X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FComparison.java;h=32e049d08b05c6faaa13c8aed17fdbc3659f9b96;hb=153dd62dc91da13ae732600e6ea55ddbe15eab39;hp=72fb1d1a7ca7776fcbb9f4b97cc8268f7f88707a;hpb=1ecf6419aba86993b3c223bf5ec0fa79427baf85;p=jalview.git diff --git a/src/jalview/util/Comparison.java b/src/jalview/util/Comparison.java index 72fb1d1..32e049d 100755 --- a/src/jalview/util/Comparison.java +++ b/src/jalview/util/Comparison.java @@ -1,114 +1,235 @@ -package jalview.util; - -import jalview.datamodel.*; - -public class Comparison { - - public static float compare(SequenceI ii, SequenceI jj) - { - return Comparison.compare(ii,jj,0,ii.getLength()-1); - } - public static float compare(SequenceI ii, SequenceI jj, int start, int end) { - - String si = ii.getSequence(); - String sj = jj.getSequence(); - - int ilen = end-start+1; - int jlen = end-start+1; - - if ( si.substring(start + ilen).equals("-") || - si.substring(start + ilen).equals(".") || - si.substring(start + ilen).equals(" ")) { - - ilen--; - - while (si.substring(start + ilen,start + ilen+1).equals("-") || - si.substring(start + ilen,start + ilen+1).equals(".") || - si.substring(start + ilen,start + ilen+1).equals(" ")) { - ilen--; - } - } - - if ( sj.substring(start + jlen).equals("-") || - sj.substring(start + jlen).equals(".") || - sj.substring(start + jlen).equals(" ")) { - jlen--; - - while (sj.substring(start + jlen,start + jlen+1).equals("-") || - sj.substring(start + jlen,start + jlen+1).equals(".") || - sj.substring(start + jlen,start + jlen+1).equals(" ")) { - 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; - } - - /** */ - public static float PID(Sequence s1 , Sequence s2) { - int res = 0; - int len; - - if (s1.getSequence().length() > s2.getSequence().length()) { - len = s1.getSequence().length(); - } else { - len = s2.getSequence().length(); - } - - int bad = 0; - - for (int i = 0; i < len; i++) { - String str1 = ""; - String str2 = ""; - - if (i < s1.getSequence().length()) { - str1 = s1.getSequence().substring(i,i+1); - } else { - str1 = "."; - } - - if (i < s2.getSequence().length()) { - str2 = s2.getSequence().substring(i,i+1); - } else { - str2 = "."; - } - - if (!(str1.equals(".") || - str1.equals("-") || - str1.equals(" ")) && - !(str2.equals(".") || - str2.equals("-") || - str2.equals(" "))) { - - if (!str1.equals(str2)) { - bad++; - } - } - } - - return (float)100*(len-bad)/len; - } -} +/* + * 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 . + */ +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; + } + + } +}