1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
|
/*****************************************************************
* @LICENSE@
*****************************************************************/
/* iupac.c
*
* Globally defines the IUPAC symbols for nucleic acid sequence
* Slowly evolving into a repository of globals. Tue Apr 20 1993
*
* CVS $Id: iupac.c,v 1.4 2003/04/14 16:00:16 eddy Exp $
*/
#include "squidconf.h"
#include "squid.h"
/* Default expected nucleotide occurrence frequencies, A/C/G/T.
* Used (for instance) as the default distribution for
* i.i.d. random nucleotide sequences.
*/
float dnafq[4] = { 0.25, 0.25, 0.25, 0.25 };
/* Dayhoff f(i) amino acid occurrence frequencies.
* From SwissProt 34: 21,210,388 residues
* In alphabetic order by single-letter code.
* Used (for instance) as the default distribution for
* i.i.d. random protein sequences.
*/
float aafq[20] = {
0.075520, /* A */
0.016973, /* C */
0.053029, /* D */
0.063204, /* E */
0.040762, /* F */
0.068448, /* G */
0.022406, /* H */
0.057284, /* I */
0.059398, /* K */
0.093399, /* L */
0.023569, /* M */
0.045293, /* N */
0.049262, /* P */
0.040231, /* Q */
0.051573, /* R */
0.072214, /* S */
0.057454, /* T */
0.065252, /* V */
0.012513, /* W */
0.031985 /* Y */
};
char aa_alphabet[] = AMINO_ALPHABET;
/* aa_index converts to pam's 27x27 scheme */
int aa_index[20] = { 0, 2, 3, 4, 5, 6, 7, 8, 10, 11,
12, 13, 15, 16, 17, 18, 19, 21, 22, 24 };
/* IUPAC code translations */
/* note: sequence chars are UPPER CASE */
struct iupactype iupac[] = {
{ 'A', 'T', NTA, NTT, },
{ 'C', 'G', NTC, NTG, },
{ 'G', 'C', NTG, NTC, },
{ 'T', 'A', NTT, NTA, },
{ 'U', 'A', NTU, NTA, },
{ 'N', 'N', NTN, NTN, },
{ ' ', ' ', NTGAP, NTGAP, },
{ 'R', 'Y', NTR, NTY, },
{ 'Y', 'R', NTY, NTR, },
{ 'M', 'K', NTM, NTK, },
{ 'K', 'M', NTK, NTM, },
{ 'S', 'S', NTS, NTS, },
{ 'W', 'W', NTW, NTW, },
{ 'H', 'D', NTH, NTD, },
{ 'B', 'V', NTB, NTV, },
{ 'V', 'B', NTV, NTB, },
{ 'D', 'H', NTD, NTH, },
};
char *stdcode1[65] = {
"K", /* AAA */
"N", /* AAC */
"K", /* AAG */
"N", /* AAU */
"T", /* ACA */
"T", /* ACC */
"T", /* ACG */
"T", /* ACU */
"R", /* AGA */
"S", /* AGC */
"R", /* AGG */
"S", /* AGU */
"I", /* AUA */
"I", /* AUC */
"M", /* AUG */
"I", /* AUU */
"Q", /* CAA */
"H", /* CAC */
"Q", /* CAG */
"H", /* CAU */
"P", /* CCA */
"P", /* CCC */
"P", /* CCG */
"P", /* CCU */
"R", /* CGA */
"R", /* CGC */
"R", /* CGG */
"R", /* CGU */
"L", /* CUA */
"L", /* CUC */
"L", /* CUG */
"L", /* CUU */
"E", /* GAA */
"D", /* GAC */
"E", /* GAG */
"D", /* GAU */
"A", /* GCA */
"A", /* GCC */
"A", /* GCG */
"A", /* GCU */
"G", /* GGA */
"G", /* GGC */
"G", /* GGG */
"G", /* GGU */
"V", /* GUA */
"V", /* GUC */
"V", /* GUG */
"V", /* GUU */
"*", /* UAA */
"Y", /* UAC */
"*", /* UAG */
"Y", /* UAU */
"S", /* UCA */
"S", /* UCC */
"S", /* UCG */
"S", /* UCU */
"*", /* UGA */
"C", /* UGC */
"W", /* UGG */
"C", /* UGU */
"L", /* UUA */
"F", /* UUC */
"L", /* UUG */
"F", /* UUU */
"X", /* unknown */
};
char *stdcode3[65] = {
"Lys", /* AAA */
"Asn", /* AAC */
"Lys", /* AAG */
"Asn", /* AAU */
"Thr", /* ACA */
"Thr", /* ACC */
"Thr", /* ACG */
"Thr", /* ACU */
"Arg", /* AGA */
"Ser", /* AGC */
"Arg", /* AGG */
"Ser", /* AGU */
"Ile", /* AUA */
"Ile", /* AUC */
"Met", /* AUG */
"Ile", /* AUU */
"Gln", /* CAA */
"His", /* CAC */
"Gln", /* CAG */
"His", /* CAU */
"Pro", /* CCA */
"Pro", /* CCC */
"Pro", /* CCG */
"Pro", /* CCU */
"Arg", /* CGA */
"Arg", /* CGC */
"Arg", /* CGG */
"Arg", /* CGU */
"Leu", /* CUA */
"Leu", /* CUC */
"Leu", /* CUG */
"Leu", /* CUU */
"Glu", /* GAA */
"Asp", /* GAC */
"Glu", /* GAG */
"Asp", /* GAU */
"Ala", /* GCA */
"Ala", /* GCC */
"Ala", /* GCG */
"Ala", /* GCU */
"Gly", /* GGA */
"Gly", /* GGC */
"Gly", /* GGG */
"Gly", /* GGU */
"Val", /* GUA */
"Val", /* GUC */
"Val", /* GUG */
"Val", /* GUU */
"***", /* UAA */
"Tyr", /* UAC */
"***", /* UAG */
"Tyr", /* UAU */
"Ser", /* UCA */
"Ser", /* UCC */
"Ser", /* UCG */
"Ser", /* UCU */
"***", /* UGA */
"Cys", /* UGC */
"Trp", /* UGG */
"Cys", /* UGU */
"Leu", /* UUA */
"Phe", /* UUC */
"Leu", /* UUG */
"Trp", /* UUU */
"XXX", /* unknown */
};
|
