X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=d978451457e07a51034cd33148c07a75463648fa;hb=35679161e01fac267b1a58bec4244baae94d7fd2;hp=4441eebb2153e9add37d64f54ff2c7fdb1109700;hpb=3e9eba89979511361b51f1c78882c9877874f2ba;p=jalview.git diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java index 4441eeb..d978451 100755 --- a/src/jalview/analysis/PCA.java +++ b/src/jalview/analysis/PCA.java @@ -1,53 +1,54 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) - * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, 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 . + * 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 java.io.*; - -import jalview.datamodel.*; -import jalview.datamodel.BinarySequence.InvalidSequenceTypeException; -import jalview.math.*; +import jalview.math.MatrixI; 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; + boolean jvCalcMode = true; - Matrix m2; + MatrixI symm; double[] eigenvalue; - Matrix eigenvector; + MatrixI eigenvector; + + StringBuilder details = new StringBuilder(1024); - StringBuffer details = new StringBuffer(); + private String[] seqs; + + private ScoreMatrix scoreMatrix; /** - * Creates a new PCA object. - * By default, uses blosum62 matrix to generate sequence similarity matrices + * 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 */ @@ -55,90 +56,96 @@ public class PCA implements Runnable { this(s, false); } - + /** - * Creates a new PCA object. - * By default, uses blosum62 matrix to generate sequence similarity matrices + * 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. + * @param nucleotides + * if true, uses standard DNA/RNA matrix for sequence similarity + * calculation. */ public PCA(String[] s, boolean nucleotides) { + this(s, nucleotides, null); + } - 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; - - String sm=nucleotides ? "DNA" : "BLOSUM62"; - ScoreMatrix smtrx=ResidueProperties.getScoreMatrix(sm); - 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)) + public PCA(String[] s, boolean nucleotides, String s_m) + { + this.seqs = s; + + // 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]; + scoreMatrix = null; + String sm = s_m; + if (sm != null) { - count++; + scoreMatrix = ResidueProperties.getScoreMatrix(sm); } - - double[][] seqmat = new double[count][bs[0].getDBinary().length]; - double[][] seqmat2 = new double[count][bs2[0].getDBinary().length]; - int i = 0; - - while (i < count) + if (scoreMatrix == null) { - seqmat[i] = bs[i].getDBinary(); - seqmat2[i] = bs2[i].getDBinary(); - i++; + // either we were given a non-existent score matrix or a scoremodel that + // isn't based on a pairwise symbol score matrix + scoreMatrix = ResidueProperties + .getScoreMatrix(sm = (nucleotides ? "DNA" : "BLOSUM62")); } - - // 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); + 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); + // if (scoreMatrix != null) + // { + // try + // { + // bs2[ii].matrixEncode(scoreMatrix); + // } catch (InvalidSequenceTypeException x) + // { + // details.append("Unexpected mismatch of sequence type and score matrix. Calculation will not be valid!\n\n"); + // } + // } + // ii++; + // } + // + // int count = 0; + // while ((count < bs.length) && (bs[count] != null)) + // { + // count++; + // } + // + // double[][] seqmat = new double[count][]; + // double[][] seqmat2 = new double[count][]; + // + // int i = 0; + // while (i < count) + // { + // seqmat[i] = bs[i].getDBinary(); + // seqmat2[i] = bs2[i].getDBinary(); + // i++; + // } + // + // /* + // * 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 - */ - - public Matrix getM() - { - return m; - } - - /** * Returns Eigenvalue * * @param i @@ -148,7 +155,7 @@ public class PCA implements Runnable */ public double getEigenvalue(int i) { - return eigenvector.d[i]; + return eigenvector.getD()[i]; } /** @@ -167,9 +174,9 @@ public class PCA implements Runnable */ 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; @@ -190,9 +197,9 @@ public class PCA implements Runnable 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); } @@ -214,12 +221,12 @@ public class PCA implements Runnable { 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() @@ -230,55 +237,62 @@ public class PCA implements Runnable /** * DOCUMENT ME! */ + @Override public void run() { - 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 - } - PrintStream ps = new PrintStream(System.out) { + @Override public void print(String x) { details.append(x); } + @Override public void println() { details.append("\n"); } }; - eigenvector.print(ps); + // long now = System.currentTimeMillis(); + try + { + details.append("PCA Calculation Mode is " + + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + + "\n"); - symm = eigenvector.copy(); + eigenvector = scoreMatrix.computePairwiseScores(seqs); - eigenvector.tred(); + details.append(" --- OrigT * Orig ---- \n"); + 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(); - // Now produce the diagonalization matrix - eigenvector.tqli(); + 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); + eigenvector.print(ps, "%8.2f"); details.append(" --- Eigenvalues ---\n"); - eigenvector.printD(ps); + eigenvector.printD(ps, "%15.4e"); ps.println(); /* * for (int seq=0;seq