X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FComparison.java;h=835a1b4c58c20712fbc58eddb22c08e6239a64d8;hb=a23cc416cd520ac6dec6052591575b264f5d25bc;hp=bd8abbdf56abbf9c51842b614bf48fffda21c6e2;hpb=865a855a4ca87eadb3e5ff284ed32ed307d9c34b;p=jalview.git
diff --git a/src/jalview/util/Comparison.java b/src/jalview/util/Comparison.java
index bd8abbd..835a1b4 100644
--- a/src/jalview/util/Comparison.java
+++ b/src/jalview/util/Comparison.java
@@ -1,35 +1,47 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
- * Copyright (C) 2014 The Jalview Authors
+ * 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.
+ * 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 .
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see .
* The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.util;
-import jalview.datamodel.*;
+import java.util.ArrayList;
+import java.util.List;
+
+import jalview.datamodel.SequenceI;
/**
- * DOCUMENT ME!
- *
- * @author $author$
- * @version $Revision$
+ * Assorted methods for analysing or comparing sequences.
*/
public class Comparison
{
- /** DOCUMENT ME!! */
- public static final String GapChars = " .-";
+ private static final int EIGHTY_FIVE = 85;
+
+ private static final int TO_UPPER_CASE = 'a' - 'A';
+
+ private static final char GAP_SPACE = ' ';
+
+ private static final char GAP_DOT = '.';
+
+ private static final char GAP_DASH = '-';
+
+ public static final String GapChars = new String(new char[]
+ { GAP_SPACE, GAP_DOT, GAP_DASH });
/**
* DOCUMENT ME!
@@ -67,12 +79,12 @@ public class Comparison
int ilen = si.length() - 1;
int jlen = sj.length() - 1;
- while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
+ while (Comparison.isGap(si.charAt(start + ilen)))
{
ilen--;
}
- while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
+ while (Comparison.isGap(sj.charAt(start + jlen)))
{
jlen--;
}
@@ -223,47 +235,66 @@ public class Comparison
}
/**
- * DOCUMENT ME!
+ * Answers true if the supplied character is a recognised gap character, else
+ * false. Currently hard-coded to recognise '-', '-' or ' ' (hyphen / dot /
+ * space).
*
* @param c
- * DOCUMENT ME!
*
- * @return DOCUMENT ME!
+ * @return
*/
public static final boolean isGap(char c)
{
- return (c == '-' || c == '.' || c == ' ') ? true : false;
+ return (c == GAP_DASH || c == GAP_DOT || c == GAP_SPACE) ? true : false;
}
+ /**
+ * Answers true if more than 85% of the sequence residues (ignoring gaps) are
+ * A, G, C, T or U, else false. This is just a heuristic guess and may give a
+ * wrong answer (as AGCT are also amino acid codes).
+ *
+ * @param seqs
+ * @return
+ */
public static final boolean isNucleotide(SequenceI[] seqs)
{
- int i = 0, iSize = seqs.length, j, jSize;
- float nt = 0, aa = 0;
- char c;
- while (i < iSize)
+ if (seqs == null)
{
- jSize = seqs[i].getLength();
- for (j = 0; j < jSize; j++)
+ return false;
+ }
+ int ntCount = 0;
+ int aaCount = 0;
+ for (SequenceI seq : seqs)
+ {
+ if (seq == null)
+ {
+ continue;
+ }
+ // TODO could possibly make an informed guess just from the first sequence
+ // to save a lengthy calculation
+ for (char c : seq.getSequence())
{
- c = seqs[i].getCharAt(j);
if ('a' <= c && c <= 'z')
{
- c -= ('a' - 'A');
+ c -= TO_UPPER_CASE;
}
if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
{
- nt++;
+ ntCount++;
}
- else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
+ else if (!Comparison.isGap(c))
{
- aa++;
+ aaCount++;
}
}
- i++;
}
- if ((nt / (nt + aa)) > 0.85f)
+ /*
+ * Check for nucleotide count > 85% of total count (in a form that evades
+ * int / float conversion or divide by zero).
+ */
+ if (ntCount * 100 > EIGHTY_FIVE * (ntCount + aaCount))
{
return true;
}
@@ -273,4 +304,27 @@ public class Comparison
}
}
+
+ /**
+ * Convenience overload of isNucleotide
+ *
+ * @param seqs
+ * @return
+ */
+ public static boolean isNucleotide(SequenceI[][] seqs)
+ {
+ if (seqs == null)
+ {
+ return false;
+ }
+ List flattened = new ArrayList();
+ for (SequenceI[] ss : seqs)
+ {
+ for (SequenceI s : ss) {
+ flattened.add(s);
+ }
+ }
+ final SequenceI[] oneDArray = flattened.toArray(new SequenceI[flattened.size()]);
+ return isNucleotide(oneDArray);
+ }
}