JAL-1705 refactored/utility methods to detect e.g. 'PhenCode_variation'

[jalview.git] / test / jalview / util / ComparisonTest.java

diff --git a/test/jalview/util/ComparisonTest.java b/test/jalview/util/ComparisonTest.java
index 51b1fa2..9aab66c 100644 (file)
--- a/test/jalview/util/ComparisonTest.java
+++ b/test/jalview/util/ComparisonTest.java
@@ -1,3 +1,23 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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.util;
 
 import static org.testng.AssertJUnit.assertEquals;
@@ -29,7 +49,7 @@ public class ComparisonTest
    * AGCTU. Test is not case-sensitive and ignores gaps.
    */
   @Test(groups = { "Functional" })
-  public void testIsNucleotide()
+  public void testIsNucleotide_sequences()
   {
     SequenceI seq = new Sequence("eightypercent", "agctuAGCPV");
     assertFalse(Comparison.isNucleotide(new SequenceI[] { seq }));
@@ -81,10 +101,10 @@ public class ComparisonTest
   }
 
   /**
-   * Test percentage identity calculation for two sequences.
+   * Test the percentage identity calculation for two sequences
    */
   @Test(groups = { "Functional" })
-  public void testPID_matchGaps()
+  public void testPID_includingGaps()
   {
     String seq1 = "ABCDEF";
     String seq2 = "abcdef";
@@ -94,6 +114,78 @@ public class ComparisonTest
     seq2 = "abcdefghijklmnopqrstuvwxyz";
     assertEquals("identical", 100f, Comparison.PID(seq1, seq2), 0.001f);
 
-    seq2 = "a---bcdef";
+    // 5 identical, 2 gap-gap, 2 gap-residue, 1 mismatch
+    seq1 = "a--b-cdefh";
+    seq2 = "a---bcdefg";
+    int length = seq1.length();
+
+    // match gap-residue, match gap-gap: 9/10 identical
+    assertEquals(90f, Comparison.PID(seq1, seq2, 0, length, true, false),
+            0.001f);
+    // overloaded version of the method signature above:
+    assertEquals(90f, Comparison.PID(seq1, seq2), 0.001f);
+
+    // don't match gap-residue, match gap-gap: 7/10 identical
+    assertEquals(70f, Comparison.PID(seq1, seq2, 0, length, false, false),
+            0.001f);
+  }
+
+  @Test(groups = { "Functional" })
+  public void testIsNucleotide()
+  {
+    assertTrue(Comparison.isNucleotide('a'));
+    assertTrue(Comparison.isNucleotide('A'));
+    assertTrue(Comparison.isNucleotide('c'));
+    assertTrue(Comparison.isNucleotide('C'));
+    assertTrue(Comparison.isNucleotide('g'));
+    assertTrue(Comparison.isNucleotide('G'));
+    assertTrue(Comparison.isNucleotide('t'));
+    assertTrue(Comparison.isNucleotide('T'));
+    assertTrue(Comparison.isNucleotide('u'));
+    assertTrue(Comparison.isNucleotide('U'));
+    assertFalse(Comparison.isNucleotide('-'));
+    assertFalse(Comparison.isNucleotide('P'));
+  }
+
+  /**
+   * Test the percentage identity calculation for two sequences
+   */
+  @Test(groups = { "Functional" })
+  public void testPID_ungappedOnly()
+  {
+    // 5 identical, 2 gap-gap, 2 gap-residue, 1 mismatch
+    String seq1 = "a--b-cdefh";
+    String seq2 = "a---bcdefg";
+    int length = seq1.length();
+
+    /*
+     * As currently coded, 'ungappedOnly' ignores gap-residue but counts
+     * gap-gap. Is this a bug - should gap-gap also be ignored, giving a PID of
+     * 5/6?
+     * 
+     * Note also there is no variant of the calculation that penalises
+     * gap-residue i.e. counts it as a mismatch. This would give a score of 5/8
+     * (if we ignore gap-gap) or 5/10 (if we count gap-gap as a match).
+     */
+    // match gap-residue, match gap-gap: 7/8 identical
+    assertEquals(87.5f, Comparison.PID(seq1, seq2, 0, length, true, true),
+            0.001f);
+
+    // don't match gap-residue with 'ungapped only' - same as above
+    assertEquals(87.5f, Comparison.PID(seq1, seq2, 0, length, false, true),
+            0.001f);
+  }
+
+  @Test(groups = { "Functional" })
+  public void testIsNucleotideSequence()
+  {
+    assertFalse(Comparison.isNucleotideSequence(null, true));
+    assertTrue(Comparison.isNucleotideSequence("", true));
+    assertTrue(Comparison.isNucleotideSequence("aAgGcCtTuU", true));
+    assertTrue(Comparison.isNucleotideSequence("aAgGcCtTuU", false));
+    assertFalse(Comparison.isNucleotideSequence("xAgGcCtTuU", false));
+    assertFalse(Comparison.isNucleotideSequence("aAgGcCtTuUx", false));
+    assertTrue(Comparison.isNucleotideSequence("a A-g.GcCtTuU", true));
+    assertFalse(Comparison.isNucleotideSequence("a A-g.GcCtTuU", false));
   }
 }