/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6)
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
+ * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
*
* 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
import java.io.*;
import jalview.datamodel.*;
+import jalview.datamodel.BinarySequence.InvalidSequenceTypeException;
import jalview.math.*;
+import jalview.schemes.ResidueProperties;
+import jalview.schemes.ScoreMatrix;
/**
* Performs Principal Component Analysis on given sequences
StringBuffer details = new StringBuffer();
/**
- * Creates a new PCA object.
+ * Creates a new PCA object. By default, uses blosum62 matrix to generate
+ * sequence similarity matrices
*
* @param s
- * Set of sequences to perform PCA on
+ * Set of amino acid sequences to perform PCA on
*/
public PCA(String[] s)
{
+ this(s, false);
+ }
+
+ /**
+ * Creates a new PCA object. By default, uses blosum62 matrix to generate
+ * sequence similarity matrices
+ *
+ * @param s
+ * Set of sequences to perform PCA on
+ * @param nucleotides
+ * if true, uses standard DNA/RNA matrix for sequence similarity
+ * calculation.
+ */
+ public PCA(String[] s, boolean nucleotides)
+ {
BinarySequence[] bs = new BinarySequence[s.length];
int ii = 0;
while ((ii < s.length) && (s[ii] != null))
{
- bs[ii] = new BinarySequence(s[ii]);
+ bs[ii] = new BinarySequence(s[ii], nucleotides);
bs[ii].encode();
ii++;
}
BinarySequence[] bs2 = new BinarySequence[s.length];
ii = 0;
+ String sm = nucleotides ? "DNA" : "BLOSUM62";
+ ScoreMatrix smtrx = ResidueProperties.getScoreMatrix(sm);
+ details.append("PCA calculation using " + sm
+ + " sequence similarity matrix\n========\n\n");
while ((ii < s.length) && (s[ii] != null))
{
- bs2[ii] = new BinarySequence(s[ii]);
- bs2[ii].blosumEncode();
+ bs2[ii] = new BinarySequence(s[ii], nucleotides);
+ if (smtrx != null)
+ {
+ try
+ {
+ bs2[ii].matrixEncode(smtrx);
+ } catch (InvalidSequenceTypeException x)
+ {
+ details.append("Unexpected mismatch of sequence type and score matrix. Calculation will not be valid!\n\n");
+ }
+ }
ii++;
}
*/
public void run()
{
+ details.append("PCA Calculation Mode is "
+ + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + "\n");
Matrix mt = m.transpose();
details.append(" --- OrigT * Orig ---- \n");
- // eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
- eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method
+ if (!jvCalcMode)
+ {
+ eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
+ }
+ else
+ {
+ eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method
+ }
PrintStream ps = new PrintStream(System.out)
{
* ps.print(","+component(seq, ev)); } ps.println(); }
*/
}
+
+ boolean jvCalcMode = true;
+
+ public void setJvCalcMode(boolean calcMode)
+ {
+ this.jvCalcMode = calcMode;
+ }
}