X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=738da7d090d7098b5641162ce933e7abd1da3a43;hb=7f5ab7d1f58d870622968e0e6a430f33403b8e4f;hp=9be0e3ced5135a4077ae6707d2ab0b4f8a33b11d;hpb=8a6fa9ea9900d0f106529c3f6283e7f9d76dd2cb;p=jalview.git

diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index 9be0e3c..738da7d 100755
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -1,113 +1,59 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6)
- * Copyright (C) 2010 J Procter, AM Waterhouse, 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 <http://www.gnu.org/licenses/>.
+ * 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 java.io.*;
+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.datamodel.*;
-import jalview.math.*;
+import java.io.PrintStream;
 
 /**
  * Performs Principal Component Analysis on given sequences
- * 
- * @author $author$
- * @version $Revision$
  */
 public class PCA implements Runnable
 {
-  Matrix m;
+  boolean jvCalcMode = true;
 
-  Matrix symm;
-
-  Matrix m2;
+  MatrixI symm;
 
   double[] eigenvalue;
 
-  Matrix eigenvector;
-
-  StringBuffer details = new StringBuffer();
-
-  /**
-   * Creates a new PCA object.
-   * 
-   * @param s
-   *          Set of sequences to perform PCA on
-   */
-  public PCA(String[] s)
-  {
-
-    BinarySequence[] bs = new BinarySequence[s.length];
-    int ii = 0;
-
-    while ((ii < s.length) && (s[ii] != null))
-    {
-      bs[ii] = new BinarySequence(s[ii]);
-      bs[ii].encode();
-      ii++;
-    }
+  MatrixI eigenvector;
 
-    BinarySequence[] bs2 = new BinarySequence[s.length];
-    ii = 0;
+  StringBuilder details = new StringBuilder(1024);
 
-    while ((ii < s.length) && (s[ii] != null))
-    {
-      bs2[ii] = new BinarySequence(s[ii]);
-      bs2[ii].blosumEncode();
-      ii++;
-    }
+  private AlignmentView seqs;
 
-    // System.out.println("Created binary encoding");
-    // printMemory(rt);
-    int count = 0;
+  private ScoreModelI scoreModel;
 
-    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()
+  public PCA(AlignmentView s, ScoreModelI sm)
   {
-    return m;
+    this.seqs = s;
+
+    scoreModel = sm;
+    details.append("PCA calculation using " + sm.getName()
+            + " sequence similarity matrix\n========\n\n");
   }
 
   /**
@@ -120,7 +66,7 @@ public class PCA implements Runnable
    */
   public double getEigenvalue(int i)
   {
-    return eigenvector.d[i];
+    return eigenvector.getD()[i];
   }
 
   /**
@@ -139,9 +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;
@@ -162,9 +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);
     }
@@ -186,12 +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()
@@ -202,48 +148,62 @@ public class PCA implements Runnable
   /**
    * DOCUMENT ME!
    */
+  @Override
   public void run()
   {
-    Matrix mt = m.transpose();
-
-    details.append(" --- OrigT * Orig ---- \n");
-    // eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
-    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 = computeSimilarity(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();
 
-    // Now produce the diagonalization matrix
-    eigenvector.tqli();
+      eigenvector.tred();
+
+      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<symm.rows;seq++) { ps.print("\"Seq"+seq+"\""); for
@@ -251,5 +211,56 @@ public class PCA implements Runnable
      * 
      * ps.print(","+component(seq, ev)); } ps.println(); }
      */
+    // System.out.println(("PCA.run() took "
+    // + (System.currentTimeMillis() - now) + "ms"));
+  }
+
+  /**
+   * 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 computeSimilarity(AlignmentView av)
+  {
+    MatrixI result = null;
+    if (scoreModel instanceof SimilarityScoreModelI)
+    {
+      result = ((SimilarityScoreModelI) scoreModel).findSimilarities(av);
+    }
+    else if (scoreModel instanceof DistanceScoreModelI)
+    {
+      result = ((DistanceScoreModelI) scoreModel).findDistances(av);
+      double maxDistance = result.getMaxValue();
+      result.subtractAllFrom(maxDistance);
+    }
+    else
+    {
+      System.err
+              .println("Unexpected type of score model, cannot calculate similarity");
+    }
+
+    return result;
+  }
+
+  public void setJvCalcMode(boolean calcMode)
+  {
+    this.jvCalcMode = calcMode;
+  }
+
+  /**
+   * 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 seqs.getSequences().length;
   }
 }