X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=3ec7995f9f67aa84c2553fcd154df0b4c934a223;hb=136c0793b90b72b928c4d77dc109dd5c644e00d3;hp=2e37e6aa738ca66b8481e2a9778aa24f6fa4ca2a;hpb=efc31b4a8d5cee63555586804a2b79c06bdb5a14;p=jalview.git
diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index 2e37e6a..3ec7995 100755
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -1,242 +1,225 @@
-/*
-* Jalview - A Sequence Alignment Editor and Viewer
-* Copyright (C) 2005 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
-*/
-package jalview.analysis;
-
-import jalview.datamodel.*;
-
-import jalview.math.*;
-
-import jalview.util.*;
-
-import java.io.*;
-
-
-/**
- * Performs Principal Component Analysis on given sequences
- *
- * @author $author$
- * @version $Revision$
- */
-public class PCA implements Runnable
-{
- Matrix m;
- Matrix symm;
- Matrix m2;
- double[] eigenvalue;
- Matrix eigenvector;
-
-
- /**
- * Creates a new PCA object.
- *
- * @param s Set of sequences to perform PCA on
- */
- public PCA(SequenceI[] s)
- {
-
- BinarySequence[] bs = new BinarySequence[s.length];
- int ii = 0;
-
- while ((ii < s.length) && (s[ii] != null))
- {
- bs[ii] = new BinarySequence(s[ii]);
- bs[ii].encode();
- ii++;
- }
-
- BinarySequence[] bs2 = new BinarySequence[s.length];
- ii = 0;
-
- while ((ii < s.length) && (s[ii] != null))
- {
- bs2[ii] = new BinarySequence(s[ii]);
- bs2[ii].blosumEncode();
- 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;
-
- while (i < count)
- {
- seqmat[i] = bs[i].getDBinary();
- seqmat2[i] = bs2[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);
-
- }
-
- /**
- * Returns the matrix used in PCA calculation
- *
- * @return java.math.Matrix object
- */
-
- public Matrix getM()
- {
- return m;
- }
-
- /**
- * Returns Eigenvalue
- *
- * @param i Index of diagonal within matrix
- *
- * @return Returns value of diagonal from matrix
- */
- public double getEigenvalue(int i)
- {
- return eigenvector.d[i];
- }
-
- /**
- * DOCUMENT ME!
- *
- * @param l DOCUMENT ME!
- * @param n DOCUMENT ME!
- * @param mm DOCUMENT ME!
- * @param factor DOCUMENT ME!
- *
- * @return DOCUMENT ME!
- */
- public float[][] getComponents(int l, int n, int mm, float factor)
- {
- float[][] out = new float[m.rows][3];
-
- for (int i = 0; i < m.rows; i++)
- {
- out[i][0] = (float) component(i, l) * factor;
- out[i][1] = (float) component(i, n) * factor;
- out[i][2] = (float) component(i, mm) * factor;
- }
-
- return out;
- }
-
- /**
- * DOCUMENT ME!
- *
- * @param n DOCUMENT ME!
- *
- * @return DOCUMENT ME!
- */
- public double[] component(int n)
- {
- // n = index of eigenvector
- double[] out = new double[m.rows];
-
- for (int i = 0; i < m.rows; i++)
- {
- out[i] = component(i, n);
- }
-
- return out;
- }
-
- /**
- * DOCUMENT ME!
- *
- * @param row DOCUMENT ME!
- * @param n DOCUMENT ME!
- *
- * @return DOCUMENT ME!
- */
- double component(int row, int n)
- {
- double out = 0.0;
-
- for (int i = 0; i < symm.cols; i++)
- {
- out += (symm.value[row][i] * eigenvector.value[i][n]);
- }
-
- return out / eigenvector.d[n];
- }
-
-
- /**
- * DOCUMENT ME!
- */
- public void run()
- {
- Matrix mt = m.transpose();
-
- // System.out.println(" --- OrigT * Orig ---- ");
- eigenvector = mt.preMultiply(m2);
-
- // eigenvector.print(System.out);
- symm = eigenvector.copy();
-
- //TextArea ta = new TextArea(25,72);
- //TextAreaPrintStream taps = new TextAreaPrintStream(System.out,ta);
- //Frame f = new Frame("PCA output");
- //f.resize(500,500);
- //f.setLayout(new BorderLayout());
- //f.add("Center",ta);
- //f.show();
- //symm.print(taps);
- long tstart = System.currentTimeMillis();
- eigenvector.tred();
-
- long tend = System.currentTimeMillis();
-
- //taps.println("Time take for tred = " + (tend-tstart) + "ms");
- //taps.println(" ---Tridiag transform matrix ---");
- //taps.println(" --- D vector ---");
- //eigenvector.printD(taps);
- //taps.println();
- //taps.println(" --- E vector ---");
- // eigenvector.printE(taps);
- //taps.println();
- // Now produce the diagonalization matrix
- tstart = System.currentTimeMillis();
- eigenvector.tqli();
- tend = System.currentTimeMillis();
-
- //System.out.println("Time take for tqli = " + (tend-tstart) + " ms");
- //System.out.println(" --- New diagonalization matrix ---");
- //System.out.println(" --- Eigenvalues ---");
- //eigenvector.printD(taps);
- //System.out.println();
- // for (int i=0; i < eigenvector.cols; i++) {
- // checkEigenvector(i,taps);
- // taps.println();
- // }
- // taps.println();
- // taps.println("Transformed sequences = ");
- // Matrix trans = m.preMultiply(eigenvector);
- // trans.print(System.out);
- }
-}
+/*
+ * 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.
+ *
+ * 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.analysis;
+
+import jalview.api.analysis.ScoreModelI;
+import jalview.api.analysis.SimilarityParamsI;
+import jalview.datamodel.AlignmentView;
+import jalview.math.MatrixI;
+
+import java.io.PrintStream;
+
+/**
+ * Performs Principal Component Analysis on given sequences
+ */
+public class PCA implements Runnable
+{
+ MatrixI symm;
+
+ double[] eigenvalue;
+
+ MatrixI eigenvector;
+
+ StringBuilder details = new StringBuilder(1024);
+
+ final private AlignmentView seqs;
+
+ private ScoreModelI scoreModel;
+
+ private SimilarityParamsI similarityParams;
+
+ public PCA(AlignmentView s, ScoreModelI sm, SimilarityParamsI options)
+ {
+ this.seqs = s;
+ this.similarityParams = options;
+ this.scoreModel = sm;
+
+ details.append("PCA calculation using " + sm.getName()
+ + " sequence similarity matrix\n========\n\n");
+ }
+
+ /**
+ * Returns Eigenvalue
+ *
+ * @param i
+ * Index of diagonal within matrix
+ *
+ * @return Returns value of diagonal from matrix
+ */
+ public double getEigenvalue(int i)
+ {
+ return eigenvector.getD()[i];
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param l
+ * DOCUMENT ME!
+ * @param n
+ * DOCUMENT ME!
+ * @param mm
+ * DOCUMENT ME!
+ * @param factor
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public float[][] getComponents(int l, int n, int mm, float factor)
+ {
+ float[][] out = new float[getHeight()][3];
+
+ for (int i = 0; i < getHeight(); i++)
+ {
+ out[i][0] = (float) component(i, l) * factor;
+ out[i][1] = (float) component(i, n) * factor;
+ out[i][2] = (float) component(i, mm) * factor;
+ }
+
+ return out;
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param n
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public double[] component(int n)
+ {
+ // n = index of eigenvector
+ double[] out = new double[getHeight()];
+
+ for (int i = 0; i < out.length; i++)
+ {
+ out[i] = component(i, n);
+ }
+
+ return out;
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param row
+ * DOCUMENT ME!
+ * @param n
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ double component(int row, int n)
+ {
+ double out = 0.0;
+
+ for (int i = 0; i < symm.width(); i++)
+ {
+ out += (symm.getValue(row, i) * eigenvector.getValue(i, n));
+ }
+
+ return out / eigenvector.getD()[n];
+ }
+
+ public String getDetails()
+ {
+ return details.toString();
+ }
+
+ /**
+ * 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");
+ }
+ };
+
+ // long now = System.currentTimeMillis();
+ try
+ {
+ eigenvector = scoreModel.findSimilarities(seqs, similarityParams);
+
+ details.append(" --- OrigT * Orig ---- \n");
+ eigenvector.print(ps, "%8.2f");
+
+ 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();
+ } catch (Exception q)
+ {
+ q.printStackTrace();
+ 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, "%8.2f");
+ details.append(" --- Eigenvalues ---\n");
+ eigenvector.printD(ps, "%15.4e");
+ ps.println();
+ /*
+ * for (int seq=0;seq