2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
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
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 import jalview.datamodel.*;
31 public class Comparison
34 public static final String GapChars = " .-";
44 * @return DOCUMENT ME!
46 public static final float compare(SequenceI ii, SequenceI jj)
48 return Comparison.compare(ii, jj, 0, ii.getLength() - 1);
52 * this was supposed to be an ungapped pid calculation
64 public static float compare(SequenceI ii, SequenceI jj, int start, int end)
66 String si = ii.getSequenceAsString();
67 String sj = jj.getSequenceAsString();
69 int ilen = si.length() - 1;
70 int jlen = sj.length() - 1;
72 while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
77 while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
88 for (int j = 0; j < jlen; j++)
90 if (si.substring(start + j, start + j + 1).equals(
91 sj.substring(start + j, start + j + 1)))
99 pid = (float) match / (float) ilen * 100;
103 for (int j = 0; j < jlen; j++)
105 if (si.substring(start + j, start + j + 1).equals(
106 sj.substring(start + j, start + j + 1)))
114 pid = (float) match / (float) jlen * 100;
121 * this is a gapped PID calculation
129 public final static float PID(String seq1, String seq2)
131 return PID(seq1, seq2, 0, seq1.length());
134 static final int caseShift = 'a' - 'A';
136 // Another pid with region specification
137 public final static float PID(String seq1, String seq2, int start, int end)
139 return PID(seq1, seq2, start, end, true, false);
143 * Calculate percent identity for a pair of sequences over a particular range,
144 * with different options for ignoring gaps.
153 * - if true - gaps match any character, if false, do not match
155 * @param ungappedOnly
156 * - if true - only count PID over ungapped columns
159 public final static float PID(String seq1, String seq2, int start,
160 int end, boolean wcGaps, boolean ungappedOnly)
162 int s1len = seq1.length();
163 int s2len = seq2.length();
165 int len = Math.min(s1len, s2len);
174 start = len - 1; // we just use a single residue for the difference
177 int elen = len - start, bad = 0;
181 for (int i = start; i < len; i++)
183 chr1 = seq1.charAt(i);
185 chr2 = seq2.charAt(i);
186 agap = isGap(chr1) || isGap(chr2);
187 if ('a' <= chr1 && chr1 <= 'z')
190 // Faster than toUpperCase
193 if ('a' <= chr2 && chr2 <= 'z')
196 // Faster than toUpperCase
224 return ((float) 100 * (elen - bad)) / elen;
233 * @return DOCUMENT ME!
235 public static final boolean isGap(char c)
237 return (c == '-' || c == '.' || c == ' ') ? true : false;
240 public static final boolean isNucleotide(SequenceI[] seqs)
242 int i = 0, iSize = seqs.length, j, jSize;
243 float nt = 0, aa = 0;
247 jSize = seqs[i].getLength();
248 for (j = 0; j < jSize; j++)
250 c = seqs[i].getCharAt(j);
251 if ('a' <= c && c <= 'z')
256 if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
260 else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
268 if ((nt / (nt + aa)) > 0.85f)