formatting

[jalview.git] / src / jalview / analysis / PCA.java

diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index 47f2d0d..43dab7c 100755 (executable)
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -20,7 +20,10 @@ package jalview.analysis;
 import java.io.*;
 
 import jalview.datamodel.*;
+import jalview.datamodel.BinarySequence.InvalidSequenceTypeException;
 import jalview.math.*;
+import jalview.schemes.ResidueProperties;
+import jalview.schemes.ScoreMatrix;
 
 /**
  * Performs Principal Component Analysis on given sequences
@@ -43,20 +46,36 @@ public class PCA implements Runnable
   StringBuffer details = new StringBuffer();
 
   /**
-   * Creates a new PCA object.
+   * Creates a new PCA object. By default, uses blosum62 matrix to generate
+   * sequence similarity matrices
    * 
    * @param s
-   *          Set of sequences to perform PCA on
+   *          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)
+  {
 
     BinarySequence[] bs = new BinarySequence[s.length];
     int ii = 0;
 
     while ((ii < s.length) && (s[ii] != null))
     {
-      bs[ii] = new BinarySequence(s[ii]);
+      bs[ii] = new BinarySequence(s[ii], nucleotides);
       bs[ii].encode();
       ii++;
     }
@@ -64,10 +83,23 @@ public class PCA implements Runnable
     BinarySequence[] bs2 = new BinarySequence[s.length];
     ii = 0;
 
+    String sm = nucleotides ? "DNA" : "BLOSUM62";
+    ScoreMatrix smtrx = ResidueProperties.getScoreMatrix(sm);
+    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]);
-      bs2[ii].blosumEncode();
+      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++;
     }
 
@@ -204,11 +236,19 @@ public class PCA implements Runnable
    */
   public void run()
   {
+    details.append("PCA Calculation Mode is "
+            + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + "\n");
     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
+    if (!jvCalcMode)
+    {
+      eigenvector = mt.preMultiply(m); // standard seqspace comparison matrix
+    }
+    else
+    {
+      eigenvector = mt.preMultiply(m2); // jalview variation on seqsmace method
+    }
 
     PrintStream ps = new PrintStream(System.out)
     {
@@ -252,4 +292,11 @@ public class PCA implements Runnable
      * ps.print(","+component(seq, ev)); } ps.println(); }
      */
   }
+
+  boolean jvCalcMode = true;
+
+  public void setJvCalcMode(boolean calcMode)
+  {
+    this.jvCalcMode = calcMode;
+  }
 }