X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FComparison.java;h=22e1ab7b39d3070c163f3bcd4dbcfb9b6d1e40f5;hb=b0f76adef2787dd14566525e66a4073278e75d67;hp=d35d84cf53eff789efa86f539b8b82480bf12bf4;hpb=666701168bbf6308964633ade95bfa3a84903ad7;p=jalview.git
diff --git a/src/jalview/util/Comparison.java b/src/jalview/util/Comparison.java
old mode 100755
new mode 100644
index d35d84c..22e1ab7
--- a/src/jalview/util/Comparison.java
+++ b/src/jalview/util/Comparison.java
@@ -1,222 +1,451 @@
-/*
-* Jalview - A Sequence Alignment Editor and Viewer
-* Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
-*
-* This program 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 2
-* of the License, or (at your option) any later version.
-*
-* This program 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 this program; if not, write to the Free Software
-* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
-*/
-package jalview.util;
-
-import jalview.datamodel.*;
-
-
-/**
- * DOCUMENT ME!
- *
- * @author $author$
- * @version $Revision$
- */
-public class Comparison
-{
- /** DOCUMENT ME!! */
- public static String GapChars = " .-";
-
- /**
- * DOCUMENT ME!
- *
- * @param ii DOCUMENT ME!
- * @param jj DOCUMENT ME!
- *
- * @return DOCUMENT ME!
- */
- public static 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.getSequence();
- String sj = jj.getSequence();
-
- 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 boolean isGap(char c)
- {
- return (c == '-' || c == '.' || c == ' ') ? true : false;
- }
-
- public static 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;
-
- }
-}
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * 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 .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.util;
+
+import jalview.datamodel.SequenceI;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * Assorted methods for analysing or comparing sequences.
+ */
+public class Comparison
+{
+ private static final int EIGHTY_FIVE = 85;
+
+ private static final int TO_UPPER_CASE = 'a' - 'A';
+
+ public static final char GAP_SPACE = ' ';
+
+ public static final char GAP_DOT = '.';
+
+ public static final char GAP_DASH = '-';
+
+ public static final String GapChars = new String(new char[] { GAP_SPACE,
+ GAP_DOT, GAP_DASH });
+
+ /**
+ * 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 (Comparison.isGap(si.charAt(start + ilen)))
+ {
+ ilen--;
+ }
+
+ while (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
+ * @deprecated use PIDModel.computePID()
+ */
+ @Deprecated
+ 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
+ /**
+ * @deprecated use PIDModel.computePID()
+ */
+ @Deprecated
+ public final static float PID(String seq1, String seq2, int start, int end)
+ {
+ return PID(seq1, seq2, start, end, true, false);
+ }
+
+ /**
+ * Calculate percent identity for a pair of sequences over a particular range,
+ * with different options for ignoring gaps.
+ *
+ * @param seq1
+ * @param seq2
+ * @param start
+ * - position in seqs
+ * @param end
+ * - position in seqs
+ * @param wcGaps
+ * - if true - gaps match any character, if false, do not match
+ * anything
+ * @param ungappedOnly
+ * - if true - only count PID over ungapped columns
+ * @return
+ * @deprecated use PIDModel.computePID()
+ */
+ @Deprecated
+ public final static float PID(String seq1, String seq2, int start,
+ int end, boolean wcGaps, boolean ungappedOnly)
+ {
+ 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 elen = len - start, bad = 0;
+ char chr1;
+ char chr2;
+ boolean agap;
+ for (int i = start; i < len; i++)
+ {
+ chr1 = seq1.charAt(i);
+
+ chr2 = seq2.charAt(i);
+ agap = isGap(chr1) || isGap(chr2);
+ 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)
+ {
+ if (agap)
+ {
+ if (ungappedOnly)
+ {
+ elen--;
+ }
+ else if (!wcGaps)
+ {
+ bad++;
+ }
+ }
+ else
+ {
+ bad++;
+ }
+ }
+
+ }
+ if (elen < 1)
+ {
+ return 0f;
+ }
+ return ((float) 100 * (elen - bad)) / elen;
+ }
+
+ /**
+ * Answers true if the supplied character is a recognised gap character, else
+ * false. Currently hard-coded to recognise '-', '-' or ' ' (hyphen / dot /
+ * space).
+ *
+ * @param c
+ *
+ * @return
+ */
+ public static final boolean isGap(char c)
+ {
+ return (c == GAP_DASH || c == GAP_DOT || c == GAP_SPACE) ? true : false;
+ }
+
+ /**
+ * Overloaded method signature to test whether a single sequence is nucleotide
+ * (that is, more than 85% CGTA)
+ *
+ * @param seq
+ * @return
+ */
+ public static final boolean isNucleotide(SequenceI seq)
+ {
+ return isNucleotide(new SequenceI[] { seq });
+ }
+
+ /**
+ * Answers true if more than 85% of the sequence residues (ignoring gaps) are
+ * A, G, C, T or U, else false. This is just a heuristic guess and may give a
+ * wrong answer (as AGCT are also amino acid codes).
+ *
+ * @param seqs
+ * @return
+ */
+ public static final boolean isNucleotide(SequenceI[] seqs)
+ {
+ if (seqs == null)
+ {
+ return false;
+ }
+ char[][] letters = new char[seqs.length][];
+ for (int i = 0; i < seqs.length; i++)
+ {
+ if (seqs[i] != null)
+ {
+ char[] sequence = seqs[i].getSequence();
+ if (sequence != null)
+ {
+ letters[i] = sequence;
+ }
+ }
+ }
+
+ return areNucleotide(letters);
+ }
+
+ /**
+ * Answers true if more than 85% of the sequence residues (ignoring gaps) are
+ * A, G, C, T or U, else false. This is just a heuristic guess and may give a
+ * wrong answer (as AGCT are also amino acid codes).
+ *
+ * @param letters
+ * @return
+ */
+ static final boolean areNucleotide(char[][] letters)
+ {
+ int ntCount = 0;
+ int aaCount = 0;
+ for (char[] seq : letters)
+ {
+ if (seq == null)
+ {
+ continue;
+ }
+ // TODO could possibly make an informed guess just from the first sequence
+ // to save a lengthy calculation
+ for (char c : seq)
+ {
+ if (isNucleotide(c))
+ {
+ ntCount++;
+ }
+ else if (!isGap(c))
+ {
+ aaCount++;
+ }
+ }
+ }
+
+ /*
+ * Check for nucleotide count > 85% of total count (in a form that evades
+ * int / float conversion or divide by zero).
+ */
+ if (ntCount * 100 > EIGHTY_FIVE * (ntCount + aaCount))
+ {
+ return true;
+ }
+ else
+ {
+ return false;
+ }
+
+ }
+
+ /**
+ * Answers true if the character is one of aAcCgGtTuU
+ *
+ * @param c
+ * @return
+ */
+ public static boolean isNucleotide(char c)
+ {
+ if ('a' <= c && c <= 'z')
+ {
+ c -= TO_UPPER_CASE;
+ }
+
+ switch (c)
+ {
+ case 'A':
+ case 'C':
+ case 'G':
+ case 'T':
+ case 'U':
+ return true;
+ }
+ return false;
+ }
+
+ /**
+ * Answers true if every character in the string is one of aAcCgGtTuU, or
+ * (optionally) a gap character (dot, dash, space), else false
+ *
+ * @param s
+ * @param allowGaps
+ * @return
+ */
+ public static boolean isNucleotideSequence(String s, boolean allowGaps)
+ {
+ if (s == null)
+ {
+ return false;
+ }
+ for (int i = 0; i < s.length(); i++)
+ {
+ char c = s.charAt(i);
+ if (!isNucleotide(c))
+ {
+ if (!allowGaps || !isGap(c))
+ {
+ return false;
+ }
+ }
+ }
+ return true;
+ }
+
+ /**
+ * Convenience overload of isNucleotide
+ *
+ * @param seqs
+ * @return
+ */
+ public static boolean isNucleotide(SequenceI[][] seqs)
+ {
+ if (seqs == null)
+ {
+ return false;
+ }
+ List flattened = new ArrayList();
+ for (SequenceI[] ss : seqs)
+ {
+ for (SequenceI s : ss)
+ {
+ flattened.add(s);
+ }
+ }
+ final SequenceI[] oneDArray = flattened.toArray(new SequenceI[flattened
+ .size()]);
+ return isNucleotide(oneDArray);
+ }
+
+ /**
+ * Compares two residues either case sensitively or case insensitively
+ * depending on the caseSensitive flag
+ *
+ * @param c1
+ * first char
+ * @param c2
+ * second char to compare with
+ * @param caseSensitive
+ * if true comparison will be case sensitive otherwise its not
+ * @return
+ */
+ public static boolean isSameResidue(char c1, char c2,
+ boolean caseSensitive)
+ {
+ if (caseSensitive)
+ {
+ return (c1 == c2);
+ }
+ else
+ {
+ return Character.toUpperCase(c1) == Character.toUpperCase(c2);
+ }
+ }
+}