-// PCA.java \r
-package jalview.analysis;\r
-\r
-import jalview.math.*;\r
-import jalview.datamodel.*;\r
-import jalview.util.*;\r
-\r
-import java.awt.*;\r
-import java.io.*;\r
-\r
-public class PCA implements Runnable {\r
- Matrix m;\r
- Matrix symm;\r
- Matrix m2;\r
-\r
- double[] eigenvalue;\r
- Matrix eigenvector;\r
-\r
- public PCA(Matrix m) {\r
- this.m = m;\r
- }\r
-\r
- public PCA(SequenceI[] s) {\r
- Runtime rt = Runtime.getRuntime();\r
-\r
- BinarySequence[] bs = new BinarySequence[s.length];\r
- int ii = 0;\r
- while (ii < s.length && s[ii] != null) {\r
-\r
- bs[ii] = new BinarySequence(s[ii]);\r
- bs[ii].encode();\r
- ii++;\r
- }\r
-\r
- BinarySequence[] bs2 = new BinarySequence[s.length];\r
- ii = 0;\r
- while (ii < s.length && s[ii] != null) {\r
-\r
- bs2[ii] = new BinarySequence(s[ii]);\r
- bs2[ii].blosumEncode();\r
- ii++;\r
- }\r
-\r
-\r
- //System.out.println("Created binary encoding");\r
- //printMemory(rt);\r
-\r
- int count=0;\r
- while (count < bs.length && bs[count] != null) {\r
- count++;\r
- }\r
- double[][] seqmat = new double[count][bs[0].getDBinary().length];\r
- double[][] seqmat2 = new double[count][bs2[0].getDBinary().length];\r
- int i=0;\r
- while (i < count) {\r
- seqmat[i] = bs[i].getDBinary();\r
- seqmat2[i] = bs2[i].getDBinary();\r
- i++;\r
- }\r
- //System.out.println("Created array");\r
- //printMemory(rt);\r
- // System.out.println(" --- Original matrix ---- ");\r
- m = new Matrix(seqmat,count,bs[0].getDBinary().length);\r
- m2 = new Matrix(seqmat2,count,bs2[0].getDBinary().length);\r
-\r
- //System.out.println("Created matrix");\r
- printMemory(rt);\r
- }\r
-\r
- public static void printMemory(Runtime rt) {\r
- System.out.println("Free memory = " + rt.freeMemory());\r
- }\r
-\r
- public Matrix getM() {\r
- return m;\r
- }\r
-\r
- public double[] getEigenvector(int i) {\r
- return eigenvector.getColumn(i);\r
- }\r
-\r
- public double getEigenvalue(int i) {\r
- return eigenvector.d[i];\r
- }\r
- public float[][] getComponents(int l, int n, int mm) {\r
- return getComponents(l,n,mm,1);\r
- }\r
- public float[][] getComponents(int l, int n, int mm, float factor) {\r
- float[][] out = new float[m.rows][3];\r
-\r
- for (int i = 0; i < m.rows;i++) {\r
- out[i][0] = (float)component(i,l)*factor;\r
- out[i][1] = (float)component(i,n)*factor;\r
- out[i][2] = (float)component(i,mm)*factor;\r
- }\r
- return out;\r
- }\r
-\r
- public double[] component(int n) {\r
- // n = index of eigenvector\r
- double[] out = new double[m.rows];\r
-\r
- for (int i=0; i < m.rows; i++) {\r
- out[i] = component(i,n);\r
- }\r
- return out;\r
- }\r
- public double component(int row, int n) {\r
- double out = 0.0;\r
-\r
- for (int i = 0; i < symm.cols; i++) {\r
- out += symm.value[row][i] * eigenvector.value[i][n];\r
- }\r
- return out/eigenvector.d[n];\r
- }\r
-\r
- public void checkEigenvector(int n,PrintStream ps) {\r
- ps.println(" --- Eigenvector " + n + " --- ");\r
-\r
- double[] eigenv = eigenvector.getColumn(n);\r
-\r
- for (int i=0; i < eigenv.length;i++) {\r
- Format.print(ps,"%15.4f",eigenv[i]);\r
- }\r
-\r
- System.out.println();\r
-\r
- double[] neigenv = symm.vectorPostMultiply(eigenv);\r
- System.out.println(" --- symmat * eigenv / lambda --- ");\r
- if (eigenvector.d[n] > 1e-4) {\r
- for (int i=0; i < neigenv.length;i++) {\r
- Format.print(System.out,"%15.4f",neigenv[i]/eigenvector.d[n]);\r
- }\r
- }\r
- System.out.println();\r
- }\r
-\r
- public void run() {\r
- Matrix mt = m.transpose();\r
- // System.out.println(" --- OrigT * Orig ---- ");\r
- eigenvector = mt.preMultiply(m2);\r
- // eigenvector.print(System.out);\r
- symm = eigenvector.copy();\r
-\r
- //TextArea ta = new TextArea(25,72);\r
- //TextAreaPrintStream taps = new TextAreaPrintStream(System.out,ta);\r
- //Frame f = new Frame("PCA output");\r
- //f.resize(500,500);\r
- //f.setLayout(new BorderLayout());\r
- //f.add("Center",ta);\r
- //f.show();\r
- //symm.print(taps);\r
- long tstart = System.currentTimeMillis();\r
- eigenvector.tred();\r
- long tend = System.currentTimeMillis();\r
- //taps.println("Time take for tred = " + (tend-tstart) + "ms");\r
- //taps.println(" ---Tridiag transform matrix ---");\r
-\r
- //taps.println(" --- D vector ---");\r
- //eigenvector.printD(taps);\r
- //taps.println();\r
- //taps.println(" --- E vector ---");\r
- // eigenvector.printE(taps);\r
- //taps.println();\r
-\r
- // Now produce the diagonalization matrix\r
- tstart = System.currentTimeMillis();\r
- eigenvector.tqli();\r
- tend = System.currentTimeMillis();\r
- //System.out.println("Time take for tqli = " + (tend-tstart) + " ms");\r
-\r
- //System.out.println(" --- New diagonalization matrix ---");\r
-\r
- //System.out.println(" --- Eigenvalues ---");\r
- //eigenvector.printD(taps);\r
-\r
- //System.out.println();\r
-\r
- // for (int i=0; i < eigenvector.cols; i++) {\r
- // checkEigenvector(i,taps);\r
- // taps.println();\r
- // }\r
-\r
- // taps.println();\r
- // taps.println("Transformed sequences = ");\r
- // Matrix trans = m.preMultiply(eigenvector);\r
- // trans.print(System.out);\r
- }\r
-\r
-}\r
+/*
+ * 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 <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.analysis;
+
+import jalview.datamodel.BinarySequence;
+import jalview.datamodel.BinarySequence.InvalidSequenceTypeException;
+import jalview.math.Matrix;
+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;
+
+ Matrix symm;
+
+ Matrix m2;
+
+ double[] eigenvalue;
+
+ Matrix eigenvector;
+
+ StringBuffer details = new StringBuffer();
+
+ /**
+ * Creates a new PCA object. By default, uses blosum62 matrix to generate
+ * sequence similarity matrices
+ *
+ * @param s
+ * 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)
+ {
+ this(s, nucleotides, null);
+ }
+
+ public PCA(String[] s, boolean nucleotides, String s_m)
+ {
+
+ BinarySequence[] bs = new BinarySequence[s.length];
+ int ii = 0;
+
+ while ((ii < s.length) && (s[ii] != null))
+ {
+ bs[ii] = new BinarySequence(s[ii], nucleotides);
+ bs[ii].encode();
+ ii++;
+ }
+
+ BinarySequence[] bs2 = new BinarySequence[s.length];
+ ii = 0;
+ ScoreMatrix smtrx = null;
+ String sm = s_m;
+ if (sm != null)
+ {
+ smtrx = ResidueProperties.getScoreMatrix(sm);
+ }
+ 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"));
+ }
+ 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], 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++;
+ }
+
+ // 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];
+ }
+
+ public String getDetails()
+ {
+ return details.toString();
+ }
+
+ /**
+ * DOCUMENT ME!
+ */
+ public void run()
+ {
+ PrintStream ps = new PrintStream(System.out)
+ {
+ public void print(String x)
+ {
+ details.append(x);
+ }
+
+ 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
+ {
+ eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace
+ // method
+ }
+
+ 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();
+ } 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);
+ 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(); }
+ */
+ }
+
+ boolean jvCalcMode = true;
+
+ public void setJvCalcMode(boolean calcMode)
+ {
+ this.jvCalcMode = calcMode;
+ }
+}
git://source.jalview.org / jalview.git / blobdiff