/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
+ * 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.io.*;
-
-import jalview.datamodel.*;
+import jalview.datamodel.BinarySequence;
import jalview.datamodel.BinarySequence.InvalidSequenceTypeException;
-import jalview.math.*;
+import jalview.math.Matrix;
+import jalview.math.MatrixI;
+import jalview.math.SparseMatrix;
import jalview.schemes.ResidueProperties;
import jalview.schemes.ScoreMatrix;
+import java.io.PrintStream;
+
/**
* Performs Principal Component Analysis on given sequences
- *
- * @author $author$
- * @version $Revision$
*/
public class PCA implements Runnable
{
- Matrix m;
+ boolean jvCalcMode = true;
+
+ MatrixI m;
- Matrix symm;
+ MatrixI symm;
- Matrix m2;
+ MatrixI m2;
double[] eigenvalue;
- Matrix eigenvector;
+ MatrixI eigenvector;
- StringBuffer details = new StringBuffer();
+ StringBuilder details = new StringBuilder(1024);
/**
* Creates a new PCA object. By default, uses blosum62 matrix to generate
{
this(s, nucleotides, null);
}
+
public PCA(String[] s, boolean nucleotides, String s_m)
{
}
BinarySequence[] bs2 = new BinarySequence[s.length];
- ii = 0;
ScoreMatrix smtrx = null;
- String sm=s_m;
- if (sm!=null)
+ String sm = s_m;
+ if (sm != null)
{
smtrx = ResidueProperties.getScoreMatrix(sm);
}
- if (smtrx==null)
+ if (smtrx == null)
{
- // either we were given a non-existent score matrix or a scoremodel that isn't based on a pairwise symbol score matrix
- smtrx = ResidueProperties.getScoreMatrix(sm=(nucleotides ? "DNA" : "BLOSUM62"));
+ // either we were given a non-existent score matrix or a scoremodel that
+ // isn't based on a pairwise symbol score matrix
+ smtrx = ResidueProperties.getScoreMatrix(sm = (nucleotides ? "DNA"
+ : "BLOSUM62"));
}
details.append("PCA calculation using " + sm
+ " sequence similarity matrix\n========\n\n");
+ ii = 0;
while ((ii < s.length) && (s[ii] != null))
{
bs2[ii] = new BinarySequence(s[ii], nucleotides);
ii++;
}
- // System.out.println("Created binary encoding");
- // printMemory(rt);
int count = 0;
-
while ((count < bs.length) && (bs[count] != null))
{
count++;
}
- double[][] seqmat = new double[count][bs[0].getDBinary().length];
- double[][] seqmat2 = new double[count][bs2[0].getDBinary().length];
- int i = 0;
+ double[][] seqmat = new double[count][];
+ double[][] seqmat2 = new double[count][];
+ int i = 0;
while (i < count)
{
seqmat[i] = bs[i].getDBinary();
i++;
}
- // System.out.println("Created array");
- // printMemory(rt);
- // System.out.println(" --- Original matrix ---- ");
- m = new Matrix(seqmat, count, bs[0].getDBinary().length);
- m2 = new Matrix(seqmat2, count, bs2[0].getDBinary().length);
+ /*
+ * using a SparseMatrix to hold the encoded sequences matrix
+ * greatly speeds up matrix multiplication as these are mostly zero
+ */
+ m = new SparseMatrix(seqmat);
+ m2 = new Matrix(seqmat2);
}
/**
* Returns the matrix used in PCA calculation
*
- * @return java.math.Matrix object
+ * @return
*/
- public Matrix getM()
+ public MatrixI getM()
{
return m;
}
*/
public double getEigenvalue(int i)
{
- return eigenvector.d[i];
+ return eigenvector.getD()[i];
}
/**
*/
public float[][] getComponents(int l, int n, int mm, float factor)
{
- float[][] out = new float[m.rows][3];
+ float[][] out = new float[m.height()][3];
- for (int i = 0; i < m.rows; i++)
+ for (int i = 0; i < m.height(); i++)
{
out[i][0] = (float) component(i, l) * factor;
out[i][1] = (float) component(i, n) * factor;
public double[] component(int n)
{
// n = index of eigenvector
- double[] out = new double[m.rows];
+ double[] out = new double[m.height()];
- for (int i = 0; i < m.rows; i++)
+ for (int i = 0; i < m.height(); i++)
{
out[i] = component(i, n);
}
{
double out = 0.0;
- for (int i = 0; i < symm.cols; i++)
+ for (int i = 0; i < symm.width(); i++)
{
- out += (symm.value[row][i] * eigenvector.value[i][n]);
+ out += (symm.getValue(row, i) * eigenvector.getValue(i, n));
}
- return out / eigenvector.d[n];
+ return out / eigenvector.getD()[n];
}
public String getDetails()
/**
* DOCUMENT ME!
*/
+ @Override
public void run()
{
PrintStream ps = new PrintStream(System.out)
{
+ @Override
public void print(String x)
{
details.append(x);
}
+ @Override
public void println()
{
details.append("\n");
}
};
- try {
- details.append("PCA Calculation Mode is "
- + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + "\n");
- Matrix mt = m.transpose();
-
- details.append(" --- OrigT * Orig ---- \n");
- if (!jvCalcMode)
- {
- eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
- }
- else
+ // long now = System.currentTimeMillis();
+ try
{
- eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method
- }
+ details.append("PCA Calculation Mode is "
+ + (jvCalcMode ? "Jalview variant" : "Original SeqSpace")
+ + "\n");
+ MatrixI mt = m.transpose();
- eigenvector.print(ps);
+ details.append(" --- OrigT * Orig ---- \n");
- symm = eigenvector.copy();
+ eigenvector = mt.preMultiply(jvCalcMode ? m2 : m);
- eigenvector.tred();
+ eigenvector.print(ps, "%8.2f");
- details.append(" ---Tridiag transform matrix ---\n");
- details.append(" --- D vector ---\n");
- eigenvector.printD(ps);
- ps.println();
- details.append("--- E vector ---\n");
- eigenvector.printE(ps);
- ps.println();
+ symm = eigenvector.copy();
+
+ eigenvector.tred();
+
+ details.append(" ---Tridiag transform matrix ---\n");
+ details.append(" --- D vector ---\n");
+ eigenvector.printD(ps, "%15.4e");
+ ps.println();
+ details.append("--- E vector ---\n");
+ eigenvector.printE(ps, "%15.4e");
+ ps.println();
- // Now produce the diagonalization matrix
- eigenvector.tqli();
+ // Now produce the diagonalization matrix
+ eigenvector.tqli();
} catch (Exception q)
{
q.printStackTrace();
- details.append("\n*** Unexpected exception when performing PCA ***\n"+q.getLocalizedMessage());
+ details.append("\n*** Unexpected exception when performing PCA ***\n"
+ + q.getLocalizedMessage());
details.append("*** Matrices below may not be fully diagonalised. ***\n");
}
details.append(" --- New diagonalization matrix ---\n");
- eigenvector.print(ps);
+ eigenvector.print(ps, "%8.2f");
details.append(" --- Eigenvalues ---\n");
- eigenvector.printD(ps);
+ eigenvector.printD(ps, "%15.4e");
ps.println();
/*
* for (int seq=0;seq<symm.rows;seq++) { ps.print("\"Seq"+seq+"\""); for
*
* ps.print(","+component(seq, ev)); } ps.println(); }
*/
+ // System.out.println(("PCA.run() took "
+ // + (System.currentTimeMillis() - now) + "ms"));
}
- boolean jvCalcMode = true;
-
public void setJvCalcMode(boolean calcMode)
{
this.jvCalcMode = calcMode;