2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
3 * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
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/>.
20 import jalview.datamodel.*;
28 public class Comparison
31 public static final String GapChars = " .-";
41 * @return DOCUMENT ME!
43 public static final float compare(SequenceI ii, SequenceI jj)
45 return Comparison.compare(ii, jj, 0, ii.getLength() - 1);
49 * this was supposed to be an ungapped pid calculation
61 public static float compare(SequenceI ii, SequenceI jj, int start, int end)
63 String si = ii.getSequenceAsString();
64 String sj = jj.getSequenceAsString();
66 int ilen = si.length() - 1;
67 int jlen = sj.length() - 1;
69 while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
74 while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
85 for (int j = 0; j < jlen; j++)
87 if (si.substring(start + j, start + j + 1).equals(
88 sj.substring(start + j, start + j + 1)))
96 pid = (float) match / (float) ilen * 100;
100 for (int j = 0; j < jlen; j++)
102 if (si.substring(start + j, start + j + 1).equals(
103 sj.substring(start + j, start + j + 1)))
111 pid = (float) match / (float) jlen * 100;
118 * this is a gapped PID calculation
126 public final static float PID(String seq1, String seq2)
128 return PID(seq1, seq2, 0, seq1.length());
131 static final int caseShift = 'a' - 'A';
133 // Another pid with region specification
134 public final static float PID(String seq1, String seq2, int start, int end)
136 return PID(seq1, seq2, start, end, true, false);
140 * Calculate percent identity for a pair of sequences over a particular range,
141 * with different options for ignoring gaps.
150 * - if true - gaps match any character, if false, do not match
152 * @param ungappedOnly
153 * - if true - only count PID over ungapped columns
156 public final static float PID(String seq1, String seq2, int start,
157 int end, boolean wcGaps, boolean ungappedOnly)
159 int s1len = seq1.length();
160 int s2len = seq2.length();
162 int len = Math.min(s1len, s2len);
171 start = len - 1; // we just use a single residue for the difference
174 int elen = len - start, bad = 0;
178 for (int i = start; i < len; i++)
180 chr1 = seq1.charAt(i);
182 chr2 = seq2.charAt(i);
183 agap = isGap(chr1) || isGap(chr2);
184 if ('a' <= chr1 && chr1 <= 'z')
187 // Faster than toUpperCase
190 if ('a' <= chr2 && chr2 <= 'z')
193 // Faster than toUpperCase
221 return ((float) 100 * (elen - bad)) / elen;
230 * @return DOCUMENT ME!
232 public static final boolean isGap(char c)
234 return (c == '-' || c == '.' || c == ' ') ? true : false;
237 public static final boolean isNucleotide(SequenceI[] seqs)
239 int i = 0, iSize = seqs.length, j, jSize;
240 float nt = 0, aa = 0;
244 jSize = seqs[i].getLength();
245 for (j = 0; j < jSize; j++)
247 c = seqs[i].getCharAt(j);
248 if ('a' <= c && c <= 'z')
253 if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
257 else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
265 if ((nt / (nt + aa)) > 0.85f)