraycopy(sequence, i, tmp, index, sequence.length - i); } - public void addDBRef(DBRefEntry entry) - { - if(dbrefs == null) - dbrefs = new DBRefEntry[0]; + sequence = tmp; + } - DBRefEntry [] temp = new DBRefEntry[dbrefs.length+1]; - System.arraycopy(dbrefs, 0, temp, 0, dbrefs.length); + @Override + public void insertCharAt(int i, char c) + { + insertCharAt(i, 1, c); + } - temp[temp.length-1] = entry; + @Override + public String getVamsasId() + { + return vamsasId; + } - dbrefs = temp; - } + @Override + public void setVamsasId(String id) + { + vamsasId = id; + } - public void setDatasetSequence(SequenceI seq) + @Override + public void setDBRef(DBRefEntry[] dbref) + { + dbrefs = dbref; + } + + @Override + public DBRefEntry[] getDBRef() + { + if (dbrefs == null && datasetSequence != null + && this != datasetSequence) { - datasetSequence = seq; + return datasetSequence.getDBRef(); } + return dbrefs; + } - public SequenceI getDatasetSequence() + @Override + public void addDBRef(DBRefEntry entry) + { + if (dbrefs == null) { - return datasetSequence; + dbrefs = new DBRefEntry[0]; } - public AlignmentAnnotation [] getAnnotation() + int i, iSize = dbrefs.length; + + for (i = 0; i < iSize; i++) { - if(annotation==null) - return null; + if (dbrefs[i].equalRef(entry)) + { + if (entry.getMap() != null) + { + if (dbrefs[i].getMap() == null) + { + // overwrite with 'superior' entry that contains a mapping. + dbrefs[i] = entry; + } + } + return; + } + } - AlignmentAnnotation [] ret = new AlignmentAnnotation[annotation.size()]; - for(int r = 0; r(); + } + if (!this.annotation.contains(annotation)) { - return hiddenSequences; + this.annotation.addElement(annotation); } + annotation.setSequenceRef(this); + } - public void addHiddenSequence(SequenceI seq) + public void removeAlignmentAnnotation(AlignmentAnnotation annotation) + { + if (this.annotation != null) { - if(hiddenSequences==null) + this.annotation.removeElement(annotation); + if (this.annotation.size() == 0) { - hiddenSequences = new SequenceGroup(); + this.annotation = null; } - hiddenSequences.addSequence(seq, false); } + } - public void showHiddenSequence(SequenceI seq) + /** + * test if this is a valid candidate for another sequence's dataset sequence. + * + */ + private boolean isValidDatasetSequence() + { + if (datasetSequence != null) + { + return false; + } + for (int i = 0; i < sequence.length; i++) { - hiddenSequences.deleteSequence(seq, false); - if (hiddenSequences.getSize(false) < 1) + if (jalview.util.Comparison.isGap(sequence[i])) { - hiddenSequences = null; + return false; } } + return true; + } - public void changeCase(boolean toUpper, int start, int end) + @Override + public SequenceI deriveSequence() + { + SequenceI seq = new Sequence(this); + if (datasetSequence != null) { - StringBuffer newSeq = new StringBuffer(); - - if(end>sequence.length()) - end = sequence.length(); - - if (start > 0) + // duplicate current sequence with same dataset + seq.setDatasetSequence(datasetSequence); + } + else + { + if (isValidDatasetSequence()) { - newSeq.append(sequence.substring(0, start)); + // Use this as dataset sequence + seq.setDatasetSequence(this); } - - if (toUpper) - newSeq.append(sequence.substring(start, end).toUpperCase()); else - newSeq.append(sequence.substring(start, end).toLowerCase()); - - if (end < sequence.length()) - newSeq.append(sequence.substring(end)); - - sequence = newSeq.toString(); + { + // Create a new, valid dataset sequence + SequenceI ds = seq; + ds.setSequence(AlignSeq.extractGaps( + jalview.util.Comparison.GapChars, new String(sequence))); + setDatasetSequence(ds); + ds.setSequenceFeatures(getSequenceFeatures()); + seq = this; // and return this sequence as the derived sequence. + } } + return seq; + } - public void toggleCase(int start, int end) + /* + * (non-Javadoc) + * + * @see jalview.datamodel.SequenceI#createDatasetSequence() + */ + public SequenceI createDatasetSequence() + { + if (datasetSequence == null) { - StringBuffer newSeq = new StringBuffer(); + datasetSequence = new Sequence(getName(), AlignSeq.extractGaps( + jalview.util.Comparison.GapChars, getSequenceAsString()), + getStart(), getEnd()); + datasetSequence.setSequenceFeatures(getSequenceFeatures()); + datasetSequence.setDescription(getDescription()); + setSequenceFeatures(null); + // move database references onto dataset sequence + datasetSequence.setDBRef(getDBRef()); + setDBRef(null); + datasetSequence.setPDBId(getAllPDBEntries()); + setPDBId(null); + datasetSequence.updatePDBIds(); + if (annotation != null) + { + for (AlignmentAnnotation aa : annotation) + { + AlignmentAnnotation _aa = new AlignmentAnnotation(aa); + _aa.sequenceRef = datasetSequence; + _aa.adjustForAlignment(); // uses annotation's own record of + // sequence-column mapping + datasetSequence.addAlignmentAnnotation(_aa); + } + } + } + return datasetSequence; + } - if(end>sequence.length()) - end = sequence.length(); + /* + * (non-Javadoc) + * + * @see + * jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[] + * annotations) + */ + public void setAlignmentAnnotation(AlignmentAnnotation[] annotations) + { + if (annotation != null) + { + annotation.removeAllElements(); + } + if (annotations != null) + { + for (int i = 0; i < annotations.length; i++) + { + if (annotations[i] != null) + { + addAlignmentAnnotation(annotations[i]); + } + } + } + } - if (start > 0) - { - newSeq.append(sequence.substring(0, start)); - } + @Override + public AlignmentAnnotation[] getAnnotation(String label) + { + if (annotation == null || annotation.size() == 0) + { + return null; + } - char nextChar; - for(int c=start; c 0) + { + Enumeration en = newpdb.elements(); + while (en.hasMoreElements()) + { + addPDBId((PDBEntry) en.nextElement()); + } + return true; + } + return false; + } - newSeq.append(nextChar); - } + @Override + public void transferAnnotation(SequenceI entry, Mapping mp) + { + if (datasetSequence != null) + { + datasetSequence.transferAnnotation(entry, mp); + return; + } + if (entry.getDatasetSequence() != null) + { + transferAnnotation(entry.getDatasetSequence(), mp); + return; + } + // transfer any new features from entry onto sequence + if (entry.getSequenceFeatures() != null) + { - if (end < sequence.length()) - newSeq.append(sequence.substring(end)); + SequenceFeature[] sfs = entry.getSequenceFeatures(); + for (int si = 0; si < sfs.length; si++) + { + SequenceFeature sf[] = (mp != null) ? mp.locateFeature(sfs[si]) + : new SequenceFeature[] { new SequenceFeature(sfs[si]) }; + if (sf != null && sf.length > 0) + { + for (int sfi = 0; sfi < sf.length; sfi++) + { + addSequenceFeature(sf[sfi]); + } + } + } + } - sequence = newSeq.toString(); + // transfer PDB entries + if (entry.getAllPDBEntries() != null) + { + Enumeration e = entry.getAllPDBEntries().elements(); + while (e.hasMoreElements()) + { + PDBEntry pdb = (PDBEntry) e.nextElement(); + addPDBId(pdb); + } + } + // transfer database references + DBRefEntry[] entryRefs = entry.getDBRef(); + if (entryRefs != null) + { + for (int r = 0; r < entryRefs.length; r++) + { + DBRefEntry newref = new DBRefEntry(entryRefs[r]); + if (newref.getMap() != null && mp != null) + { + // remap ref using our local mapping + } + // we also assume all version string setting is done by dbSourceProxy + /* + * if (!newref.getSource().equalsIgnoreCase(dbSource)) { + * newref.setSource(dbSource); } + */ + addDBRef(newref); + } } + } - public SequenceI getSubSequence(int start) + /** + * @return The index (zero-based) on this sequence in the MSA. It returns + * {@code -1} if this information is not available. + */ + public int getIndex() { - int e=getLength(); - if (start>=e) - return null; - return getSubSequence(start, getLength()); + return index; } - public int removeGaps() { - if (sequence!=null) - return removeGaps(0, getLength()); - return 0; + /** + * Defines the position of this sequence in the MSA. Use the value {@code -1} + * if this information is undefined. + * + * @param The + * position for this sequence. This value is zero-based (zero for + * this first sequence) + */ + public void setIndex(int value) + { + index = value; } - public int removeGaps(int start, int end) { - int jSize = getLength(); - int oSize=jSize; - if (jSize<=start) - return 0; - if (end>jSize) - end = jSize; + public void setRNA(RNA r) + { + rna = r; + } - // Removing a range is much quicker than removing gaps - // one by one for long sequences - int j = start; - int rangeStart=-1, rangeEnd=-1; + public RNA getRNA() + { + return rna; + } - do + @Override + public List getAlignmentAnnotations(String calcId, + String label) + { + List result = new ArrayList(); + if (this.annotation != null) { - if (jalview.util.Comparison.isGap(getCharAt(j))) - { - if(rangeStart==-1) - { - rangeStart = j; - rangeEnd = j+1; - } - else - { - rangeEnd++; - } - j++; - } - else + for (AlignmentAnnotation ann : annotation) { - if(rangeStart>-1) + if (ann.calcId != null && ann.calcId.equals(calcId) + && ann.label != null && ann.label.equals(label)) { - deleteChars(rangeStart, rangeEnd); - j-=rangeEnd-rangeStart; - jSize-=rangeEnd-rangeStart; - rangeStart = -1; - rangeEnd = -1; + result.add(ann); } - else - j++; } } - while (j < end && j < jSize); - if(rangeStart>-1) + return result; + } + + public String toString() + { + return getDisplayId(false); + } + + @Override + public PDBEntry getPDBEntry(String pdbIdStr) + { + if (getDatasetSequence() == null + || getDatasetSequence().getAllPDBEntries() == null) + { + return null; + } + List entries = getDatasetSequence().getAllPDBEntries(); + for (PDBEntry entry : entries) { - deleteChars(rangeStart, rangeEnd); - jSize-=rangeEnd-rangeStart; + if (entry.getId().equalsIgnoreCase(pdbIdStr)) + { + return entry; + } } - return oSize-jSize; // number of deleted characters. + return null; } }