X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequence.java;h=81a0f408da1d0274e337597e49d17fa3cf073bed;hb=855f7a4bb3e8d5fcfa9059df64262fc73f0164be;hp=635043b6eda8e2b8982dad4dc23132bcddf629bd;hpb=174230b4233d9ce80f94527768d2cd2f76da11ab;p=jalview.git diff --git a/src/jalview/datamodel/Sequence.java b/src/jalview/datamodel/Sequence.java index 635043b..81a0f40 100755 --- a/src/jalview/datamodel/Sequence.java +++ b/src/jalview/datamodel/Sequence.java @@ -1,6 +1,6 @@ /* * Jalview - A Sequence Alignment Editor and Viewer -* Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle + * Copyright (C) 2007 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 @@ -18,10 +18,10 @@ */ package jalview.datamodel; -import java.awt.*; import java.util.*; +import jalview.analysis.*; /** * DOCUMENT ME! @@ -29,750 +29,814 @@ import java.util.*; * @author $author$ * @version $Revision$ */ -public class Sequence implements SequenceI +public class Sequence + 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; - } - - this.end = endRes; - } - - } + SequenceI datasetSequence; + String name; + private char [] sequence; + String description; + int start; + int end; + 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; + + + /** + * 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.toCharArray(); + this.start = start; + this.end = end; + parseId(); + checkValidRange(); + } - /** - * Creates a new Sequence object. - * - * @param name DOCUMENT ME! - * @param sequence DOCUMENT ME! - */ - public Sequence(String name, String sequence) - { - this(name, sequence, 1, -1); - } + public Sequence(String name, char [] sequence, int start, int end) + { + this.name = name; + this.sequence = sequence; + this.start = start; + this.end = end; + parseId(); + checkValidRange(); + } - /** - * Creates a new Sequence object. - * - * @param seq DOCUMENT ME! - */ - public Sequence(SequenceI seq) - { - this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd()); - } + com.stevesoft.pat.Regex limitrx = new com.stevesoft.pat.Regex( + "[/][0-9]{1,}[-][0-9]{1,}$"); + com.stevesoft.pat.Regex endrx = new com.stevesoft.pat.Regex( + "[0-9]{1,}$"); - /** - * DOCUMENT ME! - * - * @param v DOCUMENT ME! - */ - public void setSequenceFeatures(SequenceFeature [] features) + void parseId() + { + // Does sequence have the /start-end signiature? + if (limitrx.search(name)) { - sequenceFeatures = features; + name = limitrx.left(); + endrx.search(limitrx.stringMatched()); + setStart(Integer.parseInt(limitrx.stringMatched().substring(1, + endrx.matchedFrom() - 1))); + setEnd(Integer.parseInt(endrx.stringMatched())); } + } - public synchronized void addSequenceFeature(SequenceFeature sf) + void checkValidRange() + { + if (end < 1) { - if(sequenceFeatures==null) - { - sequenceFeatures = new SequenceFeature[0]; - } - - for(int i=0; i 0) + { + endRes += start - 1; + } - SequenceFeature [] temp = new SequenceFeature[sequenceFeatures.length+1]; - System.arraycopy(sequenceFeatures, 0, temp, 0, sequenceFeatures.length); - temp[sequenceFeatures.length] = sf; - - sequenceFeatures = temp; + this.end = endRes; } + } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public SequenceFeature [] getSequenceFeatures() - { - return sequenceFeatures; - } - - public void addPDBId(PDBEntry entry) - { - if(pdbIds == null) - pdbIds = new Vector(); + /** + * Creates a new Sequence object. + * + * @param name DOCUMENT ME! + * @param sequence DOCUMENT ME! + */ + public Sequence(String name, String sequence) + { + this(name, sequence, 1, -1); + } - pdbIds.addElement(entry); + /** + * 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.getName(), + seq.getSequence(), + seq.getStart(), + seq.getEnd()); + description = seq.getDescription(); + if (seq.getSequenceFeatures()!=null) { + SequenceFeature[] sf = seq.getSequenceFeatures(); + for (int i=0; i= sequence.length()) - { - return ""; - } + pdbIds.addElement(entry); + } - if (end >= sequence.length()) - { - end = sequence.length(); - } + /** + * DOCUMENT ME! + * + * @param id DOCUMENT ME! + */ + public void setPDBId(Vector id) + { + pdbIds = id; + } - 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 ' '; - } - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public Vector getPDBId() + { + return pdbIds; + } - /** - * DOCUMENT ME! - * - * @param desc DOCUMENT ME! - */ - public void setDescription(String desc) + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getDisplayId(boolean jvsuffix) + { + StringBuffer result = new StringBuffer(name); + if (jvsuffix) { - this.description = desc; + result.append("/" + start + "-" + end); } - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public String getDescription() - { - return this.description; - } + return result.toString(); + } - /** - * DOCUMENT ME! - * - * @param pos DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int findIndex(int pos) - { - // returns the alignment position for a residue - int j = start; - int i = 0; + /** + * DOCUMENT ME! + * + * @param name DOCUMENT ME! + */ + public void setName(String name) + { + this.name = name; + this.parseId(); + } - while ((i < sequence.length()) && (j <= end) && (j <= pos)) - { - if (!jalview.util.Comparison.isGap(sequence.charAt(i))) - { - j++; - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getName() + { + return this.name; + } - i++; - } + /** + * DOCUMENT ME! + * + * @param start DOCUMENT ME! + */ + public void setStart(int start) + { + this.start = start; + } - if ((j == end) && (j < pos)) - { - return end + 1; - } - else - { - return i; - } - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getStart() + { + return this.start; + } - /** - * 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) - { - int j = 0; - int pos = start; - int seqlen=sequence.length(); - while ((j < i) && (j < seqlen)) - { - if (!jalview.util.Comparison.isGap((sequence.charAt(j)))) - { - pos++; - } + /** + * DOCUMENT ME! + * + * @param end DOCUMENT ME! + */ + public void setEnd(int end) + { + this.end = end; + } - j++; - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getEnd() + { + return this.end; + } - return pos; - } + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int getLength() + { + return this.sequence.length; + } - /** - * 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; + /** + * DOCUMENT ME! + * + * @param seq DOCUMENT ME! + */ + public void setSequence(String seq) + { + this.sequence = seq.toCharArray(); + checkValidRange(); + } - while (j < sequence.length()) - { - if (!jalview.util.Comparison.isGap(sequence.charAt(j))) - { - map[p++] = j; - } - j++; - } + public String getSequenceAsString() + { + return new String(sequence); + } - return map; - } + public String getSequenceAsString(int start, int end) + { + return new String(getSequence(start, end)); + } - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - */ - public void deleteCharAt(int i) - { - if (i >= sequence.length()) - { - return; - } - sequence = sequence.substring(0, i) + sequence.substring(i + 1); - } + public char [] getSequence() + { + return sequence; + } - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - * @param j DOCUMENT ME! - */ - public void deleteChars(int i, int j) + /** + * DOCUMENT ME! + * + * @param start DOCUMENT ME! + * @param end DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public char [] getSequence(int start, int end) + { + // JBPNote - left to user to pad the result here (TODO:Decide on this policy) + if (start >= sequence.length) { - if (i >= sequence.length()) - { - return; - } - - if (j >= sequence.length()) - { - sequence = sequence.substring(0, i); - } - else - { - sequence = sequence.substring(0, i) + sequence.substring(j); - } + return new char[0]; } - - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - * @param c DOCUMENT ME! - * @param chop DOCUMENT ME! - */ - public void insertCharAt(int i, char c) + if (end >= sequence.length) { - String tmp = new String(sequence); + end = sequence.length; + } - if (i < sequence.length()) - { - sequence = tmp.substring(0, i) + String.valueOf(c) + - tmp.substring(i); - } - 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()]; + char [] reply = new char[end-start]; + System.arraycopy(sequence, start, reply, 0, end-start); - for (int j = 0, k = ch.length; j < k; j++) - ch[j] = c; + return reply; + } - sequence = tmp + String.valueOf(ch); - } - } - /** - * DOCUMENT ME! - * - * @param c DOCUMENT ME! - */ - public void setColor(Color c) + /** + * 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) { - this.color = c; + start = 0; } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public Color getColor() + char [] seq = getSequence(start, end); + if (seq.length == 0) { - return color; + return null; } - - public String getVamsasId() + 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 vamsasId; + nseq.setDatasetSequence(datasetSequence); } - - public void setVamsasId(String id) + else { - vamsasId = id; + nseq.setDatasetSequence(this); } + return nseq; + } - public void setDBRef(DBRefEntry [] dbref) + /** + * DOCUMENT ME! + * + * @param i DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public char getCharAt(int i) + { + if (i < sequence.length) { - dbrefs = dbref; + return sequence[i]; } - - public DBRefEntry [] getDBRef() + else { - return dbrefs; + return ' '; } + } - public void addDBRef(DBRefEntry entry) - { - if(dbrefs == null) - dbrefs = new DBRefEntry[0]; + /** + * DOCUMENT ME! + * + * @param desc DOCUMENT ME! + */ + public void setDescription(String desc) + { + this.description = desc; + } - DBRefEntry [] temp = new DBRefEntry[dbrefs.length+1]; - System.arraycopy(dbrefs, 0, temp, 0, dbrefs.length); + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String getDescription() + { + return this.description; + } + + /** + * Return the alignment position for a sequence position + * + * @param pos lying from start to end + * + * @return aligned position of residue pos + */ + public int findIndex(int pos) + { + // returns the alignment position for a residue + int j = start; + int i = 0; - temp[temp.length-1] = entry; + while ( (i < sequence.length) && (j <= end) && (j <= pos)) + { + if (!jalview.util.Comparison.isGap(sequence[i])) + { + j++; + } - dbrefs = temp; + i++; } - public void setDatasetSequence(SequenceI seq) + if ( (j == end) && (j < pos)) { - datasetSequence = seq; + return end + 1; } - - public SequenceI getDatasetSequence() + else { - return datasetSequence; + return i; } + } - public AlignmentAnnotation [] getAnnotation() + /** + * 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) + { + int j = 0; + int pos = start; + int seqlen = sequence.length; + while ( (j < i) && (j < seqlen)) { - if(annotation==null) - return null; - - AlignmentAnnotation [] ret = new AlignmentAnnotation[annotation.size()]; - for(int r = 0; r= sequence.length) { - return hiddenSequences; + return; } - public void addHiddenSequence(SequenceI seq) + char [] tmp; + + if (j >= sequence.length) { - if(hiddenSequences==null) - { - hiddenSequences = new SequenceGroup(); - } - hiddenSequences.addSequence(seq, false); + tmp = new char[i]; + System.arraycopy(sequence,0,tmp,0,i); + } + else + { + tmp = new char[sequence.length-j+i]; + System.arraycopy(sequence,0,tmp,0,i); + System.arraycopy(sequence,j,tmp,i,sequence.length-j); } - public void showHiddenSequence(SequenceI seq) + if (this.datasetSequence != null) { - hiddenSequences.deleteSequence(seq, false); - if (hiddenSequences.getSize(false) < 1) + for (int s = i; s < j; s++) { - hiddenSequences = null; + if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23) + { + + Sequence ds = new Sequence(name, + AlignSeq.extractGaps( + jalview.util.Comparison.GapChars, + this.getSequenceAsString() + ), + start, + end); + ds.setDescription(description); + } + break; } } - public void changeCase(boolean toUpper, int start, int end) - { - StringBuffer newSeq = new StringBuffer(); + sequence = tmp; + + } - if(end>sequence.length()) - end = sequence.length(); - if (start > 0) - { - newSeq.append(sequence.substring(0, start)); - } + /** + * DOCUMENT ME! + * + * @param i DOCUMENT ME! + * @param c DOCUMENT ME! + * @param chop DOCUMENT ME! + */ + public void insertCharAt(int i, int length, char c) + { + char [] tmp = new char[sequence.length+length]; - if (toUpper) - newSeq.append(sequence.substring(start, end).toUpperCase()); - else - newSeq.append(sequence.substring(start, end).toLowerCase()); + if (i >= sequence.length) + { + System.arraycopy(sequence, 0, tmp, 0, sequence.length); + i = sequence.length; + } + else + { + System.arraycopy(sequence, 0, tmp, 0, i); + } - if (end < sequence.length()) - newSeq.append(sequence.substring(end)); - sequence = newSeq.toString(); + int index = i; + while (length > 0) + { + tmp[ index++ ] = c; + length--; } - public void toggleCase(int start, int end) + if (i < sequence.length) { - StringBuffer newSeq = new StringBuffer(); + System.arraycopy(sequence, i, tmp, index, sequence.length-i ); + } - if(end>sequence.length()) - end = sequence.length(); + sequence = tmp; + } - if (start > 0) - { - newSeq.append(sequence.substring(0, start)); - } + public void insertCharAt(int i, char c) + { + insertCharAt(i, 1, c); + } - char nextChar; - for(int c=start; c=e) + return datasetSequence; + } + + public AlignmentAnnotation[] getAnnotation() + { + if (annotation == null) + { return null; - return getSubSequence(start, getLength()); + } + + AlignmentAnnotation[] ret = new AlignmentAnnotation[annotation.size()]; + for (int r = 0; r < ret.length; r++) + { + ret[r] = (AlignmentAnnotation) annotation.elementAt(r); + } + + return ret; } - public int removeGaps() { - if (sequence!=null) - return removeGaps(0, getLength()); - return 0; + public void addAlignmentAnnotation(AlignmentAnnotation annotation) + { + if (this.annotation == null) + { + this.annotation = new Vector(); + } + + this.annotation.addElement(annotation); + annotation.setSequenceRef(this); } - 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 removeAlignmentAnnotation(AlignmentAnnotation annotation) + { + if(this.annotation!=null) + { + this.annotation.removeElement(annotation); + if(this.annotation.size()==0) + this.annotation = null; + } + } - // Removing a range is much quicker than removing gaps - // one by one for long sequences - int j = start; - int rangeStart=-1, rangeEnd=-1; - do + /** + * 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-1) - { - deleteChars(rangeStart, rangeEnd); - j-=rangeEnd-rangeStart; - jSize-=rangeEnd-rangeStart; - rangeStart = -1; - rangeEnd = -1; - } - else - j++; + // Use this as dataset sequence + seq.setDatasetSequence(this); + } else { + // Create a new, valid dataset sequence + SequenceI ds = seq; + ds.setSequence(AlignSeq.extractGaps(jalview.util.Comparison.GapChars, new String(sequence))); + setDatasetSequence(ds); + seq = this; // and return this sequence as the derived sequence. } } - while (j < end && j < jSize); - if(rangeStart>-1) - { - deleteChars(rangeStart, rangeEnd); - jSize-=rangeEnd-rangeStart; + return seq; + } + /* (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