X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=1cf21fd9f385ef5b03cf325a34ad424f0dced6bc;hb=2cc3a62e1ae63428db854af668e963f1b23af553;hp=eaea7bf9471363c11d87f739fd31f10872b6bb40;hpb=05d2ce87440717d47ba3dc6ef293e25e4543fdd1;p=jalview.git

diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index eaea7bf..1cf21fd 100755
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -20,144 +20,50 @@
  */
 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.datamodel.Point;
+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;
-
-  double[] eigenvalue;
-
-  Matrix eigenvector;
-
-  StringBuffer details = new StringBuffer();
-
-  /**
-   * 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.
+  /*
+   * inputs
    */
-  public PCA(String[] s, boolean nucleotides)
-  {
-    this(s, nucleotides, null);
-  }
+  final private AlignmentView seqs;
 
-  public PCA(String[] s, boolean nucleotides, String s_m)
-  {
+  final private ScoreModelI scoreModel;
 
-    BinarySequence[] bs = new BinarySequence[s.length];
-    int ii = 0;
+  final private SimilarityParamsI similarityParams;
 
-    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;
-    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
-            + " 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++;
-    }
+  /*
+   * outputs
+   */
+  private MatrixI symm;
 
-    // System.out.println("Created array");
-    // printMemory(rt);
-    // System.out.println(" --- Original matrix ---- ");
-    m = new Matrix(seqmat);
-    m2 = new Matrix(seqmat2);
+  private MatrixI eigenvector;
 
-  }
+  private String details;
 
   /**
-   * Returns the matrix used in PCA calculation
+   * Constructor given the sequences to compute for, the similarity model to
+   * use, and a set of parameters for sequence comparison
    * 
-   * @return java.math.Matrix object
+   * @param sequences
+   * @param sm
+   * @param options
    */
-
-  public Matrix getM()
+  public PCA(AlignmentView sequences, ScoreModelI sm, SimilarityParamsI options)
   {
-    return m;
+    this.seqs = sequences;
+    this.scoreModel = sm;
+    this.similarityParams = options;
   }
 
   /**
@@ -170,7 +76,7 @@ public class PCA implements Runnable
    */
   public double getEigenvalue(int i)
   {
-    return eigenvector.d[i];
+    return eigenvector.getD()[i];
   }
 
   /**
@@ -187,15 +93,16 @@ public class PCA implements Runnable
    * 
    * @return DOCUMENT ME!
    */
-  public float[][] getComponents(int l, int n, int mm, float factor)
+  public Point[] getComponents(int l, int n, int mm, float factor)
   {
-    float[][] out = new float[m.rows][3];
+    Point[] out = new Point[getHeight()];
 
-    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;
-      out[i][2] = (float) component(i, mm) * factor;
+      float x = (float) component(i, l) * factor;
+      float y = (float) component(i, n) * factor;
+      float z = (float) component(i, mm) * factor;
+      out[i] = new Point(x, y, z);
     }
 
     return out;
@@ -212,9 +119,9 @@ 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);
     }
@@ -236,70 +143,56 @@ 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];
   }
 
+  /**
+   * Answers a formatted text report of the PCA calculation results (matrices
+   * and eigenvalues) suitable for display
+   * 
+   * @return
+   */
   public String getDetails()
   {
-    return details.toString();
+    return details;
   }
 
   /**
-   * DOCUMENT ME!
+   * Performs the PCA calculation
    */
   @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");
-      }
-    };
+    /*
+     * print details to a string buffer as they are computed
+     */
+    StringBuilder sb = new StringBuilder(1024);
+    sb.append("PCA calculation using ").append(scoreModel.getName())
+            .append(" sequence similarity matrix\n========\n\n");
+    PrintStream ps = wrapOutputBuffer(sb);
 
     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);
+      sb.append(" --- OrigT * Orig ---- \n");
+      eigenvector.print(ps, "%8.2f");
 
       symm = eigenvector.copy();
 
       eigenvector.tred();
 
-      details.append(" ---Tridiag transform matrix ---\n");
-      details.append(" --- D vector ---\n");
-      eigenvector.printD(ps);
+      sb.append(" ---Tridiag transform matrix ---\n");
+      sb.append(" --- D vector ---\n");
+      eigenvector.printD(ps, "%15.4e");
       ps.println();
-      details.append("--- E vector ---\n");
-      eigenvector.printE(ps);
+      sb.append("--- E vector ---\n");
+      eigenvector.printE(ps, "%15.4e");
       ps.println();
 
       // Now produce the diagonalization matrix
@@ -307,28 +200,56 @@ public class PCA implements Runnable
     } catch (Exception q)
     {
       q.printStackTrace();
-      details.append("\n*** Unexpected exception when performing PCA ***\n"
+      sb.append("\n*** Unexpected exception when performing PCA ***\n"
               + q.getLocalizedMessage());
-      details.append("*** Matrices below may not be fully diagonalised. ***\n");
+      sb.append(
+              "*** Matrices below may not be fully diagonalised. ***\n");
     }
 
-    details.append(" --- New diagonalization matrix ---\n");
-    eigenvector.print(ps);
-    details.append(" --- Eigenvalues ---\n");
-    eigenvector.printD(ps);
+    sb.append(" --- New diagonalization matrix ---\n");
+    eigenvector.print(ps, "%8.2f");
+    sb.append(" --- Eigenvalues ---\n");
+    eigenvector.printD(ps, "%15.4e");
     ps.println();
-    /*
-     * for (int seq=0;seq<symm.rows;seq++) { ps.print("\"Seq"+seq+"\""); for
-     * (int ev=0;ev<symm.rows; ev++) {
-     * 
-     * ps.print(","+component(seq, ev)); } ps.println(); }
-     */
+
+    details = sb.toString();
   }
 
-  boolean jvCalcMode = true;
+  /**
+   * Returns a PrintStream that wraps (appends its output to) the given
+   * StringBuilder
+   * 
+   * @param sb
+   * @return
+   */
+  protected PrintStream wrapOutputBuffer(StringBuilder sb)
+  {
+    PrintStream ps = new PrintStream(System.out)
+    {
+      @Override
+      public void print(String x)
+      {
+        sb.append(x);
+      }
 
-  public void setJvCalcMode(boolean calcMode)
+      @Override
+      public void println()
+      {
+        sb.append("\n");
+      }
+    };
+    return ps;
+  }
+
+  /**
+   * 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()
   {
-    this.jvCalcMode = calcMode;
+    // TODO can any of seqs[] be null?
+    return seqs.getSequences().length;
   }
 }