X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;fp=src%2Fjalview%2Fanalysis%2FPCA.java;h=42a168dab78a24d40c6f572fd4e10d404f6dcaab;hb=f063821ed0be9c1581af74643a1aa5798731af65;hp=06a139bb6df27db1c145b93309e3dff54063298d;hpb=fd18e2c73cd015d4e38ad91da0e5d7532ff0ef42;p=jalview.git diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java index 06a139b..42a168d 100755 --- a/src/jalview/analysis/PCA.java +++ b/src/jalview/analysis/PCA.java @@ -20,144 +20,40 @@ */ 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 jalview.api.analysis.ScoreModelI; +import jalview.api.analysis.SimilarityParamsI; +import jalview.datamodel.AlignmentView; +import jalview.math.MatrixI; 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; + MatrixI symm; double[] eigenvalue; - Matrix eigenvector; + MatrixI eigenvector; - StringBuffer details = new StringBuffer(); + StringBuilder details = new StringBuilder(1024); - /** - * 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); - } + final private AlignmentView seqs; - public PCA(String[] s, boolean nucleotides, String s_m) - { + private ScoreModelI scoreModel; - BinarySequence[] bs = new BinarySequence[s.length]; - int ii = 0; + private SimilarityParamsI similarityParams; - while ((ii < s.length) && (s[ii] != null)) - { - bs[ii] = new BinarySequence(s[ii], nucleotides); - bs[ii].encode(); - ii++; - } + public PCA(AlignmentView s, ScoreModelI sm, SimilarityParamsI options) + { + this.seqs = s; + this.similarityParams = options; + this.scoreModel = sm; - 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 + details.append("PCA calculation using " + sm.getName() + " 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; } /** @@ -170,7 +66,7 @@ public class PCA implements Runnable */ public double getEigenvalue(int i) { - return eigenvector.d[i]; + return eigenvector.getD()[i]; } /** @@ -189,9 +85,9 @@ 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 +108,9 @@ 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 +132,12 @@ 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() @@ -252,40 +148,31 @@ public class PCA implements Runnable /** * DOCUMENT ME! */ + @Override public void run() { PrintStream ps = new PrintStream(System.out) { + @Override public void print(String x) { details.append(x); } + @Override public void println() { details.append("\n"); } }; + // long now = System.currentTimeMillis(); try { - details.append("PCA Calculation Mode is " - + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") - + "\n"); - Matrix mt = m.transpose(); + eigenvector = scoreModel.findSimilarities(seqs, similarityParams); 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); + eigenvector.print(ps, "%8.2f"); symm = eigenvector.copy(); @@ -293,10 +180,10 @@ 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 @@ -306,13 +193,14 @@ public class PCA implements Runnable 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( + "*** 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