/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
- * Copyright (C) 2011 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.io.*;
+import jalview.api.analysis.ScoreModelI;
+import jalview.api.analysis.SimilarityParamsI;
+import jalview.datamodel.AlignmentView;
+import jalview.math.MatrixI;
-import jalview.datamodel.*;
-import jalview.math.*;
+import java.io.PrintStream;
/**
* 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;
-
- StringBuffer details = new StringBuffer();
-
- /**
- * Creates a new PCA object.
- *
- * @param s
- * Set of sequences to perform PCA on
+ /*
+ * inputs
*/
- public PCA(String[] 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;
+ final private AlignmentView seqs;
- 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++;
- }
+ final private ScoreModelI scoreModel;
- double[][] seqmat = new double[count][bs[0].getDBinary().length];
- double[][] seqmat2 = new double[count][bs2[0].getDBinary().length];
- int i = 0;
+ final private SimilarityParamsI similarityParams;
- while (i < count)
- {
- seqmat[i] = bs[i].getDBinary();
- seqmat2[i] = bs2[i].getDBinary();
- i++;
- }
+ /*
+ * outputs
+ */
+ private MatrixI symm;
- // 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);
+ private MatrixI eigenvector;
- }
+ private String details;
/**
- * Returns the matrix used in PCA calculation
+ * Constructor given the sequences to compute for, the similarity model to
+ * use, and a set of parameters for sequence comparison
*
- * @return java.math.Matrix object
+ * @param sequences
+ * @param sm
+ * @param options
*/
-
- public Matrix getM()
+ public PCA(AlignmentView sequences, ScoreModelI sm, SimilarityParamsI options)
{
- return m;
+ this.seqs = sequences;
+ this.scoreModel = sm;
+ this.similarityParams = options;
}
/**
*/
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[getHeight()][3];
- for (int i = 0; i < m.rows; i++)
+ for (int i = 0; i < getHeight(); 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[getHeight()];
- for (int i = 0; i < m.rows; i++)
+ for (int i = 0; i < out.length; 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];
}
+ /**
+ * Answers a formatted text report of the PCA calculation results (matrices
+ * and eigenvalues) suitable for display
+ *
+ * @return
+ */
public String getDetails()
{
- return details.toString();
+ return details;
}
/**
- * DOCUMENT ME!
+ * Performs the PCA calculation
*/
+ @Override
public void run()
{
- Matrix mt = m.transpose();
+ /*
+ * print details to a string buffer as they are computed
+ */
+ StringBuilder sb = new StringBuilder(1024);
+ sb.append("PCA calculation using ").append(scoreModel.getName())
+ .append(" sequence similarity matrix\n========\n\n");
+ PrintStream ps = wrapOutputBuffer(sb);
+
+ try
+ {
+ eigenvector = scoreModel.findSimilarities(seqs, similarityParams);
+
+ sb.append(" --- OrigT * Orig ---- \n");
+ eigenvector.print(ps, "%8.2f");
+
+ symm = eigenvector.copy();
+
+ eigenvector.tred();
+
+ sb.append(" ---Tridiag transform matrix ---\n");
+ sb.append(" --- D vector ---\n");
+ eigenvector.printD(ps, "%15.4e");
+ ps.println();
+ sb.append("--- E vector ---\n");
+ eigenvector.printE(ps, "%15.4e");
+ ps.println();
+
+ // Now produce the diagonalization matrix
+ eigenvector.tqli();
+ } catch (Exception q)
+ {
+ q.printStackTrace();
+ sb.append("\n*** Unexpected exception when performing PCA ***\n"
+ + q.getLocalizedMessage());
+ sb.append(
+ "*** Matrices below may not be fully diagonalised. ***\n");
+ }
+
+ sb.append(" --- New diagonalization matrix ---\n");
+ eigenvector.print(ps, "%8.2f");
+ sb.append(" --- Eigenvalues ---\n");
+ eigenvector.printD(ps, "%15.4e");
+ ps.println();
- details.append(" --- OrigT * Orig ---- \n");
- // eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
- eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method
+ details = sb.toString();
+ }
+ /**
+ * Returns a PrintStream that wraps (sends its output to) the given
+ * StringBuilder
+ *
+ * @param sb
+ * @return
+ */
+ protected PrintStream wrapOutputBuffer(StringBuilder sb)
+ {
PrintStream ps = new PrintStream(System.out)
{
+ @Override
public void print(String x)
{
- details.append(x);
+ sb.append(x);
}
+ @Override
public void println()
{
- details.append("\n");
+ sb.append("\n");
}
};
+ return ps;
+ }
- eigenvector.print(ps);
-
- symm = eigenvector.copy();
-
- eigenvector.tred();
-
- 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();
-
- // Now produce the diagonalization matrix
- eigenvector.tqli();
-
- details.append(" --- New diagonalization matrix ---\n");
- eigenvector.print(ps);
- details.append(" --- Eigenvalues ---\n");
- eigenvector.printD(ps);
- ps.println();
- /*
- * for (int seq=0;seq<symm.rows;seq++) { ps.print("\"Seq"+seq+"\""); for
- * (int ev=0;ev<symm.rows; ev++) {
- *
- * ps.print(","+component(seq, ev)); } ps.println(); }
- */
+ /**
+ * Answers the N dimensions of the NxN PCA matrix. This is the number of
+ * sequences involved in the pairwise score calculation.
+ *
+ * @return
+ */
+ public int getHeight()
+ {
+ // TODO can any of seqs[] be null?
+ return seqs.getSequences().length;
}
}