2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
3 * Copyright (C) 2014 The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
17 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 import jalview.datamodel.*;
29 public class Comparison
32 public static final String GapChars = " .-";
42 * @return DOCUMENT ME!
44 public static final float compare(SequenceI ii, SequenceI jj)
46 return Comparison.compare(ii, jj, 0, ii.getLength() - 1);
50 * this was supposed to be an ungapped pid calculation
62 public static float compare(SequenceI ii, SequenceI jj, int start, int end)
64 String si = ii.getSequenceAsString();
65 String sj = jj.getSequenceAsString();
67 int ilen = si.length() - 1;
68 int jlen = sj.length() - 1;
70 while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
75 while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
86 for (int j = 0; j < jlen; j++)
88 if (si.substring(start + j, start + j + 1).equals(
89 sj.substring(start + j, start + j + 1)))
97 pid = (float) match / (float) ilen * 100;
101 for (int j = 0; j < jlen; j++)
103 if (si.substring(start + j, start + j + 1).equals(
104 sj.substring(start + j, start + j + 1)))
112 pid = (float) match / (float) jlen * 100;
119 * this is a gapped PID calculation
127 public final static float PID(String seq1, String seq2)
129 return PID(seq1, seq2, 0, seq1.length());
132 static final int caseShift = 'a' - 'A';
134 // Another pid with region specification
135 public final static float PID(String seq1, String seq2, int start, int end)
137 return PID(seq1, seq2, start, end, true, false);
141 * Calculate percent identity for a pair of sequences over a particular range,
142 * with different options for ignoring gaps.
151 * - if true - gaps match any character, if false, do not match
153 * @param ungappedOnly
154 * - if true - only count PID over ungapped columns
157 public final static float PID(String seq1, String seq2, int start,
158 int end, boolean wcGaps, boolean ungappedOnly)
160 int s1len = seq1.length();
161 int s2len = seq2.length();
163 int len = Math.min(s1len, s2len);
172 start = len - 1; // we just use a single residue for the difference
175 int elen = len - start, bad = 0;
179 for (int i = start; i < len; i++)
181 chr1 = seq1.charAt(i);
183 chr2 = seq2.charAt(i);
184 agap = isGap(chr1) || isGap(chr2);
185 if ('a' <= chr1 && chr1 <= 'z')
188 // Faster than toUpperCase
191 if ('a' <= chr2 && chr2 <= 'z')
194 // Faster than toUpperCase
222 return ((float) 100 * (elen - bad)) / elen;
231 * @return DOCUMENT ME!
233 public static final boolean isGap(char c)
235 return (c == '-' || c == '.' || c == ' ') ? true : false;
238 public static final boolean isNucleotide(SequenceI[] seqs)
240 int i = 0, iSize = seqs.length, j, jSize;
241 float nt = 0, aa = 0;
245 jSize = seqs[i].getLength();
246 for (j = 0; j < jSize; j++)
248 c = seqs[i].getCharAt(j);
249 if ('a' <= c && c <= 'z')
254 if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
258 else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
266 if ((nt / (nt + aa)) > 0.85f)