-/*\r
-* Jalview - A Sequence Alignment Editor and Viewer\r
-* Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
-*\r
-* This program is free software; you can redistribute it and/or\r
-* modify it under the terms of the GNU General Public License\r
-* as published by the Free Software Foundation; either version 2\r
-* of the License, or (at your option) any later version.\r
-*\r
-* This program is distributed in the hope that it will be useful,\r
-* but WITHOUT ANY WARRANTY; without even the implied warranty of\r
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
-* GNU General Public License for more details.\r
-*\r
-* You should have received a copy of the GNU General Public License\r
-* along with this program; if not, write to the Free Software\r
-* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
-*/\r
-package jalview.util;\r
-\r
-import jalview.datamodel.*;\r
-\r
-\r
-/**\r
- * DOCUMENT ME!\r
- *\r
- * @author $author$\r
- * @version $Revision$\r
- */\r
-public class Comparison\r
-{\r
- /** DOCUMENT ME!! */\r
- public static String GapChars = " .-";\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @param ii DOCUMENT ME!\r
- * @param jj DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public static float compare(SequenceI ii, SequenceI jj)\r
- {\r
- return Comparison.compare(ii, jj, 0, ii.getLength() - 1);\r
- }\r
-\r
- /**\r
- * this was supposed to be an ungapped pid calculation\r
- * @param ii SequenceI\r
- * @param jj SequenceI\r
- * @param start int\r
- * @param end int\r
- * @return float\r
- */\r
- public static float compare(SequenceI ii, SequenceI jj, int start, int end)\r
- {\r
- String si = ii.getSequence();\r
- String sj = jj.getSequence();\r
-\r
- int ilen = si.length() - 1;\r
- int jlen = sj.length() - 1;\r
-\r
- while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))\r
- {\r
- ilen--;\r
- }\r
-\r
- while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))\r
- {\r
- jlen--;\r
- }\r
-\r
- int count = 0;\r
- int match = 0;\r
- float pid = -1;\r
-\r
- if (ilen > jlen)\r
- {\r
- for (int j = 0; j < jlen; j++)\r
- {\r
- if (si.substring(start + j, start + j + 1).equals(sj.substring(start +\r
- j, start + j + 1)))\r
- {\r
- match++;\r
- }\r
-\r
- count++;\r
- }\r
-\r
- pid = (float) match / (float) ilen * 100;\r
- }\r
- else\r
- {\r
- for (int j = 0; j < jlen; j++)\r
- {\r
- if (si.substring(start + j, start + j + 1).equals(sj.substring(start +\r
- j, start + j + 1)))\r
- {\r
- match++;\r
- }\r
-\r
- count++;\r
- }\r
-\r
- pid = (float) match / (float) jlen * 100;\r
- }\r
-\r
- return pid;\r
- }\r
-\r
- /**\r
- * this is a gapped PID calculation\r
- *\r
- * @param s1 SequenceI\r
- * @param s2 SequenceI\r
- * @return float\r
- */\r
- public static float PID(SequenceI s1, SequenceI s2)\r
- {\r
- int len;\r
-\r
- if (s1.getSequence().length() > s2.getSequence().length())\r
- {\r
- len = s1.getSequence().length();\r
- }\r
- else\r
- {\r
- len = s2.getSequence().length();\r
- }\r
-\r
- int bad = 0;\r
-\r
- for (int i = 0; i < len; i++)\r
- {\r
- char chr1;\r
- char chr2;\r
-\r
- if (i < s1.getSequence().length())\r
- {\r
- chr1 = Character.toUpperCase(s1.getSequence().charAt(i));\r
- }\r
- else\r
- {\r
- chr1 = '.';\r
- }\r
-\r
- if (i < s2.getSequence().length())\r
- {\r
- chr2 = Character.toUpperCase(s2.getSequence().charAt(i));\r
- }\r
- else\r
- {\r
- chr2 = '.';\r
- }\r
-\r
- if (!(jalview.util.Comparison.isGap(chr1)) &&\r
- !(jalview.util.Comparison.isGap(chr2)))\r
- {\r
- if (chr1 != chr2)\r
- {\r
- bad++;\r
- }\r
- }\r
- }\r
-\r
- return ((float) 100 * (len - bad)) / len;\r
- }\r
-\r
- // Another pid with region specification\r
- public static float PID(SequenceI s1, SequenceI s2, int start, int end)\r
- {\r
- int len;\r
-\r
- if (s1.getSequence().length() > s2.getSequence().length())\r
- {\r
- len = s1.getSequence().length();\r
- }\r
- else\r
- {\r
- len = s2.getSequence().length();\r
- }\r
-\r
- if (end < len)\r
- {\r
- len = end;\r
- }\r
-\r
- if (len < start)\r
- {\r
- start = len - 1; // we just use a single residue for the difference\r
- }\r
-\r
- int bad = 0;\r
-\r
- for (int i = start; i < len; i++)\r
- {\r
- char chr1;\r
- char chr2;\r
-\r
- if (i < s1.getSequence().length())\r
- {\r
- chr1 = Character.toUpperCase(s1.getSequence().charAt(i));\r
- }\r
- else\r
- {\r
- chr1 = '.';\r
- }\r
-\r
- if (i < s2.getSequence().length())\r
- {\r
- chr2 = Character.toUpperCase(s2.getSequence().charAt(i));\r
- }\r
- else\r
- {\r
- chr2 = '.';\r
- }\r
-\r
- if (!(jalview.util.Comparison.isGap(chr1)) &&\r
- !(jalview.util.Comparison.isGap(chr2)))\r
- {\r
- if (chr1 != chr2)\r
- {\r
- bad++;\r
- }\r
- }\r
- }\r
-\r
- return ((float) 100 * (len - bad)) / len;\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @param c DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public static boolean isGap(char c)\r
- {\r
- return ( c=='-' || c=='.' || c==' ' ) ? true : false;\r
- }\r
-}\r
+/*
+ * 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 <http://www.gnu.org/licenses/>.
+ * 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';
+
+ private static final char GAP_SPACE = ' ';
+
+ private static final char GAP_DOT = '.';
+
+ private 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
+ */
+ 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)
+ {
+ 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
+ */
+ 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;
+ }
+
+ /**
+ * 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<SequenceI> flattened = new ArrayList<SequenceI>();
+ for (SequenceI[] ss : seqs)
+ {
+ for (SequenceI s : ss)
+ {
+ flattened.add(s);
+ }
+ }
+ final SequenceI[] oneDArray = flattened.toArray(new SequenceI[flattened
+ .size()]);
+ return isNucleotide(oneDArray);
+ }
+}