X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FAlignSeq.java;h=573c545cd56885a2dfdae4bbc2bf4340f573d85c;hb=865a855a4ca87eadb3e5ff284ed32ed307d9c34b;hp=bf66f30e02b2d59781cb6df06fdb722c155cd51e;hpb=34f1207ac30761e3aac6ede40075446f7fec9900;p=jalview.git

diff --git a/src/jalview/analysis/AlignSeq.java b/src/jalview/analysis/AlignSeq.java
index bf66f30..573c545 100755
--- a/src/jalview/analysis/AlignSeq.java
+++ b/src/jalview/analysis/AlignSeq.java
@@ -1,19 +1,20 @@
 /*
- * 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 2.8.0b1)
+ * 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;
 
@@ -143,7 +144,7 @@ public class AlignSeq
   public AlignSeq(SequenceI s1, String string1, SequenceI s2,
           String string2, String type)
   {
-    SeqInit(s1, string1, s2, string2, type);
+    SeqInit(s1, string1.toUpperCase(), s2, string2.toUpperCase(), type);
   }
 
   /**
@@ -382,13 +383,13 @@ public class AlignSeq
     {
       intToStr = pep;
       charToInt = ResidueProperties.aaIndex;
-      defInt = 23;
+      defInt = ResidueProperties.maxProteinIndex;
     }
     else if (type.equals(AlignSeq.DNA))
     {
       intToStr = dna;
       charToInt = ResidueProperties.nucleotideIndex;
-      defInt = 4;
+      defInt = ResidueProperties.maxNucleotideIndex;
     }
     else
     {
@@ -501,22 +502,23 @@ public class AlignSeq
     // TODO: Use original sequence characters rather than re-translated
     // characters in output
     // Find the biggest id length for formatting purposes
-    String s1id=s1.getName(),s2id=s2.getName();
+    String s1id = s1.getName(), s2id = s2.getName();
     int maxid = s1.getName().length();
     if (s2.getName().length() > maxid)
     {
       maxid = s2.getName().length();
     }
-    if (maxid>30) {
+    if (maxid > 30)
+    {
       maxid = 30;
       // JAL-527 - truncate the sequence ids
-      if (s1.getName().length()>maxid)
+      if (s1.getName().length() > maxid)
       {
-        s1id = s1.getName().substring(0,30);
+        s1id = s1.getName().substring(0, 30);
       }
-      if (s2.getName().length()>maxid)
+      if (s2.getName().length() > maxid)
       {
-        s2id = s2.getName().substring(0,30);
+        s2id = s2.getName().substring(0, 30);
       }
     }
     int len = 72 - maxid - 1;
@@ -537,8 +539,7 @@ public class AlignSeq
     for (int j = 0; j < nochunks; j++)
     {
       // Print the first aligned sequence
-      output.append(new Format("%" + (maxid) + "s").form(s1id)
-              + " ");
+      output.append(new Format("%" + (maxid) + "s").form(s1id) + " ");
 
       for (int i = 0; i < len; i++)
       {
@@ -918,4 +919,93 @@ public class AlignSeq
       }
     }
   }
+
+  /**
+   * compute the PID vector used by the redundancy filter.
+   * 
+   * @param originalSequences
+   *          - sequences in alignment that are to filtered
+   * @param omitHidden
+   *          - null or strings to be analysed (typically, visible portion of
+   *          each sequence in alignment)
+   * @param start
+   *          - first column in window for calculation
+   * @param end
+   *          - last column in window for calculation
+   * @param ungapped
+   *          - if true then use ungapped sequence to compute PID
+   * @return vector containing maximum PID for i-th sequence and any sequences
+   *         longer than that seuqence
+   */
+  public static float[] computeRedundancyMatrix(
+          SequenceI[] originalSequences, String[] omitHidden, int start,
+          int end, boolean ungapped)
+  {
+    int height = originalSequences.length;
+    float[] redundancy = new float[height];
+    int[] lngth = new int[height];
+    for (int i = 0; i < height; i++)
+    {
+      redundancy[i] = 0f;
+      lngth[i] = -1;
+    }
+
+    // long start = System.currentTimeMillis();
+
+    float pid;
+    String seqi, seqj;
+    for (int i = 0; i < height; i++)
+    {
+
+      for (int j = 0; j < i; j++)
+      {
+        if (i == j)
+        {
+          continue;
+        }
+
+        if (omitHidden == null)
+        {
+          seqi = originalSequences[i].getSequenceAsString(start, end);
+          seqj = originalSequences[j].getSequenceAsString(start, end);
+        }
+        else
+        {
+          seqi = omitHidden[i];
+          seqj = omitHidden[j];
+        }
+        if (lngth[i] == -1)
+        {
+          String ug = AlignSeq.extractGaps(Comparison.GapChars, seqi);
+          lngth[i] = ug.length();
+          if (ungapped)
+          {
+            seqi = ug;
+          }
+        }
+        if (lngth[j] == -1)
+        {
+          String ug = AlignSeq.extractGaps(Comparison.GapChars, seqj);
+          lngth[j] = ug.length();
+          if (ungapped)
+          {
+            seqj = ug;
+          }
+        }
+        pid = Comparison.PID(seqi, seqj);
+
+        // use real sequence length rather than string length
+        if (lngth[j] < lngth[i])
+        {
+          redundancy[j] = Math.max(pid, redundancy[j]);
+        }
+        else
+        {
+          redundancy[i] = Math.max(pid, redundancy[i]);
+        }
+
+      }
+    }
+    return redundancy;
+  }
 }