English
biology
alphafold
bio-compute
shivendrra commited on
Commit
aedecf8
·
verified ·
1 Parent(s): 84ae784

uploading updated vocabs

Browse files
vocab/as_json/base_1k.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 1,
3
+ "vocab_size": 5,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4
10
+ }
11
+ }
vocab/as_json/base_2k.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 2,
3
+ "vocab_size": 30,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4,
10
+ "--": 5,
11
+ "-A": 6,
12
+ "-C": 7,
13
+ "-G": 8,
14
+ "-T": 9,
15
+ "A-": 10,
16
+ "AA": 11,
17
+ "AC": 12,
18
+ "AG": 13,
19
+ "AT": 14,
20
+ "C-": 15,
21
+ "CA": 16,
22
+ "CC": 17,
23
+ "CG": 18,
24
+ "CT": 19,
25
+ "G-": 20,
26
+ "GA": 21,
27
+ "GC": 22,
28
+ "GG": 23,
29
+ "GT": 24,
30
+ "T-": 25,
31
+ "TA": 26,
32
+ "TC": 27,
33
+ "TG": 28,
34
+ "TT": 29
35
+ }
36
+ }
vocab/as_json/base_3k.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 3,
3
+ "vocab_size": 155,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4,
10
+ "--": 5,
11
+ "-A": 6,
12
+ "-C": 7,
13
+ "-G": 8,
14
+ "-T": 9,
15
+ "A-": 10,
16
+ "AA": 11,
17
+ "AC": 12,
18
+ "AG": 13,
19
+ "AT": 14,
20
+ "C-": 15,
21
+ "CA": 16,
22
+ "CC": 17,
23
+ "CG": 18,
24
+ "CT": 19,
25
+ "G-": 20,
26
+ "GA": 21,
27
+ "GC": 22,
28
+ "GG": 23,
29
+ "GT": 24,
30
+ "T-": 25,
31
+ "TA": 26,
32
+ "TC": 27,
33
+ "TG": 28,
34
+ "TT": 29,
35
+ "---": 30,
36
+ "--A": 31,
37
+ "--C": 32,
38
+ "--G": 33,
39
+ "--T": 34,
40
+ "-A-": 35,
41
+ "-AA": 36,
42
+ "-AC": 37,
43
+ "-AG": 38,
44
+ "-AT": 39,
45
+ "-C-": 40,
46
+ "-CA": 41,
47
+ "-CC": 42,
48
+ "-CG": 43,
49
+ "-CT": 44,
50
+ "-G-": 45,
51
+ "-GA": 46,
52
+ "-GC": 47,
53
+ "-GG": 48,
54
+ "-GT": 49,
55
+ "-T-": 50,
56
+ "-TA": 51,
57
+ "-TC": 52,
58
+ "-TG": 53,
59
+ "-TT": 54,
60
+ "A--": 55,
61
+ "A-A": 56,
62
+ "A-C": 57,
63
+ "A-G": 58,
64
+ "A-T": 59,
65
+ "AA-": 60,
66
+ "AAA": 61,
67
+ "AAC": 62,
68
+ "AAG": 63,
69
+ "AAT": 64,
70
+ "AC-": 65,
71
+ "ACA": 66,
72
+ "ACC": 67,
73
+ "ACG": 68,
74
+ "ACT": 69,
75
+ "AG-": 70,
76
+ "AGA": 71,
77
+ "AGC": 72,
78
+ "AGG": 73,
79
+ "AGT": 74,
80
+ "AT-": 75,
81
+ "ATA": 76,
82
+ "ATC": 77,
83
+ "ATG": 78,
84
+ "ATT": 79,
85
+ "C--": 80,
86
+ "C-A": 81,
87
+ "C-C": 82,
88
+ "C-G": 83,
89
+ "C-T": 84,
90
+ "CA-": 85,
91
+ "CAA": 86,
92
+ "CAC": 87,
93
+ "CAG": 88,
94
+ "CAT": 89,
95
+ "CC-": 90,
96
+ "CCA": 91,
97
+ "CCC": 92,
98
+ "CCG": 93,
99
+ "CCT": 94,
100
+ "CG-": 95,
101
+ "CGA": 96,
102
+ "CGC": 97,
103
+ "CGG": 98,
104
+ "CGT": 99,
105
+ "CT-": 100,
106
+ "CTA": 101,
107
+ "CTC": 102,
108
+ "CTG": 103,
109
+ "CTT": 104,
110
+ "G--": 105,
111
+ "G-A": 106,
112
+ "G-C": 107,
113
+ "G-G": 108,
114
+ "G-T": 109,
115
+ "GA-": 110,
116
+ "GAA": 111,
117
+ "GAC": 112,
118
+ "GAG": 113,
119
+ "GAT": 114,
120
+ "GC-": 115,
121
+ "GCA": 116,
122
+ "GCC": 117,
123
+ "GCG": 118,
124
+ "GCT": 119,
125
+ "GG-": 120,
126
+ "GGA": 121,
127
+ "GGC": 122,
128
+ "GGG": 123,
129
+ "GGT": 124,
130
+ "GT-": 125,
131
+ "GTA": 126,
132
+ "GTC": 127,
133
+ "GTG": 128,
134
+ "GTT": 129,
135
+ "T--": 130,
136
+ "T-A": 131,
137
+ "T-C": 132,
138
+ "T-G": 133,
139
+ "T-T": 134,
140
+ "TA-": 135,
141
+ "TAA": 136,
142
+ "TAC": 137,
143
+ "TAG": 138,
144
+ "TAT": 139,
145
+ "TC-": 140,
146
+ "TCA": 141,
147
+ "TCC": 142,
148
+ "TCG": 143,
149
+ "TCT": 144,
150
+ "TG-": 145,
151
+ "TGA": 146,
152
+ "TGC": 147,
153
+ "TGG": 148,
154
+ "TGT": 149,
155
+ "TT-": 150,
156
+ "TTA": 151,
157
+ "TTC": 152,
158
+ "TTG": 153,
159
+ "TTT": 154
160
+ }
161
+ }
vocab/as_json/base_4k.json ADDED
@@ -0,0 +1,786 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 4,
3
+ "vocab_size": 780,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4,
10
+ "--": 5,
11
+ "-A": 6,
12
+ "-C": 7,
13
+ "-G": 8,
14
+ "-T": 9,
15
+ "A-": 10,
16
+ "AA": 11,
17
+ "AC": 12,
18
+ "AG": 13,
19
+ "AT": 14,
20
+ "C-": 15,
21
+ "CA": 16,
22
+ "CC": 17,
23
+ "CG": 18,
24
+ "CT": 19,
25
+ "G-": 20,
26
+ "GA": 21,
27
+ "GC": 22,
28
+ "GG": 23,
29
+ "GT": 24,
30
+ "T-": 25,
31
+ "TA": 26,
32
+ "TC": 27,
33
+ "TG": 28,
34
+ "TT": 29,
35
+ "---": 30,
36
+ "--A": 31,
37
+ "--C": 32,
38
+ "--G": 33,
39
+ "--T": 34,
40
+ "-A-": 35,
41
+ "-AA": 36,
42
+ "-AC": 37,
43
+ "-AG": 38,
44
+ "-AT": 39,
45
+ "-C-": 40,
46
+ "-CA": 41,
47
+ "-CC": 42,
48
+ "-CG": 43,
49
+ "-CT": 44,
50
+ "-G-": 45,
51
+ "-GA": 46,
52
+ "-GC": 47,
53
+ "-GG": 48,
54
+ "-GT": 49,
55
+ "-T-": 50,
56
+ "-TA": 51,
57
+ "-TC": 52,
58
+ "-TG": 53,
59
+ "-TT": 54,
60
+ "A--": 55,
61
+ "A-A": 56,
62
+ "A-C": 57,
63
+ "A-G": 58,
64
+ "A-T": 59,
65
+ "AA-": 60,
66
+ "AAA": 61,
67
+ "AAC": 62,
68
+ "AAG": 63,
69
+ "AAT": 64,
70
+ "AC-": 65,
71
+ "ACA": 66,
72
+ "ACC": 67,
73
+ "ACG": 68,
74
+ "ACT": 69,
75
+ "AG-": 70,
76
+ "AGA": 71,
77
+ "AGC": 72,
78
+ "AGG": 73,
79
+ "AGT": 74,
80
+ "AT-": 75,
81
+ "ATA": 76,
82
+ "ATC": 77,
83
+ "ATG": 78,
84
+ "ATT": 79,
85
+ "C--": 80,
86
+ "C-A": 81,
87
+ "C-C": 82,
88
+ "C-G": 83,
89
+ "C-T": 84,
90
+ "CA-": 85,
91
+ "CAA": 86,
92
+ "CAC": 87,
93
+ "CAG": 88,
94
+ "CAT": 89,
95
+ "CC-": 90,
96
+ "CCA": 91,
97
+ "CCC": 92,
98
+ "CCG": 93,
99
+ "CCT": 94,
100
+ "CG-": 95,
101
+ "CGA": 96,
102
+ "CGC": 97,
103
+ "CGG": 98,
104
+ "CGT": 99,
105
+ "CT-": 100,
106
+ "CTA": 101,
107
+ "CTC": 102,
108
+ "CTG": 103,
109
+ "CTT": 104,
110
+ "G--": 105,
111
+ "G-A": 106,
112
+ "G-C": 107,
113
+ "G-G": 108,
114
+ "G-T": 109,
115
+ "GA-": 110,
116
+ "GAA": 111,
117
+ "GAC": 112,
118
+ "GAG": 113,
119
+ "GAT": 114,
120
+ "GC-": 115,
121
+ "GCA": 116,
122
+ "GCC": 117,
123
+ "GCG": 118,
124
+ "GCT": 119,
125
+ "GG-": 120,
126
+ "GGA": 121,
127
+ "GGC": 122,
128
+ "GGG": 123,
129
+ "GGT": 124,
130
+ "GT-": 125,
131
+ "GTA": 126,
132
+ "GTC": 127,
133
+ "GTG": 128,
134
+ "GTT": 129,
135
+ "T--": 130,
136
+ "T-A": 131,
137
+ "T-C": 132,
138
+ "T-G": 133,
139
+ "T-T": 134,
140
+ "TA-": 135,
141
+ "TAA": 136,
142
+ "TAC": 137,
143
+ "TAG": 138,
144
+ "TAT": 139,
145
+ "TC-": 140,
146
+ "TCA": 141,
147
+ "TCC": 142,
148
+ "TCG": 143,
149
+ "TCT": 144,
150
+ "TG-": 145,
151
+ "TGA": 146,
152
+ "TGC": 147,
153
+ "TGG": 148,
154
+ "TGT": 149,
155
+ "TT-": 150,
156
+ "TTA": 151,
157
+ "TTC": 152,
158
+ "TTG": 153,
159
+ "TTT": 154,
160
+ "----": 155,
161
+ "---A": 156,
162
+ "---C": 157,
163
+ "---G": 158,
164
+ "---T": 159,
165
+ "--A-": 160,
166
+ "--AA": 161,
167
+ "--AC": 162,
168
+ "--AG": 163,
169
+ "--AT": 164,
170
+ "--C-": 165,
171
+ "--CA": 166,
172
+ "--CC": 167,
173
+ "--CG": 168,
174
+ "--CT": 169,
175
+ "--G-": 170,
176
+ "--GA": 171,
177
+ "--GC": 172,
178
+ "--GG": 173,
179
+ "--GT": 174,
180
+ "--T-": 175,
181
+ "--TA": 176,
182
+ "--TC": 177,
183
+ "--TG": 178,
184
+ "--TT": 179,
185
+ "-A--": 180,
186
+ "-A-A": 181,
187
+ "-A-C": 182,
188
+ "-A-G": 183,
189
+ "-A-T": 184,
190
+ "-AA-": 185,
191
+ "-AAA": 186,
192
+ "-AAC": 187,
193
+ "-AAG": 188,
194
+ "-AAT": 189,
195
+ "-AC-": 190,
196
+ "-ACA": 191,
197
+ "-ACC": 192,
198
+ "-ACG": 193,
199
+ "-ACT": 194,
200
+ "-AG-": 195,
201
+ "-AGA": 196,
202
+ "-AGC": 197,
203
+ "-AGG": 198,
204
+ "-AGT": 199,
205
+ "-AT-": 200,
206
+ "-ATA": 201,
207
+ "-ATC": 202,
208
+ "-ATG": 203,
209
+ "-ATT": 204,
210
+ "-C--": 205,
211
+ "-C-A": 206,
212
+ "-C-C": 207,
213
+ "-C-G": 208,
214
+ "-C-T": 209,
215
+ "-CA-": 210,
216
+ "-CAA": 211,
217
+ "-CAC": 212,
218
+ "-CAG": 213,
219
+ "-CAT": 214,
220
+ "-CC-": 215,
221
+ "-CCA": 216,
222
+ "-CCC": 217,
223
+ "-CCG": 218,
224
+ "-CCT": 219,
225
+ "-CG-": 220,
226
+ "-CGA": 221,
227
+ "-CGC": 222,
228
+ "-CGG": 223,
229
+ "-CGT": 224,
230
+ "-CT-": 225,
231
+ "-CTA": 226,
232
+ "-CTC": 227,
233
+ "-CTG": 228,
234
+ "-CTT": 229,
235
+ "-G--": 230,
236
+ "-G-A": 231,
237
+ "-G-C": 232,
238
+ "-G-G": 233,
239
+ "-G-T": 234,
240
+ "-GA-": 235,
241
+ "-GAA": 236,
242
+ "-GAC": 237,
243
+ "-GAG": 238,
244
+ "-GAT": 239,
245
+ "-GC-": 240,
246
+ "-GCA": 241,
247
+ "-GCC": 242,
248
+ "-GCG": 243,
249
+ "-GCT": 244,
250
+ "-GG-": 245,
251
+ "-GGA": 246,
252
+ "-GGC": 247,
253
+ "-GGG": 248,
254
+ "-GGT": 249,
255
+ "-GT-": 250,
256
+ "-GTA": 251,
257
+ "-GTC": 252,
258
+ "-GTG": 253,
259
+ "-GTT": 254,
260
+ "-T--": 255,
261
+ "-T-A": 256,
262
+ "-T-C": 257,
263
+ "-T-G": 258,
264
+ "-T-T": 259,
265
+ "-TA-": 260,
266
+ "-TAA": 261,
267
+ "-TAC": 262,
268
+ "-TAG": 263,
269
+ "-TAT": 264,
270
+ "-TC-": 265,
271
+ "-TCA": 266,
272
+ "-TCC": 267,
273
+ "-TCG": 268,
274
+ "-TCT": 269,
275
+ "-TG-": 270,
276
+ "-TGA": 271,
277
+ "-TGC": 272,
278
+ "-TGG": 273,
279
+ "-TGT": 274,
280
+ "-TT-": 275,
281
+ "-TTA": 276,
282
+ "-TTC": 277,
283
+ "-TTG": 278,
284
+ "-TTT": 279,
285
+ "A---": 280,
286
+ "A--A": 281,
287
+ "A--C": 282,
288
+ "A--G": 283,
289
+ "A--T": 284,
290
+ "A-A-": 285,
291
+ "A-AA": 286,
292
+ "A-AC": 287,
293
+ "A-AG": 288,
294
+ "A-AT": 289,
295
+ "A-C-": 290,
296
+ "A-CA": 291,
297
+ "A-CC": 292,
298
+ "A-CG": 293,
299
+ "A-CT": 294,
300
+ "A-G-": 295,
301
+ "A-GA": 296,
302
+ "A-GC": 297,
303
+ "A-GG": 298,
304
+ "A-GT": 299,
305
+ "A-T-": 300,
306
+ "A-TA": 301,
307
+ "A-TC": 302,
308
+ "A-TG": 303,
309
+ "A-TT": 304,
310
+ "AA--": 305,
311
+ "AA-A": 306,
312
+ "AA-C": 307,
313
+ "AA-G": 308,
314
+ "AA-T": 309,
315
+ "AAA-": 310,
316
+ "AAAA": 311,
317
+ "AAAC": 312,
318
+ "AAAG": 313,
319
+ "AAAT": 314,
320
+ "AAC-": 315,
321
+ "AACA": 316,
322
+ "AACC": 317,
323
+ "AACG": 318,
324
+ "AACT": 319,
325
+ "AAG-": 320,
326
+ "AAGA": 321,
327
+ "AAGC": 322,
328
+ "AAGG": 323,
329
+ "AAGT": 324,
330
+ "AAT-": 325,
331
+ "AATA": 326,
332
+ "AATC": 327,
333
+ "AATG": 328,
334
+ "AATT": 329,
335
+ "AC--": 330,
336
+ "AC-A": 331,
337
+ "AC-C": 332,
338
+ "AC-G": 333,
339
+ "AC-T": 334,
340
+ "ACA-": 335,
341
+ "ACAA": 336,
342
+ "ACAC": 337,
343
+ "ACAG": 338,
344
+ "ACAT": 339,
345
+ "ACC-": 340,
346
+ "ACCA": 341,
347
+ "ACCC": 342,
348
+ "ACCG": 343,
349
+ "ACCT": 344,
350
+ "ACG-": 345,
351
+ "ACGA": 346,
352
+ "ACGC": 347,
353
+ "ACGG": 348,
354
+ "ACGT": 349,
355
+ "ACT-": 350,
356
+ "ACTA": 351,
357
+ "ACTC": 352,
358
+ "ACTG": 353,
359
+ "ACTT": 354,
360
+ "AG--": 355,
361
+ "AG-A": 356,
362
+ "AG-C": 357,
363
+ "AG-G": 358,
364
+ "AG-T": 359,
365
+ "AGA-": 360,
366
+ "AGAA": 361,
367
+ "AGAC": 362,
368
+ "AGAG": 363,
369
+ "AGAT": 364,
370
+ "AGC-": 365,
371
+ "AGCA": 366,
372
+ "AGCC": 367,
373
+ "AGCG": 368,
374
+ "AGCT": 369,
375
+ "AGG-": 370,
376
+ "AGGA": 371,
377
+ "AGGC": 372,
378
+ "AGGG": 373,
379
+ "AGGT": 374,
380
+ "AGT-": 375,
381
+ "AGTA": 376,
382
+ "AGTC": 377,
383
+ "AGTG": 378,
384
+ "AGTT": 379,
385
+ "AT--": 380,
386
+ "AT-A": 381,
387
+ "AT-C": 382,
388
+ "AT-G": 383,
389
+ "AT-T": 384,
390
+ "ATA-": 385,
391
+ "ATAA": 386,
392
+ "ATAC": 387,
393
+ "ATAG": 388,
394
+ "ATAT": 389,
395
+ "ATC-": 390,
396
+ "ATCA": 391,
397
+ "ATCC": 392,
398
+ "ATCG": 393,
399
+ "ATCT": 394,
400
+ "ATG-": 395,
401
+ "ATGA": 396,
402
+ "ATGC": 397,
403
+ "ATGG": 398,
404
+ "ATGT": 399,
405
+ "ATT-": 400,
406
+ "ATTA": 401,
407
+ "ATTC": 402,
408
+ "ATTG": 403,
409
+ "ATTT": 404,
410
+ "C---": 405,
411
+ "C--A": 406,
412
+ "C--C": 407,
413
+ "C--G": 408,
414
+ "C--T": 409,
415
+ "C-A-": 410,
416
+ "C-AA": 411,
417
+ "C-AC": 412,
418
+ "C-AG": 413,
419
+ "C-AT": 414,
420
+ "C-C-": 415,
421
+ "C-CA": 416,
422
+ "C-CC": 417,
423
+ "C-CG": 418,
424
+ "C-CT": 419,
425
+ "C-G-": 420,
426
+ "C-GA": 421,
427
+ "C-GC": 422,
428
+ "C-GG": 423,
429
+ "C-GT": 424,
430
+ "C-T-": 425,
431
+ "C-TA": 426,
432
+ "C-TC": 427,
433
+ "C-TG": 428,
434
+ "C-TT": 429,
435
+ "CA--": 430,
436
+ "CA-A": 431,
437
+ "CA-C": 432,
438
+ "CA-G": 433,
439
+ "CA-T": 434,
440
+ "CAA-": 435,
441
+ "CAAA": 436,
442
+ "CAAC": 437,
443
+ "CAAG": 438,
444
+ "CAAT": 439,
445
+ "CAC-": 440,
446
+ "CACA": 441,
447
+ "CACC": 442,
448
+ "CACG": 443,
449
+ "CACT": 444,
450
+ "CAG-": 445,
451
+ "CAGA": 446,
452
+ "CAGC": 447,
453
+ "CAGG": 448,
454
+ "CAGT": 449,
455
+ "CAT-": 450,
456
+ "CATA": 451,
457
+ "CATC": 452,
458
+ "CATG": 453,
459
+ "CATT": 454,
460
+ "CC--": 455,
461
+ "CC-A": 456,
462
+ "CC-C": 457,
463
+ "CC-G": 458,
464
+ "CC-T": 459,
465
+ "CCA-": 460,
466
+ "CCAA": 461,
467
+ "CCAC": 462,
468
+ "CCAG": 463,
469
+ "CCAT": 464,
470
+ "CCC-": 465,
471
+ "CCCA": 466,
472
+ "CCCC": 467,
473
+ "CCCG": 468,
474
+ "CCCT": 469,
475
+ "CCG-": 470,
476
+ "CCGA": 471,
477
+ "CCGC": 472,
478
+ "CCGG": 473,
479
+ "CCGT": 474,
480
+ "CCT-": 475,
481
+ "CCTA": 476,
482
+ "CCTC": 477,
483
+ "CCTG": 478,
484
+ "CCTT": 479,
485
+ "CG--": 480,
486
+ "CG-A": 481,
487
+ "CG-C": 482,
488
+ "CG-G": 483,
489
+ "CG-T": 484,
490
+ "CGA-": 485,
491
+ "CGAA": 486,
492
+ "CGAC": 487,
493
+ "CGAG": 488,
494
+ "CGAT": 489,
495
+ "CGC-": 490,
496
+ "CGCA": 491,
497
+ "CGCC": 492,
498
+ "CGCG": 493,
499
+ "CGCT": 494,
500
+ "CGG-": 495,
501
+ "CGGA": 496,
502
+ "CGGC": 497,
503
+ "CGGG": 498,
504
+ "CGGT": 499,
505
+ "CGT-": 500,
506
+ "CGTA": 501,
507
+ "CGTC": 502,
508
+ "CGTG": 503,
509
+ "CGTT": 504,
510
+ "CT--": 505,
511
+ "CT-A": 506,
512
+ "CT-C": 507,
513
+ "CT-G": 508,
514
+ "CT-T": 509,
515
+ "CTA-": 510,
516
+ "CTAA": 511,
517
+ "CTAC": 512,
518
+ "CTAG": 513,
519
+ "CTAT": 514,
520
+ "CTC-": 515,
521
+ "CTCA": 516,
522
+ "CTCC": 517,
523
+ "CTCG": 518,
524
+ "CTCT": 519,
525
+ "CTG-": 520,
526
+ "CTGA": 521,
527
+ "CTGC": 522,
528
+ "CTGG": 523,
529
+ "CTGT": 524,
530
+ "CTT-": 525,
531
+ "CTTA": 526,
532
+ "CTTC": 527,
533
+ "CTTG": 528,
534
+ "CTTT": 529,
535
+ "G---": 530,
536
+ "G--A": 531,
537
+ "G--C": 532,
538
+ "G--G": 533,
539
+ "G--T": 534,
540
+ "G-A-": 535,
541
+ "G-AA": 536,
542
+ "G-AC": 537,
543
+ "G-AG": 538,
544
+ "G-AT": 539,
545
+ "G-C-": 540,
546
+ "G-CA": 541,
547
+ "G-CC": 542,
548
+ "G-CG": 543,
549
+ "G-CT": 544,
550
+ "G-G-": 545,
551
+ "G-GA": 546,
552
+ "G-GC": 547,
553
+ "G-GG": 548,
554
+ "G-GT": 549,
555
+ "G-T-": 550,
556
+ "G-TA": 551,
557
+ "G-TC": 552,
558
+ "G-TG": 553,
559
+ "G-TT": 554,
560
+ "GA--": 555,
561
+ "GA-A": 556,
562
+ "GA-C": 557,
563
+ "GA-G": 558,
564
+ "GA-T": 559,
565
+ "GAA-": 560,
566
+ "GAAA": 561,
567
+ "GAAC": 562,
568
+ "GAAG": 563,
569
+ "GAAT": 564,
570
+ "GAC-": 565,
571
+ "GACA": 566,
572
+ "GACC": 567,
573
+ "GACG": 568,
574
+ "GACT": 569,
575
+ "GAG-": 570,
576
+ "GAGA": 571,
577
+ "GAGC": 572,
578
+ "GAGG": 573,
579
+ "GAGT": 574,
580
+ "GAT-": 575,
581
+ "GATA": 576,
582
+ "GATC": 577,
583
+ "GATG": 578,
584
+ "GATT": 579,
585
+ "GC--": 580,
586
+ "GC-A": 581,
587
+ "GC-C": 582,
588
+ "GC-G": 583,
589
+ "GC-T": 584,
590
+ "GCA-": 585,
591
+ "GCAA": 586,
592
+ "GCAC": 587,
593
+ "GCAG": 588,
594
+ "GCAT": 589,
595
+ "GCC-": 590,
596
+ "GCCA": 591,
597
+ "GCCC": 592,
598
+ "GCCG": 593,
599
+ "GCCT": 594,
600
+ "GCG-": 595,
601
+ "GCGA": 596,
602
+ "GCGC": 597,
603
+ "GCGG": 598,
604
+ "GCGT": 599,
605
+ "GCT-": 600,
606
+ "GCTA": 601,
607
+ "GCTC": 602,
608
+ "GCTG": 603,
609
+ "GCTT": 604,
610
+ "GG--": 605,
611
+ "GG-A": 606,
612
+ "GG-C": 607,
613
+ "GG-G": 608,
614
+ "GG-T": 609,
615
+ "GGA-": 610,
616
+ "GGAA": 611,
617
+ "GGAC": 612,
618
+ "GGAG": 613,
619
+ "GGAT": 614,
620
+ "GGC-": 615,
621
+ "GGCA": 616,
622
+ "GGCC": 617,
623
+ "GGCG": 618,
624
+ "GGCT": 619,
625
+ "GGG-": 620,
626
+ "GGGA": 621,
627
+ "GGGC": 622,
628
+ "GGGG": 623,
629
+ "GGGT": 624,
630
+ "GGT-": 625,
631
+ "GGTA": 626,
632
+ "GGTC": 627,
633
+ "GGTG": 628,
634
+ "GGTT": 629,
635
+ "GT--": 630,
636
+ "GT-A": 631,
637
+ "GT-C": 632,
638
+ "GT-G": 633,
639
+ "GT-T": 634,
640
+ "GTA-": 635,
641
+ "GTAA": 636,
642
+ "GTAC": 637,
643
+ "GTAG": 638,
644
+ "GTAT": 639,
645
+ "GTC-": 640,
646
+ "GTCA": 641,
647
+ "GTCC": 642,
648
+ "GTCG": 643,
649
+ "GTCT": 644,
650
+ "GTG-": 645,
651
+ "GTGA": 646,
652
+ "GTGC": 647,
653
+ "GTGG": 648,
654
+ "GTGT": 649,
655
+ "GTT-": 650,
656
+ "GTTA": 651,
657
+ "GTTC": 652,
658
+ "GTTG": 653,
659
+ "GTTT": 654,
660
+ "T---": 655,
661
+ "T--A": 656,
662
+ "T--C": 657,
663
+ "T--G": 658,
664
+ "T--T": 659,
665
+ "T-A-": 660,
666
+ "T-AA": 661,
667
+ "T-AC": 662,
668
+ "T-AG": 663,
669
+ "T-AT": 664,
670
+ "T-C-": 665,
671
+ "T-CA": 666,
672
+ "T-CC": 667,
673
+ "T-CG": 668,
674
+ "T-CT": 669,
675
+ "T-G-": 670,
676
+ "T-GA": 671,
677
+ "T-GC": 672,
678
+ "T-GG": 673,
679
+ "T-GT": 674,
680
+ "T-T-": 675,
681
+ "T-TA": 676,
682
+ "T-TC": 677,
683
+ "T-TG": 678,
684
+ "T-TT": 679,
685
+ "TA--": 680,
686
+ "TA-A": 681,
687
+ "TA-C": 682,
688
+ "TA-G": 683,
689
+ "TA-T": 684,
690
+ "TAA-": 685,
691
+ "TAAA": 686,
692
+ "TAAC": 687,
693
+ "TAAG": 688,
694
+ "TAAT": 689,
695
+ "TAC-": 690,
696
+ "TACA": 691,
697
+ "TACC": 692,
698
+ "TACG": 693,
699
+ "TACT": 694,
700
+ "TAG-": 695,
701
+ "TAGA": 696,
702
+ "TAGC": 697,
703
+ "TAGG": 698,
704
+ "TAGT": 699,
705
+ "TAT-": 700,
706
+ "TATA": 701,
707
+ "TATC": 702,
708
+ "TATG": 703,
709
+ "TATT": 704,
710
+ "TC--": 705,
711
+ "TC-A": 706,
712
+ "TC-C": 707,
713
+ "TC-G": 708,
714
+ "TC-T": 709,
715
+ "TCA-": 710,
716
+ "TCAA": 711,
717
+ "TCAC": 712,
718
+ "TCAG": 713,
719
+ "TCAT": 714,
720
+ "TCC-": 715,
721
+ "TCCA": 716,
722
+ "TCCC": 717,
723
+ "TCCG": 718,
724
+ "TCCT": 719,
725
+ "TCG-": 720,
726
+ "TCGA": 721,
727
+ "TCGC": 722,
728
+ "TCGG": 723,
729
+ "TCGT": 724,
730
+ "TCT-": 725,
731
+ "TCTA": 726,
732
+ "TCTC": 727,
733
+ "TCTG": 728,
734
+ "TCTT": 729,
735
+ "TG--": 730,
736
+ "TG-A": 731,
737
+ "TG-C": 732,
738
+ "TG-G": 733,
739
+ "TG-T": 734,
740
+ "TGA-": 735,
741
+ "TGAA": 736,
742
+ "TGAC": 737,
743
+ "TGAG": 738,
744
+ "TGAT": 739,
745
+ "TGC-": 740,
746
+ "TGCA": 741,
747
+ "TGCC": 742,
748
+ "TGCG": 743,
749
+ "TGCT": 744,
750
+ "TGG-": 745,
751
+ "TGGA": 746,
752
+ "TGGC": 747,
753
+ "TGGG": 748,
754
+ "TGGT": 749,
755
+ "TGT-": 750,
756
+ "TGTA": 751,
757
+ "TGTC": 752,
758
+ "TGTG": 753,
759
+ "TGTT": 754,
760
+ "TT--": 755,
761
+ "TT-A": 756,
762
+ "TT-C": 757,
763
+ "TT-G": 758,
764
+ "TT-T": 759,
765
+ "TTA-": 760,
766
+ "TTAA": 761,
767
+ "TTAC": 762,
768
+ "TTAG": 763,
769
+ "TTAT": 764,
770
+ "TTC-": 765,
771
+ "TTCA": 766,
772
+ "TTCC": 767,
773
+ "TTCG": 768,
774
+ "TTCT": 769,
775
+ "TTG-": 770,
776
+ "TTGA": 771,
777
+ "TTGC": 772,
778
+ "TTGG": 773,
779
+ "TTGT": 774,
780
+ "TTT-": 775,
781
+ "TTTA": 776,
782
+ "TTTC": 777,
783
+ "TTTG": 778,
784
+ "TTTT": 779
785
+ }
786
+ }
vocab/as_json/base_5k.json ADDED
@@ -0,0 +1,3911 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 5,
3
+ "vocab_size": 3905,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4,
10
+ "--": 5,
11
+ "-A": 6,
12
+ "-C": 7,
13
+ "-G": 8,
14
+ "-T": 9,
15
+ "A-": 10,
16
+ "AA": 11,
17
+ "AC": 12,
18
+ "AG": 13,
19
+ "AT": 14,
20
+ "C-": 15,
21
+ "CA": 16,
22
+ "CC": 17,
23
+ "CG": 18,
24
+ "CT": 19,
25
+ "G-": 20,
26
+ "GA": 21,
27
+ "GC": 22,
28
+ "GG": 23,
29
+ "GT": 24,
30
+ "T-": 25,
31
+ "TA": 26,
32
+ "TC": 27,
33
+ "TG": 28,
34
+ "TT": 29,
35
+ "---": 30,
36
+ "--A": 31,
37
+ "--C": 32,
38
+ "--G": 33,
39
+ "--T": 34,
40
+ "-A-": 35,
41
+ "-AA": 36,
42
+ "-AC": 37,
43
+ "-AG": 38,
44
+ "-AT": 39,
45
+ "-C-": 40,
46
+ "-CA": 41,
47
+ "-CC": 42,
48
+ "-CG": 43,
49
+ "-CT": 44,
50
+ "-G-": 45,
51
+ "-GA": 46,
52
+ "-GC": 47,
53
+ "-GG": 48,
54
+ "-GT": 49,
55
+ "-T-": 50,
56
+ "-TA": 51,
57
+ "-TC": 52,
58
+ "-TG": 53,
59
+ "-TT": 54,
60
+ "A--": 55,
61
+ "A-A": 56,
62
+ "A-C": 57,
63
+ "A-G": 58,
64
+ "A-T": 59,
65
+ "AA-": 60,
66
+ "AAA": 61,
67
+ "AAC": 62,
68
+ "AAG": 63,
69
+ "AAT": 64,
70
+ "AC-": 65,
71
+ "ACA": 66,
72
+ "ACC": 67,
73
+ "ACG": 68,
74
+ "ACT": 69,
75
+ "AG-": 70,
76
+ "AGA": 71,
77
+ "AGC": 72,
78
+ "AGG": 73,
79
+ "AGT": 74,
80
+ "AT-": 75,
81
+ "ATA": 76,
82
+ "ATC": 77,
83
+ "ATG": 78,
84
+ "ATT": 79,
85
+ "C--": 80,
86
+ "C-A": 81,
87
+ "C-C": 82,
88
+ "C-G": 83,
89
+ "C-T": 84,
90
+ "CA-": 85,
91
+ "CAA": 86,
92
+ "CAC": 87,
93
+ "CAG": 88,
94
+ "CAT": 89,
95
+ "CC-": 90,
96
+ "CCA": 91,
97
+ "CCC": 92,
98
+ "CCG": 93,
99
+ "CCT": 94,
100
+ "CG-": 95,
101
+ "CGA": 96,
102
+ "CGC": 97,
103
+ "CGG": 98,
104
+ "CGT": 99,
105
+ "CT-": 100,
106
+ "CTA": 101,
107
+ "CTC": 102,
108
+ "CTG": 103,
109
+ "CTT": 104,
110
+ "G--": 105,
111
+ "G-A": 106,
112
+ "G-C": 107,
113
+ "G-G": 108,
114
+ "G-T": 109,
115
+ "GA-": 110,
116
+ "GAA": 111,
117
+ "GAC": 112,
118
+ "GAG": 113,
119
+ "GAT": 114,
120
+ "GC-": 115,
121
+ "GCA": 116,
122
+ "GCC": 117,
123
+ "GCG": 118,
124
+ "GCT": 119,
125
+ "GG-": 120,
126
+ "GGA": 121,
127
+ "GGC": 122,
128
+ "GGG": 123,
129
+ "GGT": 124,
130
+ "GT-": 125,
131
+ "GTA": 126,
132
+ "GTC": 127,
133
+ "GTG": 128,
134
+ "GTT": 129,
135
+ "T--": 130,
136
+ "T-A": 131,
137
+ "T-C": 132,
138
+ "T-G": 133,
139
+ "T-T": 134,
140
+ "TA-": 135,
141
+ "TAA": 136,
142
+ "TAC": 137,
143
+ "TAG": 138,
144
+ "TAT": 139,
145
+ "TC-": 140,
146
+ "TCA": 141,
147
+ "TCC": 142,
148
+ "TCG": 143,
149
+ "TCT": 144,
150
+ "TG-": 145,
151
+ "TGA": 146,
152
+ "TGC": 147,
153
+ "TGG": 148,
154
+ "TGT": 149,
155
+ "TT-": 150,
156
+ "TTA": 151,
157
+ "TTC": 152,
158
+ "TTG": 153,
159
+ "TTT": 154,
160
+ "----": 155,
161
+ "---A": 156,
162
+ "---C": 157,
163
+ "---G": 158,
164
+ "---T": 159,
165
+ "--A-": 160,
166
+ "--AA": 161,
167
+ "--AC": 162,
168
+ "--AG": 163,
169
+ "--AT": 164,
170
+ "--C-": 165,
171
+ "--CA": 166,
172
+ "--CC": 167,
173
+ "--CG": 168,
174
+ "--CT": 169,
175
+ "--G-": 170,
176
+ "--GA": 171,
177
+ "--GC": 172,
178
+ "--GG": 173,
179
+ "--GT": 174,
180
+ "--T-": 175,
181
+ "--TA": 176,
182
+ "--TC": 177,
183
+ "--TG": 178,
184
+ "--TT": 179,
185
+ "-A--": 180,
186
+ "-A-A": 181,
187
+ "-A-C": 182,
188
+ "-A-G": 183,
189
+ "-A-T": 184,
190
+ "-AA-": 185,
191
+ "-AAA": 186,
192
+ "-AAC": 187,
193
+ "-AAG": 188,
194
+ "-AAT": 189,
195
+ "-AC-": 190,
196
+ "-ACA": 191,
197
+ "-ACC": 192,
198
+ "-ACG": 193,
199
+ "-ACT": 194,
200
+ "-AG-": 195,
201
+ "-AGA": 196,
202
+ "-AGC": 197,
203
+ "-AGG": 198,
204
+ "-AGT": 199,
205
+ "-AT-": 200,
206
+ "-ATA": 201,
207
+ "-ATC": 202,
208
+ "-ATG": 203,
209
+ "-ATT": 204,
210
+ "-C--": 205,
211
+ "-C-A": 206,
212
+ "-C-C": 207,
213
+ "-C-G": 208,
214
+ "-C-T": 209,
215
+ "-CA-": 210,
216
+ "-CAA": 211,
217
+ "-CAC": 212,
218
+ "-CAG": 213,
219
+ "-CAT": 214,
220
+ "-CC-": 215,
221
+ "-CCA": 216,
222
+ "-CCC": 217,
223
+ "-CCG": 218,
224
+ "-CCT": 219,
225
+ "-CG-": 220,
226
+ "-CGA": 221,
227
+ "-CGC": 222,
228
+ "-CGG": 223,
229
+ "-CGT": 224,
230
+ "-CT-": 225,
231
+ "-CTA": 226,
232
+ "-CTC": 227,
233
+ "-CTG": 228,
234
+ "-CTT": 229,
235
+ "-G--": 230,
236
+ "-G-A": 231,
237
+ "-G-C": 232,
238
+ "-G-G": 233,
239
+ "-G-T": 234,
240
+ "-GA-": 235,
241
+ "-GAA": 236,
242
+ "-GAC": 237,
243
+ "-GAG": 238,
244
+ "-GAT": 239,
245
+ "-GC-": 240,
246
+ "-GCA": 241,
247
+ "-GCC": 242,
248
+ "-GCG": 243,
249
+ "-GCT": 244,
250
+ "-GG-": 245,
251
+ "-GGA": 246,
252
+ "-GGC": 247,
253
+ "-GGG": 248,
254
+ "-GGT": 249,
255
+ "-GT-": 250,
256
+ "-GTA": 251,
257
+ "-GTC": 252,
258
+ "-GTG": 253,
259
+ "-GTT": 254,
260
+ "-T--": 255,
261
+ "-T-A": 256,
262
+ "-T-C": 257,
263
+ "-T-G": 258,
264
+ "-T-T": 259,
265
+ "-TA-": 260,
266
+ "-TAA": 261,
267
+ "-TAC": 262,
268
+ "-TAG": 263,
269
+ "-TAT": 264,
270
+ "-TC-": 265,
271
+ "-TCA": 266,
272
+ "-TCC": 267,
273
+ "-TCG": 268,
274
+ "-TCT": 269,
275
+ "-TG-": 270,
276
+ "-TGA": 271,
277
+ "-TGC": 272,
278
+ "-TGG": 273,
279
+ "-TGT": 274,
280
+ "-TT-": 275,
281
+ "-TTA": 276,
282
+ "-TTC": 277,
283
+ "-TTG": 278,
284
+ "-TTT": 279,
285
+ "A---": 280,
286
+ "A--A": 281,
287
+ "A--C": 282,
288
+ "A--G": 283,
289
+ "A--T": 284,
290
+ "A-A-": 285,
291
+ "A-AA": 286,
292
+ "A-AC": 287,
293
+ "A-AG": 288,
294
+ "A-AT": 289,
295
+ "A-C-": 290,
296
+ "A-CA": 291,
297
+ "A-CC": 292,
298
+ "A-CG": 293,
299
+ "A-CT": 294,
300
+ "A-G-": 295,
301
+ "A-GA": 296,
302
+ "A-GC": 297,
303
+ "A-GG": 298,
304
+ "A-GT": 299,
305
+ "A-T-": 300,
306
+ "A-TA": 301,
307
+ "A-TC": 302,
308
+ "A-TG": 303,
309
+ "A-TT": 304,
310
+ "AA--": 305,
311
+ "AA-A": 306,
312
+ "AA-C": 307,
313
+ "AA-G": 308,
314
+ "AA-T": 309,
315
+ "AAA-": 310,
316
+ "AAAA": 311,
317
+ "AAAC": 312,
318
+ "AAAG": 313,
319
+ "AAAT": 314,
320
+ "AAC-": 315,
321
+ "AACA": 316,
322
+ "AACC": 317,
323
+ "AACG": 318,
324
+ "AACT": 319,
325
+ "AAG-": 320,
326
+ "AAGA": 321,
327
+ "AAGC": 322,
328
+ "AAGG": 323,
329
+ "AAGT": 324,
330
+ "AAT-": 325,
331
+ "AATA": 326,
332
+ "AATC": 327,
333
+ "AATG": 328,
334
+ "AATT": 329,
335
+ "AC--": 330,
336
+ "AC-A": 331,
337
+ "AC-C": 332,
338
+ "AC-G": 333,
339
+ "AC-T": 334,
340
+ "ACA-": 335,
341
+ "ACAA": 336,
342
+ "ACAC": 337,
343
+ "ACAG": 338,
344
+ "ACAT": 339,
345
+ "ACC-": 340,
346
+ "ACCA": 341,
347
+ "ACCC": 342,
348
+ "ACCG": 343,
349
+ "ACCT": 344,
350
+ "ACG-": 345,
351
+ "ACGA": 346,
352
+ "ACGC": 347,
353
+ "ACGG": 348,
354
+ "ACGT": 349,
355
+ "ACT-": 350,
356
+ "ACTA": 351,
357
+ "ACTC": 352,
358
+ "ACTG": 353,
359
+ "ACTT": 354,
360
+ "AG--": 355,
361
+ "AG-A": 356,
362
+ "AG-C": 357,
363
+ "AG-G": 358,
364
+ "AG-T": 359,
365
+ "AGA-": 360,
366
+ "AGAA": 361,
367
+ "AGAC": 362,
368
+ "AGAG": 363,
369
+ "AGAT": 364,
370
+ "AGC-": 365,
371
+ "AGCA": 366,
372
+ "AGCC": 367,
373
+ "AGCG": 368,
374
+ "AGCT": 369,
375
+ "AGG-": 370,
376
+ "AGGA": 371,
377
+ "AGGC": 372,
378
+ "AGGG": 373,
379
+ "AGGT": 374,
380
+ "AGT-": 375,
381
+ "AGTA": 376,
382
+ "AGTC": 377,
383
+ "AGTG": 378,
384
+ "AGTT": 379,
385
+ "AT--": 380,
386
+ "AT-A": 381,
387
+ "AT-C": 382,
388
+ "AT-G": 383,
389
+ "AT-T": 384,
390
+ "ATA-": 385,
391
+ "ATAA": 386,
392
+ "ATAC": 387,
393
+ "ATAG": 388,
394
+ "ATAT": 389,
395
+ "ATC-": 390,
396
+ "ATCA": 391,
397
+ "ATCC": 392,
398
+ "ATCG": 393,
399
+ "ATCT": 394,
400
+ "ATG-": 395,
401
+ "ATGA": 396,
402
+ "ATGC": 397,
403
+ "ATGG": 398,
404
+ "ATGT": 399,
405
+ "ATT-": 400,
406
+ "ATTA": 401,
407
+ "ATTC": 402,
408
+ "ATTG": 403,
409
+ "ATTT": 404,
410
+ "C---": 405,
411
+ "C--A": 406,
412
+ "C--C": 407,
413
+ "C--G": 408,
414
+ "C--T": 409,
415
+ "C-A-": 410,
416
+ "C-AA": 411,
417
+ "C-AC": 412,
418
+ "C-AG": 413,
419
+ "C-AT": 414,
420
+ "C-C-": 415,
421
+ "C-CA": 416,
422
+ "C-CC": 417,
423
+ "C-CG": 418,
424
+ "C-CT": 419,
425
+ "C-G-": 420,
426
+ "C-GA": 421,
427
+ "C-GC": 422,
428
+ "C-GG": 423,
429
+ "C-GT": 424,
430
+ "C-T-": 425,
431
+ "C-TA": 426,
432
+ "C-TC": 427,
433
+ "C-TG": 428,
434
+ "C-TT": 429,
435
+ "CA--": 430,
436
+ "CA-A": 431,
437
+ "CA-C": 432,
438
+ "CA-G": 433,
439
+ "CA-T": 434,
440
+ "CAA-": 435,
441
+ "CAAA": 436,
442
+ "CAAC": 437,
443
+ "CAAG": 438,
444
+ "CAAT": 439,
445
+ "CAC-": 440,
446
+ "CACA": 441,
447
+ "CACC": 442,
448
+ "CACG": 443,
449
+ "CACT": 444,
450
+ "CAG-": 445,
451
+ "CAGA": 446,
452
+ "CAGC": 447,
453
+ "CAGG": 448,
454
+ "CAGT": 449,
455
+ "CAT-": 450,
456
+ "CATA": 451,
457
+ "CATC": 452,
458
+ "CATG": 453,
459
+ "CATT": 454,
460
+ "CC--": 455,
461
+ "CC-A": 456,
462
+ "CC-C": 457,
463
+ "CC-G": 458,
464
+ "CC-T": 459,
465
+ "CCA-": 460,
466
+ "CCAA": 461,
467
+ "CCAC": 462,
468
+ "CCAG": 463,
469
+ "CCAT": 464,
470
+ "CCC-": 465,
471
+ "CCCA": 466,
472
+ "CCCC": 467,
473
+ "CCCG": 468,
474
+ "CCCT": 469,
475
+ "CCG-": 470,
476
+ "CCGA": 471,
477
+ "CCGC": 472,
478
+ "CCGG": 473,
479
+ "CCGT": 474,
480
+ "CCT-": 475,
481
+ "CCTA": 476,
482
+ "CCTC": 477,
483
+ "CCTG": 478,
484
+ "CCTT": 479,
485
+ "CG--": 480,
486
+ "CG-A": 481,
487
+ "CG-C": 482,
488
+ "CG-G": 483,
489
+ "CG-T": 484,
490
+ "CGA-": 485,
491
+ "CGAA": 486,
492
+ "CGAC": 487,
493
+ "CGAG": 488,
494
+ "CGAT": 489,
495
+ "CGC-": 490,
496
+ "CGCA": 491,
497
+ "CGCC": 492,
498
+ "CGCG": 493,
499
+ "CGCT": 494,
500
+ "CGG-": 495,
501
+ "CGGA": 496,
502
+ "CGGC": 497,
503
+ "CGGG": 498,
504
+ "CGGT": 499,
505
+ "CGT-": 500,
506
+ "CGTA": 501,
507
+ "CGTC": 502,
508
+ "CGTG": 503,
509
+ "CGTT": 504,
510
+ "CT--": 505,
511
+ "CT-A": 506,
512
+ "CT-C": 507,
513
+ "CT-G": 508,
514
+ "CT-T": 509,
515
+ "CTA-": 510,
516
+ "CTAA": 511,
517
+ "CTAC": 512,
518
+ "CTAG": 513,
519
+ "CTAT": 514,
520
+ "CTC-": 515,
521
+ "CTCA": 516,
522
+ "CTCC": 517,
523
+ "CTCG": 518,
524
+ "CTCT": 519,
525
+ "CTG-": 520,
526
+ "CTGA": 521,
527
+ "CTGC": 522,
528
+ "CTGG": 523,
529
+ "CTGT": 524,
530
+ "CTT-": 525,
531
+ "CTTA": 526,
532
+ "CTTC": 527,
533
+ "CTTG": 528,
534
+ "CTTT": 529,
535
+ "G---": 530,
536
+ "G--A": 531,
537
+ "G--C": 532,
538
+ "G--G": 533,
539
+ "G--T": 534,
540
+ "G-A-": 535,
541
+ "G-AA": 536,
542
+ "G-AC": 537,
543
+ "G-AG": 538,
544
+ "G-AT": 539,
545
+ "G-C-": 540,
546
+ "G-CA": 541,
547
+ "G-CC": 542,
548
+ "G-CG": 543,
549
+ "G-CT": 544,
550
+ "G-G-": 545,
551
+ "G-GA": 546,
552
+ "G-GC": 547,
553
+ "G-GG": 548,
554
+ "G-GT": 549,
555
+ "G-T-": 550,
556
+ "G-TA": 551,
557
+ "G-TC": 552,
558
+ "G-TG": 553,
559
+ "G-TT": 554,
560
+ "GA--": 555,
561
+ "GA-A": 556,
562
+ "GA-C": 557,
563
+ "GA-G": 558,
564
+ "GA-T": 559,
565
+ "GAA-": 560,
566
+ "GAAA": 561,
567
+ "GAAC": 562,
568
+ "GAAG": 563,
569
+ "GAAT": 564,
570
+ "GAC-": 565,
571
+ "GACA": 566,
572
+ "GACC": 567,
573
+ "GACG": 568,
574
+ "GACT": 569,
575
+ "GAG-": 570,
576
+ "GAGA": 571,
577
+ "GAGC": 572,
578
+ "GAGG": 573,
579
+ "GAGT": 574,
580
+ "GAT-": 575,
581
+ "GATA": 576,
582
+ "GATC": 577,
583
+ "GATG": 578,
584
+ "GATT": 579,
585
+ "GC--": 580,
586
+ "GC-A": 581,
587
+ "GC-C": 582,
588
+ "GC-G": 583,
589
+ "GC-T": 584,
590
+ "GCA-": 585,
591
+ "GCAA": 586,
592
+ "GCAC": 587,
593
+ "GCAG": 588,
594
+ "GCAT": 589,
595
+ "GCC-": 590,
596
+ "GCCA": 591,
597
+ "GCCC": 592,
598
+ "GCCG": 593,
599
+ "GCCT": 594,
600
+ "GCG-": 595,
601
+ "GCGA": 596,
602
+ "GCGC": 597,
603
+ "GCGG": 598,
604
+ "GCGT": 599,
605
+ "GCT-": 600,
606
+ "GCTA": 601,
607
+ "GCTC": 602,
608
+ "GCTG": 603,
609
+ "GCTT": 604,
610
+ "GG--": 605,
611
+ "GG-A": 606,
612
+ "GG-C": 607,
613
+ "GG-G": 608,
614
+ "GG-T": 609,
615
+ "GGA-": 610,
616
+ "GGAA": 611,
617
+ "GGAC": 612,
618
+ "GGAG": 613,
619
+ "GGAT": 614,
620
+ "GGC-": 615,
621
+ "GGCA": 616,
622
+ "GGCC": 617,
623
+ "GGCG": 618,
624
+ "GGCT": 619,
625
+ "GGG-": 620,
626
+ "GGGA": 621,
627
+ "GGGC": 622,
628
+ "GGGG": 623,
629
+ "GGGT": 624,
630
+ "GGT-": 625,
631
+ "GGTA": 626,
632
+ "GGTC": 627,
633
+ "GGTG": 628,
634
+ "GGTT": 629,
635
+ "GT--": 630,
636
+ "GT-A": 631,
637
+ "GT-C": 632,
638
+ "GT-G": 633,
639
+ "GT-T": 634,
640
+ "GTA-": 635,
641
+ "GTAA": 636,
642
+ "GTAC": 637,
643
+ "GTAG": 638,
644
+ "GTAT": 639,
645
+ "GTC-": 640,
646
+ "GTCA": 641,
647
+ "GTCC": 642,
648
+ "GTCG": 643,
649
+ "GTCT": 644,
650
+ "GTG-": 645,
651
+ "GTGA": 646,
652
+ "GTGC": 647,
653
+ "GTGG": 648,
654
+ "GTGT": 649,
655
+ "GTT-": 650,
656
+ "GTTA": 651,
657
+ "GTTC": 652,
658
+ "GTTG": 653,
659
+ "GTTT": 654,
660
+ "T---": 655,
661
+ "T--A": 656,
662
+ "T--C": 657,
663
+ "T--G": 658,
664
+ "T--T": 659,
665
+ "T-A-": 660,
666
+ "T-AA": 661,
667
+ "T-AC": 662,
668
+ "T-AG": 663,
669
+ "T-AT": 664,
670
+ "T-C-": 665,
671
+ "T-CA": 666,
672
+ "T-CC": 667,
673
+ "T-CG": 668,
674
+ "T-CT": 669,
675
+ "T-G-": 670,
676
+ "T-GA": 671,
677
+ "T-GC": 672,
678
+ "T-GG": 673,
679
+ "T-GT": 674,
680
+ "T-T-": 675,
681
+ "T-TA": 676,
682
+ "T-TC": 677,
683
+ "T-TG": 678,
684
+ "T-TT": 679,
685
+ "TA--": 680,
686
+ "TA-A": 681,
687
+ "TA-C": 682,
688
+ "TA-G": 683,
689
+ "TA-T": 684,
690
+ "TAA-": 685,
691
+ "TAAA": 686,
692
+ "TAAC": 687,
693
+ "TAAG": 688,
694
+ "TAAT": 689,
695
+ "TAC-": 690,
696
+ "TACA": 691,
697
+ "TACC": 692,
698
+ "TACG": 693,
699
+ "TACT": 694,
700
+ "TAG-": 695,
701
+ "TAGA": 696,
702
+ "TAGC": 697,
703
+ "TAGG": 698,
704
+ "TAGT": 699,
705
+ "TAT-": 700,
706
+ "TATA": 701,
707
+ "TATC": 702,
708
+ "TATG": 703,
709
+ "TATT": 704,
710
+ "TC--": 705,
711
+ "TC-A": 706,
712
+ "TC-C": 707,
713
+ "TC-G": 708,
714
+ "TC-T": 709,
715
+ "TCA-": 710,
716
+ "TCAA": 711,
717
+ "TCAC": 712,
718
+ "TCAG": 713,
719
+ "TCAT": 714,
720
+ "TCC-": 715,
721
+ "TCCA": 716,
722
+ "TCCC": 717,
723
+ "TCCG": 718,
724
+ "TCCT": 719,
725
+ "TCG-": 720,
726
+ "TCGA": 721,
727
+ "TCGC": 722,
728
+ "TCGG": 723,
729
+ "TCGT": 724,
730
+ "TCT-": 725,
731
+ "TCTA": 726,
732
+ "TCTC": 727,
733
+ "TCTG": 728,
734
+ "TCTT": 729,
735
+ "TG--": 730,
736
+ "TG-A": 731,
737
+ "TG-C": 732,
738
+ "TG-G": 733,
739
+ "TG-T": 734,
740
+ "TGA-": 735,
741
+ "TGAA": 736,
742
+ "TGAC": 737,
743
+ "TGAG": 738,
744
+ "TGAT": 739,
745
+ "TGC-": 740,
746
+ "TGCA": 741,
747
+ "TGCC": 742,
748
+ "TGCG": 743,
749
+ "TGCT": 744,
750
+ "TGG-": 745,
751
+ "TGGA": 746,
752
+ "TGGC": 747,
753
+ "TGGG": 748,
754
+ "TGGT": 749,
755
+ "TGT-": 750,
756
+ "TGTA": 751,
757
+ "TGTC": 752,
758
+ "TGTG": 753,
759
+ "TGTT": 754,
760
+ "TT--": 755,
761
+ "TT-A": 756,
762
+ "TT-C": 757,
763
+ "TT-G": 758,
764
+ "TT-T": 759,
765
+ "TTA-": 760,
766
+ "TTAA": 761,
767
+ "TTAC": 762,
768
+ "TTAG": 763,
769
+ "TTAT": 764,
770
+ "TTC-": 765,
771
+ "TTCA": 766,
772
+ "TTCC": 767,
773
+ "TTCG": 768,
774
+ "TTCT": 769,
775
+ "TTG-": 770,
776
+ "TTGA": 771,
777
+ "TTGC": 772,
778
+ "TTGG": 773,
779
+ "TTGT": 774,
780
+ "TTT-": 775,
781
+ "TTTA": 776,
782
+ "TTTC": 777,
783
+ "TTTG": 778,
784
+ "TTTT": 779,
785
+ "-----": 780,
786
+ "----A": 781,
787
+ "----C": 782,
788
+ "----G": 783,
789
+ "----T": 784,
790
+ "---A-": 785,
791
+ "---AA": 786,
792
+ "---AC": 787,
793
+ "---AG": 788,
794
+ "---AT": 789,
795
+ "---C-": 790,
796
+ "---CA": 791,
797
+ "---CC": 792,
798
+ "---CG": 793,
799
+ "---CT": 794,
800
+ "---G-": 795,
801
+ "---GA": 796,
802
+ "---GC": 797,
803
+ "---GG": 798,
804
+ "---GT": 799,
805
+ "---T-": 800,
806
+ "---TA": 801,
807
+ "---TC": 802,
808
+ "---TG": 803,
809
+ "---TT": 804,
810
+ "--A--": 805,
811
+ "--A-A": 806,
812
+ "--A-C": 807,
813
+ "--A-G": 808,
814
+ "--A-T": 809,
815
+ "--AA-": 810,
816
+ "--AAA": 811,
817
+ "--AAC": 812,
818
+ "--AAG": 813,
819
+ "--AAT": 814,
820
+ "--AC-": 815,
821
+ "--ACA": 816,
822
+ "--ACC": 817,
823
+ "--ACG": 818,
824
+ "--ACT": 819,
825
+ "--AG-": 820,
826
+ "--AGA": 821,
827
+ "--AGC": 822,
828
+ "--AGG": 823,
829
+ "--AGT": 824,
830
+ "--AT-": 825,
831
+ "--ATA": 826,
832
+ "--ATC": 827,
833
+ "--ATG": 828,
834
+ "--ATT": 829,
835
+ "--C--": 830,
836
+ "--C-A": 831,
837
+ "--C-C": 832,
838
+ "--C-G": 833,
839
+ "--C-T": 834,
840
+ "--CA-": 835,
841
+ "--CAA": 836,
842
+ "--CAC": 837,
843
+ "--CAG": 838,
844
+ "--CAT": 839,
845
+ "--CC-": 840,
846
+ "--CCA": 841,
847
+ "--CCC": 842,
848
+ "--CCG": 843,
849
+ "--CCT": 844,
850
+ "--CG-": 845,
851
+ "--CGA": 846,
852
+ "--CGC": 847,
853
+ "--CGG": 848,
854
+ "--CGT": 849,
855
+ "--CT-": 850,
856
+ "--CTA": 851,
857
+ "--CTC": 852,
858
+ "--CTG": 853,
859
+ "--CTT": 854,
860
+ "--G--": 855,
861
+ "--G-A": 856,
862
+ "--G-C": 857,
863
+ "--G-G": 858,
864
+ "--G-T": 859,
865
+ "--GA-": 860,
866
+ "--GAA": 861,
867
+ "--GAC": 862,
868
+ "--GAG": 863,
869
+ "--GAT": 864,
870
+ "--GC-": 865,
871
+ "--GCA": 866,
872
+ "--GCC": 867,
873
+ "--GCG": 868,
874
+ "--GCT": 869,
875
+ "--GG-": 870,
876
+ "--GGA": 871,
877
+ "--GGC": 872,
878
+ "--GGG": 873,
879
+ "--GGT": 874,
880
+ "--GT-": 875,
881
+ "--GTA": 876,
882
+ "--GTC": 877,
883
+ "--GTG": 878,
884
+ "--GTT": 879,
885
+ "--T--": 880,
886
+ "--T-A": 881,
887
+ "--T-C": 882,
888
+ "--T-G": 883,
889
+ "--T-T": 884,
890
+ "--TA-": 885,
891
+ "--TAA": 886,
892
+ "--TAC": 887,
893
+ "--TAG": 888,
894
+ "--TAT": 889,
895
+ "--TC-": 890,
896
+ "--TCA": 891,
897
+ "--TCC": 892,
898
+ "--TCG": 893,
899
+ "--TCT": 894,
900
+ "--TG-": 895,
901
+ "--TGA": 896,
902
+ "--TGC": 897,
903
+ "--TGG": 898,
904
+ "--TGT": 899,
905
+ "--TT-": 900,
906
+ "--TTA": 901,
907
+ "--TTC": 902,
908
+ "--TTG": 903,
909
+ "--TTT": 904,
910
+ "-A---": 905,
911
+ "-A--A": 906,
912
+ "-A--C": 907,
913
+ "-A--G": 908,
914
+ "-A--T": 909,
915
+ "-A-A-": 910,
916
+ "-A-AA": 911,
917
+ "-A-AC": 912,
918
+ "-A-AG": 913,
919
+ "-A-AT": 914,
920
+ "-A-C-": 915,
921
+ "-A-CA": 916,
922
+ "-A-CC": 917,
923
+ "-A-CG": 918,
924
+ "-A-CT": 919,
925
+ "-A-G-": 920,
926
+ "-A-GA": 921,
927
+ "-A-GC": 922,
928
+ "-A-GG": 923,
929
+ "-A-GT": 924,
930
+ "-A-T-": 925,
931
+ "-A-TA": 926,
932
+ "-A-TC": 927,
933
+ "-A-TG": 928,
934
+ "-A-TT": 929,
935
+ "-AA--": 930,
936
+ "-AA-A": 931,
937
+ "-AA-C": 932,
938
+ "-AA-G": 933,
939
+ "-AA-T": 934,
940
+ "-AAA-": 935,
941
+ "-AAAA": 936,
942
+ "-AAAC": 937,
943
+ "-AAAG": 938,
944
+ "-AAAT": 939,
945
+ "-AAC-": 940,
946
+ "-AACA": 941,
947
+ "-AACC": 942,
948
+ "-AACG": 943,
949
+ "-AACT": 944,
950
+ "-AAG-": 945,
951
+ "-AAGA": 946,
952
+ "-AAGC": 947,
953
+ "-AAGG": 948,
954
+ "-AAGT": 949,
955
+ "-AAT-": 950,
956
+ "-AATA": 951,
957
+ "-AATC": 952,
958
+ "-AATG": 953,
959
+ "-AATT": 954,
960
+ "-AC--": 955,
961
+ "-AC-A": 956,
962
+ "-AC-C": 957,
963
+ "-AC-G": 958,
964
+ "-AC-T": 959,
965
+ "-ACA-": 960,
966
+ "-ACAA": 961,
967
+ "-ACAC": 962,
968
+ "-ACAG": 963,
969
+ "-ACAT": 964,
970
+ "-ACC-": 965,
971
+ "-ACCA": 966,
972
+ "-ACCC": 967,
973
+ "-ACCG": 968,
974
+ "-ACCT": 969,
975
+ "-ACG-": 970,
976
+ "-ACGA": 971,
977
+ "-ACGC": 972,
978
+ "-ACGG": 973,
979
+ "-ACGT": 974,
980
+ "-ACT-": 975,
981
+ "-ACTA": 976,
982
+ "-ACTC": 977,
983
+ "-ACTG": 978,
984
+ "-ACTT": 979,
985
+ "-AG--": 980,
986
+ "-AG-A": 981,
987
+ "-AG-C": 982,
988
+ "-AG-G": 983,
989
+ "-AG-T": 984,
990
+ "-AGA-": 985,
991
+ "-AGAA": 986,
992
+ "-AGAC": 987,
993
+ "-AGAG": 988,
994
+ "-AGAT": 989,
995
+ "-AGC-": 990,
996
+ "-AGCA": 991,
997
+ "-AGCC": 992,
998
+ "-AGCG": 993,
999
+ "-AGCT": 994,
1000
+ "-AGG-": 995,
1001
+ "-AGGA": 996,
1002
+ "-AGGC": 997,
1003
+ "-AGGG": 998,
1004
+ "-AGGT": 999,
1005
+ "-AGT-": 1000,
1006
+ "-AGTA": 1001,
1007
+ "-AGTC": 1002,
1008
+ "-AGTG": 1003,
1009
+ "-AGTT": 1004,
1010
+ "-AT--": 1005,
1011
+ "-AT-A": 1006,
1012
+ "-AT-C": 1007,
1013
+ "-AT-G": 1008,
1014
+ "-AT-T": 1009,
1015
+ "-ATA-": 1010,
1016
+ "-ATAA": 1011,
1017
+ "-ATAC": 1012,
1018
+ "-ATAG": 1013,
1019
+ "-ATAT": 1014,
1020
+ "-ATC-": 1015,
1021
+ "-ATCA": 1016,
1022
+ "-ATCC": 1017,
1023
+ "-ATCG": 1018,
1024
+ "-ATCT": 1019,
1025
+ "-ATG-": 1020,
1026
+ "-ATGA": 1021,
1027
+ "-ATGC": 1022,
1028
+ "-ATGG": 1023,
1029
+ "-ATGT": 1024,
1030
+ "-ATT-": 1025,
1031
+ "-ATTA": 1026,
1032
+ "-ATTC": 1027,
1033
+ "-ATTG": 1028,
1034
+ "-ATTT": 1029,
1035
+ "-C---": 1030,
1036
+ "-C--A": 1031,
1037
+ "-C--C": 1032,
1038
+ "-C--G": 1033,
1039
+ "-C--T": 1034,
1040
+ "-C-A-": 1035,
1041
+ "-C-AA": 1036,
1042
+ "-C-AC": 1037,
1043
+ "-C-AG": 1038,
1044
+ "-C-AT": 1039,
1045
+ "-C-C-": 1040,
1046
+ "-C-CA": 1041,
1047
+ "-C-CC": 1042,
1048
+ "-C-CG": 1043,
1049
+ "-C-CT": 1044,
1050
+ "-C-G-": 1045,
1051
+ "-C-GA": 1046,
1052
+ "-C-GC": 1047,
1053
+ "-C-GG": 1048,
1054
+ "-C-GT": 1049,
1055
+ "-C-T-": 1050,
1056
+ "-C-TA": 1051,
1057
+ "-C-TC": 1052,
1058
+ "-C-TG": 1053,
1059
+ "-C-TT": 1054,
1060
+ "-CA--": 1055,
1061
+ "-CA-A": 1056,
1062
+ "-CA-C": 1057,
1063
+ "-CA-G": 1058,
1064
+ "-CA-T": 1059,
1065
+ "-CAA-": 1060,
1066
+ "-CAAA": 1061,
1067
+ "-CAAC": 1062,
1068
+ "-CAAG": 1063,
1069
+ "-CAAT": 1064,
1070
+ "-CAC-": 1065,
1071
+ "-CACA": 1066,
1072
+ "-CACC": 1067,
1073
+ "-CACG": 1068,
1074
+ "-CACT": 1069,
1075
+ "-CAG-": 1070,
1076
+ "-CAGA": 1071,
1077
+ "-CAGC": 1072,
1078
+ "-CAGG": 1073,
1079
+ "-CAGT": 1074,
1080
+ "-CAT-": 1075,
1081
+ "-CATA": 1076,
1082
+ "-CATC": 1077,
1083
+ "-CATG": 1078,
1084
+ "-CATT": 1079,
1085
+ "-CC--": 1080,
1086
+ "-CC-A": 1081,
1087
+ "-CC-C": 1082,
1088
+ "-CC-G": 1083,
1089
+ "-CC-T": 1084,
1090
+ "-CCA-": 1085,
1091
+ "-CCAA": 1086,
1092
+ "-CCAC": 1087,
1093
+ "-CCAG": 1088,
1094
+ "-CCAT": 1089,
1095
+ "-CCC-": 1090,
1096
+ "-CCCA": 1091,
1097
+ "-CCCC": 1092,
1098
+ "-CCCG": 1093,
1099
+ "-CCCT": 1094,
1100
+ "-CCG-": 1095,
1101
+ "-CCGA": 1096,
1102
+ "-CCGC": 1097,
1103
+ "-CCGG": 1098,
1104
+ "-CCGT": 1099,
1105
+ "-CCT-": 1100,
1106
+ "-CCTA": 1101,
1107
+ "-CCTC": 1102,
1108
+ "-CCTG": 1103,
1109
+ "-CCTT": 1104,
1110
+ "-CG--": 1105,
1111
+ "-CG-A": 1106,
1112
+ "-CG-C": 1107,
1113
+ "-CG-G": 1108,
1114
+ "-CG-T": 1109,
1115
+ "-CGA-": 1110,
1116
+ "-CGAA": 1111,
1117
+ "-CGAC": 1112,
1118
+ "-CGAG": 1113,
1119
+ "-CGAT": 1114,
1120
+ "-CGC-": 1115,
1121
+ "-CGCA": 1116,
1122
+ "-CGCC": 1117,
1123
+ "-CGCG": 1118,
1124
+ "-CGCT": 1119,
1125
+ "-CGG-": 1120,
1126
+ "-CGGA": 1121,
1127
+ "-CGGC": 1122,
1128
+ "-CGGG": 1123,
1129
+ "-CGGT": 1124,
1130
+ "-CGT-": 1125,
1131
+ "-CGTA": 1126,
1132
+ "-CGTC": 1127,
1133
+ "-CGTG": 1128,
1134
+ "-CGTT": 1129,
1135
+ "-CT--": 1130,
1136
+ "-CT-A": 1131,
1137
+ "-CT-C": 1132,
1138
+ "-CT-G": 1133,
1139
+ "-CT-T": 1134,
1140
+ "-CTA-": 1135,
1141
+ "-CTAA": 1136,
1142
+ "-CTAC": 1137,
1143
+ "-CTAG": 1138,
1144
+ "-CTAT": 1139,
1145
+ "-CTC-": 1140,
1146
+ "-CTCA": 1141,
1147
+ "-CTCC": 1142,
1148
+ "-CTCG": 1143,
1149
+ "-CTCT": 1144,
1150
+ "-CTG-": 1145,
1151
+ "-CTGA": 1146,
1152
+ "-CTGC": 1147,
1153
+ "-CTGG": 1148,
1154
+ "-CTGT": 1149,
1155
+ "-CTT-": 1150,
1156
+ "-CTTA": 1151,
1157
+ "-CTTC": 1152,
1158
+ "-CTTG": 1153,
1159
+ "-CTTT": 1154,
1160
+ "-G---": 1155,
1161
+ "-G--A": 1156,
1162
+ "-G--C": 1157,
1163
+ "-G--G": 1158,
1164
+ "-G--T": 1159,
1165
+ "-G-A-": 1160,
1166
+ "-G-AA": 1161,
1167
+ "-G-AC": 1162,
1168
+ "-G-AG": 1163,
1169
+ "-G-AT": 1164,
1170
+ "-G-C-": 1165,
1171
+ "-G-CA": 1166,
1172
+ "-G-CC": 1167,
1173
+ "-G-CG": 1168,
1174
+ "-G-CT": 1169,
1175
+ "-G-G-": 1170,
1176
+ "-G-GA": 1171,
1177
+ "-G-GC": 1172,
1178
+ "-G-GG": 1173,
1179
+ "-G-GT": 1174,
1180
+ "-G-T-": 1175,
1181
+ "-G-TA": 1176,
1182
+ "-G-TC": 1177,
1183
+ "-G-TG": 1178,
1184
+ "-G-TT": 1179,
1185
+ "-GA--": 1180,
1186
+ "-GA-A": 1181,
1187
+ "-GA-C": 1182,
1188
+ "-GA-G": 1183,
1189
+ "-GA-T": 1184,
1190
+ "-GAA-": 1185,
1191
+ "-GAAA": 1186,
1192
+ "-GAAC": 1187,
1193
+ "-GAAG": 1188,
1194
+ "-GAAT": 1189,
1195
+ "-GAC-": 1190,
1196
+ "-GACA": 1191,
1197
+ "-GACC": 1192,
1198
+ "-GACG": 1193,
1199
+ "-GACT": 1194,
1200
+ "-GAG-": 1195,
1201
+ "-GAGA": 1196,
1202
+ "-GAGC": 1197,
1203
+ "-GAGG": 1198,
1204
+ "-GAGT": 1199,
1205
+ "-GAT-": 1200,
1206
+ "-GATA": 1201,
1207
+ "-GATC": 1202,
1208
+ "-GATG": 1203,
1209
+ "-GATT": 1204,
1210
+ "-GC--": 1205,
1211
+ "-GC-A": 1206,
1212
+ "-GC-C": 1207,
1213
+ "-GC-G": 1208,
1214
+ "-GC-T": 1209,
1215
+ "-GCA-": 1210,
1216
+ "-GCAA": 1211,
1217
+ "-GCAC": 1212,
1218
+ "-GCAG": 1213,
1219
+ "-GCAT": 1214,
1220
+ "-GCC-": 1215,
1221
+ "-GCCA": 1216,
1222
+ "-GCCC": 1217,
1223
+ "-GCCG": 1218,
1224
+ "-GCCT": 1219,
1225
+ "-GCG-": 1220,
1226
+ "-GCGA": 1221,
1227
+ "-GCGC": 1222,
1228
+ "-GCGG": 1223,
1229
+ "-GCGT": 1224,
1230
+ "-GCT-": 1225,
1231
+ "-GCTA": 1226,
1232
+ "-GCTC": 1227,
1233
+ "-GCTG": 1228,
1234
+ "-GCTT": 1229,
1235
+ "-GG--": 1230,
1236
+ "-GG-A": 1231,
1237
+ "-GG-C": 1232,
1238
+ "-GG-G": 1233,
1239
+ "-GG-T": 1234,
1240
+ "-GGA-": 1235,
1241
+ "-GGAA": 1236,
1242
+ "-GGAC": 1237,
1243
+ "-GGAG": 1238,
1244
+ "-GGAT": 1239,
1245
+ "-GGC-": 1240,
1246
+ "-GGCA": 1241,
1247
+ "-GGCC": 1242,
1248
+ "-GGCG": 1243,
1249
+ "-GGCT": 1244,
1250
+ "-GGG-": 1245,
1251
+ "-GGGA": 1246,
1252
+ "-GGGC": 1247,
1253
+ "-GGGG": 1248,
1254
+ "-GGGT": 1249,
1255
+ "-GGT-": 1250,
1256
+ "-GGTA": 1251,
1257
+ "-GGTC": 1252,
1258
+ "-GGTG": 1253,
1259
+ "-GGTT": 1254,
1260
+ "-GT--": 1255,
1261
+ "-GT-A": 1256,
1262
+ "-GT-C": 1257,
1263
+ "-GT-G": 1258,
1264
+ "-GT-T": 1259,
1265
+ "-GTA-": 1260,
1266
+ "-GTAA": 1261,
1267
+ "-GTAC": 1262,
1268
+ "-GTAG": 1263,
1269
+ "-GTAT": 1264,
1270
+ "-GTC-": 1265,
1271
+ "-GTCA": 1266,
1272
+ "-GTCC": 1267,
1273
+ "-GTCG": 1268,
1274
+ "-GTCT": 1269,
1275
+ "-GTG-": 1270,
1276
+ "-GTGA": 1271,
1277
+ "-GTGC": 1272,
1278
+ "-GTGG": 1273,
1279
+ "-GTGT": 1274,
1280
+ "-GTT-": 1275,
1281
+ "-GTTA": 1276,
1282
+ "-GTTC": 1277,
1283
+ "-GTTG": 1278,
1284
+ "-GTTT": 1279,
1285
+ "-T---": 1280,
1286
+ "-T--A": 1281,
1287
+ "-T--C": 1282,
1288
+ "-T--G": 1283,
1289
+ "-T--T": 1284,
1290
+ "-T-A-": 1285,
1291
+ "-T-AA": 1286,
1292
+ "-T-AC": 1287,
1293
+ "-T-AG": 1288,
1294
+ "-T-AT": 1289,
1295
+ "-T-C-": 1290,
1296
+ "-T-CA": 1291,
1297
+ "-T-CC": 1292,
1298
+ "-T-CG": 1293,
1299
+ "-T-CT": 1294,
1300
+ "-T-G-": 1295,
1301
+ "-T-GA": 1296,
1302
+ "-T-GC": 1297,
1303
+ "-T-GG": 1298,
1304
+ "-T-GT": 1299,
1305
+ "-T-T-": 1300,
1306
+ "-T-TA": 1301,
1307
+ "-T-TC": 1302,
1308
+ "-T-TG": 1303,
1309
+ "-T-TT": 1304,
1310
+ "-TA--": 1305,
1311
+ "-TA-A": 1306,
1312
+ "-TA-C": 1307,
1313
+ "-TA-G": 1308,
1314
+ "-TA-T": 1309,
1315
+ "-TAA-": 1310,
1316
+ "-TAAA": 1311,
1317
+ "-TAAC": 1312,
1318
+ "-TAAG": 1313,
1319
+ "-TAAT": 1314,
1320
+ "-TAC-": 1315,
1321
+ "-TACA": 1316,
1322
+ "-TACC": 1317,
1323
+ "-TACG": 1318,
1324
+ "-TACT": 1319,
1325
+ "-TAG-": 1320,
1326
+ "-TAGA": 1321,
1327
+ "-TAGC": 1322,
1328
+ "-TAGG": 1323,
1329
+ "-TAGT": 1324,
1330
+ "-TAT-": 1325,
1331
+ "-TATA": 1326,
1332
+ "-TATC": 1327,
1333
+ "-TATG": 1328,
1334
+ "-TATT": 1329,
1335
+ "-TC--": 1330,
1336
+ "-TC-A": 1331,
1337
+ "-TC-C": 1332,
1338
+ "-TC-G": 1333,
1339
+ "-TC-T": 1334,
1340
+ "-TCA-": 1335,
1341
+ "-TCAA": 1336,
1342
+ "-TCAC": 1337,
1343
+ "-TCAG": 1338,
1344
+ "-TCAT": 1339,
1345
+ "-TCC-": 1340,
1346
+ "-TCCA": 1341,
1347
+ "-TCCC": 1342,
1348
+ "-TCCG": 1343,
1349
+ "-TCCT": 1344,
1350
+ "-TCG-": 1345,
1351
+ "-TCGA": 1346,
1352
+ "-TCGC": 1347,
1353
+ "-TCGG": 1348,
1354
+ "-TCGT": 1349,
1355
+ "-TCT-": 1350,
1356
+ "-TCTA": 1351,
1357
+ "-TCTC": 1352,
1358
+ "-TCTG": 1353,
1359
+ "-TCTT": 1354,
1360
+ "-TG--": 1355,
1361
+ "-TG-A": 1356,
1362
+ "-TG-C": 1357,
1363
+ "-TG-G": 1358,
1364
+ "-TG-T": 1359,
1365
+ "-TGA-": 1360,
1366
+ "-TGAA": 1361,
1367
+ "-TGAC": 1362,
1368
+ "-TGAG": 1363,
1369
+ "-TGAT": 1364,
1370
+ "-TGC-": 1365,
1371
+ "-TGCA": 1366,
1372
+ "-TGCC": 1367,
1373
+ "-TGCG": 1368,
1374
+ "-TGCT": 1369,
1375
+ "-TGG-": 1370,
1376
+ "-TGGA": 1371,
1377
+ "-TGGC": 1372,
1378
+ "-TGGG": 1373,
1379
+ "-TGGT": 1374,
1380
+ "-TGT-": 1375,
1381
+ "-TGTA": 1376,
1382
+ "-TGTC": 1377,
1383
+ "-TGTG": 1378,
1384
+ "-TGTT": 1379,
1385
+ "-TT--": 1380,
1386
+ "-TT-A": 1381,
1387
+ "-TT-C": 1382,
1388
+ "-TT-G": 1383,
1389
+ "-TT-T": 1384,
1390
+ "-TTA-": 1385,
1391
+ "-TTAA": 1386,
1392
+ "-TTAC": 1387,
1393
+ "-TTAG": 1388,
1394
+ "-TTAT": 1389,
1395
+ "-TTC-": 1390,
1396
+ "-TTCA": 1391,
1397
+ "-TTCC": 1392,
1398
+ "-TTCG": 1393,
1399
+ "-TTCT": 1394,
1400
+ "-TTG-": 1395,
1401
+ "-TTGA": 1396,
1402
+ "-TTGC": 1397,
1403
+ "-TTGG": 1398,
1404
+ "-TTGT": 1399,
1405
+ "-TTT-": 1400,
1406
+ "-TTTA": 1401,
1407
+ "-TTTC": 1402,
1408
+ "-TTTG": 1403,
1409
+ "-TTTT": 1404,
1410
+ "A----": 1405,
1411
+ "A---A": 1406,
1412
+ "A---C": 1407,
1413
+ "A---G": 1408,
1414
+ "A---T": 1409,
1415
+ "A--A-": 1410,
1416
+ "A--AA": 1411,
1417
+ "A--AC": 1412,
1418
+ "A--AG": 1413,
1419
+ "A--AT": 1414,
1420
+ "A--C-": 1415,
1421
+ "A--CA": 1416,
1422
+ "A--CC": 1417,
1423
+ "A--CG": 1418,
1424
+ "A--CT": 1419,
1425
+ "A--G-": 1420,
1426
+ "A--GA": 1421,
1427
+ "A--GC": 1422,
1428
+ "A--GG": 1423,
1429
+ "A--GT": 1424,
1430
+ "A--T-": 1425,
1431
+ "A--TA": 1426,
1432
+ "A--TC": 1427,
1433
+ "A--TG": 1428,
1434
+ "A--TT": 1429,
1435
+ "A-A--": 1430,
1436
+ "A-A-A": 1431,
1437
+ "A-A-C": 1432,
1438
+ "A-A-G": 1433,
1439
+ "A-A-T": 1434,
1440
+ "A-AA-": 1435,
1441
+ "A-AAA": 1436,
1442
+ "A-AAC": 1437,
1443
+ "A-AAG": 1438,
1444
+ "A-AAT": 1439,
1445
+ "A-AC-": 1440,
1446
+ "A-ACA": 1441,
1447
+ "A-ACC": 1442,
1448
+ "A-ACG": 1443,
1449
+ "A-ACT": 1444,
1450
+ "A-AG-": 1445,
1451
+ "A-AGA": 1446,
1452
+ "A-AGC": 1447,
1453
+ "A-AGG": 1448,
1454
+ "A-AGT": 1449,
1455
+ "A-AT-": 1450,
1456
+ "A-ATA": 1451,
1457
+ "A-ATC": 1452,
1458
+ "A-ATG": 1453,
1459
+ "A-ATT": 1454,
1460
+ "A-C--": 1455,
1461
+ "A-C-A": 1456,
1462
+ "A-C-C": 1457,
1463
+ "A-C-G": 1458,
1464
+ "A-C-T": 1459,
1465
+ "A-CA-": 1460,
1466
+ "A-CAA": 1461,
1467
+ "A-CAC": 1462,
1468
+ "A-CAG": 1463,
1469
+ "A-CAT": 1464,
1470
+ "A-CC-": 1465,
1471
+ "A-CCA": 1466,
1472
+ "A-CCC": 1467,
1473
+ "A-CCG": 1468,
1474
+ "A-CCT": 1469,
1475
+ "A-CG-": 1470,
1476
+ "A-CGA": 1471,
1477
+ "A-CGC": 1472,
1478
+ "A-CGG": 1473,
1479
+ "A-CGT": 1474,
1480
+ "A-CT-": 1475,
1481
+ "A-CTA": 1476,
1482
+ "A-CTC": 1477,
1483
+ "A-CTG": 1478,
1484
+ "A-CTT": 1479,
1485
+ "A-G--": 1480,
1486
+ "A-G-A": 1481,
1487
+ "A-G-C": 1482,
1488
+ "A-G-G": 1483,
1489
+ "A-G-T": 1484,
1490
+ "A-GA-": 1485,
1491
+ "A-GAA": 1486,
1492
+ "A-GAC": 1487,
1493
+ "A-GAG": 1488,
1494
+ "A-GAT": 1489,
1495
+ "A-GC-": 1490,
1496
+ "A-GCA": 1491,
1497
+ "A-GCC": 1492,
1498
+ "A-GCG": 1493,
1499
+ "A-GCT": 1494,
1500
+ "A-GG-": 1495,
1501
+ "A-GGA": 1496,
1502
+ "A-GGC": 1497,
1503
+ "A-GGG": 1498,
1504
+ "A-GGT": 1499,
1505
+ "A-GT-": 1500,
1506
+ "A-GTA": 1501,
1507
+ "A-GTC": 1502,
1508
+ "A-GTG": 1503,
1509
+ "A-GTT": 1504,
1510
+ "A-T--": 1505,
1511
+ "A-T-A": 1506,
1512
+ "A-T-C": 1507,
1513
+ "A-T-G": 1508,
1514
+ "A-T-T": 1509,
1515
+ "A-TA-": 1510,
1516
+ "A-TAA": 1511,
1517
+ "A-TAC": 1512,
1518
+ "A-TAG": 1513,
1519
+ "A-TAT": 1514,
1520
+ "A-TC-": 1515,
1521
+ "A-TCA": 1516,
1522
+ "A-TCC": 1517,
1523
+ "A-TCG": 1518,
1524
+ "A-TCT": 1519,
1525
+ "A-TG-": 1520,
1526
+ "A-TGA": 1521,
1527
+ "A-TGC": 1522,
1528
+ "A-TGG": 1523,
1529
+ "A-TGT": 1524,
1530
+ "A-TT-": 1525,
1531
+ "A-TTA": 1526,
1532
+ "A-TTC": 1527,
1533
+ "A-TTG": 1528,
1534
+ "A-TTT": 1529,
1535
+ "AA---": 1530,
1536
+ "AA--A": 1531,
1537
+ "AA--C": 1532,
1538
+ "AA--G": 1533,
1539
+ "AA--T": 1534,
1540
+ "AA-A-": 1535,
1541
+ "AA-AA": 1536,
1542
+ "AA-AC": 1537,
1543
+ "AA-AG": 1538,
1544
+ "AA-AT": 1539,
1545
+ "AA-C-": 1540,
1546
+ "AA-CA": 1541,
1547
+ "AA-CC": 1542,
1548
+ "AA-CG": 1543,
1549
+ "AA-CT": 1544,
1550
+ "AA-G-": 1545,
1551
+ "AA-GA": 1546,
1552
+ "AA-GC": 1547,
1553
+ "AA-GG": 1548,
1554
+ "AA-GT": 1549,
1555
+ "AA-T-": 1550,
1556
+ "AA-TA": 1551,
1557
+ "AA-TC": 1552,
1558
+ "AA-TG": 1553,
1559
+ "AA-TT": 1554,
1560
+ "AAA--": 1555,
1561
+ "AAA-A": 1556,
1562
+ "AAA-C": 1557,
1563
+ "AAA-G": 1558,
1564
+ "AAA-T": 1559,
1565
+ "AAAA-": 1560,
1566
+ "AAAAA": 1561,
1567
+ "AAAAC": 1562,
1568
+ "AAAAG": 1563,
1569
+ "AAAAT": 1564,
1570
+ "AAAC-": 1565,
1571
+ "AAACA": 1566,
1572
+ "AAACC": 1567,
1573
+ "AAACG": 1568,
1574
+ "AAACT": 1569,
1575
+ "AAAG-": 1570,
1576
+ "AAAGA": 1571,
1577
+ "AAAGC": 1572,
1578
+ "AAAGG": 1573,
1579
+ "AAAGT": 1574,
1580
+ "AAAT-": 1575,
1581
+ "AAATA": 1576,
1582
+ "AAATC": 1577,
1583
+ "AAATG": 1578,
1584
+ "AAATT": 1579,
1585
+ "AAC--": 1580,
1586
+ "AAC-A": 1581,
1587
+ "AAC-C": 1582,
1588
+ "AAC-G": 1583,
1589
+ "AAC-T": 1584,
1590
+ "AACA-": 1585,
1591
+ "AACAA": 1586,
1592
+ "AACAC": 1587,
1593
+ "AACAG": 1588,
1594
+ "AACAT": 1589,
1595
+ "AACC-": 1590,
1596
+ "AACCA": 1591,
1597
+ "AACCC": 1592,
1598
+ "AACCG": 1593,
1599
+ "AACCT": 1594,
1600
+ "AACG-": 1595,
1601
+ "AACGA": 1596,
1602
+ "AACGC": 1597,
1603
+ "AACGG": 1598,
1604
+ "AACGT": 1599,
1605
+ "AACT-": 1600,
1606
+ "AACTA": 1601,
1607
+ "AACTC": 1602,
1608
+ "AACTG": 1603,
1609
+ "AACTT": 1604,
1610
+ "AAG--": 1605,
1611
+ "AAG-A": 1606,
1612
+ "AAG-C": 1607,
1613
+ "AAG-G": 1608,
1614
+ "AAG-T": 1609,
1615
+ "AAGA-": 1610,
1616
+ "AAGAA": 1611,
1617
+ "AAGAC": 1612,
1618
+ "AAGAG": 1613,
1619
+ "AAGAT": 1614,
1620
+ "AAGC-": 1615,
1621
+ "AAGCA": 1616,
1622
+ "AAGCC": 1617,
1623
+ "AAGCG": 1618,
1624
+ "AAGCT": 1619,
1625
+ "AAGG-": 1620,
1626
+ "AAGGA": 1621,
1627
+ "AAGGC": 1622,
1628
+ "AAGGG": 1623,
1629
+ "AAGGT": 1624,
1630
+ "AAGT-": 1625,
1631
+ "AAGTA": 1626,
1632
+ "AAGTC": 1627,
1633
+ "AAGTG": 1628,
1634
+ "AAGTT": 1629,
1635
+ "AAT--": 1630,
1636
+ "AAT-A": 1631,
1637
+ "AAT-C": 1632,
1638
+ "AAT-G": 1633,
1639
+ "AAT-T": 1634,
1640
+ "AATA-": 1635,
1641
+ "AATAA": 1636,
1642
+ "AATAC": 1637,
1643
+ "AATAG": 1638,
1644
+ "AATAT": 1639,
1645
+ "AATC-": 1640,
1646
+ "AATCA": 1641,
1647
+ "AATCC": 1642,
1648
+ "AATCG": 1643,
1649
+ "AATCT": 1644,
1650
+ "AATG-": 1645,
1651
+ "AATGA": 1646,
1652
+ "AATGC": 1647,
1653
+ "AATGG": 1648,
1654
+ "AATGT": 1649,
1655
+ "AATT-": 1650,
1656
+ "AATTA": 1651,
1657
+ "AATTC": 1652,
1658
+ "AATTG": 1653,
1659
+ "AATTT": 1654,
1660
+ "AC---": 1655,
1661
+ "AC--A": 1656,
1662
+ "AC--C": 1657,
1663
+ "AC--G": 1658,
1664
+ "AC--T": 1659,
1665
+ "AC-A-": 1660,
1666
+ "AC-AA": 1661,
1667
+ "AC-AC": 1662,
1668
+ "AC-AG": 1663,
1669
+ "AC-AT": 1664,
1670
+ "AC-C-": 1665,
1671
+ "AC-CA": 1666,
1672
+ "AC-CC": 1667,
1673
+ "AC-CG": 1668,
1674
+ "AC-CT": 1669,
1675
+ "AC-G-": 1670,
1676
+ "AC-GA": 1671,
1677
+ "AC-GC": 1672,
1678
+ "AC-GG": 1673,
1679
+ "AC-GT": 1674,
1680
+ "AC-T-": 1675,
1681
+ "AC-TA": 1676,
1682
+ "AC-TC": 1677,
1683
+ "AC-TG": 1678,
1684
+ "AC-TT": 1679,
1685
+ "ACA--": 1680,
1686
+ "ACA-A": 1681,
1687
+ "ACA-C": 1682,
1688
+ "ACA-G": 1683,
1689
+ "ACA-T": 1684,
1690
+ "ACAA-": 1685,
1691
+ "ACAAA": 1686,
1692
+ "ACAAC": 1687,
1693
+ "ACAAG": 1688,
1694
+ "ACAAT": 1689,
1695
+ "ACAC-": 1690,
1696
+ "ACACA": 1691,
1697
+ "ACACC": 1692,
1698
+ "ACACG": 1693,
1699
+ "ACACT": 1694,
1700
+ "ACAG-": 1695,
1701
+ "ACAGA": 1696,
1702
+ "ACAGC": 1697,
1703
+ "ACAGG": 1698,
1704
+ "ACAGT": 1699,
1705
+ "ACAT-": 1700,
1706
+ "ACATA": 1701,
1707
+ "ACATC": 1702,
1708
+ "ACATG": 1703,
1709
+ "ACATT": 1704,
1710
+ "ACC--": 1705,
1711
+ "ACC-A": 1706,
1712
+ "ACC-C": 1707,
1713
+ "ACC-G": 1708,
1714
+ "ACC-T": 1709,
1715
+ "ACCA-": 1710,
1716
+ "ACCAA": 1711,
1717
+ "ACCAC": 1712,
1718
+ "ACCAG": 1713,
1719
+ "ACCAT": 1714,
1720
+ "ACCC-": 1715,
1721
+ "ACCCA": 1716,
1722
+ "ACCCC": 1717,
1723
+ "ACCCG": 1718,
1724
+ "ACCCT": 1719,
1725
+ "ACCG-": 1720,
1726
+ "ACCGA": 1721,
1727
+ "ACCGC": 1722,
1728
+ "ACCGG": 1723,
1729
+ "ACCGT": 1724,
1730
+ "ACCT-": 1725,
1731
+ "ACCTA": 1726,
1732
+ "ACCTC": 1727,
1733
+ "ACCTG": 1728,
1734
+ "ACCTT": 1729,
1735
+ "ACG--": 1730,
1736
+ "ACG-A": 1731,
1737
+ "ACG-C": 1732,
1738
+ "ACG-G": 1733,
1739
+ "ACG-T": 1734,
1740
+ "ACGA-": 1735,
1741
+ "ACGAA": 1736,
1742
+ "ACGAC": 1737,
1743
+ "ACGAG": 1738,
1744
+ "ACGAT": 1739,
1745
+ "ACGC-": 1740,
1746
+ "ACGCA": 1741,
1747
+ "ACGCC": 1742,
1748
+ "ACGCG": 1743,
1749
+ "ACGCT": 1744,
1750
+ "ACGG-": 1745,
1751
+ "ACGGA": 1746,
1752
+ "ACGGC": 1747,
1753
+ "ACGGG": 1748,
1754
+ "ACGGT": 1749,
1755
+ "ACGT-": 1750,
1756
+ "ACGTA": 1751,
1757
+ "ACGTC": 1752,
1758
+ "ACGTG": 1753,
1759
+ "ACGTT": 1754,
1760
+ "ACT--": 1755,
1761
+ "ACT-A": 1756,
1762
+ "ACT-C": 1757,
1763
+ "ACT-G": 1758,
1764
+ "ACT-T": 1759,
1765
+ "ACTA-": 1760,
1766
+ "ACTAA": 1761,
1767
+ "ACTAC": 1762,
1768
+ "ACTAG": 1763,
1769
+ "ACTAT": 1764,
1770
+ "ACTC-": 1765,
1771
+ "ACTCA": 1766,
1772
+ "ACTCC": 1767,
1773
+ "ACTCG": 1768,
1774
+ "ACTCT": 1769,
1775
+ "ACTG-": 1770,
1776
+ "ACTGA": 1771,
1777
+ "ACTGC": 1772,
1778
+ "ACTGG": 1773,
1779
+ "ACTGT": 1774,
1780
+ "ACTT-": 1775,
1781
+ "ACTTA": 1776,
1782
+ "ACTTC": 1777,
1783
+ "ACTTG": 1778,
1784
+ "ACTTT": 1779,
1785
+ "AG---": 1780,
1786
+ "AG--A": 1781,
1787
+ "AG--C": 1782,
1788
+ "AG--G": 1783,
1789
+ "AG--T": 1784,
1790
+ "AG-A-": 1785,
1791
+ "AG-AA": 1786,
1792
+ "AG-AC": 1787,
1793
+ "AG-AG": 1788,
1794
+ "AG-AT": 1789,
1795
+ "AG-C-": 1790,
1796
+ "AG-CA": 1791,
1797
+ "AG-CC": 1792,
1798
+ "AG-CG": 1793,
1799
+ "AG-CT": 1794,
1800
+ "AG-G-": 1795,
1801
+ "AG-GA": 1796,
1802
+ "AG-GC": 1797,
1803
+ "AG-GG": 1798,
1804
+ "AG-GT": 1799,
1805
+ "AG-T-": 1800,
1806
+ "AG-TA": 1801,
1807
+ "AG-TC": 1802,
1808
+ "AG-TG": 1803,
1809
+ "AG-TT": 1804,
1810
+ "AGA--": 1805,
1811
+ "AGA-A": 1806,
1812
+ "AGA-C": 1807,
1813
+ "AGA-G": 1808,
1814
+ "AGA-T": 1809,
1815
+ "AGAA-": 1810,
1816
+ "AGAAA": 1811,
1817
+ "AGAAC": 1812,
1818
+ "AGAAG": 1813,
1819
+ "AGAAT": 1814,
1820
+ "AGAC-": 1815,
1821
+ "AGACA": 1816,
1822
+ "AGACC": 1817,
1823
+ "AGACG": 1818,
1824
+ "AGACT": 1819,
1825
+ "AGAG-": 1820,
1826
+ "AGAGA": 1821,
1827
+ "AGAGC": 1822,
1828
+ "AGAGG": 1823,
1829
+ "AGAGT": 1824,
1830
+ "AGAT-": 1825,
1831
+ "AGATA": 1826,
1832
+ "AGATC": 1827,
1833
+ "AGATG": 1828,
1834
+ "AGATT": 1829,
1835
+ "AGC--": 1830,
1836
+ "AGC-A": 1831,
1837
+ "AGC-C": 1832,
1838
+ "AGC-G": 1833,
1839
+ "AGC-T": 1834,
1840
+ "AGCA-": 1835,
1841
+ "AGCAA": 1836,
1842
+ "AGCAC": 1837,
1843
+ "AGCAG": 1838,
1844
+ "AGCAT": 1839,
1845
+ "AGCC-": 1840,
1846
+ "AGCCA": 1841,
1847
+ "AGCCC": 1842,
1848
+ "AGCCG": 1843,
1849
+ "AGCCT": 1844,
1850
+ "AGCG-": 1845,
1851
+ "AGCGA": 1846,
1852
+ "AGCGC": 1847,
1853
+ "AGCGG": 1848,
1854
+ "AGCGT": 1849,
1855
+ "AGCT-": 1850,
1856
+ "AGCTA": 1851,
1857
+ "AGCTC": 1852,
1858
+ "AGCTG": 1853,
1859
+ "AGCTT": 1854,
1860
+ "AGG--": 1855,
1861
+ "AGG-A": 1856,
1862
+ "AGG-C": 1857,
1863
+ "AGG-G": 1858,
1864
+ "AGG-T": 1859,
1865
+ "AGGA-": 1860,
1866
+ "AGGAA": 1861,
1867
+ "AGGAC": 1862,
1868
+ "AGGAG": 1863,
1869
+ "AGGAT": 1864,
1870
+ "AGGC-": 1865,
1871
+ "AGGCA": 1866,
1872
+ "AGGCC": 1867,
1873
+ "AGGCG": 1868,
1874
+ "AGGCT": 1869,
1875
+ "AGGG-": 1870,
1876
+ "AGGGA": 1871,
1877
+ "AGGGC": 1872,
1878
+ "AGGGG": 1873,
1879
+ "AGGGT": 1874,
1880
+ "AGGT-": 1875,
1881
+ "AGGTA": 1876,
1882
+ "AGGTC": 1877,
1883
+ "AGGTG": 1878,
1884
+ "AGGTT": 1879,
1885
+ "AGT--": 1880,
1886
+ "AGT-A": 1881,
1887
+ "AGT-C": 1882,
1888
+ "AGT-G": 1883,
1889
+ "AGT-T": 1884,
1890
+ "AGTA-": 1885,
1891
+ "AGTAA": 1886,
1892
+ "AGTAC": 1887,
1893
+ "AGTAG": 1888,
1894
+ "AGTAT": 1889,
1895
+ "AGTC-": 1890,
1896
+ "AGTCA": 1891,
1897
+ "AGTCC": 1892,
1898
+ "AGTCG": 1893,
1899
+ "AGTCT": 1894,
1900
+ "AGTG-": 1895,
1901
+ "AGTGA": 1896,
1902
+ "AGTGC": 1897,
1903
+ "AGTGG": 1898,
1904
+ "AGTGT": 1899,
1905
+ "AGTT-": 1900,
1906
+ "AGTTA": 1901,
1907
+ "AGTTC": 1902,
1908
+ "AGTTG": 1903,
1909
+ "AGTTT": 1904,
1910
+ "AT---": 1905,
1911
+ "AT--A": 1906,
1912
+ "AT--C": 1907,
1913
+ "AT--G": 1908,
1914
+ "AT--T": 1909,
1915
+ "AT-A-": 1910,
1916
+ "AT-AA": 1911,
1917
+ "AT-AC": 1912,
1918
+ "AT-AG": 1913,
1919
+ "AT-AT": 1914,
1920
+ "AT-C-": 1915,
1921
+ "AT-CA": 1916,
1922
+ "AT-CC": 1917,
1923
+ "AT-CG": 1918,
1924
+ "AT-CT": 1919,
1925
+ "AT-G-": 1920,
1926
+ "AT-GA": 1921,
1927
+ "AT-GC": 1922,
1928
+ "AT-GG": 1923,
1929
+ "AT-GT": 1924,
1930
+ "AT-T-": 1925,
1931
+ "AT-TA": 1926,
1932
+ "AT-TC": 1927,
1933
+ "AT-TG": 1928,
1934
+ "AT-TT": 1929,
1935
+ "ATA--": 1930,
1936
+ "ATA-A": 1931,
1937
+ "ATA-C": 1932,
1938
+ "ATA-G": 1933,
1939
+ "ATA-T": 1934,
1940
+ "ATAA-": 1935,
1941
+ "ATAAA": 1936,
1942
+ "ATAAC": 1937,
1943
+ "ATAAG": 1938,
1944
+ "ATAAT": 1939,
1945
+ "ATAC-": 1940,
1946
+ "ATACA": 1941,
1947
+ "ATACC": 1942,
1948
+ "ATACG": 1943,
1949
+ "ATACT": 1944,
1950
+ "ATAG-": 1945,
1951
+ "ATAGA": 1946,
1952
+ "ATAGC": 1947,
1953
+ "ATAGG": 1948,
1954
+ "ATAGT": 1949,
1955
+ "ATAT-": 1950,
1956
+ "ATATA": 1951,
1957
+ "ATATC": 1952,
1958
+ "ATATG": 1953,
1959
+ "ATATT": 1954,
1960
+ "ATC--": 1955,
1961
+ "ATC-A": 1956,
1962
+ "ATC-C": 1957,
1963
+ "ATC-G": 1958,
1964
+ "ATC-T": 1959,
1965
+ "ATCA-": 1960,
1966
+ "ATCAA": 1961,
1967
+ "ATCAC": 1962,
1968
+ "ATCAG": 1963,
1969
+ "ATCAT": 1964,
1970
+ "ATCC-": 1965,
1971
+ "ATCCA": 1966,
1972
+ "ATCCC": 1967,
1973
+ "ATCCG": 1968,
1974
+ "ATCCT": 1969,
1975
+ "ATCG-": 1970,
1976
+ "ATCGA": 1971,
1977
+ "ATCGC": 1972,
1978
+ "ATCGG": 1973,
1979
+ "ATCGT": 1974,
1980
+ "ATCT-": 1975,
1981
+ "ATCTA": 1976,
1982
+ "ATCTC": 1977,
1983
+ "ATCTG": 1978,
1984
+ "ATCTT": 1979,
1985
+ "ATG--": 1980,
1986
+ "ATG-A": 1981,
1987
+ "ATG-C": 1982,
1988
+ "ATG-G": 1983,
1989
+ "ATG-T": 1984,
1990
+ "ATGA-": 1985,
1991
+ "ATGAA": 1986,
1992
+ "ATGAC": 1987,
1993
+ "ATGAG": 1988,
1994
+ "ATGAT": 1989,
1995
+ "ATGC-": 1990,
1996
+ "ATGCA": 1991,
1997
+ "ATGCC": 1992,
1998
+ "ATGCG": 1993,
1999
+ "ATGCT": 1994,
2000
+ "ATGG-": 1995,
2001
+ "ATGGA": 1996,
2002
+ "ATGGC": 1997,
2003
+ "ATGGG": 1998,
2004
+ "ATGGT": 1999,
2005
+ "ATGT-": 2000,
2006
+ "ATGTA": 2001,
2007
+ "ATGTC": 2002,
2008
+ "ATGTG": 2003,
2009
+ "ATGTT": 2004,
2010
+ "ATT--": 2005,
2011
+ "ATT-A": 2006,
2012
+ "ATT-C": 2007,
2013
+ "ATT-G": 2008,
2014
+ "ATT-T": 2009,
2015
+ "ATTA-": 2010,
2016
+ "ATTAA": 2011,
2017
+ "ATTAC": 2012,
2018
+ "ATTAG": 2013,
2019
+ "ATTAT": 2014,
2020
+ "ATTC-": 2015,
2021
+ "ATTCA": 2016,
2022
+ "ATTCC": 2017,
2023
+ "ATTCG": 2018,
2024
+ "ATTCT": 2019,
2025
+ "ATTG-": 2020,
2026
+ "ATTGA": 2021,
2027
+ "ATTGC": 2022,
2028
+ "ATTGG": 2023,
2029
+ "ATTGT": 2024,
2030
+ "ATTT-": 2025,
2031
+ "ATTTA": 2026,
2032
+ "ATTTC": 2027,
2033
+ "ATTTG": 2028,
2034
+ "ATTTT": 2029,
2035
+ "C----": 2030,
2036
+ "C---A": 2031,
2037
+ "C---C": 2032,
2038
+ "C---G": 2033,
2039
+ "C---T": 2034,
2040
+ "C--A-": 2035,
2041
+ "C--AA": 2036,
2042
+ "C--AC": 2037,
2043
+ "C--AG": 2038,
2044
+ "C--AT": 2039,
2045
+ "C--C-": 2040,
2046
+ "C--CA": 2041,
2047
+ "C--CC": 2042,
2048
+ "C--CG": 2043,
2049
+ "C--CT": 2044,
2050
+ "C--G-": 2045,
2051
+ "C--GA": 2046,
2052
+ "C--GC": 2047,
2053
+ "C--GG": 2048,
2054
+ "C--GT": 2049,
2055
+ "C--T-": 2050,
2056
+ "C--TA": 2051,
2057
+ "C--TC": 2052,
2058
+ "C--TG": 2053,
2059
+ "C--TT": 2054,
2060
+ "C-A--": 2055,
2061
+ "C-A-A": 2056,
2062
+ "C-A-C": 2057,
2063
+ "C-A-G": 2058,
2064
+ "C-A-T": 2059,
2065
+ "C-AA-": 2060,
2066
+ "C-AAA": 2061,
2067
+ "C-AAC": 2062,
2068
+ "C-AAG": 2063,
2069
+ "C-AAT": 2064,
2070
+ "C-AC-": 2065,
2071
+ "C-ACA": 2066,
2072
+ "C-ACC": 2067,
2073
+ "C-ACG": 2068,
2074
+ "C-ACT": 2069,
2075
+ "C-AG-": 2070,
2076
+ "C-AGA": 2071,
2077
+ "C-AGC": 2072,
2078
+ "C-AGG": 2073,
2079
+ "C-AGT": 2074,
2080
+ "C-AT-": 2075,
2081
+ "C-ATA": 2076,
2082
+ "C-ATC": 2077,
2083
+ "C-ATG": 2078,
2084
+ "C-ATT": 2079,
2085
+ "C-C--": 2080,
2086
+ "C-C-A": 2081,
2087
+ "C-C-C": 2082,
2088
+ "C-C-G": 2083,
2089
+ "C-C-T": 2084,
2090
+ "C-CA-": 2085,
2091
+ "C-CAA": 2086,
2092
+ "C-CAC": 2087,
2093
+ "C-CAG": 2088,
2094
+ "C-CAT": 2089,
2095
+ "C-CC-": 2090,
2096
+ "C-CCA": 2091,
2097
+ "C-CCC": 2092,
2098
+ "C-CCG": 2093,
2099
+ "C-CCT": 2094,
2100
+ "C-CG-": 2095,
2101
+ "C-CGA": 2096,
2102
+ "C-CGC": 2097,
2103
+ "C-CGG": 2098,
2104
+ "C-CGT": 2099,
2105
+ "C-CT-": 2100,
2106
+ "C-CTA": 2101,
2107
+ "C-CTC": 2102,
2108
+ "C-CTG": 2103,
2109
+ "C-CTT": 2104,
2110
+ "C-G--": 2105,
2111
+ "C-G-A": 2106,
2112
+ "C-G-C": 2107,
2113
+ "C-G-G": 2108,
2114
+ "C-G-T": 2109,
2115
+ "C-GA-": 2110,
2116
+ "C-GAA": 2111,
2117
+ "C-GAC": 2112,
2118
+ "C-GAG": 2113,
2119
+ "C-GAT": 2114,
2120
+ "C-GC-": 2115,
2121
+ "C-GCA": 2116,
2122
+ "C-GCC": 2117,
2123
+ "C-GCG": 2118,
2124
+ "C-GCT": 2119,
2125
+ "C-GG-": 2120,
2126
+ "C-GGA": 2121,
2127
+ "C-GGC": 2122,
2128
+ "C-GGG": 2123,
2129
+ "C-GGT": 2124,
2130
+ "C-GT-": 2125,
2131
+ "C-GTA": 2126,
2132
+ "C-GTC": 2127,
2133
+ "C-GTG": 2128,
2134
+ "C-GTT": 2129,
2135
+ "C-T--": 2130,
2136
+ "C-T-A": 2131,
2137
+ "C-T-C": 2132,
2138
+ "C-T-G": 2133,
2139
+ "C-T-T": 2134,
2140
+ "C-TA-": 2135,
2141
+ "C-TAA": 2136,
2142
+ "C-TAC": 2137,
2143
+ "C-TAG": 2138,
2144
+ "C-TAT": 2139,
2145
+ "C-TC-": 2140,
2146
+ "C-TCA": 2141,
2147
+ "C-TCC": 2142,
2148
+ "C-TCG": 2143,
2149
+ "C-TCT": 2144,
2150
+ "C-TG-": 2145,
2151
+ "C-TGA": 2146,
2152
+ "C-TGC": 2147,
2153
+ "C-TGG": 2148,
2154
+ "C-TGT": 2149,
2155
+ "C-TT-": 2150,
2156
+ "C-TTA": 2151,
2157
+ "C-TTC": 2152,
2158
+ "C-TTG": 2153,
2159
+ "C-TTT": 2154,
2160
+ "CA---": 2155,
2161
+ "CA--A": 2156,
2162
+ "CA--C": 2157,
2163
+ "CA--G": 2158,
2164
+ "CA--T": 2159,
2165
+ "CA-A-": 2160,
2166
+ "CA-AA": 2161,
2167
+ "CA-AC": 2162,
2168
+ "CA-AG": 2163,
2169
+ "CA-AT": 2164,
2170
+ "CA-C-": 2165,
2171
+ "CA-CA": 2166,
2172
+ "CA-CC": 2167,
2173
+ "CA-CG": 2168,
2174
+ "CA-CT": 2169,
2175
+ "CA-G-": 2170,
2176
+ "CA-GA": 2171,
2177
+ "CA-GC": 2172,
2178
+ "CA-GG": 2173,
2179
+ "CA-GT": 2174,
2180
+ "CA-T-": 2175,
2181
+ "CA-TA": 2176,
2182
+ "CA-TC": 2177,
2183
+ "CA-TG": 2178,
2184
+ "CA-TT": 2179,
2185
+ "CAA--": 2180,
2186
+ "CAA-A": 2181,
2187
+ "CAA-C": 2182,
2188
+ "CAA-G": 2183,
2189
+ "CAA-T": 2184,
2190
+ "CAAA-": 2185,
2191
+ "CAAAA": 2186,
2192
+ "CAAAC": 2187,
2193
+ "CAAAG": 2188,
2194
+ "CAAAT": 2189,
2195
+ "CAAC-": 2190,
2196
+ "CAACA": 2191,
2197
+ "CAACC": 2192,
2198
+ "CAACG": 2193,
2199
+ "CAACT": 2194,
2200
+ "CAAG-": 2195,
2201
+ "CAAGA": 2196,
2202
+ "CAAGC": 2197,
2203
+ "CAAGG": 2198,
2204
+ "CAAGT": 2199,
2205
+ "CAAT-": 2200,
2206
+ "CAATA": 2201,
2207
+ "CAATC": 2202,
2208
+ "CAATG": 2203,
2209
+ "CAATT": 2204,
2210
+ "CAC--": 2205,
2211
+ "CAC-A": 2206,
2212
+ "CAC-C": 2207,
2213
+ "CAC-G": 2208,
2214
+ "CAC-T": 2209,
2215
+ "CACA-": 2210,
2216
+ "CACAA": 2211,
2217
+ "CACAC": 2212,
2218
+ "CACAG": 2213,
2219
+ "CACAT": 2214,
2220
+ "CACC-": 2215,
2221
+ "CACCA": 2216,
2222
+ "CACCC": 2217,
2223
+ "CACCG": 2218,
2224
+ "CACCT": 2219,
2225
+ "CACG-": 2220,
2226
+ "CACGA": 2221,
2227
+ "CACGC": 2222,
2228
+ "CACGG": 2223,
2229
+ "CACGT": 2224,
2230
+ "CACT-": 2225,
2231
+ "CACTA": 2226,
2232
+ "CACTC": 2227,
2233
+ "CACTG": 2228,
2234
+ "CACTT": 2229,
2235
+ "CAG--": 2230,
2236
+ "CAG-A": 2231,
2237
+ "CAG-C": 2232,
2238
+ "CAG-G": 2233,
2239
+ "CAG-T": 2234,
2240
+ "CAGA-": 2235,
2241
+ "CAGAA": 2236,
2242
+ "CAGAC": 2237,
2243
+ "CAGAG": 2238,
2244
+ "CAGAT": 2239,
2245
+ "CAGC-": 2240,
2246
+ "CAGCA": 2241,
2247
+ "CAGCC": 2242,
2248
+ "CAGCG": 2243,
2249
+ "CAGCT": 2244,
2250
+ "CAGG-": 2245,
2251
+ "CAGGA": 2246,
2252
+ "CAGGC": 2247,
2253
+ "CAGGG": 2248,
2254
+ "CAGGT": 2249,
2255
+ "CAGT-": 2250,
2256
+ "CAGTA": 2251,
2257
+ "CAGTC": 2252,
2258
+ "CAGTG": 2253,
2259
+ "CAGTT": 2254,
2260
+ "CAT--": 2255,
2261
+ "CAT-A": 2256,
2262
+ "CAT-C": 2257,
2263
+ "CAT-G": 2258,
2264
+ "CAT-T": 2259,
2265
+ "CATA-": 2260,
2266
+ "CATAA": 2261,
2267
+ "CATAC": 2262,
2268
+ "CATAG": 2263,
2269
+ "CATAT": 2264,
2270
+ "CATC-": 2265,
2271
+ "CATCA": 2266,
2272
+ "CATCC": 2267,
2273
+ "CATCG": 2268,
2274
+ "CATCT": 2269,
2275
+ "CATG-": 2270,
2276
+ "CATGA": 2271,
2277
+ "CATGC": 2272,
2278
+ "CATGG": 2273,
2279
+ "CATGT": 2274,
2280
+ "CATT-": 2275,
2281
+ "CATTA": 2276,
2282
+ "CATTC": 2277,
2283
+ "CATTG": 2278,
2284
+ "CATTT": 2279,
2285
+ "CC---": 2280,
2286
+ "CC--A": 2281,
2287
+ "CC--C": 2282,
2288
+ "CC--G": 2283,
2289
+ "CC--T": 2284,
2290
+ "CC-A-": 2285,
2291
+ "CC-AA": 2286,
2292
+ "CC-AC": 2287,
2293
+ "CC-AG": 2288,
2294
+ "CC-AT": 2289,
2295
+ "CC-C-": 2290,
2296
+ "CC-CA": 2291,
2297
+ "CC-CC": 2292,
2298
+ "CC-CG": 2293,
2299
+ "CC-CT": 2294,
2300
+ "CC-G-": 2295,
2301
+ "CC-GA": 2296,
2302
+ "CC-GC": 2297,
2303
+ "CC-GG": 2298,
2304
+ "CC-GT": 2299,
2305
+ "CC-T-": 2300,
2306
+ "CC-TA": 2301,
2307
+ "CC-TC": 2302,
2308
+ "CC-TG": 2303,
2309
+ "CC-TT": 2304,
2310
+ "CCA--": 2305,
2311
+ "CCA-A": 2306,
2312
+ "CCA-C": 2307,
2313
+ "CCA-G": 2308,
2314
+ "CCA-T": 2309,
2315
+ "CCAA-": 2310,
2316
+ "CCAAA": 2311,
2317
+ "CCAAC": 2312,
2318
+ "CCAAG": 2313,
2319
+ "CCAAT": 2314,
2320
+ "CCAC-": 2315,
2321
+ "CCACA": 2316,
2322
+ "CCACC": 2317,
2323
+ "CCACG": 2318,
2324
+ "CCACT": 2319,
2325
+ "CCAG-": 2320,
2326
+ "CCAGA": 2321,
2327
+ "CCAGC": 2322,
2328
+ "CCAGG": 2323,
2329
+ "CCAGT": 2324,
2330
+ "CCAT-": 2325,
2331
+ "CCATA": 2326,
2332
+ "CCATC": 2327,
2333
+ "CCATG": 2328,
2334
+ "CCATT": 2329,
2335
+ "CCC--": 2330,
2336
+ "CCC-A": 2331,
2337
+ "CCC-C": 2332,
2338
+ "CCC-G": 2333,
2339
+ "CCC-T": 2334,
2340
+ "CCCA-": 2335,
2341
+ "CCCAA": 2336,
2342
+ "CCCAC": 2337,
2343
+ "CCCAG": 2338,
2344
+ "CCCAT": 2339,
2345
+ "CCCC-": 2340,
2346
+ "CCCCA": 2341,
2347
+ "CCCCC": 2342,
2348
+ "CCCCG": 2343,
2349
+ "CCCCT": 2344,
2350
+ "CCCG-": 2345,
2351
+ "CCCGA": 2346,
2352
+ "CCCGC": 2347,
2353
+ "CCCGG": 2348,
2354
+ "CCCGT": 2349,
2355
+ "CCCT-": 2350,
2356
+ "CCCTA": 2351,
2357
+ "CCCTC": 2352,
2358
+ "CCCTG": 2353,
2359
+ "CCCTT": 2354,
2360
+ "CCG--": 2355,
2361
+ "CCG-A": 2356,
2362
+ "CCG-C": 2357,
2363
+ "CCG-G": 2358,
2364
+ "CCG-T": 2359,
2365
+ "CCGA-": 2360,
2366
+ "CCGAA": 2361,
2367
+ "CCGAC": 2362,
2368
+ "CCGAG": 2363,
2369
+ "CCGAT": 2364,
2370
+ "CCGC-": 2365,
2371
+ "CCGCA": 2366,
2372
+ "CCGCC": 2367,
2373
+ "CCGCG": 2368,
2374
+ "CCGCT": 2369,
2375
+ "CCGG-": 2370,
2376
+ "CCGGA": 2371,
2377
+ "CCGGC": 2372,
2378
+ "CCGGG": 2373,
2379
+ "CCGGT": 2374,
2380
+ "CCGT-": 2375,
2381
+ "CCGTA": 2376,
2382
+ "CCGTC": 2377,
2383
+ "CCGTG": 2378,
2384
+ "CCGTT": 2379,
2385
+ "CCT--": 2380,
2386
+ "CCT-A": 2381,
2387
+ "CCT-C": 2382,
2388
+ "CCT-G": 2383,
2389
+ "CCT-T": 2384,
2390
+ "CCTA-": 2385,
2391
+ "CCTAA": 2386,
2392
+ "CCTAC": 2387,
2393
+ "CCTAG": 2388,
2394
+ "CCTAT": 2389,
2395
+ "CCTC-": 2390,
2396
+ "CCTCA": 2391,
2397
+ "CCTCC": 2392,
2398
+ "CCTCG": 2393,
2399
+ "CCTCT": 2394,
2400
+ "CCTG-": 2395,
2401
+ "CCTGA": 2396,
2402
+ "CCTGC": 2397,
2403
+ "CCTGG": 2398,
2404
+ "CCTGT": 2399,
2405
+ "CCTT-": 2400,
2406
+ "CCTTA": 2401,
2407
+ "CCTTC": 2402,
2408
+ "CCTTG": 2403,
2409
+ "CCTTT": 2404,
2410
+ "CG---": 2405,
2411
+ "CG--A": 2406,
2412
+ "CG--C": 2407,
2413
+ "CG--G": 2408,
2414
+ "CG--T": 2409,
2415
+ "CG-A-": 2410,
2416
+ "CG-AA": 2411,
2417
+ "CG-AC": 2412,
2418
+ "CG-AG": 2413,
2419
+ "CG-AT": 2414,
2420
+ "CG-C-": 2415,
2421
+ "CG-CA": 2416,
2422
+ "CG-CC": 2417,
2423
+ "CG-CG": 2418,
2424
+ "CG-CT": 2419,
2425
+ "CG-G-": 2420,
2426
+ "CG-GA": 2421,
2427
+ "CG-GC": 2422,
2428
+ "CG-GG": 2423,
2429
+ "CG-GT": 2424,
2430
+ "CG-T-": 2425,
2431
+ "CG-TA": 2426,
2432
+ "CG-TC": 2427,
2433
+ "CG-TG": 2428,
2434
+ "CG-TT": 2429,
2435
+ "CGA--": 2430,
2436
+ "CGA-A": 2431,
2437
+ "CGA-C": 2432,
2438
+ "CGA-G": 2433,
2439
+ "CGA-T": 2434,
2440
+ "CGAA-": 2435,
2441
+ "CGAAA": 2436,
2442
+ "CGAAC": 2437,
2443
+ "CGAAG": 2438,
2444
+ "CGAAT": 2439,
2445
+ "CGAC-": 2440,
2446
+ "CGACA": 2441,
2447
+ "CGACC": 2442,
2448
+ "CGACG": 2443,
2449
+ "CGACT": 2444,
2450
+ "CGAG-": 2445,
2451
+ "CGAGA": 2446,
2452
+ "CGAGC": 2447,
2453
+ "CGAGG": 2448,
2454
+ "CGAGT": 2449,
2455
+ "CGAT-": 2450,
2456
+ "CGATA": 2451,
2457
+ "CGATC": 2452,
2458
+ "CGATG": 2453,
2459
+ "CGATT": 2454,
2460
+ "CGC--": 2455,
2461
+ "CGC-A": 2456,
2462
+ "CGC-C": 2457,
2463
+ "CGC-G": 2458,
2464
+ "CGC-T": 2459,
2465
+ "CGCA-": 2460,
2466
+ "CGCAA": 2461,
2467
+ "CGCAC": 2462,
2468
+ "CGCAG": 2463,
2469
+ "CGCAT": 2464,
2470
+ "CGCC-": 2465,
2471
+ "CGCCA": 2466,
2472
+ "CGCCC": 2467,
2473
+ "CGCCG": 2468,
2474
+ "CGCCT": 2469,
2475
+ "CGCG-": 2470,
2476
+ "CGCGA": 2471,
2477
+ "CGCGC": 2472,
2478
+ "CGCGG": 2473,
2479
+ "CGCGT": 2474,
2480
+ "CGCT-": 2475,
2481
+ "CGCTA": 2476,
2482
+ "CGCTC": 2477,
2483
+ "CGCTG": 2478,
2484
+ "CGCTT": 2479,
2485
+ "CGG--": 2480,
2486
+ "CGG-A": 2481,
2487
+ "CGG-C": 2482,
2488
+ "CGG-G": 2483,
2489
+ "CGG-T": 2484,
2490
+ "CGGA-": 2485,
2491
+ "CGGAA": 2486,
2492
+ "CGGAC": 2487,
2493
+ "CGGAG": 2488,
2494
+ "CGGAT": 2489,
2495
+ "CGGC-": 2490,
2496
+ "CGGCA": 2491,
2497
+ "CGGCC": 2492,
2498
+ "CGGCG": 2493,
2499
+ "CGGCT": 2494,
2500
+ "CGGG-": 2495,
2501
+ "CGGGA": 2496,
2502
+ "CGGGC": 2497,
2503
+ "CGGGG": 2498,
2504
+ "CGGGT": 2499,
2505
+ "CGGT-": 2500,
2506
+ "CGGTA": 2501,
2507
+ "CGGTC": 2502,
2508
+ "CGGTG": 2503,
2509
+ "CGGTT": 2504,
2510
+ "CGT--": 2505,
2511
+ "CGT-A": 2506,
2512
+ "CGT-C": 2507,
2513
+ "CGT-G": 2508,
2514
+ "CGT-T": 2509,
2515
+ "CGTA-": 2510,
2516
+ "CGTAA": 2511,
2517
+ "CGTAC": 2512,
2518
+ "CGTAG": 2513,
2519
+ "CGTAT": 2514,
2520
+ "CGTC-": 2515,
2521
+ "CGTCA": 2516,
2522
+ "CGTCC": 2517,
2523
+ "CGTCG": 2518,
2524
+ "CGTCT": 2519,
2525
+ "CGTG-": 2520,
2526
+ "CGTGA": 2521,
2527
+ "CGTGC": 2522,
2528
+ "CGTGG": 2523,
2529
+ "CGTGT": 2524,
2530
+ "CGTT-": 2525,
2531
+ "CGTTA": 2526,
2532
+ "CGTTC": 2527,
2533
+ "CGTTG": 2528,
2534
+ "CGTTT": 2529,
2535
+ "CT---": 2530,
2536
+ "CT--A": 2531,
2537
+ "CT--C": 2532,
2538
+ "CT--G": 2533,
2539
+ "CT--T": 2534,
2540
+ "CT-A-": 2535,
2541
+ "CT-AA": 2536,
2542
+ "CT-AC": 2537,
2543
+ "CT-AG": 2538,
2544
+ "CT-AT": 2539,
2545
+ "CT-C-": 2540,
2546
+ "CT-CA": 2541,
2547
+ "CT-CC": 2542,
2548
+ "CT-CG": 2543,
2549
+ "CT-CT": 2544,
2550
+ "CT-G-": 2545,
2551
+ "CT-GA": 2546,
2552
+ "CT-GC": 2547,
2553
+ "CT-GG": 2548,
2554
+ "CT-GT": 2549,
2555
+ "CT-T-": 2550,
2556
+ "CT-TA": 2551,
2557
+ "CT-TC": 2552,
2558
+ "CT-TG": 2553,
2559
+ "CT-TT": 2554,
2560
+ "CTA--": 2555,
2561
+ "CTA-A": 2556,
2562
+ "CTA-C": 2557,
2563
+ "CTA-G": 2558,
2564
+ "CTA-T": 2559,
2565
+ "CTAA-": 2560,
2566
+ "CTAAA": 2561,
2567
+ "CTAAC": 2562,
2568
+ "CTAAG": 2563,
2569
+ "CTAAT": 2564,
2570
+ "CTAC-": 2565,
2571
+ "CTACA": 2566,
2572
+ "CTACC": 2567,
2573
+ "CTACG": 2568,
2574
+ "CTACT": 2569,
2575
+ "CTAG-": 2570,
2576
+ "CTAGA": 2571,
2577
+ "CTAGC": 2572,
2578
+ "CTAGG": 2573,
2579
+ "CTAGT": 2574,
2580
+ "CTAT-": 2575,
2581
+ "CTATA": 2576,
2582
+ "CTATC": 2577,
2583
+ "CTATG": 2578,
2584
+ "CTATT": 2579,
2585
+ "CTC--": 2580,
2586
+ "CTC-A": 2581,
2587
+ "CTC-C": 2582,
2588
+ "CTC-G": 2583,
2589
+ "CTC-T": 2584,
2590
+ "CTCA-": 2585,
2591
+ "CTCAA": 2586,
2592
+ "CTCAC": 2587,
2593
+ "CTCAG": 2588,
2594
+ "CTCAT": 2589,
2595
+ "CTCC-": 2590,
2596
+ "CTCCA": 2591,
2597
+ "CTCCC": 2592,
2598
+ "CTCCG": 2593,
2599
+ "CTCCT": 2594,
2600
+ "CTCG-": 2595,
2601
+ "CTCGA": 2596,
2602
+ "CTCGC": 2597,
2603
+ "CTCGG": 2598,
2604
+ "CTCGT": 2599,
2605
+ "CTCT-": 2600,
2606
+ "CTCTA": 2601,
2607
+ "CTCTC": 2602,
2608
+ "CTCTG": 2603,
2609
+ "CTCTT": 2604,
2610
+ "CTG--": 2605,
2611
+ "CTG-A": 2606,
2612
+ "CTG-C": 2607,
2613
+ "CTG-G": 2608,
2614
+ "CTG-T": 2609,
2615
+ "CTGA-": 2610,
2616
+ "CTGAA": 2611,
2617
+ "CTGAC": 2612,
2618
+ "CTGAG": 2613,
2619
+ "CTGAT": 2614,
2620
+ "CTGC-": 2615,
2621
+ "CTGCA": 2616,
2622
+ "CTGCC": 2617,
2623
+ "CTGCG": 2618,
2624
+ "CTGCT": 2619,
2625
+ "CTGG-": 2620,
2626
+ "CTGGA": 2621,
2627
+ "CTGGC": 2622,
2628
+ "CTGGG": 2623,
2629
+ "CTGGT": 2624,
2630
+ "CTGT-": 2625,
2631
+ "CTGTA": 2626,
2632
+ "CTGTC": 2627,
2633
+ "CTGTG": 2628,
2634
+ "CTGTT": 2629,
2635
+ "CTT--": 2630,
2636
+ "CTT-A": 2631,
2637
+ "CTT-C": 2632,
2638
+ "CTT-G": 2633,
2639
+ "CTT-T": 2634,
2640
+ "CTTA-": 2635,
2641
+ "CTTAA": 2636,
2642
+ "CTTAC": 2637,
2643
+ "CTTAG": 2638,
2644
+ "CTTAT": 2639,
2645
+ "CTTC-": 2640,
2646
+ "CTTCA": 2641,
2647
+ "CTTCC": 2642,
2648
+ "CTTCG": 2643,
2649
+ "CTTCT": 2644,
2650
+ "CTTG-": 2645,
2651
+ "CTTGA": 2646,
2652
+ "CTTGC": 2647,
2653
+ "CTTGG": 2648,
2654
+ "CTTGT": 2649,
2655
+ "CTTT-": 2650,
2656
+ "CTTTA": 2651,
2657
+ "CTTTC": 2652,
2658
+ "CTTTG": 2653,
2659
+ "CTTTT": 2654,
2660
+ "G----": 2655,
2661
+ "G---A": 2656,
2662
+ "G---C": 2657,
2663
+ "G---G": 2658,
2664
+ "G---T": 2659,
2665
+ "G--A-": 2660,
2666
+ "G--AA": 2661,
2667
+ "G--AC": 2662,
2668
+ "G--AG": 2663,
2669
+ "G--AT": 2664,
2670
+ "G--C-": 2665,
2671
+ "G--CA": 2666,
2672
+ "G--CC": 2667,
2673
+ "G--CG": 2668,
2674
+ "G--CT": 2669,
2675
+ "G--G-": 2670,
2676
+ "G--GA": 2671,
2677
+ "G--GC": 2672,
2678
+ "G--GG": 2673,
2679
+ "G--GT": 2674,
2680
+ "G--T-": 2675,
2681
+ "G--TA": 2676,
2682
+ "G--TC": 2677,
2683
+ "G--TG": 2678,
2684
+ "G--TT": 2679,
2685
+ "G-A--": 2680,
2686
+ "G-A-A": 2681,
2687
+ "G-A-C": 2682,
2688
+ "G-A-G": 2683,
2689
+ "G-A-T": 2684,
2690
+ "G-AA-": 2685,
2691
+ "G-AAA": 2686,
2692
+ "G-AAC": 2687,
2693
+ "G-AAG": 2688,
2694
+ "G-AAT": 2689,
2695
+ "G-AC-": 2690,
2696
+ "G-ACA": 2691,
2697
+ "G-ACC": 2692,
2698
+ "G-ACG": 2693,
2699
+ "G-ACT": 2694,
2700
+ "G-AG-": 2695,
2701
+ "G-AGA": 2696,
2702
+ "G-AGC": 2697,
2703
+ "G-AGG": 2698,
2704
+ "G-AGT": 2699,
2705
+ "G-AT-": 2700,
2706
+ "G-ATA": 2701,
2707
+ "G-ATC": 2702,
2708
+ "G-ATG": 2703,
2709
+ "G-ATT": 2704,
2710
+ "G-C--": 2705,
2711
+ "G-C-A": 2706,
2712
+ "G-C-C": 2707,
2713
+ "G-C-G": 2708,
2714
+ "G-C-T": 2709,
2715
+ "G-CA-": 2710,
2716
+ "G-CAA": 2711,
2717
+ "G-CAC": 2712,
2718
+ "G-CAG": 2713,
2719
+ "G-CAT": 2714,
2720
+ "G-CC-": 2715,
2721
+ "G-CCA": 2716,
2722
+ "G-CCC": 2717,
2723
+ "G-CCG": 2718,
2724
+ "G-CCT": 2719,
2725
+ "G-CG-": 2720,
2726
+ "G-CGA": 2721,
2727
+ "G-CGC": 2722,
2728
+ "G-CGG": 2723,
2729
+ "G-CGT": 2724,
2730
+ "G-CT-": 2725,
2731
+ "G-CTA": 2726,
2732
+ "G-CTC": 2727,
2733
+ "G-CTG": 2728,
2734
+ "G-CTT": 2729,
2735
+ "G-G--": 2730,
2736
+ "G-G-A": 2731,
2737
+ "G-G-C": 2732,
2738
+ "G-G-G": 2733,
2739
+ "G-G-T": 2734,
2740
+ "G-GA-": 2735,
2741
+ "G-GAA": 2736,
2742
+ "G-GAC": 2737,
2743
+ "G-GAG": 2738,
2744
+ "G-GAT": 2739,
2745
+ "G-GC-": 2740,
2746
+ "G-GCA": 2741,
2747
+ "G-GCC": 2742,
2748
+ "G-GCG": 2743,
2749
+ "G-GCT": 2744,
2750
+ "G-GG-": 2745,
2751
+ "G-GGA": 2746,
2752
+ "G-GGC": 2747,
2753
+ "G-GGG": 2748,
2754
+ "G-GGT": 2749,
2755
+ "G-GT-": 2750,
2756
+ "G-GTA": 2751,
2757
+ "G-GTC": 2752,
2758
+ "G-GTG": 2753,
2759
+ "G-GTT": 2754,
2760
+ "G-T--": 2755,
2761
+ "G-T-A": 2756,
2762
+ "G-T-C": 2757,
2763
+ "G-T-G": 2758,
2764
+ "G-T-T": 2759,
2765
+ "G-TA-": 2760,
2766
+ "G-TAA": 2761,
2767
+ "G-TAC": 2762,
2768
+ "G-TAG": 2763,
2769
+ "G-TAT": 2764,
2770
+ "G-TC-": 2765,
2771
+ "G-TCA": 2766,
2772
+ "G-TCC": 2767,
2773
+ "G-TCG": 2768,
2774
+ "G-TCT": 2769,
2775
+ "G-TG-": 2770,
2776
+ "G-TGA": 2771,
2777
+ "G-TGC": 2772,
2778
+ "G-TGG": 2773,
2779
+ "G-TGT": 2774,
2780
+ "G-TT-": 2775,
2781
+ "G-TTA": 2776,
2782
+ "G-TTC": 2777,
2783
+ "G-TTG": 2778,
2784
+ "G-TTT": 2779,
2785
+ "GA---": 2780,
2786
+ "GA--A": 2781,
2787
+ "GA--C": 2782,
2788
+ "GA--G": 2783,
2789
+ "GA--T": 2784,
2790
+ "GA-A-": 2785,
2791
+ "GA-AA": 2786,
2792
+ "GA-AC": 2787,
2793
+ "GA-AG": 2788,
2794
+ "GA-AT": 2789,
2795
+ "GA-C-": 2790,
2796
+ "GA-CA": 2791,
2797
+ "GA-CC": 2792,
2798
+ "GA-CG": 2793,
2799
+ "GA-CT": 2794,
2800
+ "GA-G-": 2795,
2801
+ "GA-GA": 2796,
2802
+ "GA-GC": 2797,
2803
+ "GA-GG": 2798,
2804
+ "GA-GT": 2799,
2805
+ "GA-T-": 2800,
2806
+ "GA-TA": 2801,
2807
+ "GA-TC": 2802,
2808
+ "GA-TG": 2803,
2809
+ "GA-TT": 2804,
2810
+ "GAA--": 2805,
2811
+ "GAA-A": 2806,
2812
+ "GAA-C": 2807,
2813
+ "GAA-G": 2808,
2814
+ "GAA-T": 2809,
2815
+ "GAAA-": 2810,
2816
+ "GAAAA": 2811,
2817
+ "GAAAC": 2812,
2818
+ "GAAAG": 2813,
2819
+ "GAAAT": 2814,
2820
+ "GAAC-": 2815,
2821
+ "GAACA": 2816,
2822
+ "GAACC": 2817,
2823
+ "GAACG": 2818,
2824
+ "GAACT": 2819,
2825
+ "GAAG-": 2820,
2826
+ "GAAGA": 2821,
2827
+ "GAAGC": 2822,
2828
+ "GAAGG": 2823,
2829
+ "GAAGT": 2824,
2830
+ "GAAT-": 2825,
2831
+ "GAATA": 2826,
2832
+ "GAATC": 2827,
2833
+ "GAATG": 2828,
2834
+ "GAATT": 2829,
2835
+ "GAC--": 2830,
2836
+ "GAC-A": 2831,
2837
+ "GAC-C": 2832,
2838
+ "GAC-G": 2833,
2839
+ "GAC-T": 2834,
2840
+ "GACA-": 2835,
2841
+ "GACAA": 2836,
2842
+ "GACAC": 2837,
2843
+ "GACAG": 2838,
2844
+ "GACAT": 2839,
2845
+ "GACC-": 2840,
2846
+ "GACCA": 2841,
2847
+ "GACCC": 2842,
2848
+ "GACCG": 2843,
2849
+ "GACCT": 2844,
2850
+ "GACG-": 2845,
2851
+ "GACGA": 2846,
2852
+ "GACGC": 2847,
2853
+ "GACGG": 2848,
2854
+ "GACGT": 2849,
2855
+ "GACT-": 2850,
2856
+ "GACTA": 2851,
2857
+ "GACTC": 2852,
2858
+ "GACTG": 2853,
2859
+ "GACTT": 2854,
2860
+ "GAG--": 2855,
2861
+ "GAG-A": 2856,
2862
+ "GAG-C": 2857,
2863
+ "GAG-G": 2858,
2864
+ "GAG-T": 2859,
2865
+ "GAGA-": 2860,
2866
+ "GAGAA": 2861,
2867
+ "GAGAC": 2862,
2868
+ "GAGAG": 2863,
2869
+ "GAGAT": 2864,
2870
+ "GAGC-": 2865,
2871
+ "GAGCA": 2866,
2872
+ "GAGCC": 2867,
2873
+ "GAGCG": 2868,
2874
+ "GAGCT": 2869,
2875
+ "GAGG-": 2870,
2876
+ "GAGGA": 2871,
2877
+ "GAGGC": 2872,
2878
+ "GAGGG": 2873,
2879
+ "GAGGT": 2874,
2880
+ "GAGT-": 2875,
2881
+ "GAGTA": 2876,
2882
+ "GAGTC": 2877,
2883
+ "GAGTG": 2878,
2884
+ "GAGTT": 2879,
2885
+ "GAT--": 2880,
2886
+ "GAT-A": 2881,
2887
+ "GAT-C": 2882,
2888
+ "GAT-G": 2883,
2889
+ "GAT-T": 2884,
2890
+ "GATA-": 2885,
2891
+ "GATAA": 2886,
2892
+ "GATAC": 2887,
2893
+ "GATAG": 2888,
2894
+ "GATAT": 2889,
2895
+ "GATC-": 2890,
2896
+ "GATCA": 2891,
2897
+ "GATCC": 2892,
2898
+ "GATCG": 2893,
2899
+ "GATCT": 2894,
2900
+ "GATG-": 2895,
2901
+ "GATGA": 2896,
2902
+ "GATGC": 2897,
2903
+ "GATGG": 2898,
2904
+ "GATGT": 2899,
2905
+ "GATT-": 2900,
2906
+ "GATTA": 2901,
2907
+ "GATTC": 2902,
2908
+ "GATTG": 2903,
2909
+ "GATTT": 2904,
2910
+ "GC---": 2905,
2911
+ "GC--A": 2906,
2912
+ "GC--C": 2907,
2913
+ "GC--G": 2908,
2914
+ "GC--T": 2909,
2915
+ "GC-A-": 2910,
2916
+ "GC-AA": 2911,
2917
+ "GC-AC": 2912,
2918
+ "GC-AG": 2913,
2919
+ "GC-AT": 2914,
2920
+ "GC-C-": 2915,
2921
+ "GC-CA": 2916,
2922
+ "GC-CC": 2917,
2923
+ "GC-CG": 2918,
2924
+ "GC-CT": 2919,
2925
+ "GC-G-": 2920,
2926
+ "GC-GA": 2921,
2927
+ "GC-GC": 2922,
2928
+ "GC-GG": 2923,
2929
+ "GC-GT": 2924,
2930
+ "GC-T-": 2925,
2931
+ "GC-TA": 2926,
2932
+ "GC-TC": 2927,
2933
+ "GC-TG": 2928,
2934
+ "GC-TT": 2929,
2935
+ "GCA--": 2930,
2936
+ "GCA-A": 2931,
2937
+ "GCA-C": 2932,
2938
+ "GCA-G": 2933,
2939
+ "GCA-T": 2934,
2940
+ "GCAA-": 2935,
2941
+ "GCAAA": 2936,
2942
+ "GCAAC": 2937,
2943
+ "GCAAG": 2938,
2944
+ "GCAAT": 2939,
2945
+ "GCAC-": 2940,
2946
+ "GCACA": 2941,
2947
+ "GCACC": 2942,
2948
+ "GCACG": 2943,
2949
+ "GCACT": 2944,
2950
+ "GCAG-": 2945,
2951
+ "GCAGA": 2946,
2952
+ "GCAGC": 2947,
2953
+ "GCAGG": 2948,
2954
+ "GCAGT": 2949,
2955
+ "GCAT-": 2950,
2956
+ "GCATA": 2951,
2957
+ "GCATC": 2952,
2958
+ "GCATG": 2953,
2959
+ "GCATT": 2954,
2960
+ "GCC--": 2955,
2961
+ "GCC-A": 2956,
2962
+ "GCC-C": 2957,
2963
+ "GCC-G": 2958,
2964
+ "GCC-T": 2959,
2965
+ "GCCA-": 2960,
2966
+ "GCCAA": 2961,
2967
+ "GCCAC": 2962,
2968
+ "GCCAG": 2963,
2969
+ "GCCAT": 2964,
2970
+ "GCCC-": 2965,
2971
+ "GCCCA": 2966,
2972
+ "GCCCC": 2967,
2973
+ "GCCCG": 2968,
2974
+ "GCCCT": 2969,
2975
+ "GCCG-": 2970,
2976
+ "GCCGA": 2971,
2977
+ "GCCGC": 2972,
2978
+ "GCCGG": 2973,
2979
+ "GCCGT": 2974,
2980
+ "GCCT-": 2975,
2981
+ "GCCTA": 2976,
2982
+ "GCCTC": 2977,
2983
+ "GCCTG": 2978,
2984
+ "GCCTT": 2979,
2985
+ "GCG--": 2980,
2986
+ "GCG-A": 2981,
2987
+ "GCG-C": 2982,
2988
+ "GCG-G": 2983,
2989
+ "GCG-T": 2984,
2990
+ "GCGA-": 2985,
2991
+ "GCGAA": 2986,
2992
+ "GCGAC": 2987,
2993
+ "GCGAG": 2988,
2994
+ "GCGAT": 2989,
2995
+ "GCGC-": 2990,
2996
+ "GCGCA": 2991,
2997
+ "GCGCC": 2992,
2998
+ "GCGCG": 2993,
2999
+ "GCGCT": 2994,
3000
+ "GCGG-": 2995,
3001
+ "GCGGA": 2996,
3002
+ "GCGGC": 2997,
3003
+ "GCGGG": 2998,
3004
+ "GCGGT": 2999,
3005
+ "GCGT-": 3000,
3006
+ "GCGTA": 3001,
3007
+ "GCGTC": 3002,
3008
+ "GCGTG": 3003,
3009
+ "GCGTT": 3004,
3010
+ "GCT--": 3005,
3011
+ "GCT-A": 3006,
3012
+ "GCT-C": 3007,
3013
+ "GCT-G": 3008,
3014
+ "GCT-T": 3009,
3015
+ "GCTA-": 3010,
3016
+ "GCTAA": 3011,
3017
+ "GCTAC": 3012,
3018
+ "GCTAG": 3013,
3019
+ "GCTAT": 3014,
3020
+ "GCTC-": 3015,
3021
+ "GCTCA": 3016,
3022
+ "GCTCC": 3017,
3023
+ "GCTCG": 3018,
3024
+ "GCTCT": 3019,
3025
+ "GCTG-": 3020,
3026
+ "GCTGA": 3021,
3027
+ "GCTGC": 3022,
3028
+ "GCTGG": 3023,
3029
+ "GCTGT": 3024,
3030
+ "GCTT-": 3025,
3031
+ "GCTTA": 3026,
3032
+ "GCTTC": 3027,
3033
+ "GCTTG": 3028,
3034
+ "GCTTT": 3029,
3035
+ "GG---": 3030,
3036
+ "GG--A": 3031,
3037
+ "GG--C": 3032,
3038
+ "GG--G": 3033,
3039
+ "GG--T": 3034,
3040
+ "GG-A-": 3035,
3041
+ "GG-AA": 3036,
3042
+ "GG-AC": 3037,
3043
+ "GG-AG": 3038,
3044
+ "GG-AT": 3039,
3045
+ "GG-C-": 3040,
3046
+ "GG-CA": 3041,
3047
+ "GG-CC": 3042,
3048
+ "GG-CG": 3043,
3049
+ "GG-CT": 3044,
3050
+ "GG-G-": 3045,
3051
+ "GG-GA": 3046,
3052
+ "GG-GC": 3047,
3053
+ "GG-GG": 3048,
3054
+ "GG-GT": 3049,
3055
+ "GG-T-": 3050,
3056
+ "GG-TA": 3051,
3057
+ "GG-TC": 3052,
3058
+ "GG-TG": 3053,
3059
+ "GG-TT": 3054,
3060
+ "GGA--": 3055,
3061
+ "GGA-A": 3056,
3062
+ "GGA-C": 3057,
3063
+ "GGA-G": 3058,
3064
+ "GGA-T": 3059,
3065
+ "GGAA-": 3060,
3066
+ "GGAAA": 3061,
3067
+ "GGAAC": 3062,
3068
+ "GGAAG": 3063,
3069
+ "GGAAT": 3064,
3070
+ "GGAC-": 3065,
3071
+ "GGACA": 3066,
3072
+ "GGACC": 3067,
3073
+ "GGACG": 3068,
3074
+ "GGACT": 3069,
3075
+ "GGAG-": 3070,
3076
+ "GGAGA": 3071,
3077
+ "GGAGC": 3072,
3078
+ "GGAGG": 3073,
3079
+ "GGAGT": 3074,
3080
+ "GGAT-": 3075,
3081
+ "GGATA": 3076,
3082
+ "GGATC": 3077,
3083
+ "GGATG": 3078,
3084
+ "GGATT": 3079,
3085
+ "GGC--": 3080,
3086
+ "GGC-A": 3081,
3087
+ "GGC-C": 3082,
3088
+ "GGC-G": 3083,
3089
+ "GGC-T": 3084,
3090
+ "GGCA-": 3085,
3091
+ "GGCAA": 3086,
3092
+ "GGCAC": 3087,
3093
+ "GGCAG": 3088,
3094
+ "GGCAT": 3089,
3095
+ "GGCC-": 3090,
3096
+ "GGCCA": 3091,
3097
+ "GGCCC": 3092,
3098
+ "GGCCG": 3093,
3099
+ "GGCCT": 3094,
3100
+ "GGCG-": 3095,
3101
+ "GGCGA": 3096,
3102
+ "GGCGC": 3097,
3103
+ "GGCGG": 3098,
3104
+ "GGCGT": 3099,
3105
+ "GGCT-": 3100,
3106
+ "GGCTA": 3101,
3107
+ "GGCTC": 3102,
3108
+ "GGCTG": 3103,
3109
+ "GGCTT": 3104,
3110
+ "GGG--": 3105,
3111
+ "GGG-A": 3106,
3112
+ "GGG-C": 3107,
3113
+ "GGG-G": 3108,
3114
+ "GGG-T": 3109,
3115
+ "GGGA-": 3110,
3116
+ "GGGAA": 3111,
3117
+ "GGGAC": 3112,
3118
+ "GGGAG": 3113,
3119
+ "GGGAT": 3114,
3120
+ "GGGC-": 3115,
3121
+ "GGGCA": 3116,
3122
+ "GGGCC": 3117,
3123
+ "GGGCG": 3118,
3124
+ "GGGCT": 3119,
3125
+ "GGGG-": 3120,
3126
+ "GGGGA": 3121,
3127
+ "GGGGC": 3122,
3128
+ "GGGGG": 3123,
3129
+ "GGGGT": 3124,
3130
+ "GGGT-": 3125,
3131
+ "GGGTA": 3126,
3132
+ "GGGTC": 3127,
3133
+ "GGGTG": 3128,
3134
+ "GGGTT": 3129,
3135
+ "GGT--": 3130,
3136
+ "GGT-A": 3131,
3137
+ "GGT-C": 3132,
3138
+ "GGT-G": 3133,
3139
+ "GGT-T": 3134,
3140
+ "GGTA-": 3135,
3141
+ "GGTAA": 3136,
3142
+ "GGTAC": 3137,
3143
+ "GGTAG": 3138,
3144
+ "GGTAT": 3139,
3145
+ "GGTC-": 3140,
3146
+ "GGTCA": 3141,
3147
+ "GGTCC": 3142,
3148
+ "GGTCG": 3143,
3149
+ "GGTCT": 3144,
3150
+ "GGTG-": 3145,
3151
+ "GGTGA": 3146,
3152
+ "GGTGC": 3147,
3153
+ "GGTGG": 3148,
3154
+ "GGTGT": 3149,
3155
+ "GGTT-": 3150,
3156
+ "GGTTA": 3151,
3157
+ "GGTTC": 3152,
3158
+ "GGTTG": 3153,
3159
+ "GGTTT": 3154,
3160
+ "GT---": 3155,
3161
+ "GT--A": 3156,
3162
+ "GT--C": 3157,
3163
+ "GT--G": 3158,
3164
+ "GT--T": 3159,
3165
+ "GT-A-": 3160,
3166
+ "GT-AA": 3161,
3167
+ "GT-AC": 3162,
3168
+ "GT-AG": 3163,
3169
+ "GT-AT": 3164,
3170
+ "GT-C-": 3165,
3171
+ "GT-CA": 3166,
3172
+ "GT-CC": 3167,
3173
+ "GT-CG": 3168,
3174
+ "GT-CT": 3169,
3175
+ "GT-G-": 3170,
3176
+ "GT-GA": 3171,
3177
+ "GT-GC": 3172,
3178
+ "GT-GG": 3173,
3179
+ "GT-GT": 3174,
3180
+ "GT-T-": 3175,
3181
+ "GT-TA": 3176,
3182
+ "GT-TC": 3177,
3183
+ "GT-TG": 3178,
3184
+ "GT-TT": 3179,
3185
+ "GTA--": 3180,
3186
+ "GTA-A": 3181,
3187
+ "GTA-C": 3182,
3188
+ "GTA-G": 3183,
3189
+ "GTA-T": 3184,
3190
+ "GTAA-": 3185,
3191
+ "GTAAA": 3186,
3192
+ "GTAAC": 3187,
3193
+ "GTAAG": 3188,
3194
+ "GTAAT": 3189,
3195
+ "GTAC-": 3190,
3196
+ "GTACA": 3191,
3197
+ "GTACC": 3192,
3198
+ "GTACG": 3193,
3199
+ "GTACT": 3194,
3200
+ "GTAG-": 3195,
3201
+ "GTAGA": 3196,
3202
+ "GTAGC": 3197,
3203
+ "GTAGG": 3198,
3204
+ "GTAGT": 3199,
3205
+ "GTAT-": 3200,
3206
+ "GTATA": 3201,
3207
+ "GTATC": 3202,
3208
+ "GTATG": 3203,
3209
+ "GTATT": 3204,
3210
+ "GTC--": 3205,
3211
+ "GTC-A": 3206,
3212
+ "GTC-C": 3207,
3213
+ "GTC-G": 3208,
3214
+ "GTC-T": 3209,
3215
+ "GTCA-": 3210,
3216
+ "GTCAA": 3211,
3217
+ "GTCAC": 3212,
3218
+ "GTCAG": 3213,
3219
+ "GTCAT": 3214,
3220
+ "GTCC-": 3215,
3221
+ "GTCCA": 3216,
3222
+ "GTCCC": 3217,
3223
+ "GTCCG": 3218,
3224
+ "GTCCT": 3219,
3225
+ "GTCG-": 3220,
3226
+ "GTCGA": 3221,
3227
+ "GTCGC": 3222,
3228
+ "GTCGG": 3223,
3229
+ "GTCGT": 3224,
3230
+ "GTCT-": 3225,
3231
+ "GTCTA": 3226,
3232
+ "GTCTC": 3227,
3233
+ "GTCTG": 3228,
3234
+ "GTCTT": 3229,
3235
+ "GTG--": 3230,
3236
+ "GTG-A": 3231,
3237
+ "GTG-C": 3232,
3238
+ "GTG-G": 3233,
3239
+ "GTG-T": 3234,
3240
+ "GTGA-": 3235,
3241
+ "GTGAA": 3236,
3242
+ "GTGAC": 3237,
3243
+ "GTGAG": 3238,
3244
+ "GTGAT": 3239,
3245
+ "GTGC-": 3240,
3246
+ "GTGCA": 3241,
3247
+ "GTGCC": 3242,
3248
+ "GTGCG": 3243,
3249
+ "GTGCT": 3244,
3250
+ "GTGG-": 3245,
3251
+ "GTGGA": 3246,
3252
+ "GTGGC": 3247,
3253
+ "GTGGG": 3248,
3254
+ "GTGGT": 3249,
3255
+ "GTGT-": 3250,
3256
+ "GTGTA": 3251,
3257
+ "GTGTC": 3252,
3258
+ "GTGTG": 3253,
3259
+ "GTGTT": 3254,
3260
+ "GTT--": 3255,
3261
+ "GTT-A": 3256,
3262
+ "GTT-C": 3257,
3263
+ "GTT-G": 3258,
3264
+ "GTT-T": 3259,
3265
+ "GTTA-": 3260,
3266
+ "GTTAA": 3261,
3267
+ "GTTAC": 3262,
3268
+ "GTTAG": 3263,
3269
+ "GTTAT": 3264,
3270
+ "GTTC-": 3265,
3271
+ "GTTCA": 3266,
3272
+ "GTTCC": 3267,
3273
+ "GTTCG": 3268,
3274
+ "GTTCT": 3269,
3275
+ "GTTG-": 3270,
3276
+ "GTTGA": 3271,
3277
+ "GTTGC": 3272,
3278
+ "GTTGG": 3273,
3279
+ "GTTGT": 3274,
3280
+ "GTTT-": 3275,
3281
+ "GTTTA": 3276,
3282
+ "GTTTC": 3277,
3283
+ "GTTTG": 3278,
3284
+ "GTTTT": 3279,
3285
+ "T----": 3280,
3286
+ "T---A": 3281,
3287
+ "T---C": 3282,
3288
+ "T---G": 3283,
3289
+ "T---T": 3284,
3290
+ "T--A-": 3285,
3291
+ "T--AA": 3286,
3292
+ "T--AC": 3287,
3293
+ "T--AG": 3288,
3294
+ "T--AT": 3289,
3295
+ "T--C-": 3290,
3296
+ "T--CA": 3291,
3297
+ "T--CC": 3292,
3298
+ "T--CG": 3293,
3299
+ "T--CT": 3294,
3300
+ "T--G-": 3295,
3301
+ "T--GA": 3296,
3302
+ "T--GC": 3297,
3303
+ "T--GG": 3298,
3304
+ "T--GT": 3299,
3305
+ "T--T-": 3300,
3306
+ "T--TA": 3301,
3307
+ "T--TC": 3302,
3308
+ "T--TG": 3303,
3309
+ "T--TT": 3304,
3310
+ "T-A--": 3305,
3311
+ "T-A-A": 3306,
3312
+ "T-A-C": 3307,
3313
+ "T-A-G": 3308,
3314
+ "T-A-T": 3309,
3315
+ "T-AA-": 3310,
3316
+ "T-AAA": 3311,
3317
+ "T-AAC": 3312,
3318
+ "T-AAG": 3313,
3319
+ "T-AAT": 3314,
3320
+ "T-AC-": 3315,
3321
+ "T-ACA": 3316,
3322
+ "T-ACC": 3317,
3323
+ "T-ACG": 3318,
3324
+ "T-ACT": 3319,
3325
+ "T-AG-": 3320,
3326
+ "T-AGA": 3321,
3327
+ "T-AGC": 3322,
3328
+ "T-AGG": 3323,
3329
+ "T-AGT": 3324,
3330
+ "T-AT-": 3325,
3331
+ "T-ATA": 3326,
3332
+ "T-ATC": 3327,
3333
+ "T-ATG": 3328,
3334
+ "T-ATT": 3329,
3335
+ "T-C--": 3330,
3336
+ "T-C-A": 3331,
3337
+ "T-C-C": 3332,
3338
+ "T-C-G": 3333,
3339
+ "T-C-T": 3334,
3340
+ "T-CA-": 3335,
3341
+ "T-CAA": 3336,
3342
+ "T-CAC": 3337,
3343
+ "T-CAG": 3338,
3344
+ "T-CAT": 3339,
3345
+ "T-CC-": 3340,
3346
+ "T-CCA": 3341,
3347
+ "T-CCC": 3342,
3348
+ "T-CCG": 3343,
3349
+ "T-CCT": 3344,
3350
+ "T-CG-": 3345,
3351
+ "T-CGA": 3346,
3352
+ "T-CGC": 3347,
3353
+ "T-CGG": 3348,
3354
+ "T-CGT": 3349,
3355
+ "T-CT-": 3350,
3356
+ "T-CTA": 3351,
3357
+ "T-CTC": 3352,
3358
+ "T-CTG": 3353,
3359
+ "T-CTT": 3354,
3360
+ "T-G--": 3355,
3361
+ "T-G-A": 3356,
3362
+ "T-G-C": 3357,
3363
+ "T-G-G": 3358,
3364
+ "T-G-T": 3359,
3365
+ "T-GA-": 3360,
3366
+ "T-GAA": 3361,
3367
+ "T-GAC": 3362,
3368
+ "T-GAG": 3363,
3369
+ "T-GAT": 3364,
3370
+ "T-GC-": 3365,
3371
+ "T-GCA": 3366,
3372
+ "T-GCC": 3367,
3373
+ "T-GCG": 3368,
3374
+ "T-GCT": 3369,
3375
+ "T-GG-": 3370,
3376
+ "T-GGA": 3371,
3377
+ "T-GGC": 3372,
3378
+ "T-GGG": 3373,
3379
+ "T-GGT": 3374,
3380
+ "T-GT-": 3375,
3381
+ "T-GTA": 3376,
3382
+ "T-GTC": 3377,
3383
+ "T-GTG": 3378,
3384
+ "T-GTT": 3379,
3385
+ "T-T--": 3380,
3386
+ "T-T-A": 3381,
3387
+ "T-T-C": 3382,
3388
+ "T-T-G": 3383,
3389
+ "T-T-T": 3384,
3390
+ "T-TA-": 3385,
3391
+ "T-TAA": 3386,
3392
+ "T-TAC": 3387,
3393
+ "T-TAG": 3388,
3394
+ "T-TAT": 3389,
3395
+ "T-TC-": 3390,
3396
+ "T-TCA": 3391,
3397
+ "T-TCC": 3392,
3398
+ "T-TCG": 3393,
3399
+ "T-TCT": 3394,
3400
+ "T-TG-": 3395,
3401
+ "T-TGA": 3396,
3402
+ "T-TGC": 3397,
3403
+ "T-TGG": 3398,
3404
+ "T-TGT": 3399,
3405
+ "T-TT-": 3400,
3406
+ "T-TTA": 3401,
3407
+ "T-TTC": 3402,
3408
+ "T-TTG": 3403,
3409
+ "T-TTT": 3404,
3410
+ "TA---": 3405,
3411
+ "TA--A": 3406,
3412
+ "TA--C": 3407,
3413
+ "TA--G": 3408,
3414
+ "TA--T": 3409,
3415
+ "TA-A-": 3410,
3416
+ "TA-AA": 3411,
3417
+ "TA-AC": 3412,
3418
+ "TA-AG": 3413,
3419
+ "TA-AT": 3414,
3420
+ "TA-C-": 3415,
3421
+ "TA-CA": 3416,
3422
+ "TA-CC": 3417,
3423
+ "TA-CG": 3418,
3424
+ "TA-CT": 3419,
3425
+ "TA-G-": 3420,
3426
+ "TA-GA": 3421,
3427
+ "TA-GC": 3422,
3428
+ "TA-GG": 3423,
3429
+ "TA-GT": 3424,
3430
+ "TA-T-": 3425,
3431
+ "TA-TA": 3426,
3432
+ "TA-TC": 3427,
3433
+ "TA-TG": 3428,
3434
+ "TA-TT": 3429,
3435
+ "TAA--": 3430,
3436
+ "TAA-A": 3431,
3437
+ "TAA-C": 3432,
3438
+ "TAA-G": 3433,
3439
+ "TAA-T": 3434,
3440
+ "TAAA-": 3435,
3441
+ "TAAAA": 3436,
3442
+ "TAAAC": 3437,
3443
+ "TAAAG": 3438,
3444
+ "TAAAT": 3439,
3445
+ "TAAC-": 3440,
3446
+ "TAACA": 3441,
3447
+ "TAACC": 3442,
3448
+ "TAACG": 3443,
3449
+ "TAACT": 3444,
3450
+ "TAAG-": 3445,
3451
+ "TAAGA": 3446,
3452
+ "TAAGC": 3447,
3453
+ "TAAGG": 3448,
3454
+ "TAAGT": 3449,
3455
+ "TAAT-": 3450,
3456
+ "TAATA": 3451,
3457
+ "TAATC": 3452,
3458
+ "TAATG": 3453,
3459
+ "TAATT": 3454,
3460
+ "TAC--": 3455,
3461
+ "TAC-A": 3456,
3462
+ "TAC-C": 3457,
3463
+ "TAC-G": 3458,
3464
+ "TAC-T": 3459,
3465
+ "TACA-": 3460,
3466
+ "TACAA": 3461,
3467
+ "TACAC": 3462,
3468
+ "TACAG": 3463,
3469
+ "TACAT": 3464,
3470
+ "TACC-": 3465,
3471
+ "TACCA": 3466,
3472
+ "TACCC": 3467,
3473
+ "TACCG": 3468,
3474
+ "TACCT": 3469,
3475
+ "TACG-": 3470,
3476
+ "TACGA": 3471,
3477
+ "TACGC": 3472,
3478
+ "TACGG": 3473,
3479
+ "TACGT": 3474,
3480
+ "TACT-": 3475,
3481
+ "TACTA": 3476,
3482
+ "TACTC": 3477,
3483
+ "TACTG": 3478,
3484
+ "TACTT": 3479,
3485
+ "TAG--": 3480,
3486
+ "TAG-A": 3481,
3487
+ "TAG-C": 3482,
3488
+ "TAG-G": 3483,
3489
+ "TAG-T": 3484,
3490
+ "TAGA-": 3485,
3491
+ "TAGAA": 3486,
3492
+ "TAGAC": 3487,
3493
+ "TAGAG": 3488,
3494
+ "TAGAT": 3489,
3495
+ "TAGC-": 3490,
3496
+ "TAGCA": 3491,
3497
+ "TAGCC": 3492,
3498
+ "TAGCG": 3493,
3499
+ "TAGCT": 3494,
3500
+ "TAGG-": 3495,
3501
+ "TAGGA": 3496,
3502
+ "TAGGC": 3497,
3503
+ "TAGGG": 3498,
3504
+ "TAGGT": 3499,
3505
+ "TAGT-": 3500,
3506
+ "TAGTA": 3501,
3507
+ "TAGTC": 3502,
3508
+ "TAGTG": 3503,
3509
+ "TAGTT": 3504,
3510
+ "TAT--": 3505,
3511
+ "TAT-A": 3506,
3512
+ "TAT-C": 3507,
3513
+ "TAT-G": 3508,
3514
+ "TAT-T": 3509,
3515
+ "TATA-": 3510,
3516
+ "TATAA": 3511,
3517
+ "TATAC": 3512,
3518
+ "TATAG": 3513,
3519
+ "TATAT": 3514,
3520
+ "TATC-": 3515,
3521
+ "TATCA": 3516,
3522
+ "TATCC": 3517,
3523
+ "TATCG": 3518,
3524
+ "TATCT": 3519,
3525
+ "TATG-": 3520,
3526
+ "TATGA": 3521,
3527
+ "TATGC": 3522,
3528
+ "TATGG": 3523,
3529
+ "TATGT": 3524,
3530
+ "TATT-": 3525,
3531
+ "TATTA": 3526,
3532
+ "TATTC": 3527,
3533
+ "TATTG": 3528,
3534
+ "TATTT": 3529,
3535
+ "TC---": 3530,
3536
+ "TC--A": 3531,
3537
+ "TC--C": 3532,
3538
+ "TC--G": 3533,
3539
+ "TC--T": 3534,
3540
+ "TC-A-": 3535,
3541
+ "TC-AA": 3536,
3542
+ "TC-AC": 3537,
3543
+ "TC-AG": 3538,
3544
+ "TC-AT": 3539,
3545
+ "TC-C-": 3540,
3546
+ "TC-CA": 3541,
3547
+ "TC-CC": 3542,
3548
+ "TC-CG": 3543,
3549
+ "TC-CT": 3544,
3550
+ "TC-G-": 3545,
3551
+ "TC-GA": 3546,
3552
+ "TC-GC": 3547,
3553
+ "TC-GG": 3548,
3554
+ "TC-GT": 3549,
3555
+ "TC-T-": 3550,
3556
+ "TC-TA": 3551,
3557
+ "TC-TC": 3552,
3558
+ "TC-TG": 3553,
3559
+ "TC-TT": 3554,
3560
+ "TCA--": 3555,
3561
+ "TCA-A": 3556,
3562
+ "TCA-C": 3557,
3563
+ "TCA-G": 3558,
3564
+ "TCA-T": 3559,
3565
+ "TCAA-": 3560,
3566
+ "TCAAA": 3561,
3567
+ "TCAAC": 3562,
3568
+ "TCAAG": 3563,
3569
+ "TCAAT": 3564,
3570
+ "TCAC-": 3565,
3571
+ "TCACA": 3566,
3572
+ "TCACC": 3567,
3573
+ "TCACG": 3568,
3574
+ "TCACT": 3569,
3575
+ "TCAG-": 3570,
3576
+ "TCAGA": 3571,
3577
+ "TCAGC": 3572,
3578
+ "TCAGG": 3573,
3579
+ "TCAGT": 3574,
3580
+ "TCAT-": 3575,
3581
+ "TCATA": 3576,
3582
+ "TCATC": 3577,
3583
+ "TCATG": 3578,
3584
+ "TCATT": 3579,
3585
+ "TCC--": 3580,
3586
+ "TCC-A": 3581,
3587
+ "TCC-C": 3582,
3588
+ "TCC-G": 3583,
3589
+ "TCC-T": 3584,
3590
+ "TCCA-": 3585,
3591
+ "TCCAA": 3586,
3592
+ "TCCAC": 3587,
3593
+ "TCCAG": 3588,
3594
+ "TCCAT": 3589,
3595
+ "TCCC-": 3590,
3596
+ "TCCCA": 3591,
3597
+ "TCCCC": 3592,
3598
+ "TCCCG": 3593,
3599
+ "TCCCT": 3594,
3600
+ "TCCG-": 3595,
3601
+ "TCCGA": 3596,
3602
+ "TCCGC": 3597,
3603
+ "TCCGG": 3598,
3604
+ "TCCGT": 3599,
3605
+ "TCCT-": 3600,
3606
+ "TCCTA": 3601,
3607
+ "TCCTC": 3602,
3608
+ "TCCTG": 3603,
3609
+ "TCCTT": 3604,
3610
+ "TCG--": 3605,
3611
+ "TCG-A": 3606,
3612
+ "TCG-C": 3607,
3613
+ "TCG-G": 3608,
3614
+ "TCG-T": 3609,
3615
+ "TCGA-": 3610,
3616
+ "TCGAA": 3611,
3617
+ "TCGAC": 3612,
3618
+ "TCGAG": 3613,
3619
+ "TCGAT": 3614,
3620
+ "TCGC-": 3615,
3621
+ "TCGCA": 3616,
3622
+ "TCGCC": 3617,
3623
+ "TCGCG": 3618,
3624
+ "TCGCT": 3619,
3625
+ "TCGG-": 3620,
3626
+ "TCGGA": 3621,
3627
+ "TCGGC": 3622,
3628
+ "TCGGG": 3623,
3629
+ "TCGGT": 3624,
3630
+ "TCGT-": 3625,
3631
+ "TCGTA": 3626,
3632
+ "TCGTC": 3627,
3633
+ "TCGTG": 3628,
3634
+ "TCGTT": 3629,
3635
+ "TCT--": 3630,
3636
+ "TCT-A": 3631,
3637
+ "TCT-C": 3632,
3638
+ "TCT-G": 3633,
3639
+ "TCT-T": 3634,
3640
+ "TCTA-": 3635,
3641
+ "TCTAA": 3636,
3642
+ "TCTAC": 3637,
3643
+ "TCTAG": 3638,
3644
+ "TCTAT": 3639,
3645
+ "TCTC-": 3640,
3646
+ "TCTCA": 3641,
3647
+ "TCTCC": 3642,
3648
+ "TCTCG": 3643,
3649
+ "TCTCT": 3644,
3650
+ "TCTG-": 3645,
3651
+ "TCTGA": 3646,
3652
+ "TCTGC": 3647,
3653
+ "TCTGG": 3648,
3654
+ "TCTGT": 3649,
3655
+ "TCTT-": 3650,
3656
+ "TCTTA": 3651,
3657
+ "TCTTC": 3652,
3658
+ "TCTTG": 3653,
3659
+ "TCTTT": 3654,
3660
+ "TG---": 3655,
3661
+ "TG--A": 3656,
3662
+ "TG--C": 3657,
3663
+ "TG--G": 3658,
3664
+ "TG--T": 3659,
3665
+ "TG-A-": 3660,
3666
+ "TG-AA": 3661,
3667
+ "TG-AC": 3662,
3668
+ "TG-AG": 3663,
3669
+ "TG-AT": 3664,
3670
+ "TG-C-": 3665,
3671
+ "TG-CA": 3666,
3672
+ "TG-CC": 3667,
3673
+ "TG-CG": 3668,
3674
+ "TG-CT": 3669,
3675
+ "TG-G-": 3670,
3676
+ "TG-GA": 3671,
3677
+ "TG-GC": 3672,
3678
+ "TG-GG": 3673,
3679
+ "TG-GT": 3674,
3680
+ "TG-T-": 3675,
3681
+ "TG-TA": 3676,
3682
+ "TG-TC": 3677,
3683
+ "TG-TG": 3678,
3684
+ "TG-TT": 3679,
3685
+ "TGA--": 3680,
3686
+ "TGA-A": 3681,
3687
+ "TGA-C": 3682,
3688
+ "TGA-G": 3683,
3689
+ "TGA-T": 3684,
3690
+ "TGAA-": 3685,
3691
+ "TGAAA": 3686,
3692
+ "TGAAC": 3687,
3693
+ "TGAAG": 3688,
3694
+ "TGAAT": 3689,
3695
+ "TGAC-": 3690,
3696
+ "TGACA": 3691,
3697
+ "TGACC": 3692,
3698
+ "TGACG": 3693,
3699
+ "TGACT": 3694,
3700
+ "TGAG-": 3695,
3701
+ "TGAGA": 3696,
3702
+ "TGAGC": 3697,
3703
+ "TGAGG": 3698,
3704
+ "TGAGT": 3699,
3705
+ "TGAT-": 3700,
3706
+ "TGATA": 3701,
3707
+ "TGATC": 3702,
3708
+ "TGATG": 3703,
3709
+ "TGATT": 3704,
3710
+ "TGC--": 3705,
3711
+ "TGC-A": 3706,
3712
+ "TGC-C": 3707,
3713
+ "TGC-G": 3708,
3714
+ "TGC-T": 3709,
3715
+ "TGCA-": 3710,
3716
+ "TGCAA": 3711,
3717
+ "TGCAC": 3712,
3718
+ "TGCAG": 3713,
3719
+ "TGCAT": 3714,
3720
+ "TGCC-": 3715,
3721
+ "TGCCA": 3716,
3722
+ "TGCCC": 3717,
3723
+ "TGCCG": 3718,
3724
+ "TGCCT": 3719,
3725
+ "TGCG-": 3720,
3726
+ "TGCGA": 3721,
3727
+ "TGCGC": 3722,
3728
+ "TGCGG": 3723,
3729
+ "TGCGT": 3724,
3730
+ "TGCT-": 3725,
3731
+ "TGCTA": 3726,
3732
+ "TGCTC": 3727,
3733
+ "TGCTG": 3728,
3734
+ "TGCTT": 3729,
3735
+ "TGG--": 3730,
3736
+ "TGG-A": 3731,
3737
+ "TGG-C": 3732,
3738
+ "TGG-G": 3733,
3739
+ "TGG-T": 3734,
3740
+ "TGGA-": 3735,
3741
+ "TGGAA": 3736,
3742
+ "TGGAC": 3737,
3743
+ "TGGAG": 3738,
3744
+ "TGGAT": 3739,
3745
+ "TGGC-": 3740,
3746
+ "TGGCA": 3741,
3747
+ "TGGCC": 3742,
3748
+ "TGGCG": 3743,
3749
+ "TGGCT": 3744,
3750
+ "TGGG-": 3745,
3751
+ "TGGGA": 3746,
3752
+ "TGGGC": 3747,
3753
+ "TGGGG": 3748,
3754
+ "TGGGT": 3749,
3755
+ "TGGT-": 3750,
3756
+ "TGGTA": 3751,
3757
+ "TGGTC": 3752,
3758
+ "TGGTG": 3753,
3759
+ "TGGTT": 3754,
3760
+ "TGT--": 3755,
3761
+ "TGT-A": 3756,
3762
+ "TGT-C": 3757,
3763
+ "TGT-G": 3758,
3764
+ "TGT-T": 3759,
3765
+ "TGTA-": 3760,
3766
+ "TGTAA": 3761,
3767
+ "TGTAC": 3762,
3768
+ "TGTAG": 3763,
3769
+ "TGTAT": 3764,
3770
+ "TGTC-": 3765,
3771
+ "TGTCA": 3766,
3772
+ "TGTCC": 3767,
3773
+ "TGTCG": 3768,
3774
+ "TGTCT": 3769,
3775
+ "TGTG-": 3770,
3776
+ "TGTGA": 3771,
3777
+ "TGTGC": 3772,
3778
+ "TGTGG": 3773,
3779
+ "TGTGT": 3774,
3780
+ "TGTT-": 3775,
3781
+ "TGTTA": 3776,
3782
+ "TGTTC": 3777,
3783
+ "TGTTG": 3778,
3784
+ "TGTTT": 3779,
3785
+ "TT---": 3780,
3786
+ "TT--A": 3781,
3787
+ "TT--C": 3782,
3788
+ "TT--G": 3783,
3789
+ "TT--T": 3784,
3790
+ "TT-A-": 3785,
3791
+ "TT-AA": 3786,
3792
+ "TT-AC": 3787,
3793
+ "TT-AG": 3788,
3794
+ "TT-AT": 3789,
3795
+ "TT-C-": 3790,
3796
+ "TT-CA": 3791,
3797
+ "TT-CC": 3792,
3798
+ "TT-CG": 3793,
3799
+ "TT-CT": 3794,
3800
+ "TT-G-": 3795,
3801
+ "TT-GA": 3796,
3802
+ "TT-GC": 3797,
3803
+ "TT-GG": 3798,
3804
+ "TT-GT": 3799,
3805
+ "TT-T-": 3800,
3806
+ "TT-TA": 3801,
3807
+ "TT-TC": 3802,
3808
+ "TT-TG": 3803,
3809
+ "TT-TT": 3804,
3810
+ "TTA--": 3805,
3811
+ "TTA-A": 3806,
3812
+ "TTA-C": 3807,
3813
+ "TTA-G": 3808,
3814
+ "TTA-T": 3809,
3815
+ "TTAA-": 3810,
3816
+ "TTAAA": 3811,
3817
+ "TTAAC": 3812,
3818
+ "TTAAG": 3813,
3819
+ "TTAAT": 3814,
3820
+ "TTAC-": 3815,
3821
+ "TTACA": 3816,
3822
+ "TTACC": 3817,
3823
+ "TTACG": 3818,
3824
+ "TTACT": 3819,
3825
+ "TTAG-": 3820,
3826
+ "TTAGA": 3821,
3827
+ "TTAGC": 3822,
3828
+ "TTAGG": 3823,
3829
+ "TTAGT": 3824,
3830
+ "TTAT-": 3825,
3831
+ "TTATA": 3826,
3832
+ "TTATC": 3827,
3833
+ "TTATG": 3828,
3834
+ "TTATT": 3829,
3835
+ "TTC--": 3830,
3836
+ "TTC-A": 3831,
3837
+ "TTC-C": 3832,
3838
+ "TTC-G": 3833,
3839
+ "TTC-T": 3834,
3840
+ "TTCA-": 3835,
3841
+ "TTCAA": 3836,
3842
+ "TTCAC": 3837,
3843
+ "TTCAG": 3838,
3844
+ "TTCAT": 3839,
3845
+ "TTCC-": 3840,
3846
+ "TTCCA": 3841,
3847
+ "TTCCC": 3842,
3848
+ "TTCCG": 3843,
3849
+ "TTCCT": 3844,
3850
+ "TTCG-": 3845,
3851
+ "TTCGA": 3846,
3852
+ "TTCGC": 3847,
3853
+ "TTCGG": 3848,
3854
+ "TTCGT": 3849,
3855
+ "TTCT-": 3850,
3856
+ "TTCTA": 3851,
3857
+ "TTCTC": 3852,
3858
+ "TTCTG": 3853,
3859
+ "TTCTT": 3854,
3860
+ "TTG--": 3855,
3861
+ "TTG-A": 3856,
3862
+ "TTG-C": 3857,
3863
+ "TTG-G": 3858,
3864
+ "TTG-T": 3859,
3865
+ "TTGA-": 3860,
3866
+ "TTGAA": 3861,
3867
+ "TTGAC": 3862,
3868
+ "TTGAG": 3863,
3869
+ "TTGAT": 3864,
3870
+ "TTGC-": 3865,
3871
+ "TTGCA": 3866,
3872
+ "TTGCC": 3867,
3873
+ "TTGCG": 3868,
3874
+ "TTGCT": 3869,
3875
+ "TTGG-": 3870,
3876
+ "TTGGA": 3871,
3877
+ "TTGGC": 3872,
3878
+ "TTGGG": 3873,
3879
+ "TTGGT": 3874,
3880
+ "TTGT-": 3875,
3881
+ "TTGTA": 3876,
3882
+ "TTGTC": 3877,
3883
+ "TTGTG": 3878,
3884
+ "TTGTT": 3879,
3885
+ "TTT--": 3880,
3886
+ "TTT-A": 3881,
3887
+ "TTT-C": 3882,
3888
+ "TTT-G": 3883,
3889
+ "TTT-T": 3884,
3890
+ "TTTA-": 3885,
3891
+ "TTTAA": 3886,
3892
+ "TTTAC": 3887,
3893
+ "TTTAG": 3888,
3894
+ "TTTAT": 3889,
3895
+ "TTTC-": 3890,
3896
+ "TTTCA": 3891,
3897
+ "TTTCC": 3892,
3898
+ "TTTCG": 3893,
3899
+ "TTTCT": 3894,
3900
+ "TTTG-": 3895,
3901
+ "TTTGA": 3896,
3902
+ "TTTGC": 3897,
3903
+ "TTTGG": 3898,
3904
+ "TTTGT": 3899,
3905
+ "TTTT-": 3900,
3906
+ "TTTTA": 3901,
3907
+ "TTTTC": 3902,
3908
+ "TTTTG": 3903,
3909
+ "TTTTT": 3904
3910
+ }
3911
+ }
vocab/as_json/cont_1k.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 1,
3
+ "vocab_size": 5,
4
+ "trained_vocab": {
5
+ "-": 0,
6
+ "A": 1,
7
+ "C": 2,
8
+ "G": 3,
9
+ "T": 4
10
+ }
11
+ }
vocab/as_json/cont_2k.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 2,
3
+ "vocab_size": 25,
4
+ "trained_vocab": {
5
+ "--": 0,
6
+ "-A": 1,
7
+ "-C": 2,
8
+ "-G": 3,
9
+ "-T": 4,
10
+ "A-": 5,
11
+ "AA": 6,
12
+ "AC": 7,
13
+ "AG": 8,
14
+ "AT": 9,
15
+ "C-": 10,
16
+ "CA": 11,
17
+ "CC": 12,
18
+ "CG": 13,
19
+ "CT": 14,
20
+ "G-": 15,
21
+ "GA": 16,
22
+ "GC": 17,
23
+ "GG": 18,
24
+ "GT": 19,
25
+ "T-": 20,
26
+ "TA": 21,
27
+ "TC": 22,
28
+ "TG": 23,
29
+ "TT": 24
30
+ }
31
+ }
vocab/as_json/cont_3k.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 3,
3
+ "vocab_size": 125,
4
+ "trained_vocab": {
5
+ "---": 0,
6
+ "--A": 1,
7
+ "--C": 2,
8
+ "--G": 3,
9
+ "--T": 4,
10
+ "-A-": 5,
11
+ "-AA": 6,
12
+ "-AC": 7,
13
+ "-AG": 8,
14
+ "-AT": 9,
15
+ "-C-": 10,
16
+ "-CA": 11,
17
+ "-CC": 12,
18
+ "-CG": 13,
19
+ "-CT": 14,
20
+ "-G-": 15,
21
+ "-GA": 16,
22
+ "-GC": 17,
23
+ "-GG": 18,
24
+ "-GT": 19,
25
+ "-T-": 20,
26
+ "-TA": 21,
27
+ "-TC": 22,
28
+ "-TG": 23,
29
+ "-TT": 24,
30
+ "A--": 25,
31
+ "A-A": 26,
32
+ "A-C": 27,
33
+ "A-G": 28,
34
+ "A-T": 29,
35
+ "AA-": 30,
36
+ "AAA": 31,
37
+ "AAC": 32,
38
+ "AAG": 33,
39
+ "AAT": 34,
40
+ "AC-": 35,
41
+ "ACA": 36,
42
+ "ACC": 37,
43
+ "ACG": 38,
44
+ "ACT": 39,
45
+ "AG-": 40,
46
+ "AGA": 41,
47
+ "AGC": 42,
48
+ "AGG": 43,
49
+ "AGT": 44,
50
+ "AT-": 45,
51
+ "ATA": 46,
52
+ "ATC": 47,
53
+ "ATG": 48,
54
+ "ATT": 49,
55
+ "C--": 50,
56
+ "C-A": 51,
57
+ "C-C": 52,
58
+ "C-G": 53,
59
+ "C-T": 54,
60
+ "CA-": 55,
61
+ "CAA": 56,
62
+ "CAC": 57,
63
+ "CAG": 58,
64
+ "CAT": 59,
65
+ "CC-": 60,
66
+ "CCA": 61,
67
+ "CCC": 62,
68
+ "CCG": 63,
69
+ "CCT": 64,
70
+ "CG-": 65,
71
+ "CGA": 66,
72
+ "CGC": 67,
73
+ "CGG": 68,
74
+ "CGT": 69,
75
+ "CT-": 70,
76
+ "CTA": 71,
77
+ "CTC": 72,
78
+ "CTG": 73,
79
+ "CTT": 74,
80
+ "G--": 75,
81
+ "G-A": 76,
82
+ "G-C": 77,
83
+ "G-G": 78,
84
+ "G-T": 79,
85
+ "GA-": 80,
86
+ "GAA": 81,
87
+ "GAC": 82,
88
+ "GAG": 83,
89
+ "GAT": 84,
90
+ "GC-": 85,
91
+ "GCA": 86,
92
+ "GCC": 87,
93
+ "GCG": 88,
94
+ "GCT": 89,
95
+ "GG-": 90,
96
+ "GGA": 91,
97
+ "GGC": 92,
98
+ "GGG": 93,
99
+ "GGT": 94,
100
+ "GT-": 95,
101
+ "GTA": 96,
102
+ "GTC": 97,
103
+ "GTG": 98,
104
+ "GTT": 99,
105
+ "T--": 100,
106
+ "T-A": 101,
107
+ "T-C": 102,
108
+ "T-G": 103,
109
+ "T-T": 104,
110
+ "TA-": 105,
111
+ "TAA": 106,
112
+ "TAC": 107,
113
+ "TAG": 108,
114
+ "TAT": 109,
115
+ "TC-": 110,
116
+ "TCA": 111,
117
+ "TCC": 112,
118
+ "TCG": 113,
119
+ "TCT": 114,
120
+ "TG-": 115,
121
+ "TGA": 116,
122
+ "TGC": 117,
123
+ "TGG": 118,
124
+ "TGT": 119,
125
+ "TT-": 120,
126
+ "TTA": 121,
127
+ "TTC": 122,
128
+ "TTG": 123,
129
+ "TTT": 124
130
+ }
131
+ }
vocab/as_json/cont_4k.json ADDED
@@ -0,0 +1,631 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 4,
3
+ "vocab_size": 625,
4
+ "trained_vocab": {
5
+ "----": 0,
6
+ "---A": 1,
7
+ "---C": 2,
8
+ "---G": 3,
9
+ "---T": 4,
10
+ "--A-": 5,
11
+ "--AA": 6,
12
+ "--AC": 7,
13
+ "--AG": 8,
14
+ "--AT": 9,
15
+ "--C-": 10,
16
+ "--CA": 11,
17
+ "--CC": 12,
18
+ "--CG": 13,
19
+ "--CT": 14,
20
+ "--G-": 15,
21
+ "--GA": 16,
22
+ "--GC": 17,
23
+ "--GG": 18,
24
+ "--GT": 19,
25
+ "--T-": 20,
26
+ "--TA": 21,
27
+ "--TC": 22,
28
+ "--TG": 23,
29
+ "--TT": 24,
30
+ "-A--": 25,
31
+ "-A-A": 26,
32
+ "-A-C": 27,
33
+ "-A-G": 28,
34
+ "-A-T": 29,
35
+ "-AA-": 30,
36
+ "-AAA": 31,
37
+ "-AAC": 32,
38
+ "-AAG": 33,
39
+ "-AAT": 34,
40
+ "-AC-": 35,
41
+ "-ACA": 36,
42
+ "-ACC": 37,
43
+ "-ACG": 38,
44
+ "-ACT": 39,
45
+ "-AG-": 40,
46
+ "-AGA": 41,
47
+ "-AGC": 42,
48
+ "-AGG": 43,
49
+ "-AGT": 44,
50
+ "-AT-": 45,
51
+ "-ATA": 46,
52
+ "-ATC": 47,
53
+ "-ATG": 48,
54
+ "-ATT": 49,
55
+ "-C--": 50,
56
+ "-C-A": 51,
57
+ "-C-C": 52,
58
+ "-C-G": 53,
59
+ "-C-T": 54,
60
+ "-CA-": 55,
61
+ "-CAA": 56,
62
+ "-CAC": 57,
63
+ "-CAG": 58,
64
+ "-CAT": 59,
65
+ "-CC-": 60,
66
+ "-CCA": 61,
67
+ "-CCC": 62,
68
+ "-CCG": 63,
69
+ "-CCT": 64,
70
+ "-CG-": 65,
71
+ "-CGA": 66,
72
+ "-CGC": 67,
73
+ "-CGG": 68,
74
+ "-CGT": 69,
75
+ "-CT-": 70,
76
+ "-CTA": 71,
77
+ "-CTC": 72,
78
+ "-CTG": 73,
79
+ "-CTT": 74,
80
+ "-G--": 75,
81
+ "-G-A": 76,
82
+ "-G-C": 77,
83
+ "-G-G": 78,
84
+ "-G-T": 79,
85
+ "-GA-": 80,
86
+ "-GAA": 81,
87
+ "-GAC": 82,
88
+ "-GAG": 83,
89
+ "-GAT": 84,
90
+ "-GC-": 85,
91
+ "-GCA": 86,
92
+ "-GCC": 87,
93
+ "-GCG": 88,
94
+ "-GCT": 89,
95
+ "-GG-": 90,
96
+ "-GGA": 91,
97
+ "-GGC": 92,
98
+ "-GGG": 93,
99
+ "-GGT": 94,
100
+ "-GT-": 95,
101
+ "-GTA": 96,
102
+ "-GTC": 97,
103
+ "-GTG": 98,
104
+ "-GTT": 99,
105
+ "-T--": 100,
106
+ "-T-A": 101,
107
+ "-T-C": 102,
108
+ "-T-G": 103,
109
+ "-T-T": 104,
110
+ "-TA-": 105,
111
+ "-TAA": 106,
112
+ "-TAC": 107,
113
+ "-TAG": 108,
114
+ "-TAT": 109,
115
+ "-TC-": 110,
116
+ "-TCA": 111,
117
+ "-TCC": 112,
118
+ "-TCG": 113,
119
+ "-TCT": 114,
120
+ "-TG-": 115,
121
+ "-TGA": 116,
122
+ "-TGC": 117,
123
+ "-TGG": 118,
124
+ "-TGT": 119,
125
+ "-TT-": 120,
126
+ "-TTA": 121,
127
+ "-TTC": 122,
128
+ "-TTG": 123,
129
+ "-TTT": 124,
130
+ "A---": 125,
131
+ "A--A": 126,
132
+ "A--C": 127,
133
+ "A--G": 128,
134
+ "A--T": 129,
135
+ "A-A-": 130,
136
+ "A-AA": 131,
137
+ "A-AC": 132,
138
+ "A-AG": 133,
139
+ "A-AT": 134,
140
+ "A-C-": 135,
141
+ "A-CA": 136,
142
+ "A-CC": 137,
143
+ "A-CG": 138,
144
+ "A-CT": 139,
145
+ "A-G-": 140,
146
+ "A-GA": 141,
147
+ "A-GC": 142,
148
+ "A-GG": 143,
149
+ "A-GT": 144,
150
+ "A-T-": 145,
151
+ "A-TA": 146,
152
+ "A-TC": 147,
153
+ "A-TG": 148,
154
+ "A-TT": 149,
155
+ "AA--": 150,
156
+ "AA-A": 151,
157
+ "AA-C": 152,
158
+ "AA-G": 153,
159
+ "AA-T": 154,
160
+ "AAA-": 155,
161
+ "AAAA": 156,
162
+ "AAAC": 157,
163
+ "AAAG": 158,
164
+ "AAAT": 159,
165
+ "AAC-": 160,
166
+ "AACA": 161,
167
+ "AACC": 162,
168
+ "AACG": 163,
169
+ "AACT": 164,
170
+ "AAG-": 165,
171
+ "AAGA": 166,
172
+ "AAGC": 167,
173
+ "AAGG": 168,
174
+ "AAGT": 169,
175
+ "AAT-": 170,
176
+ "AATA": 171,
177
+ "AATC": 172,
178
+ "AATG": 173,
179
+ "AATT": 174,
180
+ "AC--": 175,
181
+ "AC-A": 176,
182
+ "AC-C": 177,
183
+ "AC-G": 178,
184
+ "AC-T": 179,
185
+ "ACA-": 180,
186
+ "ACAA": 181,
187
+ "ACAC": 182,
188
+ "ACAG": 183,
189
+ "ACAT": 184,
190
+ "ACC-": 185,
191
+ "ACCA": 186,
192
+ "ACCC": 187,
193
+ "ACCG": 188,
194
+ "ACCT": 189,
195
+ "ACG-": 190,
196
+ "ACGA": 191,
197
+ "ACGC": 192,
198
+ "ACGG": 193,
199
+ "ACGT": 194,
200
+ "ACT-": 195,
201
+ "ACTA": 196,
202
+ "ACTC": 197,
203
+ "ACTG": 198,
204
+ "ACTT": 199,
205
+ "AG--": 200,
206
+ "AG-A": 201,
207
+ "AG-C": 202,
208
+ "AG-G": 203,
209
+ "AG-T": 204,
210
+ "AGA-": 205,
211
+ "AGAA": 206,
212
+ "AGAC": 207,
213
+ "AGAG": 208,
214
+ "AGAT": 209,
215
+ "AGC-": 210,
216
+ "AGCA": 211,
217
+ "AGCC": 212,
218
+ "AGCG": 213,
219
+ "AGCT": 214,
220
+ "AGG-": 215,
221
+ "AGGA": 216,
222
+ "AGGC": 217,
223
+ "AGGG": 218,
224
+ "AGGT": 219,
225
+ "AGT-": 220,
226
+ "AGTA": 221,
227
+ "AGTC": 222,
228
+ "AGTG": 223,
229
+ "AGTT": 224,
230
+ "AT--": 225,
231
+ "AT-A": 226,
232
+ "AT-C": 227,
233
+ "AT-G": 228,
234
+ "AT-T": 229,
235
+ "ATA-": 230,
236
+ "ATAA": 231,
237
+ "ATAC": 232,
238
+ "ATAG": 233,
239
+ "ATAT": 234,
240
+ "ATC-": 235,
241
+ "ATCA": 236,
242
+ "ATCC": 237,
243
+ "ATCG": 238,
244
+ "ATCT": 239,
245
+ "ATG-": 240,
246
+ "ATGA": 241,
247
+ "ATGC": 242,
248
+ "ATGG": 243,
249
+ "ATGT": 244,
250
+ "ATT-": 245,
251
+ "ATTA": 246,
252
+ "ATTC": 247,
253
+ "ATTG": 248,
254
+ "ATTT": 249,
255
+ "C---": 250,
256
+ "C--A": 251,
257
+ "C--C": 252,
258
+ "C--G": 253,
259
+ "C--T": 254,
260
+ "C-A-": 255,
261
+ "C-AA": 256,
262
+ "C-AC": 257,
263
+ "C-AG": 258,
264
+ "C-AT": 259,
265
+ "C-C-": 260,
266
+ "C-CA": 261,
267
+ "C-CC": 262,
268
+ "C-CG": 263,
269
+ "C-CT": 264,
270
+ "C-G-": 265,
271
+ "C-GA": 266,
272
+ "C-GC": 267,
273
+ "C-GG": 268,
274
+ "C-GT": 269,
275
+ "C-T-": 270,
276
+ "C-TA": 271,
277
+ "C-TC": 272,
278
+ "C-TG": 273,
279
+ "C-TT": 274,
280
+ "CA--": 275,
281
+ "CA-A": 276,
282
+ "CA-C": 277,
283
+ "CA-G": 278,
284
+ "CA-T": 279,
285
+ "CAA-": 280,
286
+ "CAAA": 281,
287
+ "CAAC": 282,
288
+ "CAAG": 283,
289
+ "CAAT": 284,
290
+ "CAC-": 285,
291
+ "CACA": 286,
292
+ "CACC": 287,
293
+ "CACG": 288,
294
+ "CACT": 289,
295
+ "CAG-": 290,
296
+ "CAGA": 291,
297
+ "CAGC": 292,
298
+ "CAGG": 293,
299
+ "CAGT": 294,
300
+ "CAT-": 295,
301
+ "CATA": 296,
302
+ "CATC": 297,
303
+ "CATG": 298,
304
+ "CATT": 299,
305
+ "CC--": 300,
306
+ "CC-A": 301,
307
+ "CC-C": 302,
308
+ "CC-G": 303,
309
+ "CC-T": 304,
310
+ "CCA-": 305,
311
+ "CCAA": 306,
312
+ "CCAC": 307,
313
+ "CCAG": 308,
314
+ "CCAT": 309,
315
+ "CCC-": 310,
316
+ "CCCA": 311,
317
+ "CCCC": 312,
318
+ "CCCG": 313,
319
+ "CCCT": 314,
320
+ "CCG-": 315,
321
+ "CCGA": 316,
322
+ "CCGC": 317,
323
+ "CCGG": 318,
324
+ "CCGT": 319,
325
+ "CCT-": 320,
326
+ "CCTA": 321,
327
+ "CCTC": 322,
328
+ "CCTG": 323,
329
+ "CCTT": 324,
330
+ "CG--": 325,
331
+ "CG-A": 326,
332
+ "CG-C": 327,
333
+ "CG-G": 328,
334
+ "CG-T": 329,
335
+ "CGA-": 330,
336
+ "CGAA": 331,
337
+ "CGAC": 332,
338
+ "CGAG": 333,
339
+ "CGAT": 334,
340
+ "CGC-": 335,
341
+ "CGCA": 336,
342
+ "CGCC": 337,
343
+ "CGCG": 338,
344
+ "CGCT": 339,
345
+ "CGG-": 340,
346
+ "CGGA": 341,
347
+ "CGGC": 342,
348
+ "CGGG": 343,
349
+ "CGGT": 344,
350
+ "CGT-": 345,
351
+ "CGTA": 346,
352
+ "CGTC": 347,
353
+ "CGTG": 348,
354
+ "CGTT": 349,
355
+ "CT--": 350,
356
+ "CT-A": 351,
357
+ "CT-C": 352,
358
+ "CT-G": 353,
359
+ "CT-T": 354,
360
+ "CTA-": 355,
361
+ "CTAA": 356,
362
+ "CTAC": 357,
363
+ "CTAG": 358,
364
+ "CTAT": 359,
365
+ "CTC-": 360,
366
+ "CTCA": 361,
367
+ "CTCC": 362,
368
+ "CTCG": 363,
369
+ "CTCT": 364,
370
+ "CTG-": 365,
371
+ "CTGA": 366,
372
+ "CTGC": 367,
373
+ "CTGG": 368,
374
+ "CTGT": 369,
375
+ "CTT-": 370,
376
+ "CTTA": 371,
377
+ "CTTC": 372,
378
+ "CTTG": 373,
379
+ "CTTT": 374,
380
+ "G---": 375,
381
+ "G--A": 376,
382
+ "G--C": 377,
383
+ "G--G": 378,
384
+ "G--T": 379,
385
+ "G-A-": 380,
386
+ "G-AA": 381,
387
+ "G-AC": 382,
388
+ "G-AG": 383,
389
+ "G-AT": 384,
390
+ "G-C-": 385,
391
+ "G-CA": 386,
392
+ "G-CC": 387,
393
+ "G-CG": 388,
394
+ "G-CT": 389,
395
+ "G-G-": 390,
396
+ "G-GA": 391,
397
+ "G-GC": 392,
398
+ "G-GG": 393,
399
+ "G-GT": 394,
400
+ "G-T-": 395,
401
+ "G-TA": 396,
402
+ "G-TC": 397,
403
+ "G-TG": 398,
404
+ "G-TT": 399,
405
+ "GA--": 400,
406
+ "GA-A": 401,
407
+ "GA-C": 402,
408
+ "GA-G": 403,
409
+ "GA-T": 404,
410
+ "GAA-": 405,
411
+ "GAAA": 406,
412
+ "GAAC": 407,
413
+ "GAAG": 408,
414
+ "GAAT": 409,
415
+ "GAC-": 410,
416
+ "GACA": 411,
417
+ "GACC": 412,
418
+ "GACG": 413,
419
+ "GACT": 414,
420
+ "GAG-": 415,
421
+ "GAGA": 416,
422
+ "GAGC": 417,
423
+ "GAGG": 418,
424
+ "GAGT": 419,
425
+ "GAT-": 420,
426
+ "GATA": 421,
427
+ "GATC": 422,
428
+ "GATG": 423,
429
+ "GATT": 424,
430
+ "GC--": 425,
431
+ "GC-A": 426,
432
+ "GC-C": 427,
433
+ "GC-G": 428,
434
+ "GC-T": 429,
435
+ "GCA-": 430,
436
+ "GCAA": 431,
437
+ "GCAC": 432,
438
+ "GCAG": 433,
439
+ "GCAT": 434,
440
+ "GCC-": 435,
441
+ "GCCA": 436,
442
+ "GCCC": 437,
443
+ "GCCG": 438,
444
+ "GCCT": 439,
445
+ "GCG-": 440,
446
+ "GCGA": 441,
447
+ "GCGC": 442,
448
+ "GCGG": 443,
449
+ "GCGT": 444,
450
+ "GCT-": 445,
451
+ "GCTA": 446,
452
+ "GCTC": 447,
453
+ "GCTG": 448,
454
+ "GCTT": 449,
455
+ "GG--": 450,
456
+ "GG-A": 451,
457
+ "GG-C": 452,
458
+ "GG-G": 453,
459
+ "GG-T": 454,
460
+ "GGA-": 455,
461
+ "GGAA": 456,
462
+ "GGAC": 457,
463
+ "GGAG": 458,
464
+ "GGAT": 459,
465
+ "GGC-": 460,
466
+ "GGCA": 461,
467
+ "GGCC": 462,
468
+ "GGCG": 463,
469
+ "GGCT": 464,
470
+ "GGG-": 465,
471
+ "GGGA": 466,
472
+ "GGGC": 467,
473
+ "GGGG": 468,
474
+ "GGGT": 469,
475
+ "GGT-": 470,
476
+ "GGTA": 471,
477
+ "GGTC": 472,
478
+ "GGTG": 473,
479
+ "GGTT": 474,
480
+ "GT--": 475,
481
+ "GT-A": 476,
482
+ "GT-C": 477,
483
+ "GT-G": 478,
484
+ "GT-T": 479,
485
+ "GTA-": 480,
486
+ "GTAA": 481,
487
+ "GTAC": 482,
488
+ "GTAG": 483,
489
+ "GTAT": 484,
490
+ "GTC-": 485,
491
+ "GTCA": 486,
492
+ "GTCC": 487,
493
+ "GTCG": 488,
494
+ "GTCT": 489,
495
+ "GTG-": 490,
496
+ "GTGA": 491,
497
+ "GTGC": 492,
498
+ "GTGG": 493,
499
+ "GTGT": 494,
500
+ "GTT-": 495,
501
+ "GTTA": 496,
502
+ "GTTC": 497,
503
+ "GTTG": 498,
504
+ "GTTT": 499,
505
+ "T---": 500,
506
+ "T--A": 501,
507
+ "T--C": 502,
508
+ "T--G": 503,
509
+ "T--T": 504,
510
+ "T-A-": 505,
511
+ "T-AA": 506,
512
+ "T-AC": 507,
513
+ "T-AG": 508,
514
+ "T-AT": 509,
515
+ "T-C-": 510,
516
+ "T-CA": 511,
517
+ "T-CC": 512,
518
+ "T-CG": 513,
519
+ "T-CT": 514,
520
+ "T-G-": 515,
521
+ "T-GA": 516,
522
+ "T-GC": 517,
523
+ "T-GG": 518,
524
+ "T-GT": 519,
525
+ "T-T-": 520,
526
+ "T-TA": 521,
527
+ "T-TC": 522,
528
+ "T-TG": 523,
529
+ "T-TT": 524,
530
+ "TA--": 525,
531
+ "TA-A": 526,
532
+ "TA-C": 527,
533
+ "TA-G": 528,
534
+ "TA-T": 529,
535
+ "TAA-": 530,
536
+ "TAAA": 531,
537
+ "TAAC": 532,
538
+ "TAAG": 533,
539
+ "TAAT": 534,
540
+ "TAC-": 535,
541
+ "TACA": 536,
542
+ "TACC": 537,
543
+ "TACG": 538,
544
+ "TACT": 539,
545
+ "TAG-": 540,
546
+ "TAGA": 541,
547
+ "TAGC": 542,
548
+ "TAGG": 543,
549
+ "TAGT": 544,
550
+ "TAT-": 545,
551
+ "TATA": 546,
552
+ "TATC": 547,
553
+ "TATG": 548,
554
+ "TATT": 549,
555
+ "TC--": 550,
556
+ "TC-A": 551,
557
+ "TC-C": 552,
558
+ "TC-G": 553,
559
+ "TC-T": 554,
560
+ "TCA-": 555,
561
+ "TCAA": 556,
562
+ "TCAC": 557,
563
+ "TCAG": 558,
564
+ "TCAT": 559,
565
+ "TCC-": 560,
566
+ "TCCA": 561,
567
+ "TCCC": 562,
568
+ "TCCG": 563,
569
+ "TCCT": 564,
570
+ "TCG-": 565,
571
+ "TCGA": 566,
572
+ "TCGC": 567,
573
+ "TCGG": 568,
574
+ "TCGT": 569,
575
+ "TCT-": 570,
576
+ "TCTA": 571,
577
+ "TCTC": 572,
578
+ "TCTG": 573,
579
+ "TCTT": 574,
580
+ "TG--": 575,
581
+ "TG-A": 576,
582
+ "TG-C": 577,
583
+ "TG-G": 578,
584
+ "TG-T": 579,
585
+ "TGA-": 580,
586
+ "TGAA": 581,
587
+ "TGAC": 582,
588
+ "TGAG": 583,
589
+ "TGAT": 584,
590
+ "TGC-": 585,
591
+ "TGCA": 586,
592
+ "TGCC": 587,
593
+ "TGCG": 588,
594
+ "TGCT": 589,
595
+ "TGG-": 590,
596
+ "TGGA": 591,
597
+ "TGGC": 592,
598
+ "TGGG": 593,
599
+ "TGGT": 594,
600
+ "TGT-": 595,
601
+ "TGTA": 596,
602
+ "TGTC": 597,
603
+ "TGTG": 598,
604
+ "TGTT": 599,
605
+ "TT--": 600,
606
+ "TT-A": 601,
607
+ "TT-C": 602,
608
+ "TT-G": 603,
609
+ "TT-T": 604,
610
+ "TTA-": 605,
611
+ "TTAA": 606,
612
+ "TTAC": 607,
613
+ "TTAG": 608,
614
+ "TTAT": 609,
615
+ "TTC-": 610,
616
+ "TTCA": 611,
617
+ "TTCC": 612,
618
+ "TTCG": 613,
619
+ "TTCT": 614,
620
+ "TTG-": 615,
621
+ "TTGA": 616,
622
+ "TTGC": 617,
623
+ "TTGG": 618,
624
+ "TTGT": 619,
625
+ "TTT-": 620,
626
+ "TTTA": 621,
627
+ "TTTC": 622,
628
+ "TTTG": 623,
629
+ "TTTT": 624
630
+ }
631
+ }
vocab/as_json/cont_5k.json ADDED
@@ -0,0 +1,3131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kmer": 5,
3
+ "vocab_size": 3125,
4
+ "trained_vocab": {
5
+ "-----": 0,
6
+ "----A": 1,
7
+ "----C": 2,
8
+ "----G": 3,
9
+ "----T": 4,
10
+ "---A-": 5,
11
+ "---AA": 6,
12
+ "---AC": 7,
13
+ "---AG": 8,
14
+ "---AT": 9,
15
+ "---C-": 10,
16
+ "---CA": 11,
17
+ "---CC": 12,
18
+ "---CG": 13,
19
+ "---CT": 14,
20
+ "---G-": 15,
21
+ "---GA": 16,
22
+ "---GC": 17,
23
+ "---GG": 18,
24
+ "---GT": 19,
25
+ "---T-": 20,
26
+ "---TA": 21,
27
+ "---TC": 22,
28
+ "---TG": 23,
29
+ "---TT": 24,
30
+ "--A--": 25,
31
+ "--A-A": 26,
32
+ "--A-C": 27,
33
+ "--A-G": 28,
34
+ "--A-T": 29,
35
+ "--AA-": 30,
36
+ "--AAA": 31,
37
+ "--AAC": 32,
38
+ "--AAG": 33,
39
+ "--AAT": 34,
40
+ "--AC-": 35,
41
+ "--ACA": 36,
42
+ "--ACC": 37,
43
+ "--ACG": 38,
44
+ "--ACT": 39,
45
+ "--AG-": 40,
46
+ "--AGA": 41,
47
+ "--AGC": 42,
48
+ "--AGG": 43,
49
+ "--AGT": 44,
50
+ "--AT-": 45,
51
+ "--ATA": 46,
52
+ "--ATC": 47,
53
+ "--ATG": 48,
54
+ "--ATT": 49,
55
+ "--C--": 50,
56
+ "--C-A": 51,
57
+ "--C-C": 52,
58
+ "--C-G": 53,
59
+ "--C-T": 54,
60
+ "--CA-": 55,
61
+ "--CAA": 56,
62
+ "--CAC": 57,
63
+ "--CAG": 58,
64
+ "--CAT": 59,
65
+ "--CC-": 60,
66
+ "--CCA": 61,
67
+ "--CCC": 62,
68
+ "--CCG": 63,
69
+ "--CCT": 64,
70
+ "--CG-": 65,
71
+ "--CGA": 66,
72
+ "--CGC": 67,
73
+ "--CGG": 68,
74
+ "--CGT": 69,
75
+ "--CT-": 70,
76
+ "--CTA": 71,
77
+ "--CTC": 72,
78
+ "--CTG": 73,
79
+ "--CTT": 74,
80
+ "--G--": 75,
81
+ "--G-A": 76,
82
+ "--G-C": 77,
83
+ "--G-G": 78,
84
+ "--G-T": 79,
85
+ "--GA-": 80,
86
+ "--GAA": 81,
87
+ "--GAC": 82,
88
+ "--GAG": 83,
89
+ "--GAT": 84,
90
+ "--GC-": 85,
91
+ "--GCA": 86,
92
+ "--GCC": 87,
93
+ "--GCG": 88,
94
+ "--GCT": 89,
95
+ "--GG-": 90,
96
+ "--GGA": 91,
97
+ "--GGC": 92,
98
+ "--GGG": 93,
99
+ "--GGT": 94,
100
+ "--GT-": 95,
101
+ "--GTA": 96,
102
+ "--GTC": 97,
103
+ "--GTG": 98,
104
+ "--GTT": 99,
105
+ "--T--": 100,
106
+ "--T-A": 101,
107
+ "--T-C": 102,
108
+ "--T-G": 103,
109
+ "--T-T": 104,
110
+ "--TA-": 105,
111
+ "--TAA": 106,
112
+ "--TAC": 107,
113
+ "--TAG": 108,
114
+ "--TAT": 109,
115
+ "--TC-": 110,
116
+ "--TCA": 111,
117
+ "--TCC": 112,
118
+ "--TCG": 113,
119
+ "--TCT": 114,
120
+ "--TG-": 115,
121
+ "--TGA": 116,
122
+ "--TGC": 117,
123
+ "--TGG": 118,
124
+ "--TGT": 119,
125
+ "--TT-": 120,
126
+ "--TTA": 121,
127
+ "--TTC": 122,
128
+ "--TTG": 123,
129
+ "--TTT": 124,
130
+ "-A---": 125,
131
+ "-A--A": 126,
132
+ "-A--C": 127,
133
+ "-A--G": 128,
134
+ "-A--T": 129,
135
+ "-A-A-": 130,
136
+ "-A-AA": 131,
137
+ "-A-AC": 132,
138
+ "-A-AG": 133,
139
+ "-A-AT": 134,
140
+ "-A-C-": 135,
141
+ "-A-CA": 136,
142
+ "-A-CC": 137,
143
+ "-A-CG": 138,
144
+ "-A-CT": 139,
145
+ "-A-G-": 140,
146
+ "-A-GA": 141,
147
+ "-A-GC": 142,
148
+ "-A-GG": 143,
149
+ "-A-GT": 144,
150
+ "-A-T-": 145,
151
+ "-A-TA": 146,
152
+ "-A-TC": 147,
153
+ "-A-TG": 148,
154
+ "-A-TT": 149,
155
+ "-AA--": 150,
156
+ "-AA-A": 151,
157
+ "-AA-C": 152,
158
+ "-AA-G": 153,
159
+ "-AA-T": 154,
160
+ "-AAA-": 155,
161
+ "-AAAA": 156,
162
+ "-AAAC": 157,
163
+ "-AAAG": 158,
164
+ "-AAAT": 159,
165
+ "-AAC-": 160,
166
+ "-AACA": 161,
167
+ "-AACC": 162,
168
+ "-AACG": 163,
169
+ "-AACT": 164,
170
+ "-AAG-": 165,
171
+ "-AAGA": 166,
172
+ "-AAGC": 167,
173
+ "-AAGG": 168,
174
+ "-AAGT": 169,
175
+ "-AAT-": 170,
176
+ "-AATA": 171,
177
+ "-AATC": 172,
178
+ "-AATG": 173,
179
+ "-AATT": 174,
180
+ "-AC--": 175,
181
+ "-AC-A": 176,
182
+ "-AC-C": 177,
183
+ "-AC-G": 178,
184
+ "-AC-T": 179,
185
+ "-ACA-": 180,
186
+ "-ACAA": 181,
187
+ "-ACAC": 182,
188
+ "-ACAG": 183,
189
+ "-ACAT": 184,
190
+ "-ACC-": 185,
191
+ "-ACCA": 186,
192
+ "-ACCC": 187,
193
+ "-ACCG": 188,
194
+ "-ACCT": 189,
195
+ "-ACG-": 190,
196
+ "-ACGA": 191,
197
+ "-ACGC": 192,
198
+ "-ACGG": 193,
199
+ "-ACGT": 194,
200
+ "-ACT-": 195,
201
+ "-ACTA": 196,
202
+ "-ACTC": 197,
203
+ "-ACTG": 198,
204
+ "-ACTT": 199,
205
+ "-AG--": 200,
206
+ "-AG-A": 201,
207
+ "-AG-C": 202,
208
+ "-AG-G": 203,
209
+ "-AG-T": 204,
210
+ "-AGA-": 205,
211
+ "-AGAA": 206,
212
+ "-AGAC": 207,
213
+ "-AGAG": 208,
214
+ "-AGAT": 209,
215
+ "-AGC-": 210,
216
+ "-AGCA": 211,
217
+ "-AGCC": 212,
218
+ "-AGCG": 213,
219
+ "-AGCT": 214,
220
+ "-AGG-": 215,
221
+ "-AGGA": 216,
222
+ "-AGGC": 217,
223
+ "-AGGG": 218,
224
+ "-AGGT": 219,
225
+ "-AGT-": 220,
226
+ "-AGTA": 221,
227
+ "-AGTC": 222,
228
+ "-AGTG": 223,
229
+ "-AGTT": 224,
230
+ "-AT--": 225,
231
+ "-AT-A": 226,
232
+ "-AT-C": 227,
233
+ "-AT-G": 228,
234
+ "-AT-T": 229,
235
+ "-ATA-": 230,
236
+ "-ATAA": 231,
237
+ "-ATAC": 232,
238
+ "-ATAG": 233,
239
+ "-ATAT": 234,
240
+ "-ATC-": 235,
241
+ "-ATCA": 236,
242
+ "-ATCC": 237,
243
+ "-ATCG": 238,
244
+ "-ATCT": 239,
245
+ "-ATG-": 240,
246
+ "-ATGA": 241,
247
+ "-ATGC": 242,
248
+ "-ATGG": 243,
249
+ "-ATGT": 244,
250
+ "-ATT-": 245,
251
+ "-ATTA": 246,
252
+ "-ATTC": 247,
253
+ "-ATTG": 248,
254
+ "-ATTT": 249,
255
+ "-C---": 250,
256
+ "-C--A": 251,
257
+ "-C--C": 252,
258
+ "-C--G": 253,
259
+ "-C--T": 254,
260
+ "-C-A-": 255,
261
+ "-C-AA": 256,
262
+ "-C-AC": 257,
263
+ "-C-AG": 258,
264
+ "-C-AT": 259,
265
+ "-C-C-": 260,
266
+ "-C-CA": 261,
267
+ "-C-CC": 262,
268
+ "-C-CG": 263,
269
+ "-C-CT": 264,
270
+ "-C-G-": 265,
271
+ "-C-GA": 266,
272
+ "-C-GC": 267,
273
+ "-C-GG": 268,
274
+ "-C-GT": 269,
275
+ "-C-T-": 270,
276
+ "-C-TA": 271,
277
+ "-C-TC": 272,
278
+ "-C-TG": 273,
279
+ "-C-TT": 274,
280
+ "-CA--": 275,
281
+ "-CA-A": 276,
282
+ "-CA-C": 277,
283
+ "-CA-G": 278,
284
+ "-CA-T": 279,
285
+ "-CAA-": 280,
286
+ "-CAAA": 281,
287
+ "-CAAC": 282,
288
+ "-CAAG": 283,
289
+ "-CAAT": 284,
290
+ "-CAC-": 285,
291
+ "-CACA": 286,
292
+ "-CACC": 287,
293
+ "-CACG": 288,
294
+ "-CACT": 289,
295
+ "-CAG-": 290,
296
+ "-CAGA": 291,
297
+ "-CAGC": 292,
298
+ "-CAGG": 293,
299
+ "-CAGT": 294,
300
+ "-CAT-": 295,
301
+ "-CATA": 296,
302
+ "-CATC": 297,
303
+ "-CATG": 298,
304
+ "-CATT": 299,
305
+ "-CC--": 300,
306
+ "-CC-A": 301,
307
+ "-CC-C": 302,
308
+ "-CC-G": 303,
309
+ "-CC-T": 304,
310
+ "-CCA-": 305,
311
+ "-CCAA": 306,
312
+ "-CCAC": 307,
313
+ "-CCAG": 308,
314
+ "-CCAT": 309,
315
+ "-CCC-": 310,
316
+ "-CCCA": 311,
317
+ "-CCCC": 312,
318
+ "-CCCG": 313,
319
+ "-CCCT": 314,
320
+ "-CCG-": 315,
321
+ "-CCGA": 316,
322
+ "-CCGC": 317,
323
+ "-CCGG": 318,
324
+ "-CCGT": 319,
325
+ "-CCT-": 320,
326
+ "-CCTA": 321,
327
+ "-CCTC": 322,
328
+ "-CCTG": 323,
329
+ "-CCTT": 324,
330
+ "-CG--": 325,
331
+ "-CG-A": 326,
332
+ "-CG-C": 327,
333
+ "-CG-G": 328,
334
+ "-CG-T": 329,
335
+ "-CGA-": 330,
336
+ "-CGAA": 331,
337
+ "-CGAC": 332,
338
+ "-CGAG": 333,
339
+ "-CGAT": 334,
340
+ "-CGC-": 335,
341
+ "-CGCA": 336,
342
+ "-CGCC": 337,
343
+ "-CGCG": 338,
344
+ "-CGCT": 339,
345
+ "-CGG-": 340,
346
+ "-CGGA": 341,
347
+ "-CGGC": 342,
348
+ "-CGGG": 343,
349
+ "-CGGT": 344,
350
+ "-CGT-": 345,
351
+ "-CGTA": 346,
352
+ "-CGTC": 347,
353
+ "-CGTG": 348,
354
+ "-CGTT": 349,
355
+ "-CT--": 350,
356
+ "-CT-A": 351,
357
+ "-CT-C": 352,
358
+ "-CT-G": 353,
359
+ "-CT-T": 354,
360
+ "-CTA-": 355,
361
+ "-CTAA": 356,
362
+ "-CTAC": 357,
363
+ "-CTAG": 358,
364
+ "-CTAT": 359,
365
+ "-CTC-": 360,
366
+ "-CTCA": 361,
367
+ "-CTCC": 362,
368
+ "-CTCG": 363,
369
+ "-CTCT": 364,
370
+ "-CTG-": 365,
371
+ "-CTGA": 366,
372
+ "-CTGC": 367,
373
+ "-CTGG": 368,
374
+ "-CTGT": 369,
375
+ "-CTT-": 370,
376
+ "-CTTA": 371,
377
+ "-CTTC": 372,
378
+ "-CTTG": 373,
379
+ "-CTTT": 374,
380
+ "-G---": 375,
381
+ "-G--A": 376,
382
+ "-G--C": 377,
383
+ "-G--G": 378,
384
+ "-G--T": 379,
385
+ "-G-A-": 380,
386
+ "-G-AA": 381,
387
+ "-G-AC": 382,
388
+ "-G-AG": 383,
389
+ "-G-AT": 384,
390
+ "-G-C-": 385,
391
+ "-G-CA": 386,
392
+ "-G-CC": 387,
393
+ "-G-CG": 388,
394
+ "-G-CT": 389,
395
+ "-G-G-": 390,
396
+ "-G-GA": 391,
397
+ "-G-GC": 392,
398
+ "-G-GG": 393,
399
+ "-G-GT": 394,
400
+ "-G-T-": 395,
401
+ "-G-TA": 396,
402
+ "-G-TC": 397,
403
+ "-G-TG": 398,
404
+ "-G-TT": 399,
405
+ "-GA--": 400,
406
+ "-GA-A": 401,
407
+ "-GA-C": 402,
408
+ "-GA-G": 403,
409
+ "-GA-T": 404,
410
+ "-GAA-": 405,
411
+ "-GAAA": 406,
412
+ "-GAAC": 407,
413
+ "-GAAG": 408,
414
+ "-GAAT": 409,
415
+ "-GAC-": 410,
416
+ "-GACA": 411,
417
+ "-GACC": 412,
418
+ "-GACG": 413,
419
+ "-GACT": 414,
420
+ "-GAG-": 415,
421
+ "-GAGA": 416,
422
+ "-GAGC": 417,
423
+ "-GAGG": 418,
424
+ "-GAGT": 419,
425
+ "-GAT-": 420,
426
+ "-GATA": 421,
427
+ "-GATC": 422,
428
+ "-GATG": 423,
429
+ "-GATT": 424,
430
+ "-GC--": 425,
431
+ "-GC-A": 426,
432
+ "-GC-C": 427,
433
+ "-GC-G": 428,
434
+ "-GC-T": 429,
435
+ "-GCA-": 430,
436
+ "-GCAA": 431,
437
+ "-GCAC": 432,
438
+ "-GCAG": 433,
439
+ "-GCAT": 434,
440
+ "-GCC-": 435,
441
+ "-GCCA": 436,
442
+ "-GCCC": 437,
443
+ "-GCCG": 438,
444
+ "-GCCT": 439,
445
+ "-GCG-": 440,
446
+ "-GCGA": 441,
447
+ "-GCGC": 442,
448
+ "-GCGG": 443,
449
+ "-GCGT": 444,
450
+ "-GCT-": 445,
451
+ "-GCTA": 446,
452
+ "-GCTC": 447,
453
+ "-GCTG": 448,
454
+ "-GCTT": 449,
455
+ "-GG--": 450,
456
+ "-GG-A": 451,
457
+ "-GG-C": 452,
458
+ "-GG-G": 453,
459
+ "-GG-T": 454,
460
+ "-GGA-": 455,
461
+ "-GGAA": 456,
462
+ "-GGAC": 457,
463
+ "-GGAG": 458,
464
+ "-GGAT": 459,
465
+ "-GGC-": 460,
466
+ "-GGCA": 461,
467
+ "-GGCC": 462,
468
+ "-GGCG": 463,
469
+ "-GGCT": 464,
470
+ "-GGG-": 465,
471
+ "-GGGA": 466,
472
+ "-GGGC": 467,
473
+ "-GGGG": 468,
474
+ "-GGGT": 469,
475
+ "-GGT-": 470,
476
+ "-GGTA": 471,
477
+ "-GGTC": 472,
478
+ "-GGTG": 473,
479
+ "-GGTT": 474,
480
+ "-GT--": 475,
481
+ "-GT-A": 476,
482
+ "-GT-C": 477,
483
+ "-GT-G": 478,
484
+ "-GT-T": 479,
485
+ "-GTA-": 480,
486
+ "-GTAA": 481,
487
+ "-GTAC": 482,
488
+ "-GTAG": 483,
489
+ "-GTAT": 484,
490
+ "-GTC-": 485,
491
+ "-GTCA": 486,
492
+ "-GTCC": 487,
493
+ "-GTCG": 488,
494
+ "-GTCT": 489,
495
+ "-GTG-": 490,
496
+ "-GTGA": 491,
497
+ "-GTGC": 492,
498
+ "-GTGG": 493,
499
+ "-GTGT": 494,
500
+ "-GTT-": 495,
501
+ "-GTTA": 496,
502
+ "-GTTC": 497,
503
+ "-GTTG": 498,
504
+ "-GTTT": 499,
505
+ "-T---": 500,
506
+ "-T--A": 501,
507
+ "-T--C": 502,
508
+ "-T--G": 503,
509
+ "-T--T": 504,
510
+ "-T-A-": 505,
511
+ "-T-AA": 506,
512
+ "-T-AC": 507,
513
+ "-T-AG": 508,
514
+ "-T-AT": 509,
515
+ "-T-C-": 510,
516
+ "-T-CA": 511,
517
+ "-T-CC": 512,
518
+ "-T-CG": 513,
519
+ "-T-CT": 514,
520
+ "-T-G-": 515,
521
+ "-T-GA": 516,
522
+ "-T-GC": 517,
523
+ "-T-GG": 518,
524
+ "-T-GT": 519,
525
+ "-T-T-": 520,
526
+ "-T-TA": 521,
527
+ "-T-TC": 522,
528
+ "-T-TG": 523,
529
+ "-T-TT": 524,
530
+ "-TA--": 525,
531
+ "-TA-A": 526,
532
+ "-TA-C": 527,
533
+ "-TA-G": 528,
534
+ "-TA-T": 529,
535
+ "-TAA-": 530,
536
+ "-TAAA": 531,
537
+ "-TAAC": 532,
538
+ "-TAAG": 533,
539
+ "-TAAT": 534,
540
+ "-TAC-": 535,
541
+ "-TACA": 536,
542
+ "-TACC": 537,
543
+ "-TACG": 538,
544
+ "-TACT": 539,
545
+ "-TAG-": 540,
546
+ "-TAGA": 541,
547
+ "-TAGC": 542,
548
+ "-TAGG": 543,
549
+ "-TAGT": 544,
550
+ "-TAT-": 545,
551
+ "-TATA": 546,
552
+ "-TATC": 547,
553
+ "-TATG": 548,
554
+ "-TATT": 549,
555
+ "-TC--": 550,
556
+ "-TC-A": 551,
557
+ "-TC-C": 552,
558
+ "-TC-G": 553,
559
+ "-TC-T": 554,
560
+ "-TCA-": 555,
561
+ "-TCAA": 556,
562
+ "-TCAC": 557,
563
+ "-TCAG": 558,
564
+ "-TCAT": 559,
565
+ "-TCC-": 560,
566
+ "-TCCA": 561,
567
+ "-TCCC": 562,
568
+ "-TCCG": 563,
569
+ "-TCCT": 564,
570
+ "-TCG-": 565,
571
+ "-TCGA": 566,
572
+ "-TCGC": 567,
573
+ "-TCGG": 568,
574
+ "-TCGT": 569,
575
+ "-TCT-": 570,
576
+ "-TCTA": 571,
577
+ "-TCTC": 572,
578
+ "-TCTG": 573,
579
+ "-TCTT": 574,
580
+ "-TG--": 575,
581
+ "-TG-A": 576,
582
+ "-TG-C": 577,
583
+ "-TG-G": 578,
584
+ "-TG-T": 579,
585
+ "-TGA-": 580,
586
+ "-TGAA": 581,
587
+ "-TGAC": 582,
588
+ "-TGAG": 583,
589
+ "-TGAT": 584,
590
+ "-TGC-": 585,
591
+ "-TGCA": 586,
592
+ "-TGCC": 587,
593
+ "-TGCG": 588,
594
+ "-TGCT": 589,
595
+ "-TGG-": 590,
596
+ "-TGGA": 591,
597
+ "-TGGC": 592,
598
+ "-TGGG": 593,
599
+ "-TGGT": 594,
600
+ "-TGT-": 595,
601
+ "-TGTA": 596,
602
+ "-TGTC": 597,
603
+ "-TGTG": 598,
604
+ "-TGTT": 599,
605
+ "-TT--": 600,
606
+ "-TT-A": 601,
607
+ "-TT-C": 602,
608
+ "-TT-G": 603,
609
+ "-TT-T": 604,
610
+ "-TTA-": 605,
611
+ "-TTAA": 606,
612
+ "-TTAC": 607,
613
+ "-TTAG": 608,
614
+ "-TTAT": 609,
615
+ "-TTC-": 610,
616
+ "-TTCA": 611,
617
+ "-TTCC": 612,
618
+ "-TTCG": 613,
619
+ "-TTCT": 614,
620
+ "-TTG-": 615,
621
+ "-TTGA": 616,
622
+ "-TTGC": 617,
623
+ "-TTGG": 618,
624
+ "-TTGT": 619,
625
+ "-TTT-": 620,
626
+ "-TTTA": 621,
627
+ "-TTTC": 622,
628
+ "-TTTG": 623,
629
+ "-TTTT": 624,
630
+ "A----": 625,
631
+ "A---A": 626,
632
+ "A---C": 627,
633
+ "A---G": 628,
634
+ "A---T": 629,
635
+ "A--A-": 630,
636
+ "A--AA": 631,
637
+ "A--AC": 632,
638
+ "A--AG": 633,
639
+ "A--AT": 634,
640
+ "A--C-": 635,
641
+ "A--CA": 636,
642
+ "A--CC": 637,
643
+ "A--CG": 638,
644
+ "A--CT": 639,
645
+ "A--G-": 640,
646
+ "A--GA": 641,
647
+ "A--GC": 642,
648
+ "A--GG": 643,
649
+ "A--GT": 644,
650
+ "A--T-": 645,
651
+ "A--TA": 646,
652
+ "A--TC": 647,
653
+ "A--TG": 648,
654
+ "A--TT": 649,
655
+ "A-A--": 650,
656
+ "A-A-A": 651,
657
+ "A-A-C": 652,
658
+ "A-A-G": 653,
659
+ "A-A-T": 654,
660
+ "A-AA-": 655,
661
+ "A-AAA": 656,
662
+ "A-AAC": 657,
663
+ "A-AAG": 658,
664
+ "A-AAT": 659,
665
+ "A-AC-": 660,
666
+ "A-ACA": 661,
667
+ "A-ACC": 662,
668
+ "A-ACG": 663,
669
+ "A-ACT": 664,
670
+ "A-AG-": 665,
671
+ "A-AGA": 666,
672
+ "A-AGC": 667,
673
+ "A-AGG": 668,
674
+ "A-AGT": 669,
675
+ "A-AT-": 670,
676
+ "A-ATA": 671,
677
+ "A-ATC": 672,
678
+ "A-ATG": 673,
679
+ "A-ATT": 674,
680
+ "A-C--": 675,
681
+ "A-C-A": 676,
682
+ "A-C-C": 677,
683
+ "A-C-G": 678,
684
+ "A-C-T": 679,
685
+ "A-CA-": 680,
686
+ "A-CAA": 681,
687
+ "A-CAC": 682,
688
+ "A-CAG": 683,
689
+ "A-CAT": 684,
690
+ "A-CC-": 685,
691
+ "A-CCA": 686,
692
+ "A-CCC": 687,
693
+ "A-CCG": 688,
694
+ "A-CCT": 689,
695
+ "A-CG-": 690,
696
+ "A-CGA": 691,
697
+ "A-CGC": 692,
698
+ "A-CGG": 693,
699
+ "A-CGT": 694,
700
+ "A-CT-": 695,
701
+ "A-CTA": 696,
702
+ "A-CTC": 697,
703
+ "A-CTG": 698,
704
+ "A-CTT": 699,
705
+ "A-G--": 700,
706
+ "A-G-A": 701,
707
+ "A-G-C": 702,
708
+ "A-G-G": 703,
709
+ "A-G-T": 704,
710
+ "A-GA-": 705,
711
+ "A-GAA": 706,
712
+ "A-GAC": 707,
713
+ "A-GAG": 708,
714
+ "A-GAT": 709,
715
+ "A-GC-": 710,
716
+ "A-GCA": 711,
717
+ "A-GCC": 712,
718
+ "A-GCG": 713,
719
+ "A-GCT": 714,
720
+ "A-GG-": 715,
721
+ "A-GGA": 716,
722
+ "A-GGC": 717,
723
+ "A-GGG": 718,
724
+ "A-GGT": 719,
725
+ "A-GT-": 720,
726
+ "A-GTA": 721,
727
+ "A-GTC": 722,
728
+ "A-GTG": 723,
729
+ "A-GTT": 724,
730
+ "A-T--": 725,
731
+ "A-T-A": 726,
732
+ "A-T-C": 727,
733
+ "A-T-G": 728,
734
+ "A-T-T": 729,
735
+ "A-TA-": 730,
736
+ "A-TAA": 731,
737
+ "A-TAC": 732,
738
+ "A-TAG": 733,
739
+ "A-TAT": 734,
740
+ "A-TC-": 735,
741
+ "A-TCA": 736,
742
+ "A-TCC": 737,
743
+ "A-TCG": 738,
744
+ "A-TCT": 739,
745
+ "A-TG-": 740,
746
+ "A-TGA": 741,
747
+ "A-TGC": 742,
748
+ "A-TGG": 743,
749
+ "A-TGT": 744,
750
+ "A-TT-": 745,
751
+ "A-TTA": 746,
752
+ "A-TTC": 747,
753
+ "A-TTG": 748,
754
+ "A-TTT": 749,
755
+ "AA---": 750,
756
+ "AA--A": 751,
757
+ "AA--C": 752,
758
+ "AA--G": 753,
759
+ "AA--T": 754,
760
+ "AA-A-": 755,
761
+ "AA-AA": 756,
762
+ "AA-AC": 757,
763
+ "AA-AG": 758,
764
+ "AA-AT": 759,
765
+ "AA-C-": 760,
766
+ "AA-CA": 761,
767
+ "AA-CC": 762,
768
+ "AA-CG": 763,
769
+ "AA-CT": 764,
770
+ "AA-G-": 765,
771
+ "AA-GA": 766,
772
+ "AA-GC": 767,
773
+ "AA-GG": 768,
774
+ "AA-GT": 769,
775
+ "AA-T-": 770,
776
+ "AA-TA": 771,
777
+ "AA-TC": 772,
778
+ "AA-TG": 773,
779
+ "AA-TT": 774,
780
+ "AAA--": 775,
781
+ "AAA-A": 776,
782
+ "AAA-C": 777,
783
+ "AAA-G": 778,
784
+ "AAA-T": 779,
785
+ "AAAA-": 780,
786
+ "AAAAA": 781,
787
+ "AAAAC": 782,
788
+ "AAAAG": 783,
789
+ "AAAAT": 784,
790
+ "AAAC-": 785,
791
+ "AAACA": 786,
792
+ "AAACC": 787,
793
+ "AAACG": 788,
794
+ "AAACT": 789,
795
+ "AAAG-": 790,
796
+ "AAAGA": 791,
797
+ "AAAGC": 792,
798
+ "AAAGG": 793,
799
+ "AAAGT": 794,
800
+ "AAAT-": 795,
801
+ "AAATA": 796,
802
+ "AAATC": 797,
803
+ "AAATG": 798,
804
+ "AAATT": 799,
805
+ "AAC--": 800,
806
+ "AAC-A": 801,
807
+ "AAC-C": 802,
808
+ "AAC-G": 803,
809
+ "AAC-T": 804,
810
+ "AACA-": 805,
811
+ "AACAA": 806,
812
+ "AACAC": 807,
813
+ "AACAG": 808,
814
+ "AACAT": 809,
815
+ "AACC-": 810,
816
+ "AACCA": 811,
817
+ "AACCC": 812,
818
+ "AACCG": 813,
819
+ "AACCT": 814,
820
+ "AACG-": 815,
821
+ "AACGA": 816,
822
+ "AACGC": 817,
823
+ "AACGG": 818,
824
+ "AACGT": 819,
825
+ "AACT-": 820,
826
+ "AACTA": 821,
827
+ "AACTC": 822,
828
+ "AACTG": 823,
829
+ "AACTT": 824,
830
+ "AAG--": 825,
831
+ "AAG-A": 826,
832
+ "AAG-C": 827,
833
+ "AAG-G": 828,
834
+ "AAG-T": 829,
835
+ "AAGA-": 830,
836
+ "AAGAA": 831,
837
+ "AAGAC": 832,
838
+ "AAGAG": 833,
839
+ "AAGAT": 834,
840
+ "AAGC-": 835,
841
+ "AAGCA": 836,
842
+ "AAGCC": 837,
843
+ "AAGCG": 838,
844
+ "AAGCT": 839,
845
+ "AAGG-": 840,
846
+ "AAGGA": 841,
847
+ "AAGGC": 842,
848
+ "AAGGG": 843,
849
+ "AAGGT": 844,
850
+ "AAGT-": 845,
851
+ "AAGTA": 846,
852
+ "AAGTC": 847,
853
+ "AAGTG": 848,
854
+ "AAGTT": 849,
855
+ "AAT--": 850,
856
+ "AAT-A": 851,
857
+ "AAT-C": 852,
858
+ "AAT-G": 853,
859
+ "AAT-T": 854,
860
+ "AATA-": 855,
861
+ "AATAA": 856,
862
+ "AATAC": 857,
863
+ "AATAG": 858,
864
+ "AATAT": 859,
865
+ "AATC-": 860,
866
+ "AATCA": 861,
867
+ "AATCC": 862,
868
+ "AATCG": 863,
869
+ "AATCT": 864,
870
+ "AATG-": 865,
871
+ "AATGA": 866,
872
+ "AATGC": 867,
873
+ "AATGG": 868,
874
+ "AATGT": 869,
875
+ "AATT-": 870,
876
+ "AATTA": 871,
877
+ "AATTC": 872,
878
+ "AATTG": 873,
879
+ "AATTT": 874,
880
+ "AC---": 875,
881
+ "AC--A": 876,
882
+ "AC--C": 877,
883
+ "AC--G": 878,
884
+ "AC--T": 879,
885
+ "AC-A-": 880,
886
+ "AC-AA": 881,
887
+ "AC-AC": 882,
888
+ "AC-AG": 883,
889
+ "AC-AT": 884,
890
+ "AC-C-": 885,
891
+ "AC-CA": 886,
892
+ "AC-CC": 887,
893
+ "AC-CG": 888,
894
+ "AC-CT": 889,
895
+ "AC-G-": 890,
896
+ "AC-GA": 891,
897
+ "AC-GC": 892,
898
+ "AC-GG": 893,
899
+ "AC-GT": 894,
900
+ "AC-T-": 895,
901
+ "AC-TA": 896,
902
+ "AC-TC": 897,
903
+ "AC-TG": 898,
904
+ "AC-TT": 899,
905
+ "ACA--": 900,
906
+ "ACA-A": 901,
907
+ "ACA-C": 902,
908
+ "ACA-G": 903,
909
+ "ACA-T": 904,
910
+ "ACAA-": 905,
911
+ "ACAAA": 906,
912
+ "ACAAC": 907,
913
+ "ACAAG": 908,
914
+ "ACAAT": 909,
915
+ "ACAC-": 910,
916
+ "ACACA": 911,
917
+ "ACACC": 912,
918
+ "ACACG": 913,
919
+ "ACACT": 914,
920
+ "ACAG-": 915,
921
+ "ACAGA": 916,
922
+ "ACAGC": 917,
923
+ "ACAGG": 918,
924
+ "ACAGT": 919,
925
+ "ACAT-": 920,
926
+ "ACATA": 921,
927
+ "ACATC": 922,
928
+ "ACATG": 923,
929
+ "ACATT": 924,
930
+ "ACC--": 925,
931
+ "ACC-A": 926,
932
+ "ACC-C": 927,
933
+ "ACC-G": 928,
934
+ "ACC-T": 929,
935
+ "ACCA-": 930,
936
+ "ACCAA": 931,
937
+ "ACCAC": 932,
938
+ "ACCAG": 933,
939
+ "ACCAT": 934,
940
+ "ACCC-": 935,
941
+ "ACCCA": 936,
942
+ "ACCCC": 937,
943
+ "ACCCG": 938,
944
+ "ACCCT": 939,
945
+ "ACCG-": 940,
946
+ "ACCGA": 941,
947
+ "ACCGC": 942,
948
+ "ACCGG": 943,
949
+ "ACCGT": 944,
950
+ "ACCT-": 945,
951
+ "ACCTA": 946,
952
+ "ACCTC": 947,
953
+ "ACCTG": 948,
954
+ "ACCTT": 949,
955
+ "ACG--": 950,
956
+ "ACG-A": 951,
957
+ "ACG-C": 952,
958
+ "ACG-G": 953,
959
+ "ACG-T": 954,
960
+ "ACGA-": 955,
961
+ "ACGAA": 956,
962
+ "ACGAC": 957,
963
+ "ACGAG": 958,
964
+ "ACGAT": 959,
965
+ "ACGC-": 960,
966
+ "ACGCA": 961,
967
+ "ACGCC": 962,
968
+ "ACGCG": 963,
969
+ "ACGCT": 964,
970
+ "ACGG-": 965,
971
+ "ACGGA": 966,
972
+ "ACGGC": 967,
973
+ "ACGGG": 968,
974
+ "ACGGT": 969,
975
+ "ACGT-": 970,
976
+ "ACGTA": 971,
977
+ "ACGTC": 972,
978
+ "ACGTG": 973,
979
+ "ACGTT": 974,
980
+ "ACT--": 975,
981
+ "ACT-A": 976,
982
+ "ACT-C": 977,
983
+ "ACT-G": 978,
984
+ "ACT-T": 979,
985
+ "ACTA-": 980,
986
+ "ACTAA": 981,
987
+ "ACTAC": 982,
988
+ "ACTAG": 983,
989
+ "ACTAT": 984,
990
+ "ACTC-": 985,
991
+ "ACTCA": 986,
992
+ "ACTCC": 987,
993
+ "ACTCG": 988,
994
+ "ACTCT": 989,
995
+ "ACTG-": 990,
996
+ "ACTGA": 991,
997
+ "ACTGC": 992,
998
+ "ACTGG": 993,
999
+ "ACTGT": 994,
1000
+ "ACTT-": 995,
1001
+ "ACTTA": 996,
1002
+ "ACTTC": 997,
1003
+ "ACTTG": 998,
1004
+ "ACTTT": 999,
1005
+ "AG---": 1000,
1006
+ "AG--A": 1001,
1007
+ "AG--C": 1002,
1008
+ "AG--G": 1003,
1009
+ "AG--T": 1004,
1010
+ "AG-A-": 1005,
1011
+ "AG-AA": 1006,
1012
+ "AG-AC": 1007,
1013
+ "AG-AG": 1008,
1014
+ "AG-AT": 1009,
1015
+ "AG-C-": 1010,
1016
+ "AG-CA": 1011,
1017
+ "AG-CC": 1012,
1018
+ "AG-CG": 1013,
1019
+ "AG-CT": 1014,
1020
+ "AG-G-": 1015,
1021
+ "AG-GA": 1016,
1022
+ "AG-GC": 1017,
1023
+ "AG-GG": 1018,
1024
+ "AG-GT": 1019,
1025
+ "AG-T-": 1020,
1026
+ "AG-TA": 1021,
1027
+ "AG-TC": 1022,
1028
+ "AG-TG": 1023,
1029
+ "AG-TT": 1024,
1030
+ "AGA--": 1025,
1031
+ "AGA-A": 1026,
1032
+ "AGA-C": 1027,
1033
+ "AGA-G": 1028,
1034
+ "AGA-T": 1029,
1035
+ "AGAA-": 1030,
1036
+ "AGAAA": 1031,
1037
+ "AGAAC": 1032,
1038
+ "AGAAG": 1033,
1039
+ "AGAAT": 1034,
1040
+ "AGAC-": 1035,
1041
+ "AGACA": 1036,
1042
+ "AGACC": 1037,
1043
+ "AGACG": 1038,
1044
+ "AGACT": 1039,
1045
+ "AGAG-": 1040,
1046
+ "AGAGA": 1041,
1047
+ "AGAGC": 1042,
1048
+ "AGAGG": 1043,
1049
+ "AGAGT": 1044,
1050
+ "AGAT-": 1045,
1051
+ "AGATA": 1046,
1052
+ "AGATC": 1047,
1053
+ "AGATG": 1048,
1054
+ "AGATT": 1049,
1055
+ "AGC--": 1050,
1056
+ "AGC-A": 1051,
1057
+ "AGC-C": 1052,
1058
+ "AGC-G": 1053,
1059
+ "AGC-T": 1054,
1060
+ "AGCA-": 1055,
1061
+ "AGCAA": 1056,
1062
+ "AGCAC": 1057,
1063
+ "AGCAG": 1058,
1064
+ "AGCAT": 1059,
1065
+ "AGCC-": 1060,
1066
+ "AGCCA": 1061,
1067
+ "AGCCC": 1062,
1068
+ "AGCCG": 1063,
1069
+ "AGCCT": 1064,
1070
+ "AGCG-": 1065,
1071
+ "AGCGA": 1066,
1072
+ "AGCGC": 1067,
1073
+ "AGCGG": 1068,
1074
+ "AGCGT": 1069,
1075
+ "AGCT-": 1070,
1076
+ "AGCTA": 1071,
1077
+ "AGCTC": 1072,
1078
+ "AGCTG": 1073,
1079
+ "AGCTT": 1074,
1080
+ "AGG--": 1075,
1081
+ "AGG-A": 1076,
1082
+ "AGG-C": 1077,
1083
+ "AGG-G": 1078,
1084
+ "AGG-T": 1079,
1085
+ "AGGA-": 1080,
1086
+ "AGGAA": 1081,
1087
+ "AGGAC": 1082,
1088
+ "AGGAG": 1083,
1089
+ "AGGAT": 1084,
1090
+ "AGGC-": 1085,
1091
+ "AGGCA": 1086,
1092
+ "AGGCC": 1087,
1093
+ "AGGCG": 1088,
1094
+ "AGGCT": 1089,
1095
+ "AGGG-": 1090,
1096
+ "AGGGA": 1091,
1097
+ "AGGGC": 1092,
1098
+ "AGGGG": 1093,
1099
+ "AGGGT": 1094,
1100
+ "AGGT-": 1095,
1101
+ "AGGTA": 1096,
1102
+ "AGGTC": 1097,
1103
+ "AGGTG": 1098,
1104
+ "AGGTT": 1099,
1105
+ "AGT--": 1100,
1106
+ "AGT-A": 1101,
1107
+ "AGT-C": 1102,
1108
+ "AGT-G": 1103,
1109
+ "AGT-T": 1104,
1110
+ "AGTA-": 1105,
1111
+ "AGTAA": 1106,
1112
+ "AGTAC": 1107,
1113
+ "AGTAG": 1108,
1114
+ "AGTAT": 1109,
1115
+ "AGTC-": 1110,
1116
+ "AGTCA": 1111,
1117
+ "AGTCC": 1112,
1118
+ "AGTCG": 1113,
1119
+ "AGTCT": 1114,
1120
+ "AGTG-": 1115,
1121
+ "AGTGA": 1116,
1122
+ "AGTGC": 1117,
1123
+ "AGTGG": 1118,
1124
+ "AGTGT": 1119,
1125
+ "AGTT-": 1120,
1126
+ "AGTTA": 1121,
1127
+ "AGTTC": 1122,
1128
+ "AGTTG": 1123,
1129
+ "AGTTT": 1124,
1130
+ "AT---": 1125,
1131
+ "AT--A": 1126,
1132
+ "AT--C": 1127,
1133
+ "AT--G": 1128,
1134
+ "AT--T": 1129,
1135
+ "AT-A-": 1130,
1136
+ "AT-AA": 1131,
1137
+ "AT-AC": 1132,
1138
+ "AT-AG": 1133,
1139
+ "AT-AT": 1134,
1140
+ "AT-C-": 1135,
1141
+ "AT-CA": 1136,
1142
+ "AT-CC": 1137,
1143
+ "AT-CG": 1138,
1144
+ "AT-CT": 1139,
1145
+ "AT-G-": 1140,
1146
+ "AT-GA": 1141,
1147
+ "AT-GC": 1142,
1148
+ "AT-GG": 1143,
1149
+ "AT-GT": 1144,
1150
+ "AT-T-": 1145,
1151
+ "AT-TA": 1146,
1152
+ "AT-TC": 1147,
1153
+ "AT-TG": 1148,
1154
+ "AT-TT": 1149,
1155
+ "ATA--": 1150,
1156
+ "ATA-A": 1151,
1157
+ "ATA-C": 1152,
1158
+ "ATA-G": 1153,
1159
+ "ATA-T": 1154,
1160
+ "ATAA-": 1155,
1161
+ "ATAAA": 1156,
1162
+ "ATAAC": 1157,
1163
+ "ATAAG": 1158,
1164
+ "ATAAT": 1159,
1165
+ "ATAC-": 1160,
1166
+ "ATACA": 1161,
1167
+ "ATACC": 1162,
1168
+ "ATACG": 1163,
1169
+ "ATACT": 1164,
1170
+ "ATAG-": 1165,
1171
+ "ATAGA": 1166,
1172
+ "ATAGC": 1167,
1173
+ "ATAGG": 1168,
1174
+ "ATAGT": 1169,
1175
+ "ATAT-": 1170,
1176
+ "ATATA": 1171,
1177
+ "ATATC": 1172,
1178
+ "ATATG": 1173,
1179
+ "ATATT": 1174,
1180
+ "ATC--": 1175,
1181
+ "ATC-A": 1176,
1182
+ "ATC-C": 1177,
1183
+ "ATC-G": 1178,
1184
+ "ATC-T": 1179,
1185
+ "ATCA-": 1180,
1186
+ "ATCAA": 1181,
1187
+ "ATCAC": 1182,
1188
+ "ATCAG": 1183,
1189
+ "ATCAT": 1184,
1190
+ "ATCC-": 1185,
1191
+ "ATCCA": 1186,
1192
+ "ATCCC": 1187,
1193
+ "ATCCG": 1188,
1194
+ "ATCCT": 1189,
1195
+ "ATCG-": 1190,
1196
+ "ATCGA": 1191,
1197
+ "ATCGC": 1192,
1198
+ "ATCGG": 1193,
1199
+ "ATCGT": 1194,
1200
+ "ATCT-": 1195,
1201
+ "ATCTA": 1196,
1202
+ "ATCTC": 1197,
1203
+ "ATCTG": 1198,
1204
+ "ATCTT": 1199,
1205
+ "ATG--": 1200,
1206
+ "ATG-A": 1201,
1207
+ "ATG-C": 1202,
1208
+ "ATG-G": 1203,
1209
+ "ATG-T": 1204,
1210
+ "ATGA-": 1205,
1211
+ "ATGAA": 1206,
1212
+ "ATGAC": 1207,
1213
+ "ATGAG": 1208,
1214
+ "ATGAT": 1209,
1215
+ "ATGC-": 1210,
1216
+ "ATGCA": 1211,
1217
+ "ATGCC": 1212,
1218
+ "ATGCG": 1213,
1219
+ "ATGCT": 1214,
1220
+ "ATGG-": 1215,
1221
+ "ATGGA": 1216,
1222
+ "ATGGC": 1217,
1223
+ "ATGGG": 1218,
1224
+ "ATGGT": 1219,
1225
+ "ATGT-": 1220,
1226
+ "ATGTA": 1221,
1227
+ "ATGTC": 1222,
1228
+ "ATGTG": 1223,
1229
+ "ATGTT": 1224,
1230
+ "ATT--": 1225,
1231
+ "ATT-A": 1226,
1232
+ "ATT-C": 1227,
1233
+ "ATT-G": 1228,
1234
+ "ATT-T": 1229,
1235
+ "ATTA-": 1230,
1236
+ "ATTAA": 1231,
1237
+ "ATTAC": 1232,
1238
+ "ATTAG": 1233,
1239
+ "ATTAT": 1234,
1240
+ "ATTC-": 1235,
1241
+ "ATTCA": 1236,
1242
+ "ATTCC": 1237,
1243
+ "ATTCG": 1238,
1244
+ "ATTCT": 1239,
1245
+ "ATTG-": 1240,
1246
+ "ATTGA": 1241,
1247
+ "ATTGC": 1242,
1248
+ "ATTGG": 1243,
1249
+ "ATTGT": 1244,
1250
+ "ATTT-": 1245,
1251
+ "ATTTA": 1246,
1252
+ "ATTTC": 1247,
1253
+ "ATTTG": 1248,
1254
+ "ATTTT": 1249,
1255
+ "C----": 1250,
1256
+ "C---A": 1251,
1257
+ "C---C": 1252,
1258
+ "C---G": 1253,
1259
+ "C---T": 1254,
1260
+ "C--A-": 1255,
1261
+ "C--AA": 1256,
1262
+ "C--AC": 1257,
1263
+ "C--AG": 1258,
1264
+ "C--AT": 1259,
1265
+ "C--C-": 1260,
1266
+ "C--CA": 1261,
1267
+ "C--CC": 1262,
1268
+ "C--CG": 1263,
1269
+ "C--CT": 1264,
1270
+ "C--G-": 1265,
1271
+ "C--GA": 1266,
1272
+ "C--GC": 1267,
1273
+ "C--GG": 1268,
1274
+ "C--GT": 1269,
1275
+ "C--T-": 1270,
1276
+ "C--TA": 1271,
1277
+ "C--TC": 1272,
1278
+ "C--TG": 1273,
1279
+ "C--TT": 1274,
1280
+ "C-A--": 1275,
1281
+ "C-A-A": 1276,
1282
+ "C-A-C": 1277,
1283
+ "C-A-G": 1278,
1284
+ "C-A-T": 1279,
1285
+ "C-AA-": 1280,
1286
+ "C-AAA": 1281,
1287
+ "C-AAC": 1282,
1288
+ "C-AAG": 1283,
1289
+ "C-AAT": 1284,
1290
+ "C-AC-": 1285,
1291
+ "C-ACA": 1286,
1292
+ "C-ACC": 1287,
1293
+ "C-ACG": 1288,
1294
+ "C-ACT": 1289,
1295
+ "C-AG-": 1290,
1296
+ "C-AGA": 1291,
1297
+ "C-AGC": 1292,
1298
+ "C-AGG": 1293,
1299
+ "C-AGT": 1294,
1300
+ "C-AT-": 1295,
1301
+ "C-ATA": 1296,
1302
+ "C-ATC": 1297,
1303
+ "C-ATG": 1298,
1304
+ "C-ATT": 1299,
1305
+ "C-C--": 1300,
1306
+ "C-C-A": 1301,
1307
+ "C-C-C": 1302,
1308
+ "C-C-G": 1303,
1309
+ "C-C-T": 1304,
1310
+ "C-CA-": 1305,
1311
+ "C-CAA": 1306,
1312
+ "C-CAC": 1307,
1313
+ "C-CAG": 1308,
1314
+ "C-CAT": 1309,
1315
+ "C-CC-": 1310,
1316
+ "C-CCA": 1311,
1317
+ "C-CCC": 1312,
1318
+ "C-CCG": 1313,
1319
+ "C-CCT": 1314,
1320
+ "C-CG-": 1315,
1321
+ "C-CGA": 1316,
1322
+ "C-CGC": 1317,
1323
+ "C-CGG": 1318,
1324
+ "C-CGT": 1319,
1325
+ "C-CT-": 1320,
1326
+ "C-CTA": 1321,
1327
+ "C-CTC": 1322,
1328
+ "C-CTG": 1323,
1329
+ "C-CTT": 1324,
1330
+ "C-G--": 1325,
1331
+ "C-G-A": 1326,
1332
+ "C-G-C": 1327,
1333
+ "C-G-G": 1328,
1334
+ "C-G-T": 1329,
1335
+ "C-GA-": 1330,
1336
+ "C-GAA": 1331,
1337
+ "C-GAC": 1332,
1338
+ "C-GAG": 1333,
1339
+ "C-GAT": 1334,
1340
+ "C-GC-": 1335,
1341
+ "C-GCA": 1336,
1342
+ "C-GCC": 1337,
1343
+ "C-GCG": 1338,
1344
+ "C-GCT": 1339,
1345
+ "C-GG-": 1340,
1346
+ "C-GGA": 1341,
1347
+ "C-GGC": 1342,
1348
+ "C-GGG": 1343,
1349
+ "C-GGT": 1344,
1350
+ "C-GT-": 1345,
1351
+ "C-GTA": 1346,
1352
+ "C-GTC": 1347,
1353
+ "C-GTG": 1348,
1354
+ "C-GTT": 1349,
1355
+ "C-T--": 1350,
1356
+ "C-T-A": 1351,
1357
+ "C-T-C": 1352,
1358
+ "C-T-G": 1353,
1359
+ "C-T-T": 1354,
1360
+ "C-TA-": 1355,
1361
+ "C-TAA": 1356,
1362
+ "C-TAC": 1357,
1363
+ "C-TAG": 1358,
1364
+ "C-TAT": 1359,
1365
+ "C-TC-": 1360,
1366
+ "C-TCA": 1361,
1367
+ "C-TCC": 1362,
1368
+ "C-TCG": 1363,
1369
+ "C-TCT": 1364,
1370
+ "C-TG-": 1365,
1371
+ "C-TGA": 1366,
1372
+ "C-TGC": 1367,
1373
+ "C-TGG": 1368,
1374
+ "C-TGT": 1369,
1375
+ "C-TT-": 1370,
1376
+ "C-TTA": 1371,
1377
+ "C-TTC": 1372,
1378
+ "C-TTG": 1373,
1379
+ "C-TTT": 1374,
1380
+ "CA---": 1375,
1381
+ "CA--A": 1376,
1382
+ "CA--C": 1377,
1383
+ "CA--G": 1378,
1384
+ "CA--T": 1379,
1385
+ "CA-A-": 1380,
1386
+ "CA-AA": 1381,
1387
+ "CA-AC": 1382,
1388
+ "CA-AG": 1383,
1389
+ "CA-AT": 1384,
1390
+ "CA-C-": 1385,
1391
+ "CA-CA": 1386,
1392
+ "CA-CC": 1387,
1393
+ "CA-CG": 1388,
1394
+ "CA-CT": 1389,
1395
+ "CA-G-": 1390,
1396
+ "CA-GA": 1391,
1397
+ "CA-GC": 1392,
1398
+ "CA-GG": 1393,
1399
+ "CA-GT": 1394,
1400
+ "CA-T-": 1395,
1401
+ "CA-TA": 1396,
1402
+ "CA-TC": 1397,
1403
+ "CA-TG": 1398,
1404
+ "CA-TT": 1399,
1405
+ "CAA--": 1400,
1406
+ "CAA-A": 1401,
1407
+ "CAA-C": 1402,
1408
+ "CAA-G": 1403,
1409
+ "CAA-T": 1404,
1410
+ "CAAA-": 1405,
1411
+ "CAAAA": 1406,
1412
+ "CAAAC": 1407,
1413
+ "CAAAG": 1408,
1414
+ "CAAAT": 1409,
1415
+ "CAAC-": 1410,
1416
+ "CAACA": 1411,
1417
+ "CAACC": 1412,
1418
+ "CAACG": 1413,
1419
+ "CAACT": 1414,
1420
+ "CAAG-": 1415,
1421
+ "CAAGA": 1416,
1422
+ "CAAGC": 1417,
1423
+ "CAAGG": 1418,
1424
+ "CAAGT": 1419,
1425
+ "CAAT-": 1420,
1426
+ "CAATA": 1421,
1427
+ "CAATC": 1422,
1428
+ "CAATG": 1423,
1429
+ "CAATT": 1424,
1430
+ "CAC--": 1425,
1431
+ "CAC-A": 1426,
1432
+ "CAC-C": 1427,
1433
+ "CAC-G": 1428,
1434
+ "CAC-T": 1429,
1435
+ "CACA-": 1430,
1436
+ "CACAA": 1431,
1437
+ "CACAC": 1432,
1438
+ "CACAG": 1433,
1439
+ "CACAT": 1434,
1440
+ "CACC-": 1435,
1441
+ "CACCA": 1436,
1442
+ "CACCC": 1437,
1443
+ "CACCG": 1438,
1444
+ "CACCT": 1439,
1445
+ "CACG-": 1440,
1446
+ "CACGA": 1441,
1447
+ "CACGC": 1442,
1448
+ "CACGG": 1443,
1449
+ "CACGT": 1444,
1450
+ "CACT-": 1445,
1451
+ "CACTA": 1446,
1452
+ "CACTC": 1447,
1453
+ "CACTG": 1448,
1454
+ "CACTT": 1449,
1455
+ "CAG--": 1450,
1456
+ "CAG-A": 1451,
1457
+ "CAG-C": 1452,
1458
+ "CAG-G": 1453,
1459
+ "CAG-T": 1454,
1460
+ "CAGA-": 1455,
1461
+ "CAGAA": 1456,
1462
+ "CAGAC": 1457,
1463
+ "CAGAG": 1458,
1464
+ "CAGAT": 1459,
1465
+ "CAGC-": 1460,
1466
+ "CAGCA": 1461,
1467
+ "CAGCC": 1462,
1468
+ "CAGCG": 1463,
1469
+ "CAGCT": 1464,
1470
+ "CAGG-": 1465,
1471
+ "CAGGA": 1466,
1472
+ "CAGGC": 1467,
1473
+ "CAGGG": 1468,
1474
+ "CAGGT": 1469,
1475
+ "CAGT-": 1470,
1476
+ "CAGTA": 1471,
1477
+ "CAGTC": 1472,
1478
+ "CAGTG": 1473,
1479
+ "CAGTT": 1474,
1480
+ "CAT--": 1475,
1481
+ "CAT-A": 1476,
1482
+ "CAT-C": 1477,
1483
+ "CAT-G": 1478,
1484
+ "CAT-T": 1479,
1485
+ "CATA-": 1480,
1486
+ "CATAA": 1481,
1487
+ "CATAC": 1482,
1488
+ "CATAG": 1483,
1489
+ "CATAT": 1484,
1490
+ "CATC-": 1485,
1491
+ "CATCA": 1486,
1492
+ "CATCC": 1487,
1493
+ "CATCG": 1488,
1494
+ "CATCT": 1489,
1495
+ "CATG-": 1490,
1496
+ "CATGA": 1491,
1497
+ "CATGC": 1492,
1498
+ "CATGG": 1493,
1499
+ "CATGT": 1494,
1500
+ "CATT-": 1495,
1501
+ "CATTA": 1496,
1502
+ "CATTC": 1497,
1503
+ "CATTG": 1498,
1504
+ "CATTT": 1499,
1505
+ "CC---": 1500,
1506
+ "CC--A": 1501,
1507
+ "CC--C": 1502,
1508
+ "CC--G": 1503,
1509
+ "CC--T": 1504,
1510
+ "CC-A-": 1505,
1511
+ "CC-AA": 1506,
1512
+ "CC-AC": 1507,
1513
+ "CC-AG": 1508,
1514
+ "CC-AT": 1509,
1515
+ "CC-C-": 1510,
1516
+ "CC-CA": 1511,
1517
+ "CC-CC": 1512,
1518
+ "CC-CG": 1513,
1519
+ "CC-CT": 1514,
1520
+ "CC-G-": 1515,
1521
+ "CC-GA": 1516,
1522
+ "CC-GC": 1517,
1523
+ "CC-GG": 1518,
1524
+ "CC-GT": 1519,
1525
+ "CC-T-": 1520,
1526
+ "CC-TA": 1521,
1527
+ "CC-TC": 1522,
1528
+ "CC-TG": 1523,
1529
+ "CC-TT": 1524,
1530
+ "CCA--": 1525,
1531
+ "CCA-A": 1526,
1532
+ "CCA-C": 1527,
1533
+ "CCA-G": 1528,
1534
+ "CCA-T": 1529,
1535
+ "CCAA-": 1530,
1536
+ "CCAAA": 1531,
1537
+ "CCAAC": 1532,
1538
+ "CCAAG": 1533,
1539
+ "CCAAT": 1534,
1540
+ "CCAC-": 1535,
1541
+ "CCACA": 1536,
1542
+ "CCACC": 1537,
1543
+ "CCACG": 1538,
1544
+ "CCACT": 1539,
1545
+ "CCAG-": 1540,
1546
+ "CCAGA": 1541,
1547
+ "CCAGC": 1542,
1548
+ "CCAGG": 1543,
1549
+ "CCAGT": 1544,
1550
+ "CCAT-": 1545,
1551
+ "CCATA": 1546,
1552
+ "CCATC": 1547,
1553
+ "CCATG": 1548,
1554
+ "CCATT": 1549,
1555
+ "CCC--": 1550,
1556
+ "CCC-A": 1551,
1557
+ "CCC-C": 1552,
1558
+ "CCC-G": 1553,
1559
+ "CCC-T": 1554,
1560
+ "CCCA-": 1555,
1561
+ "CCCAA": 1556,
1562
+ "CCCAC": 1557,
1563
+ "CCCAG": 1558,
1564
+ "CCCAT": 1559,
1565
+ "CCCC-": 1560,
1566
+ "CCCCA": 1561,
1567
+ "CCCCC": 1562,
1568
+ "CCCCG": 1563,
1569
+ "CCCCT": 1564,
1570
+ "CCCG-": 1565,
1571
+ "CCCGA": 1566,
1572
+ "CCCGC": 1567,
1573
+ "CCCGG": 1568,
1574
+ "CCCGT": 1569,
1575
+ "CCCT-": 1570,
1576
+ "CCCTA": 1571,
1577
+ "CCCTC": 1572,
1578
+ "CCCTG": 1573,
1579
+ "CCCTT": 1574,
1580
+ "CCG--": 1575,
1581
+ "CCG-A": 1576,
1582
+ "CCG-C": 1577,
1583
+ "CCG-G": 1578,
1584
+ "CCG-T": 1579,
1585
+ "CCGA-": 1580,
1586
+ "CCGAA": 1581,
1587
+ "CCGAC": 1582,
1588
+ "CCGAG": 1583,
1589
+ "CCGAT": 1584,
1590
+ "CCGC-": 1585,
1591
+ "CCGCA": 1586,
1592
+ "CCGCC": 1587,
1593
+ "CCGCG": 1588,
1594
+ "CCGCT": 1589,
1595
+ "CCGG-": 1590,
1596
+ "CCGGA": 1591,
1597
+ "CCGGC": 1592,
1598
+ "CCGGG": 1593,
1599
+ "CCGGT": 1594,
1600
+ "CCGT-": 1595,
1601
+ "CCGTA": 1596,
1602
+ "CCGTC": 1597,
1603
+ "CCGTG": 1598,
1604
+ "CCGTT": 1599,
1605
+ "CCT--": 1600,
1606
+ "CCT-A": 1601,
1607
+ "CCT-C": 1602,
1608
+ "CCT-G": 1603,
1609
+ "CCT-T": 1604,
1610
+ "CCTA-": 1605,
1611
+ "CCTAA": 1606,
1612
+ "CCTAC": 1607,
1613
+ "CCTAG": 1608,
1614
+ "CCTAT": 1609,
1615
+ "CCTC-": 1610,
1616
+ "CCTCA": 1611,
1617
+ "CCTCC": 1612,
1618
+ "CCTCG": 1613,
1619
+ "CCTCT": 1614,
1620
+ "CCTG-": 1615,
1621
+ "CCTGA": 1616,
1622
+ "CCTGC": 1617,
1623
+ "CCTGG": 1618,
1624
+ "CCTGT": 1619,
1625
+ "CCTT-": 1620,
1626
+ "CCTTA": 1621,
1627
+ "CCTTC": 1622,
1628
+ "CCTTG": 1623,
1629
+ "CCTTT": 1624,
1630
+ "CG---": 1625,
1631
+ "CG--A": 1626,
1632
+ "CG--C": 1627,
1633
+ "CG--G": 1628,
1634
+ "CG--T": 1629,
1635
+ "CG-A-": 1630,
1636
+ "CG-AA": 1631,
1637
+ "CG-AC": 1632,
1638
+ "CG-AG": 1633,
1639
+ "CG-AT": 1634,
1640
+ "CG-C-": 1635,
1641
+ "CG-CA": 1636,
1642
+ "CG-CC": 1637,
1643
+ "CG-CG": 1638,
1644
+ "CG-CT": 1639,
1645
+ "CG-G-": 1640,
1646
+ "CG-GA": 1641,
1647
+ "CG-GC": 1642,
1648
+ "CG-GG": 1643,
1649
+ "CG-GT": 1644,
1650
+ "CG-T-": 1645,
1651
+ "CG-TA": 1646,
1652
+ "CG-TC": 1647,
1653
+ "CG-TG": 1648,
1654
+ "CG-TT": 1649,
1655
+ "CGA--": 1650,
1656
+ "CGA-A": 1651,
1657
+ "CGA-C": 1652,
1658
+ "CGA-G": 1653,
1659
+ "CGA-T": 1654,
1660
+ "CGAA-": 1655,
1661
+ "CGAAA": 1656,
1662
+ "CGAAC": 1657,
1663
+ "CGAAG": 1658,
1664
+ "CGAAT": 1659,
1665
+ "CGAC-": 1660,
1666
+ "CGACA": 1661,
1667
+ "CGACC": 1662,
1668
+ "CGACG": 1663,
1669
+ "CGACT": 1664,
1670
+ "CGAG-": 1665,
1671
+ "CGAGA": 1666,
1672
+ "CGAGC": 1667,
1673
+ "CGAGG": 1668,
1674
+ "CGAGT": 1669,
1675
+ "CGAT-": 1670,
1676
+ "CGATA": 1671,
1677
+ "CGATC": 1672,
1678
+ "CGATG": 1673,
1679
+ "CGATT": 1674,
1680
+ "CGC--": 1675,
1681
+ "CGC-A": 1676,
1682
+ "CGC-C": 1677,
1683
+ "CGC-G": 1678,
1684
+ "CGC-T": 1679,
1685
+ "CGCA-": 1680,
1686
+ "CGCAA": 1681,
1687
+ "CGCAC": 1682,
1688
+ "CGCAG": 1683,
1689
+ "CGCAT": 1684,
1690
+ "CGCC-": 1685,
1691
+ "CGCCA": 1686,
1692
+ "CGCCC": 1687,
1693
+ "CGCCG": 1688,
1694
+ "CGCCT": 1689,
1695
+ "CGCG-": 1690,
1696
+ "CGCGA": 1691,
1697
+ "CGCGC": 1692,
1698
+ "CGCGG": 1693,
1699
+ "CGCGT": 1694,
1700
+ "CGCT-": 1695,
1701
+ "CGCTA": 1696,
1702
+ "CGCTC": 1697,
1703
+ "CGCTG": 1698,
1704
+ "CGCTT": 1699,
1705
+ "CGG--": 1700,
1706
+ "CGG-A": 1701,
1707
+ "CGG-C": 1702,
1708
+ "CGG-G": 1703,
1709
+ "CGG-T": 1704,
1710
+ "CGGA-": 1705,
1711
+ "CGGAA": 1706,
1712
+ "CGGAC": 1707,
1713
+ "CGGAG": 1708,
1714
+ "CGGAT": 1709,
1715
+ "CGGC-": 1710,
1716
+ "CGGCA": 1711,
1717
+ "CGGCC": 1712,
1718
+ "CGGCG": 1713,
1719
+ "CGGCT": 1714,
1720
+ "CGGG-": 1715,
1721
+ "CGGGA": 1716,
1722
+ "CGGGC": 1717,
1723
+ "CGGGG": 1718,
1724
+ "CGGGT": 1719,
1725
+ "CGGT-": 1720,
1726
+ "CGGTA": 1721,
1727
+ "CGGTC": 1722,
1728
+ "CGGTG": 1723,
1729
+ "CGGTT": 1724,
1730
+ "CGT--": 1725,
1731
+ "CGT-A": 1726,
1732
+ "CGT-C": 1727,
1733
+ "CGT-G": 1728,
1734
+ "CGT-T": 1729,
1735
+ "CGTA-": 1730,
1736
+ "CGTAA": 1731,
1737
+ "CGTAC": 1732,
1738
+ "CGTAG": 1733,
1739
+ "CGTAT": 1734,
1740
+ "CGTC-": 1735,
1741
+ "CGTCA": 1736,
1742
+ "CGTCC": 1737,
1743
+ "CGTCG": 1738,
1744
+ "CGTCT": 1739,
1745
+ "CGTG-": 1740,
1746
+ "CGTGA": 1741,
1747
+ "CGTGC": 1742,
1748
+ "CGTGG": 1743,
1749
+ "CGTGT": 1744,
1750
+ "CGTT-": 1745,
1751
+ "CGTTA": 1746,
1752
+ "CGTTC": 1747,
1753
+ "CGTTG": 1748,
1754
+ "CGTTT": 1749,
1755
+ "CT---": 1750,
1756
+ "CT--A": 1751,
1757
+ "CT--C": 1752,
1758
+ "CT--G": 1753,
1759
+ "CT--T": 1754,
1760
+ "CT-A-": 1755,
1761
+ "CT-AA": 1756,
1762
+ "CT-AC": 1757,
1763
+ "CT-AG": 1758,
1764
+ "CT-AT": 1759,
1765
+ "CT-C-": 1760,
1766
+ "CT-CA": 1761,
1767
+ "CT-CC": 1762,
1768
+ "CT-CG": 1763,
1769
+ "CT-CT": 1764,
1770
+ "CT-G-": 1765,
1771
+ "CT-GA": 1766,
1772
+ "CT-GC": 1767,
1773
+ "CT-GG": 1768,
1774
+ "CT-GT": 1769,
1775
+ "CT-T-": 1770,
1776
+ "CT-TA": 1771,
1777
+ "CT-TC": 1772,
1778
+ "CT-TG": 1773,
1779
+ "CT-TT": 1774,
1780
+ "CTA--": 1775,
1781
+ "CTA-A": 1776,
1782
+ "CTA-C": 1777,
1783
+ "CTA-G": 1778,
1784
+ "CTA-T": 1779,
1785
+ "CTAA-": 1780,
1786
+ "CTAAA": 1781,
1787
+ "CTAAC": 1782,
1788
+ "CTAAG": 1783,
1789
+ "CTAAT": 1784,
1790
+ "CTAC-": 1785,
1791
+ "CTACA": 1786,
1792
+ "CTACC": 1787,
1793
+ "CTACG": 1788,
1794
+ "CTACT": 1789,
1795
+ "CTAG-": 1790,
1796
+ "CTAGA": 1791,
1797
+ "CTAGC": 1792,
1798
+ "CTAGG": 1793,
1799
+ "CTAGT": 1794,
1800
+ "CTAT-": 1795,
1801
+ "CTATA": 1796,
1802
+ "CTATC": 1797,
1803
+ "CTATG": 1798,
1804
+ "CTATT": 1799,
1805
+ "CTC--": 1800,
1806
+ "CTC-A": 1801,
1807
+ "CTC-C": 1802,
1808
+ "CTC-G": 1803,
1809
+ "CTC-T": 1804,
1810
+ "CTCA-": 1805,
1811
+ "CTCAA": 1806,
1812
+ "CTCAC": 1807,
1813
+ "CTCAG": 1808,
1814
+ "CTCAT": 1809,
1815
+ "CTCC-": 1810,
1816
+ "CTCCA": 1811,
1817
+ "CTCCC": 1812,
1818
+ "CTCCG": 1813,
1819
+ "CTCCT": 1814,
1820
+ "CTCG-": 1815,
1821
+ "CTCGA": 1816,
1822
+ "CTCGC": 1817,
1823
+ "CTCGG": 1818,
1824
+ "CTCGT": 1819,
1825
+ "CTCT-": 1820,
1826
+ "CTCTA": 1821,
1827
+ "CTCTC": 1822,
1828
+ "CTCTG": 1823,
1829
+ "CTCTT": 1824,
1830
+ "CTG--": 1825,
1831
+ "CTG-A": 1826,
1832
+ "CTG-C": 1827,
1833
+ "CTG-G": 1828,
1834
+ "CTG-T": 1829,
1835
+ "CTGA-": 1830,
1836
+ "CTGAA": 1831,
1837
+ "CTGAC": 1832,
1838
+ "CTGAG": 1833,
1839
+ "CTGAT": 1834,
1840
+ "CTGC-": 1835,
1841
+ "CTGCA": 1836,
1842
+ "CTGCC": 1837,
1843
+ "CTGCG": 1838,
1844
+ "CTGCT": 1839,
1845
+ "CTGG-": 1840,
1846
+ "CTGGA": 1841,
1847
+ "CTGGC": 1842,
1848
+ "CTGGG": 1843,
1849
+ "CTGGT": 1844,
1850
+ "CTGT-": 1845,
1851
+ "CTGTA": 1846,
1852
+ "CTGTC": 1847,
1853
+ "CTGTG": 1848,
1854
+ "CTGTT": 1849,
1855
+ "CTT--": 1850,
1856
+ "CTT-A": 1851,
1857
+ "CTT-C": 1852,
1858
+ "CTT-G": 1853,
1859
+ "CTT-T": 1854,
1860
+ "CTTA-": 1855,
1861
+ "CTTAA": 1856,
1862
+ "CTTAC": 1857,
1863
+ "CTTAG": 1858,
1864
+ "CTTAT": 1859,
1865
+ "CTTC-": 1860,
1866
+ "CTTCA": 1861,
1867
+ "CTTCC": 1862,
1868
+ "CTTCG": 1863,
1869
+ "CTTCT": 1864,
1870
+ "CTTG-": 1865,
1871
+ "CTTGA": 1866,
1872
+ "CTTGC": 1867,
1873
+ "CTTGG": 1868,
1874
+ "CTTGT": 1869,
1875
+ "CTTT-": 1870,
1876
+ "CTTTA": 1871,
1877
+ "CTTTC": 1872,
1878
+ "CTTTG": 1873,
1879
+ "CTTTT": 1874,
1880
+ "G----": 1875,
1881
+ "G---A": 1876,
1882
+ "G---C": 1877,
1883
+ "G---G": 1878,
1884
+ "G---T": 1879,
1885
+ "G--A-": 1880,
1886
+ "G--AA": 1881,
1887
+ "G--AC": 1882,
1888
+ "G--AG": 1883,
1889
+ "G--AT": 1884,
1890
+ "G--C-": 1885,
1891
+ "G--CA": 1886,
1892
+ "G--CC": 1887,
1893
+ "G--CG": 1888,
1894
+ "G--CT": 1889,
1895
+ "G--G-": 1890,
1896
+ "G--GA": 1891,
1897
+ "G--GC": 1892,
1898
+ "G--GG": 1893,
1899
+ "G--GT": 1894,
1900
+ "G--T-": 1895,
1901
+ "G--TA": 1896,
1902
+ "G--TC": 1897,
1903
+ "G--TG": 1898,
1904
+ "G--TT": 1899,
1905
+ "G-A--": 1900,
1906
+ "G-A-A": 1901,
1907
+ "G-A-C": 1902,
1908
+ "G-A-G": 1903,
1909
+ "G-A-T": 1904,
1910
+ "G-AA-": 1905,
1911
+ "G-AAA": 1906,
1912
+ "G-AAC": 1907,
1913
+ "G-AAG": 1908,
1914
+ "G-AAT": 1909,
1915
+ "G-AC-": 1910,
1916
+ "G-ACA": 1911,
1917
+ "G-ACC": 1912,
1918
+ "G-ACG": 1913,
1919
+ "G-ACT": 1914,
1920
+ "G-AG-": 1915,
1921
+ "G-AGA": 1916,
1922
+ "G-AGC": 1917,
1923
+ "G-AGG": 1918,
1924
+ "G-AGT": 1919,
1925
+ "G-AT-": 1920,
1926
+ "G-ATA": 1921,
1927
+ "G-ATC": 1922,
1928
+ "G-ATG": 1923,
1929
+ "G-ATT": 1924,
1930
+ "G-C--": 1925,
1931
+ "G-C-A": 1926,
1932
+ "G-C-C": 1927,
1933
+ "G-C-G": 1928,
1934
+ "G-C-T": 1929,
1935
+ "G-CA-": 1930,
1936
+ "G-CAA": 1931,
1937
+ "G-CAC": 1932,
1938
+ "G-CAG": 1933,
1939
+ "G-CAT": 1934,
1940
+ "G-CC-": 1935,
1941
+ "G-CCA": 1936,
1942
+ "G-CCC": 1937,
1943
+ "G-CCG": 1938,
1944
+ "G-CCT": 1939,
1945
+ "G-CG-": 1940,
1946
+ "G-CGA": 1941,
1947
+ "G-CGC": 1942,
1948
+ "G-CGG": 1943,
1949
+ "G-CGT": 1944,
1950
+ "G-CT-": 1945,
1951
+ "G-CTA": 1946,
1952
+ "G-CTC": 1947,
1953
+ "G-CTG": 1948,
1954
+ "G-CTT": 1949,
1955
+ "G-G--": 1950,
1956
+ "G-G-A": 1951,
1957
+ "G-G-C": 1952,
1958
+ "G-G-G": 1953,
1959
+ "G-G-T": 1954,
1960
+ "G-GA-": 1955,
1961
+ "G-GAA": 1956,
1962
+ "G-GAC": 1957,
1963
+ "G-GAG": 1958,
1964
+ "G-GAT": 1959,
1965
+ "G-GC-": 1960,
1966
+ "G-GCA": 1961,
1967
+ "G-GCC": 1962,
1968
+ "G-GCG": 1963,
1969
+ "G-GCT": 1964,
1970
+ "G-GG-": 1965,
1971
+ "G-GGA": 1966,
1972
+ "G-GGC": 1967,
1973
+ "G-GGG": 1968,
1974
+ "G-GGT": 1969,
1975
+ "G-GT-": 1970,
1976
+ "G-GTA": 1971,
1977
+ "G-GTC": 1972,
1978
+ "G-GTG": 1973,
1979
+ "G-GTT": 1974,
1980
+ "G-T--": 1975,
1981
+ "G-T-A": 1976,
1982
+ "G-T-C": 1977,
1983
+ "G-T-G": 1978,
1984
+ "G-T-T": 1979,
1985
+ "G-TA-": 1980,
1986
+ "G-TAA": 1981,
1987
+ "G-TAC": 1982,
1988
+ "G-TAG": 1983,
1989
+ "G-TAT": 1984,
1990
+ "G-TC-": 1985,
1991
+ "G-TCA": 1986,
1992
+ "G-TCC": 1987,
1993
+ "G-TCG": 1988,
1994
+ "G-TCT": 1989,
1995
+ "G-TG-": 1990,
1996
+ "G-TGA": 1991,
1997
+ "G-TGC": 1992,
1998
+ "G-TGG": 1993,
1999
+ "G-TGT": 1994,
2000
+ "G-TT-": 1995,
2001
+ "G-TTA": 1996,
2002
+ "G-TTC": 1997,
2003
+ "G-TTG": 1998,
2004
+ "G-TTT": 1999,
2005
+ "GA---": 2000,
2006
+ "GA--A": 2001,
2007
+ "GA--C": 2002,
2008
+ "GA--G": 2003,
2009
+ "GA--T": 2004,
2010
+ "GA-A-": 2005,
2011
+ "GA-AA": 2006,
2012
+ "GA-AC": 2007,
2013
+ "GA-AG": 2008,
2014
+ "GA-AT": 2009,
2015
+ "GA-C-": 2010,
2016
+ "GA-CA": 2011,
2017
+ "GA-CC": 2012,
2018
+ "GA-CG": 2013,
2019
+ "GA-CT": 2014,
2020
+ "GA-G-": 2015,
2021
+ "GA-GA": 2016,
2022
+ "GA-GC": 2017,
2023
+ "GA-GG": 2018,
2024
+ "GA-GT": 2019,
2025
+ "GA-T-": 2020,
2026
+ "GA-TA": 2021,
2027
+ "GA-TC": 2022,
2028
+ "GA-TG": 2023,
2029
+ "GA-TT": 2024,
2030
+ "GAA--": 2025,
2031
+ "GAA-A": 2026,
2032
+ "GAA-C": 2027,
2033
+ "GAA-G": 2028,
2034
+ "GAA-T": 2029,
2035
+ "GAAA-": 2030,
2036
+ "GAAAA": 2031,
2037
+ "GAAAC": 2032,
2038
+ "GAAAG": 2033,
2039
+ "GAAAT": 2034,
2040
+ "GAAC-": 2035,
2041
+ "GAACA": 2036,
2042
+ "GAACC": 2037,
2043
+ "GAACG": 2038,
2044
+ "GAACT": 2039,
2045
+ "GAAG-": 2040,
2046
+ "GAAGA": 2041,
2047
+ "GAAGC": 2042,
2048
+ "GAAGG": 2043,
2049
+ "GAAGT": 2044,
2050
+ "GAAT-": 2045,
2051
+ "GAATA": 2046,
2052
+ "GAATC": 2047,
2053
+ "GAATG": 2048,
2054
+ "GAATT": 2049,
2055
+ "GAC--": 2050,
2056
+ "GAC-A": 2051,
2057
+ "GAC-C": 2052,
2058
+ "GAC-G": 2053,
2059
+ "GAC-T": 2054,
2060
+ "GACA-": 2055,
2061
+ "GACAA": 2056,
2062
+ "GACAC": 2057,
2063
+ "GACAG": 2058,
2064
+ "GACAT": 2059,
2065
+ "GACC-": 2060,
2066
+ "GACCA": 2061,
2067
+ "GACCC": 2062,
2068
+ "GACCG": 2063,
2069
+ "GACCT": 2064,
2070
+ "GACG-": 2065,
2071
+ "GACGA": 2066,
2072
+ "GACGC": 2067,
2073
+ "GACGG": 2068,
2074
+ "GACGT": 2069,
2075
+ "GACT-": 2070,
2076
+ "GACTA": 2071,
2077
+ "GACTC": 2072,
2078
+ "GACTG": 2073,
2079
+ "GACTT": 2074,
2080
+ "GAG--": 2075,
2081
+ "GAG-A": 2076,
2082
+ "GAG-C": 2077,
2083
+ "GAG-G": 2078,
2084
+ "GAG-T": 2079,
2085
+ "GAGA-": 2080,
2086
+ "GAGAA": 2081,
2087
+ "GAGAC": 2082,
2088
+ "GAGAG": 2083,
2089
+ "GAGAT": 2084,
2090
+ "GAGC-": 2085,
2091
+ "GAGCA": 2086,
2092
+ "GAGCC": 2087,
2093
+ "GAGCG": 2088,
2094
+ "GAGCT": 2089,
2095
+ "GAGG-": 2090,
2096
+ "GAGGA": 2091,
2097
+ "GAGGC": 2092,
2098
+ "GAGGG": 2093,
2099
+ "GAGGT": 2094,
2100
+ "GAGT-": 2095,
2101
+ "GAGTA": 2096,
2102
+ "GAGTC": 2097,
2103
+ "GAGTG": 2098,
2104
+ "GAGTT": 2099,
2105
+ "GAT--": 2100,
2106
+ "GAT-A": 2101,
2107
+ "GAT-C": 2102,
2108
+ "GAT-G": 2103,
2109
+ "GAT-T": 2104,
2110
+ "GATA-": 2105,
2111
+ "GATAA": 2106,
2112
+ "GATAC": 2107,
2113
+ "GATAG": 2108,
2114
+ "GATAT": 2109,
2115
+ "GATC-": 2110,
2116
+ "GATCA": 2111,
2117
+ "GATCC": 2112,
2118
+ "GATCG": 2113,
2119
+ "GATCT": 2114,
2120
+ "GATG-": 2115,
2121
+ "GATGA": 2116,
2122
+ "GATGC": 2117,
2123
+ "GATGG": 2118,
2124
+ "GATGT": 2119,
2125
+ "GATT-": 2120,
2126
+ "GATTA": 2121,
2127
+ "GATTC": 2122,
2128
+ "GATTG": 2123,
2129
+ "GATTT": 2124,
2130
+ "GC---": 2125,
2131
+ "GC--A": 2126,
2132
+ "GC--C": 2127,
2133
+ "GC--G": 2128,
2134
+ "GC--T": 2129,
2135
+ "GC-A-": 2130,
2136
+ "GC-AA": 2131,
2137
+ "GC-AC": 2132,
2138
+ "GC-AG": 2133,
2139
+ "GC-AT": 2134,
2140
+ "GC-C-": 2135,
2141
+ "GC-CA": 2136,
2142
+ "GC-CC": 2137,
2143
+ "GC-CG": 2138,
2144
+ "GC-CT": 2139,
2145
+ "GC-G-": 2140,
2146
+ "GC-GA": 2141,
2147
+ "GC-GC": 2142,
2148
+ "GC-GG": 2143,
2149
+ "GC-GT": 2144,
2150
+ "GC-T-": 2145,
2151
+ "GC-TA": 2146,
2152
+ "GC-TC": 2147,
2153
+ "GC-TG": 2148,
2154
+ "GC-TT": 2149,
2155
+ "GCA--": 2150,
2156
+ "GCA-A": 2151,
2157
+ "GCA-C": 2152,
2158
+ "GCA-G": 2153,
2159
+ "GCA-T": 2154,
2160
+ "GCAA-": 2155,
2161
+ "GCAAA": 2156,
2162
+ "GCAAC": 2157,
2163
+ "GCAAG": 2158,
2164
+ "GCAAT": 2159,
2165
+ "GCAC-": 2160,
2166
+ "GCACA": 2161,
2167
+ "GCACC": 2162,
2168
+ "GCACG": 2163,
2169
+ "GCACT": 2164,
2170
+ "GCAG-": 2165,
2171
+ "GCAGA": 2166,
2172
+ "GCAGC": 2167,
2173
+ "GCAGG": 2168,
2174
+ "GCAGT": 2169,
2175
+ "GCAT-": 2170,
2176
+ "GCATA": 2171,
2177
+ "GCATC": 2172,
2178
+ "GCATG": 2173,
2179
+ "GCATT": 2174,
2180
+ "GCC--": 2175,
2181
+ "GCC-A": 2176,
2182
+ "GCC-C": 2177,
2183
+ "GCC-G": 2178,
2184
+ "GCC-T": 2179,
2185
+ "GCCA-": 2180,
2186
+ "GCCAA": 2181,
2187
+ "GCCAC": 2182,
2188
+ "GCCAG": 2183,
2189
+ "GCCAT": 2184,
2190
+ "GCCC-": 2185,
2191
+ "GCCCA": 2186,
2192
+ "GCCCC": 2187,
2193
+ "GCCCG": 2188,
2194
+ "GCCCT": 2189,
2195
+ "GCCG-": 2190,
2196
+ "GCCGA": 2191,
2197
+ "GCCGC": 2192,
2198
+ "GCCGG": 2193,
2199
+ "GCCGT": 2194,
2200
+ "GCCT-": 2195,
2201
+ "GCCTA": 2196,
2202
+ "GCCTC": 2197,
2203
+ "GCCTG": 2198,
2204
+ "GCCTT": 2199,
2205
+ "GCG--": 2200,
2206
+ "GCG-A": 2201,
2207
+ "GCG-C": 2202,
2208
+ "GCG-G": 2203,
2209
+ "GCG-T": 2204,
2210
+ "GCGA-": 2205,
2211
+ "GCGAA": 2206,
2212
+ "GCGAC": 2207,
2213
+ "GCGAG": 2208,
2214
+ "GCGAT": 2209,
2215
+ "GCGC-": 2210,
2216
+ "GCGCA": 2211,
2217
+ "GCGCC": 2212,
2218
+ "GCGCG": 2213,
2219
+ "GCGCT": 2214,
2220
+ "GCGG-": 2215,
2221
+ "GCGGA": 2216,
2222
+ "GCGGC": 2217,
2223
+ "GCGGG": 2218,
2224
+ "GCGGT": 2219,
2225
+ "GCGT-": 2220,
2226
+ "GCGTA": 2221,
2227
+ "GCGTC": 2222,
2228
+ "GCGTG": 2223,
2229
+ "GCGTT": 2224,
2230
+ "GCT--": 2225,
2231
+ "GCT-A": 2226,
2232
+ "GCT-C": 2227,
2233
+ "GCT-G": 2228,
2234
+ "GCT-T": 2229,
2235
+ "GCTA-": 2230,
2236
+ "GCTAA": 2231,
2237
+ "GCTAC": 2232,
2238
+ "GCTAG": 2233,
2239
+ "GCTAT": 2234,
2240
+ "GCTC-": 2235,
2241
+ "GCTCA": 2236,
2242
+ "GCTCC": 2237,
2243
+ "GCTCG": 2238,
2244
+ "GCTCT": 2239,
2245
+ "GCTG-": 2240,
2246
+ "GCTGA": 2241,
2247
+ "GCTGC": 2242,
2248
+ "GCTGG": 2243,
2249
+ "GCTGT": 2244,
2250
+ "GCTT-": 2245,
2251
+ "GCTTA": 2246,
2252
+ "GCTTC": 2247,
2253
+ "GCTTG": 2248,
2254
+ "GCTTT": 2249,
2255
+ "GG---": 2250,
2256
+ "GG--A": 2251,
2257
+ "GG--C": 2252,
2258
+ "GG--G": 2253,
2259
+ "GG--T": 2254,
2260
+ "GG-A-": 2255,
2261
+ "GG-AA": 2256,
2262
+ "GG-AC": 2257,
2263
+ "GG-AG": 2258,
2264
+ "GG-AT": 2259,
2265
+ "GG-C-": 2260,
2266
+ "GG-CA": 2261,
2267
+ "GG-CC": 2262,
2268
+ "GG-CG": 2263,
2269
+ "GG-CT": 2264,
2270
+ "GG-G-": 2265,
2271
+ "GG-GA": 2266,
2272
+ "GG-GC": 2267,
2273
+ "GG-GG": 2268,
2274
+ "GG-GT": 2269,
2275
+ "GG-T-": 2270,
2276
+ "GG-TA": 2271,
2277
+ "GG-TC": 2272,
2278
+ "GG-TG": 2273,
2279
+ "GG-TT": 2274,
2280
+ "GGA--": 2275,
2281
+ "GGA-A": 2276,
2282
+ "GGA-C": 2277,
2283
+ "GGA-G": 2278,
2284
+ "GGA-T": 2279,
2285
+ "GGAA-": 2280,
2286
+ "GGAAA": 2281,
2287
+ "GGAAC": 2282,
2288
+ "GGAAG": 2283,
2289
+ "GGAAT": 2284,
2290
+ "GGAC-": 2285,
2291
+ "GGACA": 2286,
2292
+ "GGACC": 2287,
2293
+ "GGACG": 2288,
2294
+ "GGACT": 2289,
2295
+ "GGAG-": 2290,
2296
+ "GGAGA": 2291,
2297
+ "GGAGC": 2292,
2298
+ "GGAGG": 2293,
2299
+ "GGAGT": 2294,
2300
+ "GGAT-": 2295,
2301
+ "GGATA": 2296,
2302
+ "GGATC": 2297,
2303
+ "GGATG": 2298,
2304
+ "GGATT": 2299,
2305
+ "GGC--": 2300,
2306
+ "GGC-A": 2301,
2307
+ "GGC-C": 2302,
2308
+ "GGC-G": 2303,
2309
+ "GGC-T": 2304,
2310
+ "GGCA-": 2305,
2311
+ "GGCAA": 2306,
2312
+ "GGCAC": 2307,
2313
+ "GGCAG": 2308,
2314
+ "GGCAT": 2309,
2315
+ "GGCC-": 2310,
2316
+ "GGCCA": 2311,
2317
+ "GGCCC": 2312,
2318
+ "GGCCG": 2313,
2319
+ "GGCCT": 2314,
2320
+ "GGCG-": 2315,
2321
+ "GGCGA": 2316,
2322
+ "GGCGC": 2317,
2323
+ "GGCGG": 2318,
2324
+ "GGCGT": 2319,
2325
+ "GGCT-": 2320,
2326
+ "GGCTA": 2321,
2327
+ "GGCTC": 2322,
2328
+ "GGCTG": 2323,
2329
+ "GGCTT": 2324,
2330
+ "GGG--": 2325,
2331
+ "GGG-A": 2326,
2332
+ "GGG-C": 2327,
2333
+ "GGG-G": 2328,
2334
+ "GGG-T": 2329,
2335
+ "GGGA-": 2330,
2336
+ "GGGAA": 2331,
2337
+ "GGGAC": 2332,
2338
+ "GGGAG": 2333,
2339
+ "GGGAT": 2334,
2340
+ "GGGC-": 2335,
2341
+ "GGGCA": 2336,
2342
+ "GGGCC": 2337,
2343
+ "GGGCG": 2338,
2344
+ "GGGCT": 2339,
2345
+ "GGGG-": 2340,
2346
+ "GGGGA": 2341,
2347
+ "GGGGC": 2342,
2348
+ "GGGGG": 2343,
2349
+ "GGGGT": 2344,
2350
+ "GGGT-": 2345,
2351
+ "GGGTA": 2346,
2352
+ "GGGTC": 2347,
2353
+ "GGGTG": 2348,
2354
+ "GGGTT": 2349,
2355
+ "GGT--": 2350,
2356
+ "GGT-A": 2351,
2357
+ "GGT-C": 2352,
2358
+ "GGT-G": 2353,
2359
+ "GGT-T": 2354,
2360
+ "GGTA-": 2355,
2361
+ "GGTAA": 2356,
2362
+ "GGTAC": 2357,
2363
+ "GGTAG": 2358,
2364
+ "GGTAT": 2359,
2365
+ "GGTC-": 2360,
2366
+ "GGTCA": 2361,
2367
+ "GGTCC": 2362,
2368
+ "GGTCG": 2363,
2369
+ "GGTCT": 2364,
2370
+ "GGTG-": 2365,
2371
+ "GGTGA": 2366,
2372
+ "GGTGC": 2367,
2373
+ "GGTGG": 2368,
2374
+ "GGTGT": 2369,
2375
+ "GGTT-": 2370,
2376
+ "GGTTA": 2371,
2377
+ "GGTTC": 2372,
2378
+ "GGTTG": 2373,
2379
+ "GGTTT": 2374,
2380
+ "GT---": 2375,
2381
+ "GT--A": 2376,
2382
+ "GT--C": 2377,
2383
+ "GT--G": 2378,
2384
+ "GT--T": 2379,
2385
+ "GT-A-": 2380,
2386
+ "GT-AA": 2381,
2387
+ "GT-AC": 2382,
2388
+ "GT-AG": 2383,
2389
+ "GT-AT": 2384,
2390
+ "GT-C-": 2385,
2391
+ "GT-CA": 2386,
2392
+ "GT-CC": 2387,
2393
+ "GT-CG": 2388,
2394
+ "GT-CT": 2389,
2395
+ "GT-G-": 2390,
2396
+ "GT-GA": 2391,
2397
+ "GT-GC": 2392,
2398
+ "GT-GG": 2393,
2399
+ "GT-GT": 2394,
2400
+ "GT-T-": 2395,
2401
+ "GT-TA": 2396,
2402
+ "GT-TC": 2397,
2403
+ "GT-TG": 2398,
2404
+ "GT-TT": 2399,
2405
+ "GTA--": 2400,
2406
+ "GTA-A": 2401,
2407
+ "GTA-C": 2402,
2408
+ "GTA-G": 2403,
2409
+ "GTA-T": 2404,
2410
+ "GTAA-": 2405,
2411
+ "GTAAA": 2406,
2412
+ "GTAAC": 2407,
2413
+ "GTAAG": 2408,
2414
+ "GTAAT": 2409,
2415
+ "GTAC-": 2410,
2416
+ "GTACA": 2411,
2417
+ "GTACC": 2412,
2418
+ "GTACG": 2413,
2419
+ "GTACT": 2414,
2420
+ "GTAG-": 2415,
2421
+ "GTAGA": 2416,
2422
+ "GTAGC": 2417,
2423
+ "GTAGG": 2418,
2424
+ "GTAGT": 2419,
2425
+ "GTAT-": 2420,
2426
+ "GTATA": 2421,
2427
+ "GTATC": 2422,
2428
+ "GTATG": 2423,
2429
+ "GTATT": 2424,
2430
+ "GTC--": 2425,
2431
+ "GTC-A": 2426,
2432
+ "GTC-C": 2427,
2433
+ "GTC-G": 2428,
2434
+ "GTC-T": 2429,
2435
+ "GTCA-": 2430,
2436
+ "GTCAA": 2431,
2437
+ "GTCAC": 2432,
2438
+ "GTCAG": 2433,
2439
+ "GTCAT": 2434,
2440
+ "GTCC-": 2435,
2441
+ "GTCCA": 2436,
2442
+ "GTCCC": 2437,
2443
+ "GTCCG": 2438,
2444
+ "GTCCT": 2439,
2445
+ "GTCG-": 2440,
2446
+ "GTCGA": 2441,
2447
+ "GTCGC": 2442,
2448
+ "GTCGG": 2443,
2449
+ "GTCGT": 2444,
2450
+ "GTCT-": 2445,
2451
+ "GTCTA": 2446,
2452
+ "GTCTC": 2447,
2453
+ "GTCTG": 2448,
2454
+ "GTCTT": 2449,
2455
+ "GTG--": 2450,
2456
+ "GTG-A": 2451,
2457
+ "GTG-C": 2452,
2458
+ "GTG-G": 2453,
2459
+ "GTG-T": 2454,
2460
+ "GTGA-": 2455,
2461
+ "GTGAA": 2456,
2462
+ "GTGAC": 2457,
2463
+ "GTGAG": 2458,
2464
+ "GTGAT": 2459,
2465
+ "GTGC-": 2460,
2466
+ "GTGCA": 2461,
2467
+ "GTGCC": 2462,
2468
+ "GTGCG": 2463,
2469
+ "GTGCT": 2464,
2470
+ "GTGG-": 2465,
2471
+ "GTGGA": 2466,
2472
+ "GTGGC": 2467,
2473
+ "GTGGG": 2468,
2474
+ "GTGGT": 2469,
2475
+ "GTGT-": 2470,
2476
+ "GTGTA": 2471,
2477
+ "GTGTC": 2472,
2478
+ "GTGTG": 2473,
2479
+ "GTGTT": 2474,
2480
+ "GTT--": 2475,
2481
+ "GTT-A": 2476,
2482
+ "GTT-C": 2477,
2483
+ "GTT-G": 2478,
2484
+ "GTT-T": 2479,
2485
+ "GTTA-": 2480,
2486
+ "GTTAA": 2481,
2487
+ "GTTAC": 2482,
2488
+ "GTTAG": 2483,
2489
+ "GTTAT": 2484,
2490
+ "GTTC-": 2485,
2491
+ "GTTCA": 2486,
2492
+ "GTTCC": 2487,
2493
+ "GTTCG": 2488,
2494
+ "GTTCT": 2489,
2495
+ "GTTG-": 2490,
2496
+ "GTTGA": 2491,
2497
+ "GTTGC": 2492,
2498
+ "GTTGG": 2493,
2499
+ "GTTGT": 2494,
2500
+ "GTTT-": 2495,
2501
+ "GTTTA": 2496,
2502
+ "GTTTC": 2497,
2503
+ "GTTTG": 2498,
2504
+ "GTTTT": 2499,
2505
+ "T----": 2500,
2506
+ "T---A": 2501,
2507
+ "T---C": 2502,
2508
+ "T---G": 2503,
2509
+ "T---T": 2504,
2510
+ "T--A-": 2505,
2511
+ "T--AA": 2506,
2512
+ "T--AC": 2507,
2513
+ "T--AG": 2508,
2514
+ "T--AT": 2509,
2515
+ "T--C-": 2510,
2516
+ "T--CA": 2511,
2517
+ "T--CC": 2512,
2518
+ "T--CG": 2513,
2519
+ "T--CT": 2514,
2520
+ "T--G-": 2515,
2521
+ "T--GA": 2516,
2522
+ "T--GC": 2517,
2523
+ "T--GG": 2518,
2524
+ "T--GT": 2519,
2525
+ "T--T-": 2520,
2526
+ "T--TA": 2521,
2527
+ "T--TC": 2522,
2528
+ "T--TG": 2523,
2529
+ "T--TT": 2524,
2530
+ "T-A--": 2525,
2531
+ "T-A-A": 2526,
2532
+ "T-A-C": 2527,
2533
+ "T-A-G": 2528,
2534
+ "T-A-T": 2529,
2535
+ "T-AA-": 2530,
2536
+ "T-AAA": 2531,
2537
+ "T-AAC": 2532,
2538
+ "T-AAG": 2533,
2539
+ "T-AAT": 2534,
2540
+ "T-AC-": 2535,
2541
+ "T-ACA": 2536,
2542
+ "T-ACC": 2537,
2543
+ "T-ACG": 2538,
2544
+ "T-ACT": 2539,
2545
+ "T-AG-": 2540,
2546
+ "T-AGA": 2541,
2547
+ "T-AGC": 2542,
2548
+ "T-AGG": 2543,
2549
+ "T-AGT": 2544,
2550
+ "T-AT-": 2545,
2551
+ "T-ATA": 2546,
2552
+ "T-ATC": 2547,
2553
+ "T-ATG": 2548,
2554
+ "T-ATT": 2549,
2555
+ "T-C--": 2550,
2556
+ "T-C-A": 2551,
2557
+ "T-C-C": 2552,
2558
+ "T-C-G": 2553,
2559
+ "T-C-T": 2554,
2560
+ "T-CA-": 2555,
2561
+ "T-CAA": 2556,
2562
+ "T-CAC": 2557,
2563
+ "T-CAG": 2558,
2564
+ "T-CAT": 2559,
2565
+ "T-CC-": 2560,
2566
+ "T-CCA": 2561,
2567
+ "T-CCC": 2562,
2568
+ "T-CCG": 2563,
2569
+ "T-CCT": 2564,
2570
+ "T-CG-": 2565,
2571
+ "T-CGA": 2566,
2572
+ "T-CGC": 2567,
2573
+ "T-CGG": 2568,
2574
+ "T-CGT": 2569,
2575
+ "T-CT-": 2570,
2576
+ "T-CTA": 2571,
2577
+ "T-CTC": 2572,
2578
+ "T-CTG": 2573,
2579
+ "T-CTT": 2574,
2580
+ "T-G--": 2575,
2581
+ "T-G-A": 2576,
2582
+ "T-G-C": 2577,
2583
+ "T-G-G": 2578,
2584
+ "T-G-T": 2579,
2585
+ "T-GA-": 2580,
2586
+ "T-GAA": 2581,
2587
+ "T-GAC": 2582,
2588
+ "T-GAG": 2583,
2589
+ "T-GAT": 2584,
2590
+ "T-GC-": 2585,
2591
+ "T-GCA": 2586,
2592
+ "T-GCC": 2587,
2593
+ "T-GCG": 2588,
2594
+ "T-GCT": 2589,
2595
+ "T-GG-": 2590,
2596
+ "T-GGA": 2591,
2597
+ "T-GGC": 2592,
2598
+ "T-GGG": 2593,
2599
+ "T-GGT": 2594,
2600
+ "T-GT-": 2595,
2601
+ "T-GTA": 2596,
2602
+ "T-GTC": 2597,
2603
+ "T-GTG": 2598,
2604
+ "T-GTT": 2599,
2605
+ "T-T--": 2600,
2606
+ "T-T-A": 2601,
2607
+ "T-T-C": 2602,
2608
+ "T-T-G": 2603,
2609
+ "T-T-T": 2604,
2610
+ "T-TA-": 2605,
2611
+ "T-TAA": 2606,
2612
+ "T-TAC": 2607,
2613
+ "T-TAG": 2608,
2614
+ "T-TAT": 2609,
2615
+ "T-TC-": 2610,
2616
+ "T-TCA": 2611,
2617
+ "T-TCC": 2612,
2618
+ "T-TCG": 2613,
2619
+ "T-TCT": 2614,
2620
+ "T-TG-": 2615,
2621
+ "T-TGA": 2616,
2622
+ "T-TGC": 2617,
2623
+ "T-TGG": 2618,
2624
+ "T-TGT": 2619,
2625
+ "T-TT-": 2620,
2626
+ "T-TTA": 2621,
2627
+ "T-TTC": 2622,
2628
+ "T-TTG": 2623,
2629
+ "T-TTT": 2624,
2630
+ "TA---": 2625,
2631
+ "TA--A": 2626,
2632
+ "TA--C": 2627,
2633
+ "TA--G": 2628,
2634
+ "TA--T": 2629,
2635
+ "TA-A-": 2630,
2636
+ "TA-AA": 2631,
2637
+ "TA-AC": 2632,
2638
+ "TA-AG": 2633,
2639
+ "TA-AT": 2634,
2640
+ "TA-C-": 2635,
2641
+ "TA-CA": 2636,
2642
+ "TA-CC": 2637,
2643
+ "TA-CG": 2638,
2644
+ "TA-CT": 2639,
2645
+ "TA-G-": 2640,
2646
+ "TA-GA": 2641,
2647
+ "TA-GC": 2642,
2648
+ "TA-GG": 2643,
2649
+ "TA-GT": 2644,
2650
+ "TA-T-": 2645,
2651
+ "TA-TA": 2646,
2652
+ "TA-TC": 2647,
2653
+ "TA-TG": 2648,
2654
+ "TA-TT": 2649,
2655
+ "TAA--": 2650,
2656
+ "TAA-A": 2651,
2657
+ "TAA-C": 2652,
2658
+ "TAA-G": 2653,
2659
+ "TAA-T": 2654,
2660
+ "TAAA-": 2655,
2661
+ "TAAAA": 2656,
2662
+ "TAAAC": 2657,
2663
+ "TAAAG": 2658,
2664
+ "TAAAT": 2659,
2665
+ "TAAC-": 2660,
2666
+ "TAACA": 2661,
2667
+ "TAACC": 2662,
2668
+ "TAACG": 2663,
2669
+ "TAACT": 2664,
2670
+ "TAAG-": 2665,
2671
+ "TAAGA": 2666,
2672
+ "TAAGC": 2667,
2673
+ "TAAGG": 2668,
2674
+ "TAAGT": 2669,
2675
+ "TAAT-": 2670,
2676
+ "TAATA": 2671,
2677
+ "TAATC": 2672,
2678
+ "TAATG": 2673,
2679
+ "TAATT": 2674,
2680
+ "TAC--": 2675,
2681
+ "TAC-A": 2676,
2682
+ "TAC-C": 2677,
2683
+ "TAC-G": 2678,
2684
+ "TAC-T": 2679,
2685
+ "TACA-": 2680,
2686
+ "TACAA": 2681,
2687
+ "TACAC": 2682,
2688
+ "TACAG": 2683,
2689
+ "TACAT": 2684,
2690
+ "TACC-": 2685,
2691
+ "TACCA": 2686,
2692
+ "TACCC": 2687,
2693
+ "TACCG": 2688,
2694
+ "TACCT": 2689,
2695
+ "TACG-": 2690,
2696
+ "TACGA": 2691,
2697
+ "TACGC": 2692,
2698
+ "TACGG": 2693,
2699
+ "TACGT": 2694,
2700
+ "TACT-": 2695,
2701
+ "TACTA": 2696,
2702
+ "TACTC": 2697,
2703
+ "TACTG": 2698,
2704
+ "TACTT": 2699,
2705
+ "TAG--": 2700,
2706
+ "TAG-A": 2701,
2707
+ "TAG-C": 2702,
2708
+ "TAG-G": 2703,
2709
+ "TAG-T": 2704,
2710
+ "TAGA-": 2705,
2711
+ "TAGAA": 2706,
2712
+ "TAGAC": 2707,
2713
+ "TAGAG": 2708,
2714
+ "TAGAT": 2709,
2715
+ "TAGC-": 2710,
2716
+ "TAGCA": 2711,
2717
+ "TAGCC": 2712,
2718
+ "TAGCG": 2713,
2719
+ "TAGCT": 2714,
2720
+ "TAGG-": 2715,
2721
+ "TAGGA": 2716,
2722
+ "TAGGC": 2717,
2723
+ "TAGGG": 2718,
2724
+ "TAGGT": 2719,
2725
+ "TAGT-": 2720,
2726
+ "TAGTA": 2721,
2727
+ "TAGTC": 2722,
2728
+ "TAGTG": 2723,
2729
+ "TAGTT": 2724,
2730
+ "TAT--": 2725,
2731
+ "TAT-A": 2726,
2732
+ "TAT-C": 2727,
2733
+ "TAT-G": 2728,
2734
+ "TAT-T": 2729,
2735
+ "TATA-": 2730,
2736
+ "TATAA": 2731,
2737
+ "TATAC": 2732,
2738
+ "TATAG": 2733,
2739
+ "TATAT": 2734,
2740
+ "TATC-": 2735,
2741
+ "TATCA": 2736,
2742
+ "TATCC": 2737,
2743
+ "TATCG": 2738,
2744
+ "TATCT": 2739,
2745
+ "TATG-": 2740,
2746
+ "TATGA": 2741,
2747
+ "TATGC": 2742,
2748
+ "TATGG": 2743,
2749
+ "TATGT": 2744,
2750
+ "TATT-": 2745,
2751
+ "TATTA": 2746,
2752
+ "TATTC": 2747,
2753
+ "TATTG": 2748,
2754
+ "TATTT": 2749,
2755
+ "TC---": 2750,
2756
+ "TC--A": 2751,
2757
+ "TC--C": 2752,
2758
+ "TC--G": 2753,
2759
+ "TC--T": 2754,
2760
+ "TC-A-": 2755,
2761
+ "TC-AA": 2756,
2762
+ "TC-AC": 2757,
2763
+ "TC-AG": 2758,
2764
+ "TC-AT": 2759,
2765
+ "TC-C-": 2760,
2766
+ "TC-CA": 2761,
2767
+ "TC-CC": 2762,
2768
+ "TC-CG": 2763,
2769
+ "TC-CT": 2764,
2770
+ "TC-G-": 2765,
2771
+ "TC-GA": 2766,
2772
+ "TC-GC": 2767,
2773
+ "TC-GG": 2768,
2774
+ "TC-GT": 2769,
2775
+ "TC-T-": 2770,
2776
+ "TC-TA": 2771,
2777
+ "TC-TC": 2772,
2778
+ "TC-TG": 2773,
2779
+ "TC-TT": 2774,
2780
+ "TCA--": 2775,
2781
+ "TCA-A": 2776,
2782
+ "TCA-C": 2777,
2783
+ "TCA-G": 2778,
2784
+ "TCA-T": 2779,
2785
+ "TCAA-": 2780,
2786
+ "TCAAA": 2781,
2787
+ "TCAAC": 2782,
2788
+ "TCAAG": 2783,
2789
+ "TCAAT": 2784,
2790
+ "TCAC-": 2785,
2791
+ "TCACA": 2786,
2792
+ "TCACC": 2787,
2793
+ "TCACG": 2788,
2794
+ "TCACT": 2789,
2795
+ "TCAG-": 2790,
2796
+ "TCAGA": 2791,
2797
+ "TCAGC": 2792,
2798
+ "TCAGG": 2793,
2799
+ "TCAGT": 2794,
2800
+ "TCAT-": 2795,
2801
+ "TCATA": 2796,
2802
+ "TCATC": 2797,
2803
+ "TCATG": 2798,
2804
+ "TCATT": 2799,
2805
+ "TCC--": 2800,
2806
+ "TCC-A": 2801,
2807
+ "TCC-C": 2802,
2808
+ "TCC-G": 2803,
2809
+ "TCC-T": 2804,
2810
+ "TCCA-": 2805,
2811
+ "TCCAA": 2806,
2812
+ "TCCAC": 2807,
2813
+ "TCCAG": 2808,
2814
+ "TCCAT": 2809,
2815
+ "TCCC-": 2810,
2816
+ "TCCCA": 2811,
2817
+ "TCCCC": 2812,
2818
+ "TCCCG": 2813,
2819
+ "TCCCT": 2814,
2820
+ "TCCG-": 2815,
2821
+ "TCCGA": 2816,
2822
+ "TCCGC": 2817,
2823
+ "TCCGG": 2818,
2824
+ "TCCGT": 2819,
2825
+ "TCCT-": 2820,
2826
+ "TCCTA": 2821,
2827
+ "TCCTC": 2822,
2828
+ "TCCTG": 2823,
2829
+ "TCCTT": 2824,
2830
+ "TCG--": 2825,
2831
+ "TCG-A": 2826,
2832
+ "TCG-C": 2827,
2833
+ "TCG-G": 2828,
2834
+ "TCG-T": 2829,
2835
+ "TCGA-": 2830,
2836
+ "TCGAA": 2831,
2837
+ "TCGAC": 2832,
2838
+ "TCGAG": 2833,
2839
+ "TCGAT": 2834,
2840
+ "TCGC-": 2835,
2841
+ "TCGCA": 2836,
2842
+ "TCGCC": 2837,
2843
+ "TCGCG": 2838,
2844
+ "TCGCT": 2839,
2845
+ "TCGG-": 2840,
2846
+ "TCGGA": 2841,
2847
+ "TCGGC": 2842,
2848
+ "TCGGG": 2843,
2849
+ "TCGGT": 2844,
2850
+ "TCGT-": 2845,
2851
+ "TCGTA": 2846,
2852
+ "TCGTC": 2847,
2853
+ "TCGTG": 2848,
2854
+ "TCGTT": 2849,
2855
+ "TCT--": 2850,
2856
+ "TCT-A": 2851,
2857
+ "TCT-C": 2852,
2858
+ "TCT-G": 2853,
2859
+ "TCT-T": 2854,
2860
+ "TCTA-": 2855,
2861
+ "TCTAA": 2856,
2862
+ "TCTAC": 2857,
2863
+ "TCTAG": 2858,
2864
+ "TCTAT": 2859,
2865
+ "TCTC-": 2860,
2866
+ "TCTCA": 2861,
2867
+ "TCTCC": 2862,
2868
+ "TCTCG": 2863,
2869
+ "TCTCT": 2864,
2870
+ "TCTG-": 2865,
2871
+ "TCTGA": 2866,
2872
+ "TCTGC": 2867,
2873
+ "TCTGG": 2868,
2874
+ "TCTGT": 2869,
2875
+ "TCTT-": 2870,
2876
+ "TCTTA": 2871,
2877
+ "TCTTC": 2872,
2878
+ "TCTTG": 2873,
2879
+ "TCTTT": 2874,
2880
+ "TG---": 2875,
2881
+ "TG--A": 2876,
2882
+ "TG--C": 2877,
2883
+ "TG--G": 2878,
2884
+ "TG--T": 2879,
2885
+ "TG-A-": 2880,
2886
+ "TG-AA": 2881,
2887
+ "TG-AC": 2882,
2888
+ "TG-AG": 2883,
2889
+ "TG-AT": 2884,
2890
+ "TG-C-": 2885,
2891
+ "TG-CA": 2886,
2892
+ "TG-CC": 2887,
2893
+ "TG-CG": 2888,
2894
+ "TG-CT": 2889,
2895
+ "TG-G-": 2890,
2896
+ "TG-GA": 2891,
2897
+ "TG-GC": 2892,
2898
+ "TG-GG": 2893,
2899
+ "TG-GT": 2894,
2900
+ "TG-T-": 2895,
2901
+ "TG-TA": 2896,
2902
+ "TG-TC": 2897,
2903
+ "TG-TG": 2898,
2904
+ "TG-TT": 2899,
2905
+ "TGA--": 2900,
2906
+ "TGA-A": 2901,
2907
+ "TGA-C": 2902,
2908
+ "TGA-G": 2903,
2909
+ "TGA-T": 2904,
2910
+ "TGAA-": 2905,
2911
+ "TGAAA": 2906,
2912
+ "TGAAC": 2907,
2913
+ "TGAAG": 2908,
2914
+ "TGAAT": 2909,
2915
+ "TGAC-": 2910,
2916
+ "TGACA": 2911,
2917
+ "TGACC": 2912,
2918
+ "TGACG": 2913,
2919
+ "TGACT": 2914,
2920
+ "TGAG-": 2915,
2921
+ "TGAGA": 2916,
2922
+ "TGAGC": 2917,
2923
+ "TGAGG": 2918,
2924
+ "TGAGT": 2919,
2925
+ "TGAT-": 2920,
2926
+ "TGATA": 2921,
2927
+ "TGATC": 2922,
2928
+ "TGATG": 2923,
2929
+ "TGATT": 2924,
2930
+ "TGC--": 2925,
2931
+ "TGC-A": 2926,
2932
+ "TGC-C": 2927,
2933
+ "TGC-G": 2928,
2934
+ "TGC-T": 2929,
2935
+ "TGCA-": 2930,
2936
+ "TGCAA": 2931,
2937
+ "TGCAC": 2932,
2938
+ "TGCAG": 2933,
2939
+ "TGCAT": 2934,
2940
+ "TGCC-": 2935,
2941
+ "TGCCA": 2936,
2942
+ "TGCCC": 2937,
2943
+ "TGCCG": 2938,
2944
+ "TGCCT": 2939,
2945
+ "TGCG-": 2940,
2946
+ "TGCGA": 2941,
2947
+ "TGCGC": 2942,
2948
+ "TGCGG": 2943,
2949
+ "TGCGT": 2944,
2950
+ "TGCT-": 2945,
2951
+ "TGCTA": 2946,
2952
+ "TGCTC": 2947,
2953
+ "TGCTG": 2948,
2954
+ "TGCTT": 2949,
2955
+ "TGG--": 2950,
2956
+ "TGG-A": 2951,
2957
+ "TGG-C": 2952,
2958
+ "TGG-G": 2953,
2959
+ "TGG-T": 2954,
2960
+ "TGGA-": 2955,
2961
+ "TGGAA": 2956,
2962
+ "TGGAC": 2957,
2963
+ "TGGAG": 2958,
2964
+ "TGGAT": 2959,
2965
+ "TGGC-": 2960,
2966
+ "TGGCA": 2961,
2967
+ "TGGCC": 2962,
2968
+ "TGGCG": 2963,
2969
+ "TGGCT": 2964,
2970
+ "TGGG-": 2965,
2971
+ "TGGGA": 2966,
2972
+ "TGGGC": 2967,
2973
+ "TGGGG": 2968,
2974
+ "TGGGT": 2969,
2975
+ "TGGT-": 2970,
2976
+ "TGGTA": 2971,
2977
+ "TGGTC": 2972,
2978
+ "TGGTG": 2973,
2979
+ "TGGTT": 2974,
2980
+ "TGT--": 2975,
2981
+ "TGT-A": 2976,
2982
+ "TGT-C": 2977,
2983
+ "TGT-G": 2978,
2984
+ "TGT-T": 2979,
2985
+ "TGTA-": 2980,
2986
+ "TGTAA": 2981,
2987
+ "TGTAC": 2982,
2988
+ "TGTAG": 2983,
2989
+ "TGTAT": 2984,
2990
+ "TGTC-": 2985,
2991
+ "TGTCA": 2986,
2992
+ "TGTCC": 2987,
2993
+ "TGTCG": 2988,
2994
+ "TGTCT": 2989,
2995
+ "TGTG-": 2990,
2996
+ "TGTGA": 2991,
2997
+ "TGTGC": 2992,
2998
+ "TGTGG": 2993,
2999
+ "TGTGT": 2994,
3000
+ "TGTT-": 2995,
3001
+ "TGTTA": 2996,
3002
+ "TGTTC": 2997,
3003
+ "TGTTG": 2998,
3004
+ "TGTTT": 2999,
3005
+ "TT---": 3000,
3006
+ "TT--A": 3001,
3007
+ "TT--C": 3002,
3008
+ "TT--G": 3003,
3009
+ "TT--T": 3004,
3010
+ "TT-A-": 3005,
3011
+ "TT-AA": 3006,
3012
+ "TT-AC": 3007,
3013
+ "TT-AG": 3008,
3014
+ "TT-AT": 3009,
3015
+ "TT-C-": 3010,
3016
+ "TT-CA": 3011,
3017
+ "TT-CC": 3012,
3018
+ "TT-CG": 3013,
3019
+ "TT-CT": 3014,
3020
+ "TT-G-": 3015,
3021
+ "TT-GA": 3016,
3022
+ "TT-GC": 3017,
3023
+ "TT-GG": 3018,
3024
+ "TT-GT": 3019,
3025
+ "TT-T-": 3020,
3026
+ "TT-TA": 3021,
3027
+ "TT-TC": 3022,
3028
+ "TT-TG": 3023,
3029
+ "TT-TT": 3024,
3030
+ "TTA--": 3025,
3031
+ "TTA-A": 3026,
3032
+ "TTA-C": 3027,
3033
+ "TTA-G": 3028,
3034
+ "TTA-T": 3029,
3035
+ "TTAA-": 3030,
3036
+ "TTAAA": 3031,
3037
+ "TTAAC": 3032,
3038
+ "TTAAG": 3033,
3039
+ "TTAAT": 3034,
3040
+ "TTAC-": 3035,
3041
+ "TTACA": 3036,
3042
+ "TTACC": 3037,
3043
+ "TTACG": 3038,
3044
+ "TTACT": 3039,
3045
+ "TTAG-": 3040,
3046
+ "TTAGA": 3041,
3047
+ "TTAGC": 3042,
3048
+ "TTAGG": 3043,
3049
+ "TTAGT": 3044,
3050
+ "TTAT-": 3045,
3051
+ "TTATA": 3046,
3052
+ "TTATC": 3047,
3053
+ "TTATG": 3048,
3054
+ "TTATT": 3049,
3055
+ "TTC--": 3050,
3056
+ "TTC-A": 3051,
3057
+ "TTC-C": 3052,
3058
+ "TTC-G": 3053,
3059
+ "TTC-T": 3054,
3060
+ "TTCA-": 3055,
3061
+ "TTCAA": 3056,
3062
+ "TTCAC": 3057,
3063
+ "TTCAG": 3058,
3064
+ "TTCAT": 3059,
3065
+ "TTCC-": 3060,
3066
+ "TTCCA": 3061,
3067
+ "TTCCC": 3062,
3068
+ "TTCCG": 3063,
3069
+ "TTCCT": 3064,
3070
+ "TTCG-": 3065,
3071
+ "TTCGA": 3066,
3072
+ "TTCGC": 3067,
3073
+ "TTCGG": 3068,
3074
+ "TTCGT": 3069,
3075
+ "TTCT-": 3070,
3076
+ "TTCTA": 3071,
3077
+ "TTCTC": 3072,
3078
+ "TTCTG": 3073,
3079
+ "TTCTT": 3074,
3080
+ "TTG--": 3075,
3081
+ "TTG-A": 3076,
3082
+ "TTG-C": 3077,
3083
+ "TTG-G": 3078,
3084
+ "TTG-T": 3079,
3085
+ "TTGA-": 3080,
3086
+ "TTGAA": 3081,
3087
+ "TTGAC": 3082,
3088
+ "TTGAG": 3083,
3089
+ "TTGAT": 3084,
3090
+ "TTGC-": 3085,
3091
+ "TTGCA": 3086,
3092
+ "TTGCC": 3087,
3093
+ "TTGCG": 3088,
3094
+ "TTGCT": 3089,
3095
+ "TTGG-": 3090,
3096
+ "TTGGA": 3091,
3097
+ "TTGGC": 3092,
3098
+ "TTGGG": 3093,
3099
+ "TTGGT": 3094,
3100
+ "TTGT-": 3095,
3101
+ "TTGTA": 3096,
3102
+ "TTGTC": 3097,
3103
+ "TTGTG": 3098,
3104
+ "TTGTT": 3099,
3105
+ "TTT--": 3100,
3106
+ "TTT-A": 3101,
3107
+ "TTT-C": 3102,
3108
+ "TTT-G": 3103,
3109
+ "TTT-T": 3104,
3110
+ "TTTA-": 3105,
3111
+ "TTTAA": 3106,
3112
+ "TTTAC": 3107,
3113
+ "TTTAG": 3108,
3114
+ "TTTAT": 3109,
3115
+ "TTTC-": 3110,
3116
+ "TTTCA": 3111,
3117
+ "TTTCC": 3112,
3118
+ "TTTCG": 3113,
3119
+ "TTTCT": 3114,
3120
+ "TTTG-": 3115,
3121
+ "TTTGA": 3116,
3122
+ "TTTGC": 3117,
3123
+ "TTTGG": 3118,
3124
+ "TTTGT": 3119,
3125
+ "TTTT-": 3120,
3126
+ "TTTTA": 3121,
3127
+ "TTTTC": 3122,
3128
+ "TTTTG": 3123,
3129
+ "TTTTT": 3124
3130
+ }
3131
+ }
vocab/dna/base_1k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fec9105d949226a2e8f4f871e4ff93b808cb084ae7b3298d3394f8ef4bf7488
3
+ size 90
vocab/dna/base_2k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944d26ae025c670683624d58f754256ce5151be7d5ab2ddfd9205b1ceee3fdab
3
+ size 265
vocab/dna/base_3k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385240465043dbdb97a91e9a8f7e8d56d43ad568a49765fb2d12eadce65efd17
3
+ size 1265
vocab/dna/base_4k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2776bc8304f2aab325a927cf816ba2c2382ddb0bc0bf78ce44b9e346d60b80fa
3
+ size 7415
vocab/dna/base_5k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9879e7eb227aff1467e3f7137a0ae473d4cc4a2e3bc6a58b623e94c5611d09bd
3
+ size 41796
vocab/dna/base_6k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ce2ad09290e4a86bf83f2380d1ad3408676fb287d6a055c8c90b7c2ae8fa7d
3
+ size 229355
vocab/dna/base_7k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa619676d7828cd826550e3416b765de15bf2ebaedd0ff4b2ebb0580479634c7
3
+ size 1309520
vocab/dna/base_8k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d997a5281f944c6caa300948282848d8f09ef52d0ef0ac3e0bfbaac7b8d457e
3
+ size 7561166
vocab/dna/cont_1k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fec9105d949226a2e8f4f871e4ff93b808cb084ae7b3298d3394f8ef4bf7488
3
+ size 90
vocab/dna/cont_2k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce47c7eff12cef686e7a5aa1a67bbd9b27c4df854e7d4bd420e500473b46e81
3
+ size 235
vocab/dna/cont_3k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879ffe405c24d1328be59bd12a0450c97a06ffb030d18ccae93e078492cc3e2f
3
+ size 1060
vocab/dna/cont_4k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf9598bc000cc7f9dc23b5867bd5c930370c3f47246f9cbe90df4ef53df038a
3
+ size 6055
vocab/dna/cont_5k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b06e201c0c3b04edd17eb1c4f128e6fa08286747c8cf37f6c9dc866dfc66a48
3
+ size 34186
vocab/dna/cont_6k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a4cdcab7ee96121c69a158bb5370a366d6e351e790f7d1011912fc41451abc
3
+ size 187353
vocab/dna/cont_7k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47329dd36ae273423df63b5bf2b5fa7d15d71ce4bccefc73e9fc621da03a644
3
+ size 1040901
vocab/dna/cont_8k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d5f716ca12b951445c7ec11a767a456c794f56c2a530489e402b009c71fafd
3
+ size 6120352
vocab/protein/base_1k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9553a0cefbd50d113557cab4b57b084048873c3f23032f6e4b4ce8d0f5fb9ea
3
+ size 186
vocab/protein/base_2k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932fc436f728c61e97409ef693c0017d8b2dd424156412df6f4c341a5ade6c5c
3
+ size 3480
vocab/protein/base_3k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd704d63536c5ca3fcab5ce2f6209a8e01878df5edd4ead7e46fc1e21c26fe5
3
+ size 86856
vocab/protein/base_4k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b808ff564997d6182e822aef50bb36da5d47290f5a4a5e7a5c8fbca64f72b4e
3
+ size 2309700
vocab/protein/cont_1k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9553a0cefbd50d113557cab4b57b084048873c3f23032f6e4b4ce8d0f5fb9ea
3
+ size 186
vocab/protein/cont_2k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cce2944d21cea0ee078d55cd6c559b19ccd51d1ff2b91df58b432246e058ea
3
+ size 3333
vocab/protein/cont_3k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0dfddc4166a09fe8d0e97852a37cc63097eaf02e6a209331a8406339a493dc
3
+ size 83181
vocab/protein/cont_4k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e31f28dcdbd4275fc9295f3712d57d46a49ef4093348761e53d40ffeca1e79
3
+ size 2203192