2 * Jalview - A Sequence Alignment Editor and Viewer
\r
3 * Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
\r
5 * This program is free software; you can redistribute it and/or
\r
6 * modify it under the terms of the GNU General Public License
\r
7 * as published by the Free Software Foundation; either version 2
\r
8 * of the License, or (at your option) any later version.
\r
10 * This program is distributed in the hope that it will be useful,
\r
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
\r
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
\r
13 * GNU General Public License for more details.
\r
15 * You should have received a copy of the GNU General Public License
\r
16 * along with this program; if not, write to the Free Software
\r
17 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
\r
19 package jalview.analysis;
\r
21 import jalview.datamodel.*;
\r
27 * Takes in a vector of sequences and column start and column end
\r
28 * and returns a vector of size (end-start+1). Each element of the
\r
29 * vector contains a hashtable with the keys being residues and
\r
30 * the values being the count of each residue in that column.
\r
31 * This class is used extensively in calculating alignment colourschemes
\r
32 * that depend on the amount of conservation in each alignment column.
\r
34 * @version $Revision$
\r
36 public class AAFrequency
\r
38 /** Takes in a !!ARRAY!! of sequences and column start and column end
\r
39 * and fills given Vector of size (end-start+1). Each element of the
\r
40 * vector contains a hashtable with the keys being residues and
\r
41 * the values being the count of each residue in that column.
\r
42 * This class is used extensively in calculating alignment colourschemes
\r
43 * that depend on the amount of conservation in each alignment column. */
\r
45 public static final Hashtable [] calculate(Vector sequences, int start, int end)
\r
47 SequenceI [] seqs = new SequenceI[sequences.size()];
\r
49 for(int i=0; i<sequences.size(); i++)
\r
51 seqs[i] = (SequenceI) sequences.elementAt(i);
\r
52 if(seqs[i].getLength()>width)
\r
53 width = seqs[i].getLength();
\r
56 Hashtable [] reply = new Hashtable[width];
\r
58 calculate(seqs, start, end, reply);
\r
63 public static final void calculate(SequenceI[] sequences,
\r
65 Hashtable [] result)
\r
67 Hashtable residueHash;
\r
68 int maxCount, nongap, i, j, v, jSize = sequences.length;
\r
73 int[] values = new int[132];
\r
75 for (i = start; i < end; i++)
\r
77 residueHash = new Hashtable();
\r
81 values = new int[132];
\r
83 for (j = 0; j < jSize; j++)
\r
85 if (sequences[j].getLength() > i)
\r
87 c = sequences[j].getCharAt(i);
\r
89 if ('a' <= c && c <= 'z')
\r
94 if (jalview.util.Comparison.isGap(c))
\r
96 c = '-'; // we always use this for gaps in the property vectors
\r
112 for (v = 'A'; v < 'Z'; v++)
\r
114 if (values[v] == 0 || values[v] < maxCount)
\r
117 if (values[v] > maxCount)
\r
119 maxResidue = String.valueOf( (char) v);
\r
121 else if (values[v] == maxCount)
\r
123 maxResidue += String.valueOf( (char) v);
\r
125 maxCount = values[v];
\r
129 residueHash.put("maxCount", new Integer(maxCount));
\r
130 residueHash.put("maxResidue", maxResidue);
\r
132 percentage = ( (float) maxCount * 100) / (float) jSize;
\r
133 residueHash.put("pid_gaps", new Float(percentage));
\r
135 percentage = ( (float) maxCount * 100) / (float) nongap;
\r
136 residueHash.put("pid_nogaps", new Float(percentage));
\r
137 result[i] = residueHash;
\r