JAL-1503 update version in GPL header

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

diff --git a/src/jalview/analysis/PCA.java b/src/jalview/analysis/PCA.java
index 6af3348..733e7f9 100755 (executable)
--- a/src/jalview/analysis/PCA.java
+++ b/src/jalview/analysis/PCA.java
@@ -1,26 +1,30 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5)
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.1)
+ * Copyright (C) 2014 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.
- * 
+ *  
  * 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/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
  */
 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
@@ -43,31 +47,72 @@ 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)
+  {
+    this(s, nucleotides, null);
+  }
+  public PCA(String[] s, boolean nucleotides, String s_m)
+  {
 
     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++;
     }
 
     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]);
-      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++;
     }
 
@@ -204,12 +249,6 @@ public class PCA implements Runnable
    */
   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)
     {
       public void print(String x)
@@ -223,6 +262,21 @@ public class PCA implements Runnable
       }
     };
 
+    try {
+    details.append("PCA Calculation Mode is "
+            + (jvCalcMode ? "Jalview variant" : "Original SeqSpace") + "\n");
+    Matrix mt = m.transpose();
+
+    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);
 
     symm = eigenvector.copy();
@@ -239,21 +293,30 @@ public class PCA implements Runnable
 
     // 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);
     details.append(" --- Eigenvalues ---\n");
     eigenvector.printD(ps);
     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(); 
-    }*/
+    /*
+     * 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(); }
+     */
+  }
+
+  boolean jvCalcMode = true;
+
+  public void setJvCalcMode(boolean calcMode)
+  {
+    this.jvCalcMode = calcMode;
   }
 }