X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FPCA.java;h=b481e89d32371720ecbf9e114cea8276ece749fa;hb=582493a5b56d3e01d901c6da9906685c31a32abb;hp=d978451457e07a51034cd33148c07a75463648fa;hpb=35679161e01fac267b1a58bec4244baae94d7fd2;p=jalview.git

diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index d978451..b481e89 100755
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -20,9 +20,12 @@
  */
 package jalview.analysis;
 
+import jalview.api.analysis.DistanceScoreModelI;
+import jalview.api.analysis.ScoreModelI;
+import jalview.api.analysis.SimilarityParamsI;
+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;
 
@@ -41,108 +44,20 @@ public class PCA implements Runnable
 
   StringBuilder details = new StringBuilder(1024);
 
-  private String[] seqs;
+  private AlignmentView seqs;
 
-  private ScoreMatrix scoreMatrix;
+  private ScoreModelI scoreModel;
+  
+  private SimilarityParamsI similarityParams;
 
-  /**
-   * 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, SimilarityParamsI options)
   {
     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
+    this.similarityParams = options;
+    this.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);
-
   }
 
   /**
@@ -262,7 +177,7 @@ public class PCA implements Runnable
               + (jvCalcMode ? "Jalview variant" : "Original SeqSpace")
               + "\n");
 
-      eigenvector = scoreMatrix.computePairwiseScores(seqs);
+      eigenvector = computeSimilarity(seqs);
 
       details.append(" --- OrigT * Orig ---- \n");
       eigenvector.print(ps, "%8.2f");
@@ -304,6 +219,42 @@ public class PCA implements Runnable
     // + (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.
+   * 
+   * @param av
+   * @return
+   */
+  MatrixI computeSimilarity(AlignmentView av)
+  {
+    MatrixI result = null;
+    if (scoreModel instanceof SimilarityScoreModelI)
+    {
+      result = ((SimilarityScoreModelI) scoreModel).findSimilarities(av,
+              similarityParams);
+    }
+    else if (scoreModel instanceof DistanceScoreModelI)
+    {
+      /*
+       * find distances and convert to similarity scores
+       * reverseRange(false) preserves but reverses the min-max range
+       */
+      result = ((DistanceScoreModelI) scoreModel).findDistances(av,
+              similarityParams);
+      result.reverseRange(false);
+    }
+    else
+    {
+      System.err
+              .println("Unexpected type of score model, cannot calculate similarity");
+    }
+
+    return result;
+  }
+
   public void setJvCalcMode(boolean calcMode)
   {
     this.jvCalcMode = calcMode;
@@ -318,6 +269,6 @@ public class PCA implements Runnable
   public int getHeight()
   {
     // TODO can any of seqs[] be null?
-    return seqs.length;
+    return seqs.getSequences().length;
   }
 }