-/*\r
- * Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
- *\r
- * This program is free software; you can redistribute it and/or\r
- * modify it under the terms of the GNU General Public License\r
- * as published by the Free Software Foundation; either version 2\r
- * of the License, or (at your option) any later version.\r
- *\r
- * This program is distributed in the hope that it will be useful,\r
- * but WITHOUT ANY WARRANTY; without even the implied warranty of\r
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
- * GNU General Public License for more details.\r
- *\r
- * You should have received a copy of the GNU General Public License\r
- * along with this program; if not, write to the Free Software\r
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
- */\r
-package jalview.analysis;\r
-\r
-import java.io.*;\r
-\r
-import jalview.datamodel.*;\r
-import jalview.math.*;\r
-\r
-/**\r
- * Performs Principal Component Analysis on given sequences\r
- *\r
- * @author $author$\r
- * @version $Revision$\r
- */\r
-public class PCA\r
- implements Runnable\r
-{\r
- Matrix m;\r
- Matrix symm;\r
- Matrix m2;\r
- double[] eigenvalue;\r
- Matrix eigenvector;\r
- StringBuffer details = new StringBuffer();\r
-\r
- /**\r
- * Creates a new PCA object.\r
- *\r
- * @param s Set of sequences to perform PCA on\r
- */\r
- public PCA(String[] s)\r
- {\r
-\r
- BinarySequence[] bs = new BinarySequence[s.length];\r
- int ii = 0;\r
-\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
-\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
- //System.out.println("Created binary encoding");\r
- //printMemory(rt);\r
- int count = 0;\r
-\r
- while ( (count < bs.length) && (bs[count] != null))\r
- {\r
- count++;\r
- }\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
-\r
- while (i < count)\r
- {\r
- seqmat[i] = bs[i].getDBinary();\r
- seqmat2[i] = bs2[i].getDBinary();\r
- i++;\r
- }\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
- }\r
-\r
- /**\r
- * Returns the matrix used in PCA calculation\r
- *\r
- * @return java.math.Matrix object\r
- */\r
-\r
- public Matrix getM()\r
- {\r
- return m;\r
- }\r
-\r
- /**\r
- * Returns Eigenvalue\r
- *\r
- * @param i Index of diagonal within matrix\r
- *\r
- * @return Returns value of diagonal from matrix\r
- */\r
- public double getEigenvalue(int i)\r
- {\r
- return eigenvector.d[i];\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @param l DOCUMENT ME!\r
- * @param n DOCUMENT ME!\r
- * @param mm DOCUMENT ME!\r
- * @param factor DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public float[][] getComponents(int l, int n, int mm, float factor)\r
- {\r
- float[][] out = new float[m.rows][3];\r
-\r
- for (int i = 0; i < m.rows; i++)\r
- {\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
-\r
- return out;\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @param n DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public double[] component(int n)\r
- {\r
- // n = index of eigenvector\r
- double[] out = new double[m.rows];\r
-\r
- for (int i = 0; i < m.rows; i++)\r
- {\r
- out[i] = component(i, n);\r
- }\r
-\r
- return out;\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @param row DOCUMENT ME!\r
- * @param n DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- double component(int row, int n)\r
- {\r
- double out = 0.0;\r
-\r
- for (int i = 0; i < symm.cols; i++)\r
- {\r
- out += (symm.value[row][i] * eigenvector.value[i][n]);\r
- }\r
-\r
- return out / eigenvector.d[n];\r
- }\r
-\r
- public String getDetails()\r
- {\r
- return details.toString();\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- */\r
- public void run()\r
- {\r
- Matrix mt = m.transpose();\r
-\r
- details.append(" --- OrigT * Orig ---- \n");\r
- eigenvector = mt.preMultiply(m2);\r
-\r
- PrintStream ps = new PrintStream(System.out)\r
- {\r
- public void print(String x)\r
- {\r
- details.append(x);\r
- }\r
-\r
- public void println()\r
- {\r
- details.append("\n");\r
- }\r
- };\r
-\r
- eigenvector.print(ps);\r
-\r
- symm = eigenvector.copy();\r
-\r
- eigenvector.tred();\r
-\r
- details.append(" ---Tridiag transform matrix ---\n");\r
- details.append(" --- D vector ---\n");\r
- eigenvector.printD(ps);\r
- ps.println();\r
- details.append("--- E vector ---\n");\r
- eigenvector.printE(ps);\r
- ps.println();\r
-\r
- // Now produce the diagonalization matrix\r
- eigenvector.tqli();\r
-\r
- details.append(" --- New diagonalization matrix ---\n");\r
- details.append(" --- Eigenvalues ---\n");\r
- eigenvector.printD(ps);\r
- ps.println();\r
- // taps.println();\r
- // taps.println("Transformed sequences = ");\r
- // Matrix trans = m.preMultiply(eigenvector);\r
- // trans.print(System.out);\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.api.analysis.ScoreModelI;
+import jalview.api.analysis.SimilarityParamsI;
+import jalview.bin.Console;
+import jalview.datamodel.AlignmentView;
+import jalview.datamodel.Point;
+import jalview.math.MatrixI;
+
+import java.io.PrintStream;
+
+/**
+ * Performs Principal Component Analysis on given sequences
+ */
+public class PCA implements Runnable
+{
+ /*
+ * inputs
+ */
+ final private AlignmentView seqs;
+
+ final private ScoreModelI scoreModel;
+
+ final private SimilarityParamsI similarityParams;
+
+ /*
+ * outputs
+ */
+ private MatrixI pairwiseScores;
+
+ private MatrixI tridiagonal;
+
+ private MatrixI eigenMatrix;
+
+ /**
+ * Constructor given the sequences to compute for, the similarity model to
+ * use, and a set of parameters for sequence comparison
+ *
+ * @param sequences
+ * @param sm
+ * @param options
+ */
+ public PCA(AlignmentView sequences, ScoreModelI sm, SimilarityParamsI options)
+ {
+ this.seqs = sequences;
+ this.scoreModel = sm;
+ this.similarityParams = options;
+ }
+
+ /**
+ * Returns Eigenvalue
+ *
+ * @param i
+ * Index of diagonal within matrix
+ *
+ * @return Returns value of diagonal from matrix
+ */
+ public double getEigenvalue(int i)
+ {
+ return eigenMatrix.getD()[i];
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param l
+ * DOCUMENT ME!
+ * @param n
+ * DOCUMENT ME!
+ * @param mm
+ * DOCUMENT ME!
+ * @param factor
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public Point[] getComponents(int l, int n, int mm, float factor)
+ {
+ Point[] out = new Point[getHeight()];
+
+ for (int i = 0; i < getHeight(); i++)
+ {
+ float x = (float) component(i, l) * factor;
+ float y = (float) component(i, n) * factor;
+ float z = (float) component(i, mm) * factor;
+ out[i] = new Point(x, y, z);
+ }
+
+ 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 < pairwiseScores.width(); i++)
+ {
+ out += (pairwiseScores.getValue(row, i) * eigenMatrix.getValue(i, n));
+ }
+
+ return out / eigenMatrix.getD()[n];
+ }
+
+ /**
+ * Answers a formatted text report of the PCA calculation results (matrices
+ * and eigenvalues) suitable for display
+ *
+ * @return
+ */
+ public String getDetails()
+ {
+ StringBuilder sb = new StringBuilder(1024);
+ sb.append("PCA calculation using ").append(scoreModel.getName())
+ .append(" sequence similarity matrix\n========\n\n");
+ PrintStream ps = wrapOutputBuffer(sb);
+
+ /*
+ * pairwise similarity scores
+ */
+ sb.append(" --- OrigT * Orig ---- \n");
+ pairwiseScores.print(ps, "%8.2f");
+
+ /*
+ * tridiagonal matrix, with D and E vectors
+ */
+ sb.append(" ---Tridiag transform matrix ---\n");
+ sb.append(" --- D vector ---\n");
+ tridiagonal.printD(ps, "%15.4e");
+ ps.println();
+ sb.append("--- E vector ---\n");
+ tridiagonal.printE(ps, "%15.4e");
+ ps.println();
+
+ /*
+ * eigenvalues matrix, with D vector
+ */
+ sb.append(" --- New diagonalization matrix ---\n");
+ eigenMatrix.print(ps, "%8.2f");
+ sb.append(" --- Eigenvalues ---\n");
+ eigenMatrix.printD(ps, "%15.4e");
+ ps.println();
+
+ return sb.toString();
+ }
+
+ /**
+ * Performs the PCA calculation
+ */
+ @Override
+ public void run()
+ {
+ try
+ {
+ /*
+ * sequence pairwise similarity scores
+ */
+ pairwiseScores = scoreModel.findSimilarities(seqs, similarityParams);
+
+ /*
+ * tridiagonal matrix
+ */
+ tridiagonal = pairwiseScores.copy();
+ tridiagonal.tred();
+
+ /*
+ * the diagonalization matrix
+ */
+ eigenMatrix = tridiagonal.copy();
+ eigenMatrix.tqli();
+ } catch (Exception q)
+ {
+ Console.error("Error computing PCA: " + q.getMessage());
+ q.printStackTrace();
+ }
+ }
+
+ /**
+ * Returns a PrintStream that wraps (appends 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)
+ {
+ sb.append(x);
+ }
+
+ @Override
+ public void println()
+ {
+ sb.append("\n");
+ }
+ };
+ return ps;
+ }
+
+ /**
+ * 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 pairwiseScores.height();// seqs.getSequences().length;
+ }
+
+ /**
+ * Answers the sequence pairwise similarity scores which were the first step
+ * of the PCA calculation
+ *
+ * @return
+ */
+ public MatrixI getPairwiseScores()
+ {
+ return pairwiseScores;
+ }
+
+ public void setPairwiseScores(MatrixI m)
+ {
+ pairwiseScores = m;
+ }
+
+ public MatrixI getEigenmatrix()
+ {
+ return eigenMatrix;
+ }
+
+ public void setEigenmatrix(MatrixI m)
+ {
+ eigenMatrix = m;
+ }
+
+ public MatrixI getTridiagonal()
+ {
+ return tridiagonal;
+ }
+
+ public void setTridiagonal(MatrixI tridiagonal)
+ {
+ this.tridiagonal = tridiagonal;
+ }
+}
git://source.jalview.org / jalview.git / blobdiff