-package jalview.util;\r
-\r
-import jalview.datamodel.*;\r
-\r
-public class Comparison {\r
-\r
- public static float compare(SequenceI ii, SequenceI jj)\r
- {\r
- return Comparison.compare(ii,jj,0,ii.getLength()-1);\r
- }\r
- public static float compare(SequenceI ii, SequenceI jj, int start, int end) {\r
-\r
- String si = ii.getSequence();\r
- String sj = jj.getSequence();\r
-\r
- int ilen = si.length()-1;\r
- int jlen = sj.length()-1;\r
-\r
- while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))\r
- {\r
- ilen--;\r
- }\r
-\r
- while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))\r
- {\r
- jlen--;\r
- }\r
-\r
- int count = 0;\r
- int match = 0;\r
- float pid = -1;\r
-\r
- if (ilen > jlen) {\r
-\r
- for (int j = 0; j < jlen; j++) {\r
- if (si.substring(start + j,start + j+1).equals(sj.substring(start + j,start + j+1))) {\r
- match++;\r
- }\r
- count++;\r
- }\r
- pid = (float)match/(float)ilen * 100;\r
- } else {\r
- for (int j = 0; j < jlen; j++) {\r
- if (si.substring(start + j,start + j+1).equals(sj.substring(start + j,start + j+1))) {\r
- match++;\r
- }\r
- count++;\r
- }\r
- pid = (float)match/(float)jlen * 100;\r
- }\r
-\r
- return pid;\r
- }\r
-\r
- /** */\r
- public static float PID(SequenceI s1 , SequenceI s2)\r
- {\r
- int len;\r
-\r
- if (s1.getSequence().length() > s2.getSequence().length())\r
- len = s1.getSequence().length();\r
- else\r
- len = s2.getSequence().length();\r
-\r
-\r
- int bad = 0;\r
-\r
- for (int i = 0; i < len; i++)\r
- {\r
- char chr1;\r
- char chr2;\r
-\r
- if (i < s1.getSequence().length())\r
- chr1 = s1.getSequence().charAt(i);\r
- else\r
- chr1 = '.';\r
-\r
-\r
- if (i < s2.getSequence().length())\r
- chr2 = s2.getSequence().charAt(i);\r
- else\r
- chr2 = '.';\r
-\r
-\r
- if (!(jalview.util.Comparison.isGap( chr1 )) && !(jalview.util.Comparison.isGap( chr2 )))\r
- {\r
- if (chr1!=chr2)\r
- bad++;\r
- }\r
- }\r
-\r
- return (float)100*(len-bad)/len;\r
- }\r
- public static String GapChars = " .-";\r
- public static boolean isGap(char c)\r
- {\r
- return (c != '.' && c != '-' && c != ' ') ? false : true;\r
- }\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6)
+ * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ *
+ * 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/>.
+ */
+package jalview.util;
+
+import jalview.datamodel.*;
+
+/**
+ * DOCUMENT ME!
+ *
+ * @author $author$
+ * @version $Revision$
+ */
+public class Comparison
+{
+ /** DOCUMENT ME!! */
+ public static final String GapChars = " .-";
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param ii
+ * DOCUMENT ME!
+ * @param jj
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public static final float compare(SequenceI ii, SequenceI jj)
+ {
+ return Comparison.compare(ii, jj, 0, ii.getLength() - 1);
+ }
+
+ /**
+ * this was supposed to be an ungapped pid calculation
+ *
+ * @param ii
+ * SequenceI
+ * @param jj
+ * SequenceI
+ * @param start
+ * int
+ * @param end
+ * int
+ * @return float
+ */
+ public static float compare(SequenceI ii, SequenceI jj, int start, int end)
+ {
+ String si = ii.getSequenceAsString();
+ String sj = jj.getSequenceAsString();
+
+ int ilen = si.length() - 1;
+ int jlen = sj.length() - 1;
+
+ while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
+ {
+ ilen--;
+ }
+
+ while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
+ {
+ jlen--;
+ }
+
+ int count = 0;
+ int match = 0;
+ float pid = -1;
+
+ if (ilen > jlen)
+ {
+ for (int j = 0; j < jlen; j++)
+ {
+ if (si.substring(start + j, start + j + 1).equals(
+ sj.substring(start + j, start + j + 1)))
+ {
+ match++;
+ }
+
+ count++;
+ }
+
+ pid = (float) match / (float) ilen * 100;
+ }
+ else
+ {
+ for (int j = 0; j < jlen; j++)
+ {
+ if (si.substring(start + j, start + j + 1).equals(
+ sj.substring(start + j, start + j + 1)))
+ {
+ match++;
+ }
+
+ count++;
+ }
+
+ pid = (float) match / (float) jlen * 100;
+ }
+
+ return pid;
+ }
+
+ /**
+ * this is a gapped PID calculation
+ *
+ * @param s1
+ * SequenceI
+ * @param s2
+ * SequenceI
+ * @return float
+ */
+ public final static float PID(String seq1, String seq2)
+ {
+ return PID(seq1, seq2, 0, seq1.length());
+ }
+
+ static final int caseShift = 'a' - 'A';
+
+ // Another pid with region specification
+ public final static float PID(String seq1, String seq2, int start, int end)
+ {
+
+ int s1len = seq1.length();
+ int s2len = seq2.length();
+
+ int len = Math.min(s1len, s2len);
+
+ if (end < len)
+ {
+ len = end;
+ }
+
+ if (len < start)
+ {
+ start = len - 1; // we just use a single residue for the difference
+ }
+
+ int bad = 0;
+ char chr1;
+ char chr2;
+
+ for (int i = start; i < len; i++)
+ {
+ chr1 = seq1.charAt(i);
+
+ chr2 = seq2.charAt(i);
+
+ if ('a' <= chr1 && chr1 <= 'z')
+ {
+ // TO UPPERCASE !!!
+ // Faster than toUpperCase
+ chr1 -= caseShift;
+ }
+ if ('a' <= chr2 && chr2 <= 'z')
+ {
+ // TO UPPERCASE !!!
+ // Faster than toUpperCase
+ chr2 -= caseShift;
+ }
+
+ if (chr1 != chr2 && !isGap(chr1) && !isGap(chr2))
+ {
+ bad++;
+ }
+ }
+
+ return ((float) 100 * (len - bad)) / len;
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param c
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public static final boolean isGap(char c)
+ {
+ return (c == '-' || c == '.' || c == ' ') ? true : false;
+ }
+
+ 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)
+ {
+ jSize = seqs[i].getLength();
+ for (j = 0; j < jSize; j++)
+ {
+ c = seqs[i].getCharAt(j);
+ if ('a' <= c && c <= 'z')
+ {
+ c -= ('a' - 'A');
+ }
+
+ if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
+ {
+ nt++;
+ }
+ else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
+ {
+ aa++;
+ }
+ }
+ i++;
+ }
+
+ if ((nt / (nt + aa)) > 0.85f)
+ {
+ return true;
+ }
+ else
+ {
+ return false;
+ }
+
+ }
+}