/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5)
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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.
- *
+ * 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 <http://www.gnu.org/licenses/>.
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.analysis;
-import java.util.*;
-
-import jalview.datamodel.*;
-import jalview.io.*;
-import jalview.schemes.*;
-import jalview.util.*;
+import jalview.api.analysis.ScoreModelI;
+import jalview.datamodel.AlignmentView;
+import jalview.datamodel.BinaryNode;
+import jalview.datamodel.CigarArray;
+import jalview.datamodel.NodeTransformI;
+import jalview.datamodel.SeqCigar;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceI;
+import jalview.datamodel.SequenceNode;
+import jalview.io.NewickFile;
+import jalview.schemes.ResidueProperties;
+import jalview.util.Format;
+
+import java.util.Enumeration;
+import java.util.List;
+import java.util.Vector;
/**
- * DOCUMENT ME!
+ * NeighborJoining tree
*
* @author $author$
* @version $Revision$
}
/*
* sequenceString = new String[odata.length]; char gapChar =
- * jalview.util.Comparison.GapChars.charAt(0); for (int i = 0; i <
+ * Comparison.GapChars.charAt(0); for (int i = 0; i <
* odata.length; i++) { SequenceI oseq_aligned = odata[i].getSeq(gapChar);
* sequenceString[i] = oseq_aligned.getSequence(); }
*/
if (one2many.contains(nam))
{
countOne2Many++;
- // if (jalview.bin.Cache.log.isDebugEnabled())
- // jalview.bin.Cache.log.debug("One 2 many relationship for
+ // if (Cache.log.isDebugEnabled())
+ // Cache.log.debug("One 2 many relationship for
// "+nam.getName());
}
else
j.setPlaceholder(true);
}
}
- // if (jalview.bin.Cache.log.isDebugEnabled() && countOne2Many>0) {
- // jalview.bin.Cache.log.debug("There were "+countOne2Many+" alignment
+ // if (Cache.log.isDebugEnabled() && countOne2Many>0) {
+ // Cache.log.debug("There were "+countOne2Many+" alignment
// sequence ids (out of "+one2many.size()+" unique ids) linked to two or
// more leaves.");
// }
* DOCUMENT ME!
*/
public NJTree(SequenceI[] sequence, AlignmentView seqData, String type,
- String pwtype, int start, int end)
+ String pwtype, ScoreModelI sm, int start, int end)
{
this.sequence = sequence;
this.node = new Vector();
type = "AV";
}
- if (!(pwtype.equals("PID")))
+ if (sm == null && !(pwtype.equals("PID")))
{
if (ResidueProperties.getScoreMatrix(pwtype) == null)
{
- type = "BLOSUM62";
+ pwtype = "BLOSUM62";
}
}
noseqs = i++;
- distance = findDistances(this.seqData
- .getSequenceStrings(Comparison.GapChars.charAt(0)));
+ distance = findDistances(sm);
// System.err.println("Made distances");// dbg
makeLeaves();
// System.err.println("Made leaves");// dbg
}
/**
- * DOCUMENT ME!
+ * Generate a string representation of the Tree
*
- * @return DOCUMENT ME!
+ * @return Newick File with all tree data available
*/
public String toString()
{
- jalview.io.NewickFile fout = new jalview.io.NewickFile(getTopNode());
+ NewickFile fout = new NewickFile(getTopNode());
- return fout.print(false, true); // distances only
+ return fout.print(isHasBootstrap(), isHasDistances(),
+ isHasRootDistance()); // output all data available for tree
}
/**
*
* used when the alignment associated to a tree has changed.
*
- * @param alignment
- * Vector
+ * @param list
+ * Sequence set to be associated with tree nodes
*/
- public void UpdatePlaceHolders(Vector alignment)
+ public void UpdatePlaceHolders(List<SequenceI> list)
{
Vector leaves = new Vector();
findLeaves(top, leaves);
{
SequenceNode leaf = (SequenceNode) leaves.elementAt(i++);
- if (alignment.contains(leaf.element()))
+ if (list.contains(leaf.element()))
{
leaf.setPlaceholder(false);
}
if (seqmatcher == null)
{
// Only create this the first time we need it
- SequenceI[] seqs = new SequenceI[alignment.size()];
+ SequenceI[] seqs = new SequenceI[list.size()];
for (int j = 0; j < seqs.length; j++)
{
- seqs[j] = (SequenceI) alignment.elementAt(j);
+ seqs[j] = list.get(j);
}
seqmatcher = new SequenceIdMatcher(seqs);
}
/**
+ * rename any nodes according to their associated sequence. This will modify
+ * the tree's metadata! (ie the original NewickFile or newly generated
+ * BinaryTree's label data)
+ */
+ public void renameAssociatedNodes()
+ {
+ applyToNodes(new NodeTransformI()
+ {
+
+ @Override
+ public void transform(BinaryNode node)
+ {
+ Object el = node.element();
+ if (el != null && el instanceof SequenceI)
+ {
+ node.setName(((SequenceI) el).getName());
+ }
+ }
+ });
+ }
+
+ /**
* DOCUMENT ME!
*/
public void cluster()
}
/**
- * DOCUMENT ME!
+ * Calculate a distance matrix given the sequence input data and score model
*
- * @return DOCUMENT ME!
+ * @return similarity matrix used to compute tree
*/
- public float[][] findDistances(String[] sequenceString)
+ public float[][] findDistances(ScoreModelI _pwmatrix)
{
- float[][] distance = new float[noseqs][noseqs];
-
- if (pwtype.equals("PID"))
- {
- for (int i = 0; i < (noseqs - 1); i++)
- {
- for (int j = i; j < noseqs; j++)
- {
- if (j == i)
- {
- distance[i][i] = 0;
- }
- else
- {
- distance[i][j] = 100 - Comparison.PID(sequenceString[i],
- sequenceString[j]);
- distance[j][i] = distance[i][j];
- }
- }
- }
- }
- else
+ float[][] distance = new float[noseqs][noseqs];
+ if (_pwmatrix == null)
{
- // Pairwise substitution score (with no gap penalties)
- ScoreMatrix pwmatrix = ResidueProperties.getScoreMatrix(pwtype);
- if (pwmatrix == null)
- {
- pwmatrix = ResidueProperties.getScoreMatrix("BLOSUM62");
- }
- int maxscore = 0;
- int end = sequenceString[0].length();
- for (int i = 0; i < (noseqs - 1); i++)
- {
- for (int j = i; j < noseqs; j++)
- {
- int score = 0;
-
- for (int k = 0; k < end; k++)
- {
- try
- {
- score += pwmatrix.getPairwiseScore(sequenceString[i]
- .charAt(k), sequenceString[j].charAt(k));
- } catch (Exception ex)
- {
- System.err.println("err creating BLOSUM62 tree");
- ex.printStackTrace();
- }
- }
-
- distance[i][j] = (float) score;
-
- if (score > maxscore)
- {
- maxscore = score;
- }
- }
- }
-
- for (int i = 0; i < (noseqs - 1); i++)
+ // Resolve substitution model
+ _pwmatrix = ResidueProperties.getScoreModel(pwtype);
+ if (_pwmatrix == null)
{
- for (int j = i; j < noseqs; j++)
- {
- distance[i][j] = (float) maxscore - distance[i][j];
- distance[j][i] = distance[i][j];
- }
+ _pwmatrix = ResidueProperties.getScoreMatrix("BLOSUM62");
}
-
}
+ distance = _pwmatrix.findDistances(seqData);
return distance;
- // else
- /*
- * else if (pwtype.equals("SW")) { float max = -1;
- *
- * for (int i = 0; i < (noseqs - 1); i++) { for (int j = i; j < noseqs; j++)
- * { AlignSeq as = new AlignSeq(sequence[i], sequence[j], "pep");
- * as.calcScoreMatrix(); as.traceAlignment(); as.printAlignment(System.out);
- * distance[i][j] = (float) as.maxscore;
- *
- * if (max < distance[i][j]) { max = distance[i][j]; } } }
- *
- * for (int i = 0; i < (noseqs - 1); i++) { for (int j = i; j < noseqs; j++)
- * { distance[i][j] = max - distance[i][j]; distance[j][i] = distance[i][j];
- * } } }/
- */
}
/**
{
System.out
.println("Leaf = " + ((SequenceI) node.element()).getName());
- System.out.println("Dist " + ((SequenceNode) node).dist);
+ System.out.println("Dist " + node.dist);
System.out.println("Boot " + node.getBootstrap());
}
else
{
- System.out.println("Dist " + ((SequenceNode) node).dist);
+ System.out.println("Dist " + node.dist);
printNode((SequenceNode) node.left());
printNode((SequenceNode) node.right());
}
if ((node.left() == null) && (node.right() == null))
{
- float dist = ((SequenceNode) node).dist;
+ float dist = node.dist;
if (dist > maxDistValue)
{
- maxdist = (SequenceNode) node;
+ maxdist = node;
maxDistValue = dist;
}
}
String[] seqdatas = seqData.getSequenceStrings(gapChar);
for (int i = 0; i < seqdatas.length; i++)
{
- sb.append(new jalview.util.Format("%-" + 15 + "s").form(sequence[i]
- .getName()));
+ sb.append(new Format("%-" + 15 + "s").form(sequence[i].getName()));
sb.append(" " + seqdatas[i] + "\n");
}
return sb.toString();
+ ((SequenceI) node.element()).getName());
}
- System.out.println(" dist = " + ((SequenceNode) node).dist + " "
- + ((SequenceNode) node).count + " "
- + ((SequenceNode) node).height);
+ System.out.println(" dist = " + node.dist + " "
+ + node.count + " "
+ + node.height);
}
/**
SequenceNode l = (SequenceNode) node.left();
SequenceNode r = (SequenceNode) node.right();
- ((SequenceNode) node).count = l.count + r.count;
- ((SequenceNode) node).ycount = (l.ycount + r.ycount) / 2;
+ node.count = l.count + r.count;
+ node.ycount = (l.ycount + r.ycount) / 2;
}
else
{
- ((SequenceNode) node).count = 1;
- ((SequenceNode) node).ycount = ycount++;
+ node.count = 1;
+ node.ycount = ycount++;
}
_lycount--;
}
{
for (Enumeration nodes = node.elements(); nodes.hasMoreElements(); nodeTransformI
.transform((BinaryNode) nodes.nextElement()))
+ {
;
+ }
}
}