2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
3 * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, 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/>.
18 package jalview.schemes;
24 public class ResidueProperties
26 public static Hashtable scoreMatrices = new Hashtable();
28 // Stores residue codes/names and colours and other things
29 public static final int[] aaIndex; // aaHash version 2.1.1 and below
31 public static final int[] nucleotideIndex;
33 public static final int[] purinepyrimidineIndex;
35 public static final Hashtable aa3Hash = new Hashtable();
37 public static final Hashtable aa2Triplet = new Hashtable();
39 public static final Hashtable nucleotideName = new Hashtable();
43 aaIndex = new int[255];
44 for (int i = 0; i < 255; i++)
96 aaIndex['u'] = 22; // TODO: selenocystine triplet and codons needed. also
97 // extend subt. matrices
101 * maximum (gap) index for matrices involving protein alphabet
103 public final static int maxProteinIndex=23;
105 * maximum (gap) index for matrices involving nucleotide alphabet
107 public final static int maxNucleotideIndex=10;
111 nucleotideIndex = new int[255];
112 for (int i = 0; i < 255; i++)
114 nucleotideIndex[i] = 10; // non-nucleotide symbols are all non-gap gaps.
117 nucleotideIndex['A'] = 0;
118 nucleotideIndex['a'] = 0;
119 nucleotideIndex['C'] = 1;
120 nucleotideIndex['c'] = 1;
121 nucleotideIndex['G'] = 2;
122 nucleotideIndex['g'] = 2;
123 nucleotideIndex['T'] = 3;
124 nucleotideIndex['t'] = 3;
125 nucleotideIndex['U'] = 4;
126 nucleotideIndex['u'] = 4;
127 nucleotideIndex['I'] = 5;
128 nucleotideIndex['i'] = 5;
129 nucleotideIndex['X'] = 6;
130 nucleotideIndex['x'] = 6;
131 nucleotideIndex['R'] = 7;
132 nucleotideIndex['r'] = 7;
133 nucleotideIndex['Y'] = 8;
134 nucleotideIndex['y'] = 8;
135 nucleotideIndex['N'] = 9;
136 nucleotideIndex['n'] = 9;
138 nucleotideName.put("A", "Adenine");
139 nucleotideName.put("a", "Adenine");
140 nucleotideName.put("G", "Guanine");
141 nucleotideName.put("g", "Guanine");
142 nucleotideName.put("C", "Cytosine");
143 nucleotideName.put("c", "Cytosine");
144 nucleotideName.put("T", "Thymine");
145 nucleotideName.put("t", "Thymine");
146 nucleotideName.put("U", "Uracil");
147 nucleotideName.put("u", "Uracil");
148 nucleotideName.put("I", "Inosine");
149 nucleotideName.put("i", "Inosine");
150 nucleotideName.put("X", "Xanthine");
151 nucleotideName.put("x", "Xanthine");
152 nucleotideName.put("R", "Unknown Purine");
153 nucleotideName.put("r", "Unknown Purine");
154 nucleotideName.put("Y", "Unknown Pyrimidine");
155 nucleotideName.put("y", "Unknown Pyrimidine");
156 nucleotideName.put("N", "Unknown");
157 nucleotideName.put("n", "Unknown");
158 nucleotideName.put("W", "Weak nucleotide (A or T)");
159 nucleotideName.put("w", "Weak nucleotide (A or T)");
160 nucleotideName.put("S", "Strong nucleotide (G or C)");
161 nucleotideName.put("s", "Strong nucleotide (G or C)");
162 nucleotideName.put("M", "Amino (A or C)");
163 nucleotideName.put("m", "Amino (A or C)");
164 nucleotideName.put("K", "Keto (G or T)");
165 nucleotideName.put("k", "Keto (G or T)");
166 nucleotideName.put("B", "Not A (G or C or T)");
167 nucleotideName.put("b", "Not A (G or C or T)");
168 nucleotideName.put("H", "Not G (A or C or T)");
169 nucleotideName.put("h", "Not G (A or C or T)");
170 nucleotideName.put("D", "Not C (A or G or T)");
171 nucleotideName.put("d", "Not C (A or G or T)");
172 nucleotideName.put("V", "Not T (A or G or C");
173 nucleotideName.put("v", "Not T (A or G or C");
179 purinepyrimidineIndex = new int[255];
180 for (int i = 0; i < 255; i++)
182 purinepyrimidineIndex[i] = 3; // non-nucleotide symbols are all non-gap
186 purinepyrimidineIndex['A'] = 0;
187 purinepyrimidineIndex['a'] = 0;
188 purinepyrimidineIndex['C'] = 1;
189 purinepyrimidineIndex['c'] = 1;
190 purinepyrimidineIndex['G'] = 0;
191 purinepyrimidineIndex['g'] = 0;
192 purinepyrimidineIndex['T'] = 1;
193 purinepyrimidineIndex['t'] = 1;
194 purinepyrimidineIndex['U'] = 1;
195 purinepyrimidineIndex['u'] = 1;
196 purinepyrimidineIndex['I'] = 2;
197 purinepyrimidineIndex['i'] = 2;
198 purinepyrimidineIndex['X'] = 2;
199 purinepyrimidineIndex['x'] = 2;
200 purinepyrimidineIndex['R'] = 0;
201 purinepyrimidineIndex['r'] = 0;
202 purinepyrimidineIndex['Y'] = 1;
203 purinepyrimidineIndex['y'] = 1;
204 purinepyrimidineIndex['N'] = 2;
205 purinepyrimidineIndex['n'] = 2;
210 aa3Hash.put("ALA", new Integer(0));
211 aa3Hash.put("ARG", new Integer(1));
212 aa3Hash.put("ASN", new Integer(2));
213 aa3Hash.put("ASP", new Integer(3)); // D
214 aa3Hash.put("CYS", new Integer(4));
215 aa3Hash.put("GLN", new Integer(5)); // Q
216 aa3Hash.put("GLU", new Integer(6)); // E
217 aa3Hash.put("GLY", new Integer(7));
218 aa3Hash.put("HIS", new Integer(8));
219 aa3Hash.put("ILE", new Integer(9));
220 aa3Hash.put("LEU", new Integer(10));
221 aa3Hash.put("LYS", new Integer(11));
222 aa3Hash.put("MET", new Integer(12));
223 aa3Hash.put("PHE", new Integer(13));
224 aa3Hash.put("PRO", new Integer(14));
225 aa3Hash.put("SER", new Integer(15));
226 aa3Hash.put("THR", new Integer(16));
227 aa3Hash.put("TRP", new Integer(17));
228 aa3Hash.put("TYR", new Integer(18));
229 aa3Hash.put("VAL", new Integer(19));
230 // IUB Nomenclature for ambiguous peptides
231 aa3Hash.put("ASX", new Integer(20)); // "B";
232 aa3Hash.put("GLX", new Integer(21)); // X
233 aa3Hash.put("XAA", new Integer(22)); // X unknown
234 aa3Hash.put("-", new Integer(23));
235 aa3Hash.put("*", new Integer(23));
236 aa3Hash.put(".", new Integer(23));
237 aa3Hash.put(" ", new Integer(23));
238 aa3Hash.put("Gap", new Integer(23));
243 aa2Triplet.put("A", "ALA");
244 aa2Triplet.put("a", "ALA");
245 aa2Triplet.put("R", "ARG");
246 aa2Triplet.put("r", "ARG");
247 aa2Triplet.put("N", "ASN");
248 aa2Triplet.put("n", "ASN");
249 aa2Triplet.put("D", "ASP");
250 aa2Triplet.put("d", "ASP");
251 aa2Triplet.put("C", "CYS");
252 aa2Triplet.put("c", "CYS");
253 aa2Triplet.put("Q", "GLN");
254 aa2Triplet.put("q", "GLN");
255 aa2Triplet.put("E", "GLU");
256 aa2Triplet.put("e", "GLU");
257 aa2Triplet.put("G", "GLY");
258 aa2Triplet.put("g", "GLY");
259 aa2Triplet.put("H", "HIS");
260 aa2Triplet.put("h", "HIS");
261 aa2Triplet.put("I", "ILE");
262 aa2Triplet.put("i", "ILE");
263 aa2Triplet.put("L", "LEU");
264 aa2Triplet.put("l", "LEU");
265 aa2Triplet.put("K", "LYS");
266 aa2Triplet.put("k", "LYS");
267 aa2Triplet.put("M", "MET");
268 aa2Triplet.put("m", "MET");
269 aa2Triplet.put("F", "PHE");
270 aa2Triplet.put("f", "PHE");
271 aa2Triplet.put("P", "PRO");
272 aa2Triplet.put("p", "PRO");
273 aa2Triplet.put("S", "SER");
274 aa2Triplet.put("s", "SER");
275 aa2Triplet.put("T", "THR");
276 aa2Triplet.put("t", "THR");
277 aa2Triplet.put("W", "TRP");
278 aa2Triplet.put("w", "TRP");
279 aa2Triplet.put("Y", "TYR");
280 aa2Triplet.put("y", "TYR");
281 aa2Triplet.put("V", "VAL");
282 aa2Triplet.put("v", "VAL");
285 public static final String[] aa =
286 { "A", "R", "N", "D", "C", "Q", "E", "G", "H", "I", "L", "K", "M", "F",
287 "P", "S", "T", "W", "Y", "V", "B", "Z", "X", "_", "*", ".", " " };
289 public static final Color midBlue = new Color(100, 100, 255);
291 public static final Vector scaleColours = new Vector();
295 scaleColours.addElement(new Color(114, 0, 147));
296 scaleColours.addElement(new Color(156, 0, 98));
297 scaleColours.addElement(new Color(190, 0, 0));
298 scaleColours.addElement(Color.red);
299 scaleColours.addElement(new Color(255, 125, 0));
300 scaleColours.addElement(Color.orange);
301 scaleColours.addElement(new Color(255, 194, 85));
302 scaleColours.addElement(Color.yellow);
303 scaleColours.addElement(new Color(255, 255, 181));
304 scaleColours.addElement(Color.white);
307 public static final Color[] taylor =
308 { new Color(204, 255, 0), // A Greenish-yellowy-yellow
309 new Color(0, 0, 255), // R Blueish-bluey-blue
310 new Color(204, 0, 255), // N Blueish-reddy-blue
311 new Color(255, 0, 0), // D Reddish-reddy-red
312 new Color(255, 255, 0), // C Yellowish-yellowy-yellow
313 new Color(255, 0, 204), // Q Reddish-bluey-red
314 new Color(255, 0, 102), // E Blueish-reddy-red
315 new Color(255, 153, 0), // G Yellowy-reddy-yellow
316 new Color(0, 102, 255), // H Greenish-bluey-blue
317 new Color(102, 255, 0), // I Greenish-yellowy-green
318 new Color(51, 255, 0), // L Yellowish-greeny-green
319 new Color(102, 0, 255), // K Reddish-bluey-blue
320 new Color(0, 255, 0), // M Greenish-greeny-green
321 new Color(0, 255, 102), // F Blueish-greeny-green
322 new Color(255, 204, 0), // P Reddish-yellowy-yellow
323 new Color(255, 51, 0), // S Yellowish-reddy-red
324 new Color(255, 102, 0), // T Reddish-yellowy-red
325 new Color(0, 204, 255), // W Blueish-greeny-green
326 new Color(0, 255, 204), // Y Greenish-bluey-green
327 new Color(153, 255, 0), // V Yellowish-greeny-yellow
336 public static final Color[] nucleotide =
337 { new Color(100, 247, 63), // A
338 new Color(255, 179, 64), // C
339 new Color(235, 65, 60), // G
340 new Color(60, 136, 238), // T
341 new Color(60, 136, 238), // U
342 Color.white, // I (inosine)
343 Color.white, // X (xanthine)
350 // Added for PurinePyrimidineColourScheme
351 public static final Color[] purinepyrimidine =
352 { new Color(255, 131, 250), // A, G, R purines purplish/orchid
353 new Color(64, 224, 208), // C,U, T, Y pyrimidines turquoise
354 Color.white, // all other nucleotides
359 public static final Color[] zappo =
368 midBlue,// Color.red, // H
389 // Dunno where I got these numbers from
390 public static final double[] hyd2 =
416 public static final double[] helix =
417 { 1.42, 0.98, 0.67, 1.01, 0.70, 1.11, 1.51, 0.57, 1.00, 1.08, 1.21, 1.16,
418 1.45, 1.13, 0.57, 0.77, 0.83, 1.08, 0.69, 1.06, 0.84, 1.31, 1.00, 0.0 };
420 public static final double helixmin = 0.57;
422 public static final double helixmax = 1.51;
424 public static final double[] strand =
425 { 0.83, 0.93, 0.89, 0.54, 1.19, 1.10, 0.37, 0.75, 0.87, 1.60, 1.30, 0.74,
426 1.05, 1.38, 0.55, 0.75, 1.19, 1.37, 1.47, 1.70, 0.72, 0.74, 1.0, 0.0 };
428 public static final double strandmin = 0.37;
430 public static final double strandmax = 1.7;
432 public static final double[] turn =
433 { 0.66, 0.95, 1.56, 1.46, 1.19, 0.98, 0.74, 1.56, 0.95, 0.47, 0.59, 1.01,
434 0.60, 0.60, 1.52, 1.43, 0.96, 0.96, 1.14, 0.50, 1.51, 0.86, 1.00, 0,
437 public static final double turnmin = 0.47;
439 public static final double turnmax = 1.56;
441 public static final double[] buried =
442 { 1.7, 0.1, 0.4, 0.4, 4.6, 0.3, 0.3, 1.8, 0.8, 3.1, 2.4, 0.05, 1.9, 2.2,
443 0.6, 0.8, 0.7, 1.6, 0.5, 2.9, 0.4, 0.3, 1.358, 0.00 };
445 public static final double buriedmin = 0.05;
447 public static final double buriedmax = 4.6;
449 // This is hydropathy index
450 // Kyte, J., and Doolittle, R.F., J. Mol. Biol.
451 // 1157, 105-132, 1982
452 public static final double[] hyd =
453 { 1.8, -4.5, -3.5, -3.5, 2.5, -3.5, -3.5, -0.4, -3.2, 4.5, 3.8, -3.9,
454 1.9, 2.8, -1.6, -0.8, -0.7, -0.9, -1.3, 4.2, -3.5, -3.5, -0.49, 0.0 };
456 public static final double hydmax = 4.5;
458 public static final double hydmin = -3.9;
460 // public static final double hydmax = 1.38;
461 // public static final double hydmin = -2.53;
462 private static final int[][] BLOSUM62 =
464 { 4, -1, -2, -2, 0, -1, -1, 0, -2, -1, -1, -1, -1, -2, -1, 1, 0, -3,
465 -2, 0, -2, -1, 0, -4 },
466 { -1, 5, 0, -2, -3, 1, 0, -2, 0, -3, -2, 2, -1, -3, -2, -1, -1, -3,
467 -2, -3, -1, 0, -1, -4 },
468 { -2, 0, 6, 1, -3, 0, 0, 0, 1, -3, -3, 0, -2, -3, -2, 1, 0, -4, -2,
470 { -2, -2, 1, 6, -3, 0, 2, -1, -1, -3, -4, -1, -3, -3, -1, 0, -1, -4,
471 -3, -3, 4, 1, -1, -4 },
472 { 0, 3, -3, -3, 9, -3, -4, -3, -3, -1, -1, -3, -1, -2, -3, -1, -1,
473 -2, -2, -1, -3, -3, -2, -4 },
474 { -1, 1, 0, 0, -3, 5, 2, -2, 0, -3, -2, 1, 0, -3, -1, 0, -1, -2, -1,
476 { -1, 0, 0, 2, -4, 2, 5, -2, 0, -3, -3, 1, -2, -3, -1, 0, -1, -3, -2,
478 { 0, -2, 0, -1, -3, -2, -2, 6, -2, -4, -4, -2, -3, -3, -2, 0, -2, -2,
479 -3, -3, -1, -2, -1, -4 },
480 { -2, 0, 1, -1, -3, 0, 0, -2, 8, -3, -3, -1, -2, -1, -2, -1, -2, -2,
481 2, -3, 0, 0, -1, -4 },
482 { -1, -3, -3, -3, -1, -3, -3, -4, -3, 4, 2, -3, 1, 0, -3, -2, -1, -3,
483 -1, 3, -3, -3, -1, -4 },
484 { -1, -2, -3, -4, -1, -2, -3, -4, -3, 2, 4, -2, 2, 0, -3, -2, -1, -2,
485 -1, 1, -4, -3, -1, -4 },
486 { -1, 2, 0, -1, -3, 1, 1, -2, -1, -3, -2, 5, -1, -3, -1, 0, -1, -3,
487 -2, -2, 0, 1, -1, -4 },
488 { -1, -1, -2, -3, -1, 0, -2, -3, -2, 1, 2, -1, 5, 0, -2, -1, -1, -1,
489 -1, 1, -3, -1, -1, -4 },
490 { -2, -3, -3, -3, -2, -3, -3, -3, -1, 0, 0, -3, 0, 6, -4, -2, -2, 1,
491 3, -1, -3, -3, -1, -4 },
492 { -1, -2, -2, -1, -3, -1, -1, -2, -2, -3, -3, -1, -2, -4, 7, -1, -1,
493 -4, -3, -2, -2, -1, -2, -4 },
494 { 1, -1, 1, 0, -1, 0, 0, 0, -1, -2, -2, 0, -1, -2, -1, 4, 1, -3, -2,
496 { 0, -1, 0, -1, -1, -1, -1, -2, -2, -1, -1, -1, -1, -2, -1, 1, 5, -2,
497 -2, 0, -1, -1, 0, -4 },
498 { -3, -3, -4, -4, -2, -2, -3, -2, -2, -3, -2, -3, -1, 1, -4, -3, -2,
499 11, 2, -3, -4, -3, -2, -4 },
500 { -2, -2, -2, -3, -2, -1, -2, -3, 2, -1, -1, -2, -1, 3, -3, -2, -2,
501 2, 7, -1, -3, -2, -1, -4 },
502 { 0, -3, -3, -3, -1, -2, -2, -3, -3, 3, 1, -2, 1, -1, -2, -2, 0, -3,
503 -1, 4, -3, -2, -1, -4 },
504 { -2, -1, 3, 4, -3, 0, 1, -1, 0, -3, -4, 0, -3, -3, -2, 0, -1, -4,
505 -3, -3, 4, 1, -1, -4 },
506 { -1, 0, 0, 1, -3, 3, 4, -2, 0, -3, -3, 1, -1, -3, -1, 0, -1, -3, -2,
508 { 0, -1, -1, -1, -2, -1, -1, -1, -1, -1, -1, -1, -1, -1, -2, 0, 0,
509 -2, -1, -1, -1, -1, -1, -4 },
510 { -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4,
511 -4, -4, -4, -4, -4, -4, 1 }, };
513 static final int[][] PAM250 =
515 { 2, -2, 0, 0, -2, 0, 0, 1, -1, -1, -2, -1, -1, -3, 1, 1, 1, -6, -3,
517 { -2, 6, 0, -1, -4, 1, -1, -3, 2, -2, -3, 3, 0, -4, 0, 0, -1, 2, -4,
519 { 0, 0, 2, 2, -4, 1, 1, 0, 2, -2, -3, 1, -2, -3, 0, 1, 0, -4, -2, -2,
521 { 0, -1, 2, 4, -5, 2, 3, 1, 1, -2, -4, 0, -3, -6, -1, 0, 0, -7, -4,
523 { -2, -4, -4, -5, 12, -5, -5, -3, -3, -2, -6, -5, -5, -4, -3, 0, -2,
524 -8, 0, -2, -4, -5, -3, -8 },
525 { 0, 1, 1, 2, -5, 4, 2, -1, 3, -2, -2, 1, -1, -5, 0, -1, -1, -5, -4,
527 { 0, -1, 1, 3, -5, 2, 4, 0, 1, -2, -3, 0, -2, -5, -1, 0, 0, -7, -4,
529 { 1, -3, 0, 1, -3, -1, 0, 5, -2, -3, -4, -2, -3, -5, 0, 1, 0, -7, -5,
531 { -1, 2, 2, 1, -3, 3, 1, -2, 6, -2, -2, 0, -2, -2, 0, -1, -1, -3, 0,
533 { -1, -2, -2, -2, -2, -2, -2, -3, -2, 5, 2, -2, 2, 1, -2, -1, 0, -5,
534 -1, 4, -2, -2, -1, -8 },
535 { -2, -3, -3, -4, -6, -2, -3, -4, -2, 2, 6, -3, 4, 2, -3, -3, -2, -2,
536 -1, 2, -3, -3, -1, -8 },
537 { -1, 3, 1, 0, -5, 1, 0, -2, 0, -2, -3, 5, 0, -5, -1, 0, 0, -3, -4,
539 { -1, 0, -2, -3, -5, -1, -2, -3, -2, 2, 4, 0, 6, 0, -2, -2, -1, -4,
540 -2, 2, -2, -2, -1, -8 },
541 { -3, -4, -3, -6, -4, -5, -5, -5, -2, 1, 2, -5, 0, 9, -5, -3, -3, 0,
542 7, -1, -4, -5, -2, -8 },
543 { 1, 0, 0, -1, -3, 0, -1, 0, 0, -2, -3, -1, -2, -5, 6, 1, 0, -6, -5,
545 { 1, 0, 1, 0, 0, -1, 0, 1, -1, -1, -3, 0, -2, -3, 1, 2, 1, -2, -3,
547 { 1, -1, 0, 0, -2, -1, 0, 0, -1, 0, -2, 0, -1, -3, 0, 1, 3, -5, -3,
549 { -6, 2, -4, -7, -8, -5, -7, -7, -3, -5, -2, -3, -4, 0, -6, -2, -5,
550 17, 0, -6, -5, -6, -4, -8 },
551 { -3, -4, -2, -4, 0, -4, -4, -5, 0, -1, -1, -4, -2, 7, -5, -3, -3, 0,
552 10, -2, -3, -4, -2, -8 },
553 { 0, -2, -2, -2, -2, -2, -2, -1, -2, 4, 2, -2, 2, -1, -1, -1, 0, -6,
554 -2, 4, -2, -2, -1, -8 },
555 { 0, -1, 2, 3, -4, 1, 3, 0, 1, -2, -3, 1, -2, -4, -1, 0, 0, -5, -3,
557 { 0, 0, 1, 3, -5, 3, 3, 0, 2, -2, -3, 0, -2, -5, 0, 0, -1, -6, -4,
559 { 0, -1, 0, -1, -3, -1, -1, -1, -1, -1, -1, -1, -1, -2, -1, 0, 0, -4,
560 -2, -1, -1, -1, -1, -8 },
561 { -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8, -8,
562 -8, -8, -8, -8, -8, -8, 1 }, };
564 public static final Hashtable ssHash = new Hashtable(); // stores the number
569 ssHash.put("H", Color.magenta);
570 ssHash.put("E", Color.yellow);
571 ssHash.put("-", Color.white);
572 ssHash.put(".", Color.white);
573 ssHash.put("S", Color.cyan);
574 ssHash.put("T", Color.blue);
575 ssHash.put("G", Color.pink);
576 ssHash.put("I", Color.pink);
577 ssHash.put("B", Color.yellow);
581 * new Color(60, 136, 238), // U Color.white, // I Color.white, // X
582 * Color.white, // R Color.white, // Y Color.white, // N Color.white, // Gap
585 // JBPNote: patch matrix for T/U equivalence when working with DNA or RNA.
586 // Will equate sequences if working with mixed nucleotide sets.
587 // treats T and U identically. R and Y weak equivalence with AG and CTU.
588 // N matches any other base weakly
590 static final int[][] DNA =
592 { 10, -8, -8, -8, -8, 1, 1, -8, 1, 1, 1 }, // C
593 { -8, 10, -8, -8, 10, 1, 1, -8, 1, 1, 1 }, // T
594 { -8, -8, 10, -8, -8, 1, 1, 1, -8, 1, 1 }, // A
595 { -8, -8, -8, 10, -8, 1, 1, 1, -8, 1, 1 }, // G
596 { -8, 10, -8, -8, 10, 1, 1, -8, 1, 1, 1 }, // U
597 { 1, 1, 1, 1, 1, 10, 0, 0, 0, 1, 1 }, // I
598 { 1, 1, 1, 1, 1, 0, 10, 0, 0, 1, 1 }, // X
599 { -8, -8, 1, 1, -8, 0, 0, 10, 0, 1, 1 }, // R
600 { 1, 1, -8, -8, 1, 0, 0, 0, 10, 1, 1 }, // Y
601 { 1, 1, 1, 1, 1, 1, 1, 1, 1, 10, 1 }, // N
602 { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, // -
605 * register matrices in list
609 scoreMatrices.put("BLOSUM62", new ScoreMatrix("BLOSUM62", BLOSUM62, 0));
610 scoreMatrices.put("PAM250", new ScoreMatrix("PAM250", PAM250, 0));
611 scoreMatrices.put("DNA", new ScoreMatrix("DNA", DNA, 1));
615 public static final Color[] pidColours =
616 { midBlue, new Color(153, 153, 255),
618 new Color(204, 204, 255), };
620 public static final float[] pidThresholds =
623 public static Hashtable codonHash = new Hashtable();
625 public static Vector Lys = new Vector();
627 public static Vector Asn = new Vector();
629 public static Vector Gln = new Vector();
631 public static Vector His = new Vector();
633 public static Vector Glu = new Vector();
635 public static Vector Asp = new Vector();
637 public static Vector Tyr = new Vector();
639 public static Vector Thr = new Vector();
641 public static Vector Pro = new Vector();
643 public static Vector Ala = new Vector();
645 public static Vector Ser = new Vector();
647 public static Vector Arg = new Vector();
649 public static Vector Gly = new Vector();
651 public static Vector Trp = new Vector();
653 public static Vector Cys = new Vector();
655 public static Vector Ile = new Vector();
657 public static Vector Met = new Vector();
659 public static Vector Leu = new Vector();
661 public static Vector Val = new Vector();
663 public static Vector Phe = new Vector();
665 public static Vector STOP = new Vector();
669 codonHash.put("K", Lys);
670 codonHash.put("N", Asn);
671 codonHash.put("Q", Gln);
672 codonHash.put("H", His);
673 codonHash.put("E", Glu);
674 codonHash.put("D", Asp);
675 codonHash.put("Y", Tyr);
676 codonHash.put("T", Thr);
677 codonHash.put("P", Pro);
678 codonHash.put("A", Ala);
679 codonHash.put("S", Ser);
680 codonHash.put("R", Arg);
681 codonHash.put("G", Gly);
682 codonHash.put("W", Trp);
683 codonHash.put("C", Cys);
684 codonHash.put("I", Ile);
685 codonHash.put("M", Met);
686 codonHash.put("L", Leu);
687 codonHash.put("V", Val);
688 codonHash.put("F", Phe);
689 codonHash.put("STOP", STOP);
692 public static Hashtable codonHash2 = new Hashtable();
696 codonHash2.put("AAA", "K");
697 codonHash2.put("AAG", "K");
698 codonHash2.put("AAC", "N");
699 codonHash2.put("AAT", "N");
701 codonHash2.put("CAA", "E");
702 codonHash2.put("CAG", "E");
703 codonHash2.put("CAC", "H");
704 codonHash2.put("CAT", "H");
706 codonHash2.put("GAA", "Q");
707 codonHash2.put("GAG", "Q");
708 codonHash2.put("GAC", "D");
709 codonHash2.put("GAT", "D");
711 codonHash2.put("TAC", "Y");
712 codonHash2.put("TAT", "Y");
714 codonHash2.put("ACA", "T");
715 codonHash2.put("AAG", "T");
716 codonHash2.put("ACC", "T");
717 codonHash2.put("ACT", "T");
719 codonHash2.put("CCA", "P");
720 codonHash2.put("CCG", "P");
721 codonHash2.put("CCC", "P");
722 codonHash2.put("CCT", "P");
724 codonHash2.put("GCA", "A");
725 codonHash2.put("GCG", "A");
726 codonHash2.put("GCC", "A");
727 codonHash2.put("GCT", "A");
729 codonHash2.put("TCA", "S");
730 codonHash2.put("TCG", "S");
731 codonHash2.put("TCC", "S");
732 codonHash2.put("TCT", "S");
733 codonHash2.put("AGC", "S");
734 codonHash2.put("AGT", "S");
736 codonHash2.put("AGA", "R");
737 codonHash2.put("AGG", "R");
738 codonHash2.put("CGA", "R");
739 codonHash2.put("CGG", "R");
740 codonHash2.put("CGC", "R");
741 codonHash2.put("CGT", "R");
743 codonHash2.put("GGA", "G");
744 codonHash2.put("GGG", "G");
745 codonHash2.put("GGC", "G");
746 codonHash2.put("GGT", "G");
748 codonHash2.put("TGA", "*");
749 codonHash2.put("TAA", "*");
750 codonHash2.put("TAG", "*");
752 codonHash2.put("TGG", "W");
754 codonHash2.put("TGC", "C");
755 codonHash2.put("TGT", "C");
757 codonHash2.put("ATA", "I");
758 codonHash2.put("ATC", "I");
759 codonHash2.put("ATT", "I");
761 codonHash2.put("ATG", "M");
763 codonHash2.put("CTA", "L");
764 codonHash2.put("CTG", "L");
765 codonHash2.put("CTC", "L");
766 codonHash2.put("CTT", "L");
767 codonHash2.put("TTA", "L");
768 codonHash2.put("TTG", "L");
770 codonHash2.put("GTA", "V");
771 codonHash2.put("GTG", "V");
772 codonHash2.put("GTC", "V");
773 codonHash2.put("GTT", "V");
775 codonHash2.put("TTC", "F");
776 codonHash2.put("TTT", "F");
781 Lys.addElement("AAA");
782 Lys.addElement("AAG");
783 Asn.addElement("AAC");
784 Asn.addElement("AAT");
786 Gln.addElement("CAA");
787 Gln.addElement("CAG");
788 His.addElement("CAC");
789 His.addElement("CAT");
791 Glu.addElement("GAA");
792 Glu.addElement("GAG");
793 Asp.addElement("GAC");
794 Asp.addElement("GAT");
796 Tyr.addElement("TAC");
797 Tyr.addElement("TAT");
799 Thr.addElement("ACA");
800 Thr.addElement("ACG");
801 Thr.addElement("ACC");
802 Thr.addElement("ACT");
804 Pro.addElement("CCA");
805 Pro.addElement("CCG");
806 Pro.addElement("CCC");
807 Pro.addElement("CCT");
809 Ala.addElement("GCA");
810 Ala.addElement("GCG");
811 Ala.addElement("GCC");
812 Ala.addElement("GCT");
814 Ser.addElement("TCA");
815 Ser.addElement("TCG");
816 Ser.addElement("TCC");
817 Ser.addElement("TCT");
818 Ser.addElement("AGC");
819 Ser.addElement("AGT");
821 Arg.addElement("AGA");
822 Arg.addElement("AGG");
823 Arg.addElement("CGA");
824 Arg.addElement("CGG");
825 Arg.addElement("CGC");
826 Arg.addElement("CGT");
828 Gly.addElement("GGA");
829 Gly.addElement("GGG");
830 Gly.addElement("GGC");
831 Gly.addElement("GGT");
833 STOP.addElement("TGA");
834 STOP.addElement("TAA");
835 STOP.addElement("TAG");
837 Trp.addElement("TGG");
839 Cys.addElement("TGC");
840 Cys.addElement("TGT");
842 Ile.addElement("ATA");
843 Ile.addElement("ATC");
844 Ile.addElement("ATT");
846 Met.addElement("ATG");
848 Leu.addElement("CTA");
849 Leu.addElement("CTG");
850 Leu.addElement("CTC");
851 Leu.addElement("CTT");
852 Leu.addElement("TTA");
853 Leu.addElement("TTG");
855 Val.addElement("GTA");
856 Val.addElement("GTG");
857 Val.addElement("GTC");
858 Val.addElement("GTT");
860 Phe.addElement("TTC");
861 Phe.addElement("TTT");
864 // Stores residue codes/names and colours and other things
865 public static Hashtable propHash = new Hashtable();
867 public static Hashtable hydrophobic = new Hashtable();
869 public static Hashtable polar = new Hashtable();
871 public static Hashtable small = new Hashtable();
873 public static Hashtable positive = new Hashtable();
875 public static Hashtable negative = new Hashtable();
877 public static Hashtable charged = new Hashtable();
879 public static Hashtable aromatic = new Hashtable();
881 public static Hashtable aliphatic = new Hashtable();
883 public static Hashtable tiny = new Hashtable();
885 public static Hashtable proline = new Hashtable();
889 hydrophobic.put("I", new Integer(1));
890 hydrophobic.put("L", new Integer(1));
891 hydrophobic.put("V", new Integer(1));
892 hydrophobic.put("C", new Integer(1));
893 hydrophobic.put("A", new Integer(1));
894 hydrophobic.put("G", new Integer(1));
895 hydrophobic.put("M", new Integer(1));
896 hydrophobic.put("F", new Integer(1));
897 hydrophobic.put("Y", new Integer(1));
898 hydrophobic.put("W", new Integer(1));
899 hydrophobic.put("H", new Integer(1));
900 hydrophobic.put("K", new Integer(1));
901 hydrophobic.put("X", new Integer(1));
902 hydrophobic.put("-", new Integer(1));
903 hydrophobic.put("*", new Integer(1));
904 hydrophobic.put("R", new Integer(0));
905 hydrophobic.put("E", new Integer(0));
906 hydrophobic.put("Q", new Integer(0));
907 hydrophobic.put("D", new Integer(0));
908 hydrophobic.put("N", new Integer(0));
909 hydrophobic.put("S", new Integer(0));
910 hydrophobic.put("T", new Integer(0));
911 hydrophobic.put("P", new Integer(0));
916 polar.put("Y", new Integer(1));
917 polar.put("W", new Integer(1));
918 polar.put("H", new Integer(1));
919 polar.put("K", new Integer(1));
920 polar.put("R", new Integer(1));
921 polar.put("E", new Integer(1));
922 polar.put("Q", new Integer(1));
923 polar.put("D", new Integer(1));
924 polar.put("N", new Integer(1));
925 polar.put("S", new Integer(1));
926 polar.put("T", new Integer(1));
927 polar.put("X", new Integer(1));
928 polar.put("-", new Integer(1));
929 polar.put("*", new Integer(1));
930 polar.put("I", new Integer(0));
931 polar.put("L", new Integer(0));
932 polar.put("V", new Integer(0));
933 polar.put("C", new Integer(0));
934 polar.put("A", new Integer(0));
935 polar.put("G", new Integer(0));
936 polar.put("M", new Integer(0));
937 polar.put("F", new Integer(0));
938 polar.put("P", new Integer(0));
943 small.put("I", new Integer(0));
944 small.put("L", new Integer(0));
945 small.put("V", new Integer(1));
946 small.put("C", new Integer(1));
947 small.put("A", new Integer(1));
948 small.put("G", new Integer(1));
949 small.put("M", new Integer(0));
950 small.put("F", new Integer(0));
951 small.put("Y", new Integer(0));
952 small.put("W", new Integer(0));
953 small.put("H", new Integer(0));
954 small.put("K", new Integer(0));
955 small.put("R", new Integer(0));
956 small.put("E", new Integer(0));
957 small.put("Q", new Integer(0));
958 small.put("D", new Integer(1));
959 small.put("N", new Integer(1));
960 small.put("S", new Integer(1));
961 small.put("T", new Integer(1));
962 small.put("P", new Integer(1));
963 small.put("-", new Integer(1));
964 small.put("*", new Integer(1));
969 positive.put("I", new Integer(0));
970 positive.put("L", new Integer(0));
971 positive.put("V", new Integer(0));
972 positive.put("C", new Integer(0));
973 positive.put("A", new Integer(0));
974 positive.put("G", new Integer(0));
975 positive.put("M", new Integer(0));
976 positive.put("F", new Integer(0));
977 positive.put("Y", new Integer(0));
978 positive.put("W", new Integer(0));
979 positive.put("H", new Integer(1));
980 positive.put("K", new Integer(1));
981 positive.put("R", new Integer(1));
982 positive.put("E", new Integer(0));
983 positive.put("Q", new Integer(0));
984 positive.put("D", new Integer(0));
985 positive.put("N", new Integer(0));
986 positive.put("S", new Integer(0));
987 positive.put("T", new Integer(0));
988 positive.put("P", new Integer(0));
989 positive.put("-", new Integer(1));
990 positive.put("*", new Integer(1));
995 negative.put("I", new Integer(0));
996 negative.put("L", new Integer(0));
997 negative.put("V", new Integer(0));
998 negative.put("C", new Integer(0));
999 negative.put("A", new Integer(0));
1000 negative.put("G", new Integer(0));
1001 negative.put("M", new Integer(0));
1002 negative.put("F", new Integer(0));
1003 negative.put("Y", new Integer(0));
1004 negative.put("W", new Integer(0));
1005 negative.put("H", new Integer(0));
1006 negative.put("K", new Integer(0));
1007 negative.put("R", new Integer(0));
1008 negative.put("E", new Integer(1));
1009 negative.put("Q", new Integer(0));
1010 negative.put("D", new Integer(1));
1011 negative.put("N", new Integer(0));
1012 negative.put("S", new Integer(0));
1013 negative.put("T", new Integer(0));
1014 negative.put("P", new Integer(0));
1015 negative.put("-", new Integer(1));
1016 negative.put("*", new Integer(1));
1021 charged.put("I", new Integer(0));
1022 charged.put("L", new Integer(0));
1023 charged.put("V", new Integer(0));
1024 charged.put("C", new Integer(0));
1025 charged.put("A", new Integer(0));
1026 charged.put("G", new Integer(0));
1027 charged.put("M", new Integer(0));
1028 charged.put("F", new Integer(0));
1029 charged.put("Y", new Integer(0));
1030 charged.put("W", new Integer(0));
1031 charged.put("H", new Integer(1));
1032 charged.put("K", new Integer(1));
1033 charged.put("R", new Integer(1));
1034 charged.put("E", new Integer(1));
1035 charged.put("Q", new Integer(0));
1036 charged.put("D", new Integer(1));
1037 charged.put("N", new Integer(0)); // Asparagine is polar but not charged.
1038 // Alternative would be charged and
1039 // negative (in basic form)?
1040 charged.put("S", new Integer(0));
1041 charged.put("T", new Integer(0));
1042 charged.put("P", new Integer(0));
1043 charged.put("-", new Integer(1));
1044 charged.put("*", new Integer(1));
1049 aromatic.put("I", new Integer(0));
1050 aromatic.put("L", new Integer(0));
1051 aromatic.put("V", new Integer(0));
1052 aromatic.put("C", new Integer(0));
1053 aromatic.put("A", new Integer(0));
1054 aromatic.put("G", new Integer(0));
1055 aromatic.put("M", new Integer(0));
1056 aromatic.put("F", new Integer(1));
1057 aromatic.put("Y", new Integer(1));
1058 aromatic.put("W", new Integer(1));
1059 aromatic.put("H", new Integer(1));
1060 aromatic.put("K", new Integer(0));
1061 aromatic.put("R", new Integer(0));
1062 aromatic.put("E", new Integer(0));
1063 aromatic.put("Q", new Integer(0));
1064 aromatic.put("D", new Integer(0));
1065 aromatic.put("N", new Integer(0));
1066 aromatic.put("S", new Integer(0));
1067 aromatic.put("T", new Integer(0));
1068 aromatic.put("P", new Integer(0));
1069 aromatic.put("-", new Integer(1));
1070 aromatic.put("*", new Integer(1));
1075 aliphatic.put("I", new Integer(1));
1076 aliphatic.put("L", new Integer(1));
1077 aliphatic.put("V", new Integer(1));
1078 aliphatic.put("C", new Integer(0));
1079 aliphatic.put("A", new Integer(0));
1080 aliphatic.put("G", new Integer(0));
1081 aliphatic.put("M", new Integer(0));
1082 aliphatic.put("F", new Integer(0));
1083 aliphatic.put("Y", new Integer(0));
1084 aliphatic.put("W", new Integer(0));
1085 aliphatic.put("H", new Integer(0));
1086 aliphatic.put("K", new Integer(0));
1087 aliphatic.put("R", new Integer(0));
1088 aliphatic.put("E", new Integer(0));
1089 aliphatic.put("Q", new Integer(0));
1090 aliphatic.put("D", new Integer(0));
1091 aliphatic.put("N", new Integer(0));
1092 aliphatic.put("S", new Integer(0));
1093 aliphatic.put("T", new Integer(0));
1094 aliphatic.put("P", new Integer(0));
1095 aliphatic.put("-", new Integer(1));
1096 aliphatic.put("*", new Integer(1));
1101 tiny.put("I", new Integer(0));
1102 tiny.put("L", new Integer(0));
1103 tiny.put("V", new Integer(0));
1104 tiny.put("C", new Integer(0));
1105 tiny.put("A", new Integer(1));
1106 tiny.put("G", new Integer(1));
1107 tiny.put("M", new Integer(0));
1108 tiny.put("F", new Integer(0));
1109 tiny.put("Y", new Integer(0));
1110 tiny.put("W", new Integer(0));
1111 tiny.put("H", new Integer(0));
1112 tiny.put("K", new Integer(0));
1113 tiny.put("R", new Integer(0));
1114 tiny.put("E", new Integer(0));
1115 tiny.put("Q", new Integer(0));
1116 tiny.put("D", new Integer(0));
1117 tiny.put("N", new Integer(0));
1118 tiny.put("S", new Integer(1));
1119 tiny.put("T", new Integer(0));
1120 tiny.put("P", new Integer(0));
1121 tiny.put("-", new Integer(1));
1122 tiny.put("*", new Integer(1));
1127 proline.put("I", new Integer(0));
1128 proline.put("L", new Integer(0));
1129 proline.put("V", new Integer(0));
1130 proline.put("C", new Integer(0));
1131 proline.put("A", new Integer(0));
1132 proline.put("G", new Integer(0));
1133 proline.put("M", new Integer(0));
1134 proline.put("F", new Integer(0));
1135 proline.put("Y", new Integer(0));
1136 proline.put("W", new Integer(0));
1137 proline.put("H", new Integer(0));
1138 proline.put("K", new Integer(0));
1139 proline.put("R", new Integer(0));
1140 proline.put("E", new Integer(0));
1141 proline.put("Q", new Integer(0));
1142 proline.put("D", new Integer(0));
1143 proline.put("N", new Integer(0));
1144 proline.put("S", new Integer(0));
1145 proline.put("T", new Integer(0));
1146 proline.put("P", new Integer(1));
1147 proline.put("-", new Integer(1));
1148 proline.put("*", new Integer(1));
1153 propHash.put("hydrophobic", hydrophobic);
1154 propHash.put("small", small);
1155 propHash.put("positive", positive);
1156 propHash.put("negative", negative);
1157 propHash.put("charged", charged);
1158 propHash.put("aromatic", aromatic);
1159 propHash.put("aliphatic", aliphatic);
1160 propHash.put("tiny", tiny);
1161 propHash.put("proline", proline);
1162 propHash.put("polar", polar);
1165 private ResidueProperties()
1169 public static double getHydmax()
1174 public static double getHydmin()
1179 public static double[] getHyd()
1184 public static Hashtable getAA3Hash()
1189 public static int[][] getDNA()
1191 return ResidueProperties.DNA;
1194 public static int[][] getBLOSUM62()
1196 return ResidueProperties.BLOSUM62;
1199 public static int getPAM250(String A1, String A2)
1201 return getPAM250(A1.charAt(0), A2.charAt(0));
1204 public static int getBLOSUM62(char c1, char c2)
1210 int a = aaIndex[c1];
1211 int b = aaIndex[c2];
1213 pog = ResidueProperties.BLOSUM62[a][b];
1214 } catch (Exception e)
1216 // System.out.println("Unknown residue in " + A1 + " " + A2);
1222 public static Vector getCodons(String res)
1224 if (codonHash.containsKey(res))
1226 return (Vector) codonHash.get(res);
1232 public static String codonTranslate(String lccodon)
1234 String codon = lccodon.toUpperCase();
1235 // all base ambiguity codes yield an 'X' amino acid residue
1236 if (codon.indexOf('X') > -1 || codon.indexOf('N') > -1)
1240 Enumeration e = codonHash.keys();
1242 while (e.hasMoreElements())
1244 String key = (String) e.nextElement();
1245 Vector tmp = (Vector) codonHash.get(key);
1247 if (tmp.contains(codon))
1256 public static int[][] getDefaultPeptideMatrix()
1258 return ResidueProperties.getBLOSUM62();
1261 public static int[][] getDefaultDnaMatrix()
1263 return ResidueProperties.getDNA();
1267 * get a ScoreMatrix based on its string name
1270 * @return matrix in scoreMatrices with key pwtype or null
1272 public static ScoreMatrix getScoreMatrix(String pwtype)
1274 Object val = scoreMatrices.get(pwtype);
1277 return (ScoreMatrix) val;
1282 public static int getPAM250(char c, char d)
1287 int pog = ResidueProperties.PAM250[a][b];
1292 public static Hashtable toDssp3State;
1295 toDssp3State = new Hashtable();
1296 toDssp3State.put("H", "H");
1297 toDssp3State.put("E", "E");
1298 toDssp3State.put("C", " ");
1299 toDssp3State.put(" ", " ");
1300 toDssp3State.put("T", " ");
1301 toDssp3State.put("B", "E");
1302 toDssp3State.put("G", "H");
1303 toDssp3State.put("I", "H");
1304 toDssp3State.put("X", " ");
1308 * translate from other dssp secondary structure alphabets to 3-state
1311 * @return ssstring as a three-state secondary structure assignment.
1313 public static String getDssp3state(String ssstring)
1315 if (ssstring == null)
1319 StringBuffer ss = new StringBuffer();
1320 for (int i = 0; i < ssstring.length(); i++)
1322 String ssc = ssstring.substring(i, i + 1);
1323 if (toDssp3State.containsKey(ssc))
1325 ss.append((String) toDssp3State.get(ssc));
1332 return ss.toString();
1336 * Used by getRNASecStrucState
1339 public static Hashtable toRNAssState;
1342 toRNAssState = new Hashtable();
1343 toRNAssState.put(")", "S");
1344 toRNAssState.put("(", "S");
1348 * translate to RNA secondary structure representation
1351 * @return ssstring as a RNA-state secondary structure assignment.
1353 public static String getRNASecStrucState(String ssstring)
1355 if (ssstring == null)
1359 StringBuffer ss = new StringBuffer();
1360 for (int i = 0; i < ssstring.length(); i++)
1362 String ssc = ssstring.substring(i, i + 1);
1363 if (toRNAssState.containsKey(ssc))
1365 ss.append((String) toRNAssState.get(ssc));
1372 return ss.toString();
1375 // main method generates perl representation of residue property hash
1377 public static void main(String[] args)
1379 Hashtable aa = new Hashtable();
1380 System.out.println("my %aa = {");
1381 // invert property hashes
1382 Enumeration prop = propHash.keys();
1383 while (prop.hasMoreElements())
1385 String pname = (String) prop.nextElement();
1386 Hashtable phash = (Hashtable) propHash.get(pname);
1387 Enumeration res = phash.keys();
1388 while (res.hasMoreElements())
1390 String rname = (String) res.nextElement();
1391 Vector aprops = (Vector) aa.get(rname);
1394 aprops = new Vector();
1395 aa.put(rname, aprops);
1397 Integer hasprop = (Integer) phash.get(rname);
1398 if (hasprop.intValue() == 1)
1400 aprops.addElement(pname);
1404 Enumeration res = aa.keys();
1405 while (res.hasMoreElements())
1407 String rname = (String) res.nextElement();
1409 System.out.print("'" + rname + "' => [");
1410 Enumeration props = ((Vector) aa.get(rname)).elements();
1411 while (props.hasMoreElements())
1413 System.out.print("'" + (String) props.nextElement() + "'");
1414 if (props.hasMoreElements())
1416 System.out.println(", ");
1419 System.out.println("]" + (res.hasMoreElements() ? "," : ""));
1421 System.out.println("};");