X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=738da7d090d7098b5641162ce933e7abd1da3a43;hb=7f5ab7d1f58d870622968e0e6a430f33403b8e4f;hp=1a4060ced77e9bbf51eb17846276c7be8fe3aa88;hpb=07394c1c2d9d4ae05c85cd6d9644e4d17f2818a2;p=jalview.git diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java index 1a4060c..738da7d 100755 --- a/src/jalview/analysis/PCA.java +++ b/src/jalview/analysis/PCA.java @@ -20,10 +20,11 @@ */ package jalview.analysis; -import jalview.math.Matrix; +import jalview.api.analysis.DistanceScoreModelI; +import jalview.api.analysis.ScoreModelI; +import jalview.api.analysis.SimilarityScoreModelI; +import jalview.datamodel.AlignmentView; import jalview.math.MatrixI; -import jalview.schemes.ResidueProperties; -import jalview.schemes.ScoreMatrix; import java.io.PrintStream; @@ -42,108 +43,17 @@ public class PCA implements Runnable StringBuilder details = new StringBuilder(1024); - private String[] seqs; + private AlignmentView seqs; - private ScoreMatrix scoreMatrix; + private ScoreModelI scoreModel; - /** - * 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) + public PCA(AlignmentView s, ScoreModelI sm) { 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) - { - scoreMatrix = ResidueProperties.getScoreMatrix(sm); - } - 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 - scoreMatrix = ResidueProperties - .getScoreMatrix(sm = (nucleotides ? "DNA" : "BLOSUM62")); - } - details.append("PCA calculation using " + sm + scoreModel = sm; + details.append("PCA calculation using " + sm.getName() + " 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); - } /** @@ -263,9 +173,7 @@ public class PCA implements Runnable + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + "\n"); - // MatrixI mt = m.transpose(); - // eigenvector = mt.preMultiply(jvCalcMode ? m2 : m); - eigenvector = computePairwiseScores(); + eigenvector = computeSimilarity(seqs); details.append(" --- OrigT * Orig ---- \n"); eigenvector.print(ps, "%8.2f"); @@ -308,45 +216,35 @@ public class PCA implements Runnable } /** - * Computes an NxN matrix where N is the number of sequences, and entry [i, j] - * is sequence[i] pairwise multiplied with sequence[j], as a sum of scores - * computed using the current score matrix. For example - * + * Computes a pairwise similarity matrix for the given sequence regions using + * the configured score model. If the score model is a similarity model, then + * it computes the result directly. If it is a distance model, then use it to + * compute pairwise distances, and convert these to similarity scores by + * substracting from the maximum value. + * + * @param av + * @return */ - MatrixI computePairwiseScores() + MatrixI computeSimilarity(AlignmentView av) { - double[][] values = new double[seqs.length][]; - for (int row = 0; row < seqs.length; row++) + MatrixI result = null; + if (scoreModel instanceof SimilarityScoreModelI) { - values[row] = new double[seqs.length]; - for (int col = 0; col < seqs.length; col++) - { - int total = 0; - int width = Math.min(seqs[row].length(), seqs[col].length()); - for (int i = 0; i < width; i++) - { - char c1 = seqs[row].charAt(i); - char c2 = seqs[col].charAt(i); - int score = scoreMatrix.getPairwiseScore(c1, c2); - total += score; - } - values[row][col] = total; - } + result = ((SimilarityScoreModelI) scoreModel).findSimilarities(av); + } + else if (scoreModel instanceof DistanceScoreModelI) + { + result = ((DistanceScoreModelI) scoreModel).findDistances(av); + double maxDistance = result.getMaxValue(); + result.subtractAllFrom(maxDistance); } - return new Matrix(values); + else + { + System.err + .println("Unexpected type of score model, cannot calculate similarity"); + } + + return result; } public void setJvCalcMode(boolean calcMode) @@ -363,6 +261,6 @@ public class PCA implements Runnable public int getHeight() { // TODO can any of seqs[] be null? - return seqs.length; + return seqs.getSequences().length; } }