X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;fp=src%2Fjalview%2Fanalysis%2FPCA.java;h=9babaee1ea6928a1731b3906c1a4cbada0fa5bee;hb=d5bcc3830eab04e6db816e1c2ad8fce1dc189612;hp=eaea7bf9471363c11d87f739fd31f10872b6bb40;hpb=3ebdd4e28382e38a181aae1eed71549f603f9025;p=jalview.git diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java index eaea7bf..9babaee 100755 --- a/src/jalview/analysis/PCA.java +++ b/src/jalview/analysis/PCA.java @@ -20,9 +20,7 @@ */ package jalview.analysis; -import jalview.datamodel.BinarySequence; -import jalview.datamodel.BinarySequence.InvalidSequenceTypeException; -import jalview.math.Matrix; +import jalview.math.MatrixI; import jalview.schemes.ResidueProperties; import jalview.schemes.ScoreMatrix; @@ -30,23 +28,22 @@ 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; - StringBuffer details = new StringBuffer(); + StringBuilder details = new StringBuilder(1024); + + private String[] seqs; + + private ScoreMatrix scoreMatrix; /** * Creates a new PCA object. By default, uses blosum62 matrix to generate @@ -77,87 +74,23 @@ public class PCA implements Runnable 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]; - ii = 0; - ScoreMatrix smtrx = null; + scoreMatrix = null; String sm = s_m; if (sm != null) { - smtrx = ResidueProperties.getScoreMatrix(sm); + scoreMatrix = ResidueProperties.getScoreMatrix(sm); } - if (smtrx == null) + if (scoreMatrix == 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")); + scoreMatrix = 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); - m2 = new Matrix(seqmat2); - - } - - /** - * Returns the matrix used in PCA calculation - * - * @return java.math.Matrix object - */ - - public Matrix getM() - { - return m; } /** @@ -170,7 +103,7 @@ public class PCA implements Runnable */ public double getEigenvalue(int i) { - return eigenvector.d[i]; + return eigenvector.getD()[i]; } /** @@ -189,9 +122,9 @@ 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; @@ -212,9 +145,9 @@ 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); } @@ -236,12 +169,12 @@ 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() @@ -270,25 +203,17 @@ public class PCA implements Runnable } }; + // long now = System.currentTimeMillis(); 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 = scoreMatrix.computePairwiseScores(seqs); - eigenvector.print(ps); + details.append(" --- OrigT * Orig ---- \n"); + eigenvector.print(ps, "%8.2f"); symm = eigenvector.copy(); @@ -296,10 +221,10 @@ public class PCA implements Runnable details.append(" ---Tridiag transform matrix ---\n"); details.append(" --- D vector ---\n"); - eigenvector.printD(ps); + eigenvector.printD(ps, "%15.4e"); ps.println(); details.append("--- E vector ---\n"); - eigenvector.printE(ps); + eigenvector.printE(ps, "%15.4e"); ps.println(); // Now produce the diagonalization matrix @@ -313,9 +238,9 @@ public class PCA implements Runnable } 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