Vlasta commited on
Commit
db1d55d
·
1 Parent(s): aa1a50b

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +2076 -0
  3. tokenizer_config.json +11 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "Split",
55
+ "pattern": {
56
+ "Regex": "[a-zA-Z]{100}"
57
+ },
58
+ "behavior": "Isolated",
59
+ "invert": false
60
+ },
61
+ "post_processor": {
62
+ "type": "BertProcessing",
63
+ "sep": [
64
+ "[SEP]",
65
+ 3
66
+ ],
67
+ "cls": [
68
+ "[CLS]",
69
+ 2
70
+ ]
71
+ },
72
+ "decoder": null,
73
+ "model": {
74
+ "type": "BPE",
75
+ "dropout": null,
76
+ "unk_token": "[UNK]",
77
+ "continuing_subword_prefix": null,
78
+ "end_of_word_suffix": null,
79
+ "fuse_unk": false,
80
+ "vocab": {
81
+ "[PAD]": 0,
82
+ "[UNK]": 1,
83
+ "[CLS]": 2,
84
+ "[SEP]": 3,
85
+ "[MASK]": 4,
86
+ "A": 5,
87
+ "C": 6,
88
+ "G": 7,
89
+ "T": 8,
90
+ "AA": 9,
91
+ "TT": 10,
92
+ "CC": 11,
93
+ "AG": 12,
94
+ "TG": 13,
95
+ "TC": 14,
96
+ "AC": 15,
97
+ "GG": 16,
98
+ "ATT": 17,
99
+ "AT": 18,
100
+ "GC": 19,
101
+ "ATG": 20,
102
+ "AAAA": 21,
103
+ "ACC": 22,
104
+ "AGG": 23,
105
+ "TCC": 24,
106
+ "TAA": 25,
107
+ "AGC": 26,
108
+ "TTTT": 27,
109
+ "AAG": 28,
110
+ "ATC": 29,
111
+ "AAC": 30,
112
+ "TGC": 31,
113
+ "TGG": 32,
114
+ "TTC": 33,
115
+ "TTG": 34,
116
+ "TAG": 35,
117
+ "TAC": 36,
118
+ "CCC": 37,
119
+ "TGGG": 38,
120
+ "TATT": 39,
121
+ "AGCC": 40,
122
+ "AGAA": 41,
123
+ "AGGC": 42,
124
+ "ATAA": 43,
125
+ "GGC": 44,
126
+ "TCTC": 45,
127
+ "GCC": 46,
128
+ "GGG": 47,
129
+ "TGGC": 48,
130
+ "TCAC": 49,
131
+ "ATAC": 50,
132
+ "TCCC": 51,
133
+ "TTCC": 52,
134
+ "AGAG": 53,
135
+ "TGCC": 54,
136
+ "ACCC": 55,
137
+ "TTTC": 56,
138
+ "TGAA": 57,
139
+ "ATTC": 58,
140
+ "ATGG": 59,
141
+ "TGAG": 60,
142
+ "ATCC": 61,
143
+ "ACAC": 62,
144
+ "ATGC": 63,
145
+ "TAAAA": 64,
146
+ "TAT": 65,
147
+ "AAAG": 66,
148
+ "TTGG": 67,
149
+ "TGTC": 68,
150
+ "ACAA": 69,
151
+ "TTGC": 70,
152
+ "ATTG": 71,
153
+ "TGTT": 72,
154
+ "TAGC": 73,
155
+ "TAGG": 74,
156
+ "AGGG": 75,
157
+ "TATG": 76,
158
+ "TAAG": 77,
159
+ "AAAC": 78,
160
+ "TATC": 79,
161
+ "AAGG": 80,
162
+ "AGAC": 81,
163
+ "TGTG": 82,
164
+ "AATT": 83,
165
+ "AGTC": 84,
166
+ "AAAAG": 85,
167
+ "AATC": 86,
168
+ "ACTT": 87,
169
+ "TAAC": 88,
170
+ "AGTT": 89,
171
+ "AGTG": 90,
172
+ "AAAAC": 91,
173
+ "TACC": 92,
174
+ "AAATT": 93,
175
+ "AAGC": 94,
176
+ "AACC": 95,
177
+ "TTTG": 96,
178
+ "TGAC": 97,
179
+ "ACG": 98,
180
+ "AAAAAAAA": 99,
181
+ "ATCTC": 100,
182
+ "CCCC": 101,
183
+ "ATTTT": 102,
184
+ "TCTT": 103,
185
+ "ATGGC": 104,
186
+ "TGGGC": 105,
187
+ "ACAG": 106,
188
+ "ACTC": 107,
189
+ "ATGGG": 108,
190
+ "TTAG": 109,
191
+ "ACCCC": 110,
192
+ "GGGC": 111,
193
+ "ATTTC": 112,
194
+ "TTTTC": 113,
195
+ "AATG": 114,
196
+ "AATAA": 115,
197
+ "GGCC": 116,
198
+ "ATAG": 117,
199
+ "AGGTC": 118,
200
+ "TTTTTT": 119,
201
+ "GCCC": 120,
202
+ "AAATG": 121,
203
+ "AAACC": 122,
204
+ "TGAAG": 123,
205
+ "ATTCC": 124,
206
+ "ATTAC": 125,
207
+ "ACCAC": 126,
208
+ "TGGCC": 127,
209
+ "AGAGG": 128,
210
+ "TGTAA": 129,
211
+ "TCTG": 130,
212
+ "ACTCC": 131,
213
+ "TTTTG": 132,
214
+ "AAGTG": 133,
215
+ "AACAC": 134,
216
+ "TGGGG": 135,
217
+ "AAGGC": 136,
218
+ "TTTAA": 137,
219
+ "TCAG": 138,
220
+ "ATTGC": 139,
221
+ "ATATT": 140,
222
+ "ATAGG": 141,
223
+ "TGGAG": 142,
224
+ "TATAA": 143,
225
+ "TATAC": 144,
226
+ "AGATG": 145,
227
+ "ACTG": 146,
228
+ "ACTGC": 147,
229
+ "ATAAC": 148,
230
+ "ATCCC": 149,
231
+ "ACCTC": 150,
232
+ "TCCCC": 151,
233
+ "AAGAA": 152,
234
+ "AAGTC": 153,
235
+ "ATCTT": 154,
236
+ "TTCTC": 155,
237
+ "TGCCTC": 156,
238
+ "TACCC": 157,
239
+ "AAAGG": 158,
240
+ "AAAGC": 159,
241
+ "TTTGC": 160,
242
+ "AGAAAA": 161,
243
+ "AGTAA": 162,
244
+ "GGGG": 163,
245
+ "ATATG": 164,
246
+ "ACCTCC": 165,
247
+ "AGGCC": 166,
248
+ "TTTTTTTT": 167,
249
+ "TAGCC": 168,
250
+ "GTG": 169,
251
+ "TTAC": 170,
252
+ "TTTAG": 171,
253
+ "AGAGC": 172,
254
+ "AGATC": 173,
255
+ "AGGGC": 174,
256
+ "TGAAAA": 175,
257
+ "TCTTG": 176,
258
+ "ATACC": 177,
259
+ "TTGAA": 178,
260
+ "TATTC": 179,
261
+ "AGGCTG": 180,
262
+ "TTCCCC": 181,
263
+ "ATTACAGGC": 182,
264
+ "GAG": 183,
265
+ "TA": 184,
266
+ "AGAAG": 185,
267
+ "AGAAC": 186,
268
+ "TCTTC": 187,
269
+ "ACATT": 188,
270
+ "ATTTG": 189,
271
+ "ATTGG": 190,
272
+ "ATAAAA": 191,
273
+ "ATGCC": 192,
274
+ "TCCAG": 193,
275
+ "TAAAC": 194,
276
+ "AGCAGC": 195,
277
+ "TTGCC": 196,
278
+ "TGGGATTACAGGC": 197,
279
+ "TCTCG": 198,
280
+ "AATTTT": 199,
281
+ "AATAG": 200,
282
+ "TTTCC": 201,
283
+ "TTGGG": 202,
284
+ "AGTGG": 203,
285
+ "AGTTC": 204,
286
+ "ACATG": 205,
287
+ "ACATC": 206,
288
+ "ATAGAA": 207,
289
+ "ATATAA": 208,
290
+ "AAAAAA": 209,
291
+ "ACCAGCC": 210,
292
+ "AGCTG": 211,
293
+ "AGCTC": 212,
294
+ "TGGAGG": 213,
295
+ "TATTTATT": 214,
296
+ "TGGCTC": 215,
297
+ "TCCCAGC": 216,
298
+ "GTC": 217,
299
+ "GTGG": 218,
300
+ "AAGGG": 219,
301
+ "AAACAC": 220,
302
+ "TTAAG": 221,
303
+ "TTCCC": 222,
304
+ "AGTGTT": 223,
305
+ "TGAAC": 224,
306
+ "TGTTG": 225,
307
+ "TGTAG": 226,
308
+ "TGTAC": 227,
309
+ "TCATT": 228,
310
+ "ACAGG": 229,
311
+ "ACTTC": 230,
312
+ "ACTTG": 231,
313
+ "ATTTTC": 232,
314
+ "ATAGC": 233,
315
+ "ATAAG": 234,
316
+ "AAAAAC": 235,
317
+ "ACCATG": 236,
318
+ "AGGAGG": 237,
319
+ "TCCTC": 238,
320
+ "TCCTGCCTC": 239,
321
+ "TAATTTT": 240,
322
+ "AACATT": 241,
323
+ "TGCAA": 242,
324
+ "TATTG": 243,
325
+ "TATTCC": 244,
326
+ "TCACTGC": 245,
327
+ "TGAAGC": 246,
328
+ "AGGCTGAGGC": 247,
329
+ "TATGG": 248,
330
+ "TTATAA": 249,
331
+ "CCAGG": 250,
332
+ "TGTATT": 251,
333
+ "TCG": 252,
334
+ "TCTAA": 253,
335
+ "ATATC": 254,
336
+ "GCGG": 255,
337
+ "ATGTT": 256,
338
+ "ATGAC": 257,
339
+ "AGGAA": 258,
340
+ "TAATAC": 259,
341
+ "AGCTT": 260,
342
+ "AGCTCC": 261,
343
+ "AAGAC": 262,
344
+ "AAGATC": 263,
345
+ "TTCTCC": 264,
346
+ "TTCTAA": 265,
347
+ "TACAC": 266,
348
+ "TACTAAAA": 267,
349
+ "TGGGGG": 268,
350
+ "AGAAAG": 269,
351
+ "AGAAGC": 270,
352
+ "AGGCTGG": 271,
353
+ "GCCGCC": 272,
354
+ "ATACAAAA": 273,
355
+ "TTTCTAC": 274,
356
+ "AAAGTGC": 275,
357
+ "ATTGTC": 276,
358
+ "TCCTGCCTCAGCC": 277,
359
+ "CAA": 278,
360
+ "GAC": 279,
361
+ "TATCC": 280,
362
+ "AATGG": 281,
363
+ "AATCTC": 282,
364
+ "AAATTC": 283,
365
+ "AATATC": 284,
366
+ "AGA": 285,
367
+ "AGACC": 286,
368
+ "AGTCC": 287,
369
+ "AGTGC": 288,
370
+ "AGCCC": 289,
371
+ "AGTCTC": 290,
372
+ "AGTGCC": 291,
373
+ "AGACAA": 292,
374
+ "TGATT": 293,
375
+ "TGAGG": 294,
376
+ "TGTTTT": 295,
377
+ "TCAAAA": 296,
378
+ "TCTTTT": 297,
379
+ "ACAT": 298,
380
+ "ACTAC": 299,
381
+ "GGAC": 300,
382
+ "GGAGC": 301,
383
+ "ATTAA": 302,
384
+ "ATTATT": 303,
385
+ "ATTATG": 304,
386
+ "ATTTCC": 305,
387
+ "ATTTTGG": 306,
388
+ "ATGACC": 307,
389
+ "ATGAAC": 308,
390
+ "ATGCCC": 309,
391
+ "AAAACC": 310,
392
+ "ACCACC": 311,
393
+ "AGGAGAA": 312,
394
+ "TCCTG": 313,
395
+ "TCCATG": 314,
396
+ "TCCACC": 315,
397
+ "TAATC": 316,
398
+ "TAAGC": 317,
399
+ "AGCG": 318,
400
+ "AGCAC": 319,
401
+ "AGCAGG": 320,
402
+ "AAGCC": 321,
403
+ "AACAA": 322,
404
+ "AACTT": 323,
405
+ "AACATGG": 324,
406
+ "TGCG": 325,
407
+ "TGCTT": 326,
408
+ "TGGAA": 327,
409
+ "TGGTGG": 328,
410
+ "TTCAC": 329,
411
+ "TTGAG": 330,
412
+ "TTGTG": 331,
413
+ "TTGTAG": 332,
414
+ "TTGCCC": 333,
415
+ "TAGTAG": 334,
416
+ "TAGGGC": 335,
417
+ "CCCAC": 336,
418
+ "TATTGC": 337,
419
+ "AGCCAC": 338,
420
+ "AGCCAGG": 339,
421
+ "ATAATT": 340,
422
+ "GGCTCACTGC": 341,
423
+ "GGGTGG": 342,
424
+ "ACCCTC": 343,
425
+ "TTTCTTTT": 344,
426
+ "TATAAAA": 345,
427
+ "TTGGCC": 346,
428
+ "TAGCTGGG": 347,
429
+ "ACTTTGGG": 348,
430
+ "AAAAAAAAAAAAAAAA": 349,
431
+ "TGGGCAAC": 350,
432
+ "AGGTCAGG": 351,
433
+ "GTCC": 352,
434
+ "GTGTC": 353,
435
+ "AAAT": 354,
436
+ "AAATAA": 355,
437
+ "AATGGC": 356,
438
+ "AAATAC": 357,
439
+ "AATATG": 358,
440
+ "TTAA": 359,
441
+ "TTGGC": 360,
442
+ "TTTATC": 361,
443
+ "AGTCAC": 362,
444
+ "TGA": 363,
445
+ "TGAGC": 364,
446
+ "TGCCC": 365,
447
+ "TGATAA": 366,
448
+ "TGATGC": 367,
449
+ "TGATTG": 368,
450
+ "TGTATG": 369,
451
+ "TGTTTTC": 370,
452
+ "TCTGG": 371,
453
+ "TCTTGC": 372,
454
+ "ACGC": 373,
455
+ "ACTGG": 374,
456
+ "GGCCC": 375,
457
+ "ATTTGC": 376,
458
+ "ATTTAG": 377,
459
+ "ATTTAC": 378,
460
+ "ATTTATT": 379,
461
+ "ATAT": 380,
462
+ "ATACCC": 381,
463
+ "GCTGGAG": 382,
464
+ "ACCGC": 383,
465
+ "TCCAC": 384,
466
+ "TCCAAAA": 385,
467
+ "TAAATC": 386,
468
+ "AGCAA": 387,
469
+ "AGCATG": 388,
470
+ "AGCTTC": 389,
471
+ "TTTTGG": 390,
472
+ "TTTTAGC": 391,
473
+ "AAGAGG": 392,
474
+ "AAGTTC": 393,
475
+ "ATCAC": 394,
476
+ "ATCTAG": 395,
477
+ "AACTAA": 396,
478
+ "TGCAAAA": 397,
479
+ "TGCTAC": 398,
480
+ "TGCTAAG": 399,
481
+ "TGGATT": 400,
482
+ "TGGACTT": 401,
483
+ "TTCTTC": 402,
484
+ "TTGTC": 403,
485
+ "TAGAAAA": 404,
486
+ "TAGAGAC": 405,
487
+ "TACTG": 406,
488
+ "CCCAGG": 407,
489
+ "CCCAGCC": 408,
490
+ "TATTTT": 409,
491
+ "TCACTC": 410,
492
+ "TCACTTC": 411,
493
+ "TCCCTC": 412,
494
+ "AGAGTGAG": 413,
495
+ "TTTCTTC": 414,
496
+ "ATTCTGG": 415,
497
+ "TGAGACCAGCC": 416,
498
+ "ATCCCC": 417,
499
+ "TTGCAGTG": 418,
500
+ "TAGGTC": 419,
501
+ "AGGGCC": 420,
502
+ "AAGGCC": 421,
503
+ "AATTAC": 422,
504
+ "ATGGGCC": 423,
505
+ "ACTCCAGCC": 424,
506
+ "AAGTGATCC": 425,
507
+ "AGGCCG": 426,
508
+ "TTTTTTTTTTTT": 427,
509
+ "AGGCTGAGGCAGGAGAA": 428,
510
+ "TACTAAAAATACAAAA": 429,
511
+ "AAAGTGCTGGGATTACAGGC": 430,
512
+ "GAAC": 431,
513
+ "GTCTC": 432,
514
+ "AAATC": 433,
515
+ "AATGC": 434,
516
+ "AATTC": 435,
517
+ "AATAC": 436,
518
+ "AATATT": 437,
519
+ "AATGAG": 438,
520
+ "AATGTC": 439,
521
+ "AAATAGG": 440,
522
+ "TTATG": 441,
523
+ "TTAAC": 442,
524
+ "TTTATT": 443,
525
+ "TTATAC": 444,
526
+ "TTACCC": 445,
527
+ "TTATTC": 446,
528
+ "TTTAAAA": 447,
529
+ "CCG": 448,
530
+ "CCAC": 449,
531
+ "CCATC": 450,
532
+ "AGATT": 451,
533
+ "AGTAG": 452,
534
+ "AGAGAA": 453,
535
+ "AGATAA": 454,
536
+ "AGGGG": 455,
537
+ "AGTGGC": 456,
538
+ "AGATAC": 457,
539
+ "AGTAAAA": 458,
540
+ "TGATG": 459,
541
+ "TGTCC": 460,
542
+ "TGTGC": 461,
543
+ "TGTTC": 462,
544
+ "TGTCTC": 463,
545
+ "TGTGGC": 464,
546
+ "TGTCCC": 465,
547
+ "TGATTC": 466,
548
+ "TCGC": 467,
549
+ "TCATG": 468,
550
+ "TCTAG": 469,
551
+ "TCTAC": 470,
552
+ "ACGG": 471,
553
+ "ACTGGG": 472,
554
+ "ACATAC": 473,
555
+ "ACTGCC": 474,
556
+ "ACATGG": 475,
557
+ "ACTAAAA": 476,
558
+ "GGGGC": 477,
559
+ "GGCCCC": 478,
560
+ "ATTTTG": 479,
561
+ "ATTCCC": 480,
562
+ "ATTGGG": 481,
563
+ "ATTACAA": 482,
564
+ "ATTTTGC": 483,
565
+ "ATTTAGG": 484,
566
+ "ATTTATC": 485,
567
+ "ATTAGTC": 486,
568
+ "ATAGGC": 487,
569
+ "ATATCC": 488,
570
+ "ATACCCC": 489,
571
+ "GCG": 490,
572
+ "GCTGC": 491,
573
+ "ATGTC": 492,
574
+ "ATGATC": 493,
575
+ "ATGGCC": 494,
576
+ "ATGAAAG": 495,
577
+ "ATGTAAG": 496,
578
+ "AAAATT": 497,
579
+ "AAAAGG": 498,
580
+ "AAAAGC": 499,
581
+ "AAAAAAG": 500,
582
+ "AAAAATC": 501,
583
+ "AAAAAAC": 502,
584
+ "AAAATATT": 503,
585
+ "ACCAAG": 504,
586
+ "ACCTAG": 505,
587
+ "ACCTATT": 506,
588
+ "AGGAG": 507,
589
+ "AGGAAAA": 508,
590
+ "AGGTAA": 509,
591
+ "AGGTGC": 510,
592
+ "AGGTAC": 511,
593
+ "AGGAGAG": 512,
594
+ "TCCTAG": 513,
595
+ "TCCTCCC": 514,
596
+ "TCCACCTCC": 515,
597
+ "TAATT": 516,
598
+ "TAACC": 517,
599
+ "TAATAA": 518,
600
+ "TAAATAA": 519,
601
+ "TAAGCC": 520,
602
+ "TAATAT": 521,
603
+ "AGCACC": 522,
604
+ "AGCTAC": 523,
605
+ "AGCGCC": 524,
606
+ "AGCTTCC": 525,
607
+ "AGCTAATTTT": 526,
608
+ "TTTTAAAA": 527,
609
+ "TTTTTAAAA": 528,
610
+ "AAGTAC": 529,
611
+ "ATCG": 530,
612
+ "ATCAAC": 531,
613
+ "ATCTTC": 532,
614
+ "ATCTAAAA": 533,
615
+ "AACAG": 534,
616
+ "AACTC": 535,
617
+ "AACAGC": 536,
618
+ "AACATTC": 537,
619
+ "AACTAAAA": 538,
620
+ "TGCTG": 539,
621
+ "TGCTC": 540,
622
+ "TGCTGCC": 541,
623
+ "TGCAGTG": 542,
624
+ "TGCAGTGG": 543,
625
+ "TGGTT": 544,
626
+ "TGGAAC": 545,
627
+ "TGGTTTC": 546,
628
+ "TGGAATT": 547,
629
+ "TTGTT": 548,
630
+ "TTGTATT": 549,
631
+ "TAGTTTT": 550,
632
+ "TACAGC": 551,
633
+ "TACTTC": 552,
634
+ "TGGGCC": 553,
635
+ "TGGGTGG": 554,
636
+ "TGGGGCC": 555,
637
+ "AGCCCC": 556,
638
+ "AGCCTCCC": 557,
639
+ "AGCCGGGC": 558,
640
+ "AGCCAAGATC": 559,
641
+ "AGAATT": 560,
642
+ "AGAAAC": 561,
643
+ "AGAAGG": 562,
644
+ "AGAAGGC": 563,
645
+ "GGCG": 564,
646
+ "TCTCTC": 565,
647
+ "GCCTCC": 566,
648
+ "TGGCTAAC": 567,
649
+ "TCACACC": 568,
650
+ "TCACTTG": 569,
651
+ "AGAGAT": 570,
652
+ "AGAGAGAG": 571,
653
+ "TGCCAC": 572,
654
+ "ACCCACC": 573,
655
+ "ACCCGCC": 574,
656
+ "TTTCACCATG": 575,
657
+ "TGAAACCCC": 576,
658
+ "ATTCTCCTGCCTCAGCC": 577,
659
+ "TGAGATG": 578,
660
+ "ACACATG": 579,
661
+ "ACACAAAA": 580,
662
+ "TAAAAC": 581,
663
+ "TTGGGC": 582,
664
+ "TGTCTAA": 583,
665
+ "TTGCTCC": 584,
666
+ "ATTGATCC": 585,
667
+ "TAGCTGGGATTACAGGC": 586,
668
+ "AAACGG": 587,
669
+ "AAACACC": 588,
670
+ "AGTCTATT": 589,
671
+ "ACTTCCC": 590,
672
+ "TAACTGC": 591,
673
+ "TACCATG": 592,
674
+ "AAATTTC": 593,
675
+ "ATCTCATG": 594,
676
+ "TCTTAGC": 595,
677
+ "TGGGCGC": 596,
678
+ "AGAGGAAAA": 597,
679
+ "AGATGGGG": 598,
680
+ "TTTAGTAGAGAC": 599,
681
+ "TCTCGAAC": 600,
682
+ "TCCCAGCACTTTGGG": 601,
683
+ "TTCACGCC": 602,
684
+ "GGCTCACTGCAACC": 603,
685
+ "TAGCTGGGACTAC": 604,
686
+ "ACTCCAGCCTGGGCAAC": 605,
687
+ "CAG": 606,
688
+ "GTT": 607,
689
+ "GATG": 608,
690
+ "GTAA": 609,
691
+ "GAGC": 610,
692
+ "GTTG": 611,
693
+ "GTAC": 612,
694
+ "GTGAA": 613,
695
+ "GTAGG": 614,
696
+ "GTACC": 615,
697
+ "GACTCC": 616,
698
+ "GATCCC": 617,
699
+ "GTGCCTC": 618,
700
+ "TATGC": 619,
701
+ "AATTG": 620,
702
+ "AAAGCC": 621,
703
+ "AAAGAA": 622,
704
+ "AAAGAG": 623,
705
+ "AATTTC": 624,
706
+ "AAATCC": 625,
707
+ "AATAAAA": 626,
708
+ "AAATGGC": 627,
709
+ "AAAGGTC": 628,
710
+ "AATATAA": 629,
711
+ "TTATT": 630,
712
+ "TTTAC": 631,
713
+ "TTTGGG": 632,
714
+ "TTTGAA": 633,
715
+ "TTTGTC": 634,
716
+ "TTATTG": 635,
717
+ "TTTGTT": 636,
718
+ "TTTAGC": 637,
719
+ "TTAAAC": 638,
720
+ "TTAGTT": 639,
721
+ "TTTACC": 640,
722
+ "TTAACC": 641,
723
+ "TTACG": 642,
724
+ "TTATTGC": 643,
725
+ "TTTATTC": 644,
726
+ "CCAAAG": 645,
727
+ "AGT": 646,
728
+ "AGTTCC": 647,
729
+ "AGATTC": 648,
730
+ "AGACAC": 649,
731
+ "AGTTGG": 650,
732
+ "AGTGTC": 651,
733
+ "AGTTGC": 652,
734
+ "AGAAAAC": 653,
735
+ "AGATTTT": 654,
736
+ "AGATGGG": 655,
737
+ "AGATTTC": 656,
738
+ "AGAACAC": 657,
739
+ "AGTATTGC": 658,
740
+ "TGAT": 659,
741
+ "TGTGGG": 660,
742
+ "TGAGCC": 661,
743
+ "TGAGGC": 662,
744
+ "TGTGCC": 663,
745
+ "TGATCC": 664,
746
+ "TGACAC": 665,
747
+ "TGTAT": 666,
748
+ "TGACAA": 667,
749
+ "TGATAGG": 668,
750
+ "TGTATAC": 669,
751
+ "TGAGGTCAGG": 670,
752
+ "TCACC": 671,
753
+ "TCAGG": 672,
754
+ "TCAAG": 673,
755
+ "TCATGG": 674,
756
+ "TCATCC": 675,
757
+ "TCAAAC": 676,
758
+ "TCAATT": 677,
759
+ "TCAATC": 678,
760
+ "TCTGAC": 679,
761
+ "TCAAGTGATCC": 680,
762
+ "ACT": 681,
763
+ "ACTTTT": 682,
764
+ "ACTATT": 683,
765
+ "ACTCAC": 684,
766
+ "ACTGAG": 685,
767
+ "ACATGC": 686,
768
+ "ACATGGG": 687,
769
+ "ACTTTTTT": 688,
770
+ "ACAACAC": 689,
771
+ "ACTACCC": 690,
772
+ "ACTAATAC": 691,
773
+ "GGAG": 692,
774
+ "GGAGG": 693,
775
+ "GGATC": 694,
776
+ "GGTGGC": 695,
777
+ "GGTTGG": 696,
778
+ "GGAAAC": 697,
779
+ "GGACTC": 698,
780
+ "GGAAAAAAG": 699,
781
+ "ATTA": 700,
782
+ "ATTAG": 701,
783
+ "ATTTAA": 702,
784
+ "ATTTGGG": 703,
785
+ "ATTTCAC": 704,
786
+ "ATTACCC": 705,
787
+ "ATTTTTC": 706,
788
+ "ATTTGAG": 707,
789
+ "ATTACAG": 708,
790
+ "ATTTATAC": 709,
791
+ "ATTAAAGG": 710,
792
+ "ATTTATTTATT": 711,
793
+ "ATA": 712,
794
+ "ATAGAG": 713,
795
+ "ATATGC": 714,
796
+ "ATAAAAC": 715,
797
+ "ATATAG": 716,
798
+ "GCGGC": 717,
799
+ "GCTGGC": 718,
800
+ "GCAAGG": 719,
801
+ "GCACCAC": 720,
802
+ "ATGTAA": 721,
803
+ "ATGTGG": 722,
804
+ "ATGTTG": 723,
805
+ "ATGTAC": 724,
806
+ "ATGAGCC": 725,
807
+ "ATGTGCC": 726,
808
+ "ATGATCC": 727,
809
+ "ATGAAAC": 728,
810
+ "ATGTCTT": 729,
811
+ "ATGAATG": 730,
812
+ "ATGTGAAAA": 731,
813
+ "AAAAATG": 732,
814
+ "AAAATTC": 733,
815
+ "AAAACCC": 734,
816
+ "ACCAT": 735,
817
+ "ACCTTC": 736,
818
+ "ACCATCC": 737,
819
+ "ACCACAC": 738,
820
+ "ACCACAA": 739,
821
+ "ACCTGTT": 740,
822
+ "ACCTGTG": 741,
823
+ "ACCTTCTC": 742,
824
+ "ACCTGAGGTCAGG": 743,
825
+ "AGGT": 744,
826
+ "AGGAAG": 745,
827
+ "AGGAAC": 746,
828
+ "AGGTGG": 747,
829
+ "AGGCCC": 748,
830
+ "AGGTAGG": 749,
831
+ "AGGAAAAG": 750,
832
+ "AGGTGAC": 751,
833
+ "AGGAAACC": 752,
834
+ "TCCG": 753,
835
+ "TCCATC": 754,
836
+ "TCCAAC": 755,
837
+ "TCCAGGC": 756,
838
+ "TCCTTTAA": 757,
839
+ "TCCGCCTCC": 758,
840
+ "TAAGG": 759,
841
+ "TAAATG": 760,
842
+ "TAACCC": 761,
843
+ "TAATGAAG": 762,
844
+ "AGCA": 763,
845
+ "AGCT": 764,
846
+ "AGCAT": 765,
847
+ "AGCATC": 766,
848
+ "AGCAGGC": 767,
849
+ "AGCAAAG": 768,
850
+ "AGCTAGC": 769,
851
+ "AGCTATG": 770,
852
+ "AGCAAGG": 771,
853
+ "AGCAATAG": 772,
854
+ "AGCTCACTGC": 773,
855
+ "TTTTCC": 774,
856
+ "TTTTAT": 775,
857
+ "TTTTAATAA": 776,
858
+ "TTTTTTTTTT": 777,
859
+ "AAGTAA": 778,
860
+ "AAGCCC": 779,
861
+ "AAGTATT": 780,
862
+ "AAGAGAA": 781,
863
+ "AAGATAC": 782,
864
+ "AAGTTCC": 783,
865
+ "AAGTTTC": 784,
866
+ "AAGAGGG": 785,
867
+ "AAGAGTC": 786,
868
+ "AAGACTT": 787,
869
+ "AAGACTC": 788,
870
+ "AAGACTCC": 789,
871
+ "ATCAGCC": 790,
872
+ "ATCTCAC": 791,
873
+ "ATCACAC": 792,
874
+ "ATCTAGG": 793,
875
+ "ATCAGGG": 794,
876
+ "ATCACTT": 795,
877
+ "ATCACG": 796,
878
+ "AACTAG": 797,
879
+ "AACTGCC": 798,
880
+ "AACACTT": 799,
881
+ "TGCGC": 800,
882
+ "TGCTGC": 801,
883
+ "TGCATAC": 802,
884
+ "TGCATCC": 803,
885
+ "TGGAT": 804,
886
+ "TGGTAA": 805,
887
+ "TGGATCC": 806,
888
+ "TGGAGAC": 807,
889
+ "TGGTGTG": 808,
890
+ "TGGTTTTC": 809,
891
+ "TTCTG": 810,
892
+ "TTCACC": 811,
893
+ "TTCATC": 812,
894
+ "TTGA": 813,
895
+ "TTGAAC": 814,
896
+ "TTGAGCC": 815,
897
+ "TTGTCTC": 816,
898
+ "TTGATGC": 817,
899
+ "TTGTTGC": 818,
900
+ "TTGAATT": 819,
901
+ "TTGAATAA": 820,
902
+ "TAGTC": 821,
903
+ "TAGCCC": 822,
904
+ "TAGGCTGGAG": 823,
905
+ "TACGG": 824,
906
+ "TACTACC": 825,
907
+ "TACACTG": 826,
908
+ "TACTTGGG": 827,
909
+ "TACTGGGGCC": 828,
910
+ "CCCG": 829,
911
+ "CCCAAG": 830,
912
+ "CCCTTTC": 831,
913
+ "CCCGGCC": 832,
914
+ "CCCACCTC": 833,
915
+ "CCCAAAGAA": 834,
916
+ "TGGGTGC": 835,
917
+ "TGGGTTC": 836,
918
+ "TGGGAGGC": 837,
919
+ "TGGGTCCCC": 838,
920
+ "TGGGTTCACGCC": 839,
921
+ "TATTAC": 840,
922
+ "TATTTTCC": 841,
923
+ "TATTTTGC": 842,
924
+ "AGCCATC": 843,
925
+ "AGCCTCCAG": 844,
926
+ "AGAAAT": 845,
927
+ "AGAATGC": 846,
928
+ "AGAATTC": 847,
929
+ "AGAAAGAG": 848,
930
+ "AGAAGGCC": 849,
931
+ "AGGCTAT": 850,
932
+ "AGGCAGAGG": 851,
933
+ "AGGCTGGAG": 852,
934
+ "AGGCAGATC": 853,
935
+ "AGGCAGAAG": 854,
936
+ "ATAAATAA": 855,
937
+ "ATAATTAG": 856,
938
+ "ATAATCAG": 857,
939
+ "GGCT": 858,
940
+ "GGCGAG": 859,
941
+ "GCCTTGG": 860,
942
+ "GCCACTGC": 861,
943
+ "GGGATG": 862,
944
+ "GGGTGC": 863,
945
+ "GGGACCC": 864,
946
+ "GGGACAG": 865,
947
+ "GGGAATG": 866,
948
+ "GGGAGGCTGAGGC": 867,
949
+ "TGGCTAC": 868,
950
+ "TGGCTGAA": 869,
951
+ "TGGCTGGGG": 870,
952
+ "TGGCTTGAA": 871,
953
+ "TGGCTAATTTT": 872,
954
+ "TGGCGTGAA": 873,
955
+ "TCACAATC": 874,
956
+ "ATACAGGC": 875,
957
+ "TCCCGCC": 876,
958
+ "TCCCTGAA": 877,
959
+ "TCCCAAAGTGCTGGGATTACAGGC": 878,
960
+ "TTCCATTC": 879,
961
+ "AGAGT": 880,
962
+ "AGAGGG": 881,
963
+ "AGAGAGAC": 882,
964
+ "TGCCAGG": 883,
965
+ "TGCCTTG": 884,
966
+ "ACCCAGC": 885,
967
+ "ACCCATAC": 886,
968
+ "TTTCTAG": 887,
969
+ "TGAAT": 888,
970
+ "TGAAAC": 889,
971
+ "TGAAGGC": 890,
972
+ "TGAAACCC": 891,
973
+ "TGAAATTTAG": 892,
974
+ "ATTCTAA": 893,
975
+ "ATGGTCC": 894,
976
+ "ATGGAAG": 895,
977
+ "ATGGTAG": 896,
978
+ "ATGGAGTCTC": 897,
979
+ "TGAGTATT": 898,
980
+ "TGAGATGG": 899,
981
+ "TGAGACAA": 900,
982
+ "ATGCAAG": 901,
983
+ "ATGCAATAA": 902,
984
+ "TATAGG": 903,
985
+ "TATATGC": 904,
986
+ "AAAGAGGC": 905,
987
+ "AAAGTAT": 906,
988
+ "TTGGTC": 907,
989
+ "TGTCTTCC": 908,
990
+ "TGTCGCCC": 909,
991
+ "ACAAAC": 910,
992
+ "ACAATATTTT": 911,
993
+ "TTGCAG": 912,
994
+ "TTGCTGC": 913,
995
+ "ATTGTATT": 914,
996
+ "ATTGAGAG": 915,
997
+ "ATTGTTTTC": 916,
998
+ "TGTTTGGG": 917,
999
+ "TGTTTATT": 918,
1000
+ "TGTTGGG": 919,
1001
+ "AGGGGCC": 920,
1002
+ "AGGGTTTCACCATG": 921,
1003
+ "TATGAGC": 922,
1004
+ "AAGGAAAA": 923,
1005
+ "AAGGAGAGC": 924,
1006
+ "AATTAGCC": 925,
1007
+ "AGTCTAG": 926,
1008
+ "AAAAGAAATT": 927,
1009
+ "AATCATGC": 928,
1010
+ "AATCTGAC": 929,
1011
+ "TAACTC": 930,
1012
+ "AGTTTCC": 931,
1013
+ "AGTTTAGG": 932,
1014
+ "AGTTTGAGACCAGCC": 933,
1015
+ "AGTGAAAA": 934,
1016
+ "AGTGTAG": 935,
1017
+ "AAAACACC": 936,
1018
+ "AAAACAGAC": 937,
1019
+ "TACCTC": 938,
1020
+ "AAGCG": 939,
1021
+ "AAGCAA": 940,
1022
+ "AAGCATGC": 941,
1023
+ "AAGCACTG": 942,
1024
+ "AACCCC": 943,
1025
+ "TTTGAGG": 944,
1026
+ "TTTGCCC": 945,
1027
+ "ACGA": 946,
1028
+ "AAAAAAAAAAAA": 947,
1029
+ "ATCTCATC": 948,
1030
+ "ATCTCTGC": 949,
1031
+ "CCCCG": 950,
1032
+ "CCCCCC": 951,
1033
+ "ATTTTCCC": 952,
1034
+ "ATTTTATTG": 953,
1035
+ "TCTTTAAG": 954,
1036
+ "ATGGCAGCAGGC": 955,
1037
+ "TGGGCATGG": 956,
1038
+ "ATGGGTAG": 957,
1039
+ "TTAGTGC": 958,
1040
+ "ACCCCTGGC": 959,
1041
+ "GGGCGG": 960,
1042
+ "ATTTCTTG": 961,
1043
+ "TTTTTTTGAG": 962,
1044
+ "GCCCGCCGCC": 963,
1045
+ "AAATGAAC": 964,
1046
+ "TGAAGTTGG": 965,
1047
+ "ATTCCATG": 966,
1048
+ "ACCACTAC": 967,
1049
+ "ACCACAGAA": 968,
1050
+ "TGGCCAACATGG": 969,
1051
+ "TGTAATCTC": 970,
1052
+ "TCTGTCTC": 971,
1053
+ "TTTTGTT": 972,
1054
+ "AACACTGAC": 973,
1055
+ "TGGGGAGTC": 974,
1056
+ "TTTAAGC": 975,
1057
+ "ATAGGAGTTGG": 976,
1058
+ "TATAAAGAA": 977,
1059
+ "AGATGCC": 978,
1060
+ "ACTGCCC": 979,
1061
+ "ATAACTTC": 980,
1062
+ "TCCCCGC": 981,
1063
+ "AAGTCATGTCTT": 982,
1064
+ "AGGGCGC": 983,
1065
+ "TCTTGAAC": 984,
1066
+ "TTGAAAGCC": 985,
1067
+ "GAGTAGCTGGGATTACAGGC": 986,
1068
+ "AATTTTAC": 987,
1069
+ "TTTCCCCC": 988,
1070
+ "ACATGAAATG": 989,
1071
+ "ACATCATC": 990,
1072
+ "TCCCAGCTACTTGGG": 991,
1073
+ "TTAAGAG": 992,
1074
+ "AGTGTTGGG": 993,
1075
+ "ACTTCAAG": 994,
1076
+ "ATTTTCTGG": 995,
1077
+ "AGGAATGTG": 996,
1078
+ "TACACTGAA": 997,
1079
+ "AGGCTGGTCTCGAAC": 998,
1080
+ "AGGCTGGTCTTGAAC": 999
1081
+ },
1082
+ "merges": [
1083
+ "A A",
1084
+ "T T",
1085
+ "C C",
1086
+ "A G",
1087
+ "T G",
1088
+ "T C",
1089
+ "A C",
1090
+ "G G",
1091
+ "A TT",
1092
+ "A T",
1093
+ "G C",
1094
+ "A TG",
1095
+ "AA AA",
1096
+ "A CC",
1097
+ "AG G",
1098
+ "T CC",
1099
+ "T AA",
1100
+ "AG C",
1101
+ "TT TT",
1102
+ "AA G",
1103
+ "A TC",
1104
+ "AA C",
1105
+ "TG C",
1106
+ "TG G",
1107
+ "TT C",
1108
+ "TT G",
1109
+ "T AG",
1110
+ "T AC",
1111
+ "CC C",
1112
+ "TG GG",
1113
+ "T ATT",
1114
+ "AG CC",
1115
+ "AG AA",
1116
+ "AG GC",
1117
+ "AT AA",
1118
+ "GG C",
1119
+ "TC TC",
1120
+ "G CC",
1121
+ "GG G",
1122
+ "TG GC",
1123
+ "TC AC",
1124
+ "AT AC",
1125
+ "TCC C",
1126
+ "TT CC",
1127
+ "AG AG",
1128
+ "TG CC",
1129
+ "ACC C",
1130
+ "TT TC",
1131
+ "TG AA",
1132
+ "ATT C",
1133
+ "ATG G",
1134
+ "TG AG",
1135
+ "AT CC",
1136
+ "AC AC",
1137
+ "ATG C",
1138
+ "T AAAA",
1139
+ "T AT",
1140
+ "AA AG",
1141
+ "TT GG",
1142
+ "TG TC",
1143
+ "AC AA",
1144
+ "TT GC",
1145
+ "ATT G",
1146
+ "TG TT",
1147
+ "T AGC",
1148
+ "T AGG",
1149
+ "AG GG",
1150
+ "T ATG",
1151
+ "TAA G",
1152
+ "AA AC",
1153
+ "T ATC",
1154
+ "AA GG",
1155
+ "AG AC",
1156
+ "TG TG",
1157
+ "AA TT",
1158
+ "AG TC",
1159
+ "AAAA G",
1160
+ "AA TC",
1161
+ "AC TT",
1162
+ "TAA C",
1163
+ "AG TT",
1164
+ "AG TG",
1165
+ "AAAA C",
1166
+ "T ACC",
1167
+ "AA ATT",
1168
+ "AA GC",
1169
+ "AA CC",
1170
+ "TT TG",
1171
+ "TG AC",
1172
+ "AC G",
1173
+ "AAAA AAAA",
1174
+ "ATC TC",
1175
+ "CC CC",
1176
+ "ATT TT",
1177
+ "TC TT",
1178
+ "ATG GC",
1179
+ "TGGG C",
1180
+ "AC AG",
1181
+ "AC TC",
1182
+ "ATG GG",
1183
+ "TT AG",
1184
+ "ACC CC",
1185
+ "GG GC",
1186
+ "ATT TC",
1187
+ "TTTT C",
1188
+ "AA TG",
1189
+ "AA TAA",
1190
+ "GG CC",
1191
+ "AT AG",
1192
+ "AGG TC",
1193
+ "TTTT TT",
1194
+ "G CCC",
1195
+ "AA ATG",
1196
+ "AA ACC",
1197
+ "TG AAG",
1198
+ "ATT CC",
1199
+ "ATT AC",
1200
+ "ACC AC",
1201
+ "TGG CC",
1202
+ "AG AGG",
1203
+ "TG TAA",
1204
+ "TC TG",
1205
+ "AC TCC",
1206
+ "TTTT G",
1207
+ "AAG TG",
1208
+ "AAC AC",
1209
+ "TGGG G",
1210
+ "AA GGC",
1211
+ "TT TAA",
1212
+ "TC AG",
1213
+ "ATT GC",
1214
+ "AT ATT",
1215
+ "AT AGG",
1216
+ "TGG AG",
1217
+ "T ATAA",
1218
+ "T ATAC",
1219
+ "AG ATG",
1220
+ "AC TG",
1221
+ "AC TGC",
1222
+ "AT AAC",
1223
+ "AT CCC",
1224
+ "ACC TC",
1225
+ "TCC CC",
1226
+ "AAG AA",
1227
+ "AAG TC",
1228
+ "ATC TT",
1229
+ "TTC TC",
1230
+ "TGCC TC",
1231
+ "T ACCC",
1232
+ "AA AGG",
1233
+ "AA AGC",
1234
+ "TT TGC",
1235
+ "AG AAAA",
1236
+ "AG TAA",
1237
+ "GG GG",
1238
+ "AT ATG",
1239
+ "ACC TCC",
1240
+ "AGG CC",
1241
+ "TTTT TTTT",
1242
+ "TAG CC",
1243
+ "G TG",
1244
+ "TT AC",
1245
+ "TT TAG",
1246
+ "AG AGC",
1247
+ "AG ATC",
1248
+ "AG GGC",
1249
+ "TG AAAA",
1250
+ "TC TTG",
1251
+ "AT ACC",
1252
+ "TTG AA",
1253
+ "TATT C",
1254
+ "AGGC TG",
1255
+ "TTCC CC",
1256
+ "ATTAC AGGC",
1257
+ "G AG",
1258
+ "T A",
1259
+ "AG AAG",
1260
+ "AG AAC",
1261
+ "TC TTC",
1262
+ "AC ATT",
1263
+ "ATT TG",
1264
+ "ATT GG",
1265
+ "AT AAAA",
1266
+ "ATG CC",
1267
+ "TCC AG",
1268
+ "TAA AC",
1269
+ "AGC AGC",
1270
+ "TTG CC",
1271
+ "TGGG ATTACAGGC",
1272
+ "TCTC G",
1273
+ "AA TTTT",
1274
+ "AA TAG",
1275
+ "TT TCC",
1276
+ "TT GGG",
1277
+ "AG TGG",
1278
+ "AG TTC",
1279
+ "AC ATG",
1280
+ "AC ATC",
1281
+ "AT AGAA",
1282
+ "AT ATAA",
1283
+ "AAAA AA",
1284
+ "ACC AGCC",
1285
+ "AGC TG",
1286
+ "AGC TC",
1287
+ "TGG AGG",
1288
+ "TATT TATT",
1289
+ "TGGC TC",
1290
+ "TCCC AGC",
1291
+ "G TC",
1292
+ "G TGG",
1293
+ "AA GGG",
1294
+ "AA ACAC",
1295
+ "TT AAG",
1296
+ "TT CCC",
1297
+ "AG TGTT",
1298
+ "TG AAC",
1299
+ "TG TTG",
1300
+ "TG TAG",
1301
+ "TG TAC",
1302
+ "TC ATT",
1303
+ "AC AGG",
1304
+ "AC TTC",
1305
+ "AC TTG",
1306
+ "ATT TTC",
1307
+ "AT AGC",
1308
+ "AT AAG",
1309
+ "AAAA AC",
1310
+ "ACC ATG",
1311
+ "AGG AGG",
1312
+ "TCC TC",
1313
+ "TCC TGCCTC",
1314
+ "TAA TTTT",
1315
+ "AAC ATT",
1316
+ "TGC AA",
1317
+ "TATT G",
1318
+ "TATT CC",
1319
+ "TCAC TGC",
1320
+ "TGAA GC",
1321
+ "AGGCTG AGGC",
1322
+ "T ATGG",
1323
+ "TT ATAA",
1324
+ "CC AGG",
1325
+ "TG TATT",
1326
+ "TC G",
1327
+ "TC TAA",
1328
+ "AT ATC",
1329
+ "GC GG",
1330
+ "ATG TT",
1331
+ "ATG AC",
1332
+ "AGG AA",
1333
+ "TAA TAC",
1334
+ "AGC TT",
1335
+ "AGC TCC",
1336
+ "AAG AC",
1337
+ "AAG ATC",
1338
+ "TTC TCC",
1339
+ "TTC TAA",
1340
+ "TAC AC",
1341
+ "TAC TAAAA",
1342
+ "TGGG GG",
1343
+ "AGAA AG",
1344
+ "AGAA GC",
1345
+ "AGGC TGG",
1346
+ "GCC GCC",
1347
+ "ATAC AAAA",
1348
+ "TTTC TAC",
1349
+ "AAAG TGC",
1350
+ "ATTG TC",
1351
+ "TCCTGCCTC AGCC",
1352
+ "C AA",
1353
+ "G AC",
1354
+ "T ATCC",
1355
+ "AA TGG",
1356
+ "AA TCTC",
1357
+ "AA ATTC",
1358
+ "AA TATC",
1359
+ "AG A",
1360
+ "AG ACC",
1361
+ "AG TCC",
1362
+ "AG TGC",
1363
+ "AG CCC",
1364
+ "AG TCTC",
1365
+ "AG TGCC",
1366
+ "AG ACAA",
1367
+ "TG ATT",
1368
+ "TG AGG",
1369
+ "TG TTTT",
1370
+ "TC AAAA",
1371
+ "TC TTTT",
1372
+ "AC AT",
1373
+ "AC TAC",
1374
+ "GG AC",
1375
+ "GG AGC",
1376
+ "ATT AA",
1377
+ "ATT ATT",
1378
+ "ATT ATG",
1379
+ "ATT TCC",
1380
+ "ATT TTGG",
1381
+ "ATG ACC",
1382
+ "ATG AAC",
1383
+ "ATG CCC",
1384
+ "AAAA CC",
1385
+ "ACC ACC",
1386
+ "AGG AGAA",
1387
+ "TCC TG",
1388
+ "TCC ATG",
1389
+ "TCC ACC",
1390
+ "TAA TC",
1391
+ "TAA GC",
1392
+ "AGC G",
1393
+ "AGC AC",
1394
+ "AGC AGG",
1395
+ "AAG CC",
1396
+ "AAC AA",
1397
+ "AAC TT",
1398
+ "AAC ATGG",
1399
+ "TGC G",
1400
+ "TGC TT",
1401
+ "TGG AA",
1402
+ "TGG TGG",
1403
+ "TTC AC",
1404
+ "TTG AG",
1405
+ "TTG TG",
1406
+ "TTG TAG",
1407
+ "TTG CCC",
1408
+ "TAG TAG",
1409
+ "TAG GGC",
1410
+ "CCC AC",
1411
+ "TATT GC",
1412
+ "AGCC AC",
1413
+ "AGCC AGG",
1414
+ "ATAA TT",
1415
+ "GGC TCACTGC",
1416
+ "GGG TGG",
1417
+ "ACCC TC",
1418
+ "TTTC TTTT",
1419
+ "TAT AAAA",
1420
+ "TTGG CC",
1421
+ "TAGC TGGG",
1422
+ "ACTT TGGG",
1423
+ "AAAAAAAA AAAAAAAA",
1424
+ "TGGGC AAC",
1425
+ "AGGTC AGG",
1426
+ "G TCC",
1427
+ "G TGTC",
1428
+ "AA AT",
1429
+ "AA ATAA",
1430
+ "AA TGGC",
1431
+ "AA ATAC",
1432
+ "AA TATG",
1433
+ "TT AA",
1434
+ "TT GGC",
1435
+ "TT TATC",
1436
+ "AG TCAC",
1437
+ "TG A",
1438
+ "TG AGC",
1439
+ "TG CCC",
1440
+ "TG ATAA",
1441
+ "TG ATGC",
1442
+ "TG ATTG",
1443
+ "TG TATG",
1444
+ "TG TTTTC",
1445
+ "TC TGG",
1446
+ "TC TTGC",
1447
+ "AC GC",
1448
+ "AC TGG",
1449
+ "GG CCC",
1450
+ "ATT TGC",
1451
+ "ATT TAG",
1452
+ "ATT TAC",
1453
+ "ATT TATT",
1454
+ "AT AT",
1455
+ "AT ACCC",
1456
+ "GC TGGAG",
1457
+ "ACC GC",
1458
+ "TCC AC",
1459
+ "TCC AAAA",
1460
+ "TAA ATC",
1461
+ "AGC AA",
1462
+ "AGC ATG",
1463
+ "AGC TTC",
1464
+ "TTTT GG",
1465
+ "TTTT AGC",
1466
+ "AAG AGG",
1467
+ "AAG TTC",
1468
+ "ATC AC",
1469
+ "ATC TAG",
1470
+ "AAC TAA",
1471
+ "TGC AAAA",
1472
+ "TGC TAC",
1473
+ "TGC TAAG",
1474
+ "TGG ATT",
1475
+ "TGG ACTT",
1476
+ "TTC TTC",
1477
+ "TTG TC",
1478
+ "TAG AAAA",
1479
+ "TAG AGAC",
1480
+ "TAC TG",
1481
+ "CCC AGG",
1482
+ "CCC AGCC",
1483
+ "TATT TT",
1484
+ "TCAC TC",
1485
+ "TCAC TTC",
1486
+ "TCCC TC",
1487
+ "AGAG TGAG",
1488
+ "TTTC TTC",
1489
+ "ATTC TGG",
1490
+ "TGAG ACCAGCC",
1491
+ "ATCC CC",
1492
+ "TTGC AGTG",
1493
+ "TAGG TC",
1494
+ "AGGG CC",
1495
+ "AAGG CC",
1496
+ "AATT AC",
1497
+ "ATGGG CC",
1498
+ "ACTCC AGCC",
1499
+ "AAGTG ATCC",
1500
+ "AGGCC G",
1501
+ "TTTTTTTT TTTT",
1502
+ "AGGCTGAGGC AGGAGAA",
1503
+ "TACTAAAA ATACAAAA",
1504
+ "AAAGTGC TGGGATTACAGGC",
1505
+ "G AAC",
1506
+ "G TCTC",
1507
+ "AA ATC",
1508
+ "AA TGC",
1509
+ "AA TTC",
1510
+ "AA TAC",
1511
+ "AA TATT",
1512
+ "AA TGAG",
1513
+ "AA TGTC",
1514
+ "AA ATAGG",
1515
+ "TT ATG",
1516
+ "TT AAC",
1517
+ "TT TATT",
1518
+ "TT ATAC",
1519
+ "TT ACCC",
1520
+ "TT ATTC",
1521
+ "TT TAAAA",
1522
+ "CC G",
1523
+ "CC AC",
1524
+ "CC ATC",
1525
+ "AG ATT",
1526
+ "AG TAG",
1527
+ "AG AGAA",
1528
+ "AG ATAA",
1529
+ "AG GGG",
1530
+ "AG TGGC",
1531
+ "AG ATAC",
1532
+ "AG TAAAA",
1533
+ "TG ATG",
1534
+ "TG TCC",
1535
+ "TG TGC",
1536
+ "TG TTC",
1537
+ "TG TCTC",
1538
+ "TG TGGC",
1539
+ "TG TCCC",
1540
+ "TG ATTC",
1541
+ "TC GC",
1542
+ "TC ATG",
1543
+ "TC TAG",
1544
+ "TC TAC",
1545
+ "AC GG",
1546
+ "AC TGGG",
1547
+ "AC ATAC",
1548
+ "AC TGCC",
1549
+ "AC ATGG",
1550
+ "AC TAAAA",
1551
+ "GG GGC",
1552
+ "GG CCCC",
1553
+ "ATT TTG",
1554
+ "ATT CCC",
1555
+ "ATT GGG",
1556
+ "ATT ACAA",
1557
+ "ATT TTGC",
1558
+ "ATT TAGG",
1559
+ "ATT TATC",
1560
+ "ATT AGTC",
1561
+ "AT AGGC",
1562
+ "AT ATCC",
1563
+ "AT ACCCC",
1564
+ "GC G",
1565
+ "GC TGC",
1566
+ "ATG TC",
1567
+ "ATG ATC",
1568
+ "ATG GCC",
1569
+ "ATG AAAG",
1570
+ "ATG TAAG",
1571
+ "AAAA TT",
1572
+ "AAAA GG",
1573
+ "AAAA GC",
1574
+ "AAAA AAG",
1575
+ "AAAA ATC",
1576
+ "AAAA AAC",
1577
+ "AAAA TATT",
1578
+ "ACC AAG",
1579
+ "ACC TAG",
1580
+ "ACC TATT",
1581
+ "AGG AG",
1582
+ "AGG AAAA",
1583
+ "AGG TAA",
1584
+ "AGG TGC",
1585
+ "AGG TAC",
1586
+ "AGG AGAG",
1587
+ "TCC TAG",
1588
+ "TCC TCCC",
1589
+ "TCC ACCTCC",
1590
+ "TAA TT",
1591
+ "TAA CC",
1592
+ "TAA TAA",
1593
+ "TAA ATAA",
1594
+ "TAA GCC",
1595
+ "TAA TAT",
1596
+ "AGC ACC",
1597
+ "AGC TAC",
1598
+ "AGC GCC",
1599
+ "AGC TTCC",
1600
+ "AGC TAATTTT",
1601
+ "TTTT AAAA",
1602
+ "TTTT TAAAA",
1603
+ "AAG TAC",
1604
+ "ATC G",
1605
+ "ATC AAC",
1606
+ "ATC TTC",
1607
+ "ATC TAAAA",
1608
+ "AAC AG",
1609
+ "AAC TC",
1610
+ "AAC AGC",
1611
+ "AAC ATTC",
1612
+ "AAC TAAAA",
1613
+ "TGC TG",
1614
+ "TGC TC",
1615
+ "TGC TGCC",
1616
+ "TGC AGTG",
1617
+ "TGC AGTGG",
1618
+ "TGG TT",
1619
+ "TGG AAC",
1620
+ "TGG TTTC",
1621
+ "TGG AATT",
1622
+ "TTG TT",
1623
+ "TTG TATT",
1624
+ "TAG TTTT",
1625
+ "TAC AGC",
1626
+ "TAC TTC",
1627
+ "TGGG CC",
1628
+ "TGGG TGG",
1629
+ "TGGG GCC",
1630
+ "AGCC CC",
1631
+ "AGCC TCCC",
1632
+ "AGCC GGGC",
1633
+ "AGCC AAGATC",
1634
+ "AGAA TT",
1635
+ "AGAA AC",
1636
+ "AGAA GG",
1637
+ "AGAA GGC",
1638
+ "GGC G",
1639
+ "TCTC TC",
1640
+ "GCC TCC",
1641
+ "TGGC TAAC",
1642
+ "TCAC ACC",
1643
+ "TCAC TTG",
1644
+ "AGAG AT",
1645
+ "AGAG AGAG",
1646
+ "TGCC AC",
1647
+ "ACCC ACC",
1648
+ "ACCC GCC",
1649
+ "TTTC ACCATG",
1650
+ "TGAA ACCCC",
1651
+ "ATTC TCCTGCCTCAGCC",
1652
+ "TGAG ATG",
1653
+ "ACAC ATG",
1654
+ "ACAC AAAA",
1655
+ "TAAAA C",
1656
+ "TTGG GC",
1657
+ "TGTC TAA",
1658
+ "TTGC TCC",
1659
+ "ATTG ATCC",
1660
+ "TAGC TGGGATTACAGGC",
1661
+ "AAAC GG",
1662
+ "AAAC ACC",
1663
+ "AGTC TATT",
1664
+ "ACTT CCC",
1665
+ "TAAC TGC",
1666
+ "TACC ATG",
1667
+ "AAATT TC",
1668
+ "ATCTC ATG",
1669
+ "TCTT AGC",
1670
+ "TGGGC GC",
1671
+ "AGAGG AAAA",
1672
+ "AGATG GGG",
1673
+ "TTTAG TAGAGAC",
1674
+ "TCTCG AAC",
1675
+ "TCCCAGC ACTTTGGG",
1676
+ "TTCAC GCC",
1677
+ "GGCTCACTGC AACC",
1678
+ "TAGCTGGG ACTAC",
1679
+ "ACTCCAGCC TGGGCAAC",
1680
+ "C AG",
1681
+ "G TT",
1682
+ "G ATG",
1683
+ "G TAA",
1684
+ "G AGC",
1685
+ "G TTG",
1686
+ "G TAC",
1687
+ "G TGAA",
1688
+ "G TAGG",
1689
+ "G TACC",
1690
+ "G ACTCC",
1691
+ "G ATCCC",
1692
+ "G TGCCTC",
1693
+ "T ATGC",
1694
+ "AA TTG",
1695
+ "AA AGCC",
1696
+ "AA AGAA",
1697
+ "AA AGAG",
1698
+ "AA TTTC",
1699
+ "AA ATCC",
1700
+ "AA TAAAA",
1701
+ "AA ATGGC",
1702
+ "AA AGGTC",
1703
+ "AA TATAA",
1704
+ "TT ATT",
1705
+ "TT TAC",
1706
+ "TT TGGG",
1707
+ "TT TGAA",
1708
+ "TT TGTC",
1709
+ "TT ATTG",
1710
+ "TT TGTT",
1711
+ "TT TAGC",
1712
+ "TT AAAC",
1713
+ "TT AGTT",
1714
+ "TT TACC",
1715
+ "TT AACC",
1716
+ "TT ACG",
1717
+ "TT ATTGC",
1718
+ "TT TATTC",
1719
+ "CC AAAG",
1720
+ "AG T",
1721
+ "AG TTCC",
1722
+ "AG ATTC",
1723
+ "AG ACAC",
1724
+ "AG TTGG",
1725
+ "AG TGTC",
1726
+ "AG TTGC",
1727
+ "AG AAAAC",
1728
+ "AG ATTTT",
1729
+ "AG ATGGG",
1730
+ "AG ATTTC",
1731
+ "AG AACAC",
1732
+ "AG TATTGC",
1733
+ "TG AT",
1734
+ "TG TGGG",
1735
+ "TG AGCC",
1736
+ "TG AGGC",
1737
+ "TG TGCC",
1738
+ "TG ATCC",
1739
+ "TG ACAC",
1740
+ "TG TAT",
1741
+ "TG ACAA",
1742
+ "TG ATAGG",
1743
+ "TG TATAC",
1744
+ "TG AGGTCAGG",
1745
+ "TC ACC",
1746
+ "TC AGG",
1747
+ "TC AAG",
1748
+ "TC ATGG",
1749
+ "TC ATCC",
1750
+ "TC AAAC",
1751
+ "TC AATT",
1752
+ "TC AATC",
1753
+ "TC TGAC",
1754
+ "TC AAGTGATCC",
1755
+ "AC T",
1756
+ "AC TTTT",
1757
+ "AC TATT",
1758
+ "AC TCAC",
1759
+ "AC TGAG",
1760
+ "AC ATGC",
1761
+ "AC ATGGG",
1762
+ "AC TTTTTT",
1763
+ "AC AACAC",
1764
+ "AC TACCC",
1765
+ "AC TAATAC",
1766
+ "GG AG",
1767
+ "GG AGG",
1768
+ "GG ATC",
1769
+ "GG TGGC",
1770
+ "GG TTGG",
1771
+ "GG AAAC",
1772
+ "GG ACTC",
1773
+ "GG AAAAAAG",
1774
+ "ATT A",
1775
+ "ATT AG",
1776
+ "ATT TAA",
1777
+ "ATT TGGG",
1778
+ "ATT TCAC",
1779
+ "ATT ACCC",
1780
+ "ATT TTTC",
1781
+ "ATT TGAG",
1782
+ "ATT ACAG",
1783
+ "ATT TATAC",
1784
+ "ATT AAAGG",
1785
+ "ATT TATTTATT",
1786
+ "AT A",
1787
+ "AT AGAG",
1788
+ "AT ATGC",
1789
+ "AT AAAAC",
1790
+ "AT ATAG",
1791
+ "GC GGC",
1792
+ "GC TGGC",
1793
+ "GC AAGG",
1794
+ "GC ACCAC",
1795
+ "ATG TAA",
1796
+ "ATG TGG",
1797
+ "ATG TTG",
1798
+ "ATG TAC",
1799
+ "ATG AGCC",
1800
+ "ATG TGCC",
1801
+ "ATG ATCC",
1802
+ "ATG AAAC",
1803
+ "ATG TCTT",
1804
+ "ATG AATG",
1805
+ "ATG TGAAAA",
1806
+ "AAAA ATG",
1807
+ "AAAA TTC",
1808
+ "AAAA CCC",
1809
+ "ACC AT",
1810
+ "ACC TTC",
1811
+ "ACC ATCC",
1812
+ "ACC ACAC",
1813
+ "ACC ACAA",
1814
+ "ACC TGTT",
1815
+ "ACC TGTG",
1816
+ "ACC TTCTC",
1817
+ "ACC TGAGGTCAGG",
1818
+ "AGG T",
1819
+ "AGG AAG",
1820
+ "AGG AAC",
1821
+ "AGG TGG",
1822
+ "AGG CCC",
1823
+ "AGG TAGG",
1824
+ "AGG AAAAG",
1825
+ "AGG TGAC",
1826
+ "AGG AAACC",
1827
+ "TCC G",
1828
+ "TCC ATC",
1829
+ "TCC AAC",
1830
+ "TCC AGGC",
1831
+ "TCC TTTAA",
1832
+ "TCC GCCTCC",
1833
+ "TAA GG",
1834
+ "TAA ATG",
1835
+ "TAA CCC",
1836
+ "TAA TGAAG",
1837
+ "AGC A",
1838
+ "AGC T",
1839
+ "AGC AT",
1840
+ "AGC ATC",
1841
+ "AGC AGGC",
1842
+ "AGC AAAG",
1843
+ "AGC TAGC",
1844
+ "AGC TATG",
1845
+ "AGC AAGG",
1846
+ "AGC AATAG",
1847
+ "AGC TCACTGC",
1848
+ "TTTT CC",
1849
+ "TTTT AT",
1850
+ "TTTT AATAA",
1851
+ "TTTT TTTTTT",
1852
+ "AAG TAA",
1853
+ "AAG CCC",
1854
+ "AAG TATT",
1855
+ "AAG AGAA",
1856
+ "AAG ATAC",
1857
+ "AAG TTCC",
1858
+ "AAG TTTC",
1859
+ "AAG AGGG",
1860
+ "AAG AGTC",
1861
+ "AAG ACTT",
1862
+ "AAG ACTC",
1863
+ "AAG ACTCC",
1864
+ "ATC AGCC",
1865
+ "ATC TCAC",
1866
+ "ATC ACAC",
1867
+ "ATC TAGG",
1868
+ "ATC AGGG",
1869
+ "ATC ACTT",
1870
+ "ATC ACG",
1871
+ "AAC TAG",
1872
+ "AAC TGCC",
1873
+ "AAC ACTT",
1874
+ "TGC GC",
1875
+ "TGC TGC",
1876
+ "TGC ATAC",
1877
+ "TGC ATCC",
1878
+ "TGG AT",
1879
+ "TGG TAA",
1880
+ "TGG ATCC",
1881
+ "TGG AGAC",
1882
+ "TGG TGTG",
1883
+ "TGG TTTTC",
1884
+ "TTC TG",
1885
+ "TTC ACC",
1886
+ "TTC ATC",
1887
+ "TTG A",
1888
+ "TTG AAC",
1889
+ "TTG AGCC",
1890
+ "TTG TCTC",
1891
+ "TTG ATGC",
1892
+ "TTG TTGC",
1893
+ "TTG AATT",
1894
+ "TTG AATAA",
1895
+ "TAG TC",
1896
+ "TAG CCC",
1897
+ "TAG GCTGGAG",
1898
+ "TAC GG",
1899
+ "TAC TACC",
1900
+ "TAC ACTG",
1901
+ "TAC TTGGG",
1902
+ "TAC TGGGGCC",
1903
+ "CCC G",
1904
+ "CCC AAG",
1905
+ "CCC TTTC",
1906
+ "CCC GGCC",
1907
+ "CCC ACCTC",
1908
+ "CCC AAAGAA",
1909
+ "TGGG TGC",
1910
+ "TGGG TTC",
1911
+ "TGGG AGGC",
1912
+ "TGGG TCCCC",
1913
+ "TGGG TTCACGCC",
1914
+ "TATT AC",
1915
+ "TATT TTCC",
1916
+ "TATT TTGC",
1917
+ "AGCC ATC",
1918
+ "AGCC TCCAG",
1919
+ "AGAA AT",
1920
+ "AGAA TGC",
1921
+ "AGAA TTC",
1922
+ "AGAA AGAG",
1923
+ "AGAA GGCC",
1924
+ "AGGC TAT",
1925
+ "AGGC AGAGG",
1926
+ "AGGC TGGAG",
1927
+ "AGGC AGATC",
1928
+ "AGGC AGAAG",
1929
+ "ATAA ATAA",
1930
+ "ATAA TTAG",
1931
+ "ATAA TCAG",
1932
+ "GGC T",
1933
+ "GGC GAG",
1934
+ "GCC TTGG",
1935
+ "GCC ACTGC",
1936
+ "GGG ATG",
1937
+ "GGG TGC",
1938
+ "GGG ACCC",
1939
+ "GGG ACAG",
1940
+ "GGG AATG",
1941
+ "GGG AGGCTGAGGC",
1942
+ "TGGC TAC",
1943
+ "TGGC TGAA",
1944
+ "TGGC TGGGG",
1945
+ "TGGC TTGAA",
1946
+ "TGGC TAATTTT",
1947
+ "TGGC GTGAA",
1948
+ "TCAC AATC",
1949
+ "ATAC AGGC",
1950
+ "TCCC GCC",
1951
+ "TCCC TGAA",
1952
+ "TCCC AAAGTGCTGGGATTACAGGC",
1953
+ "TTCC ATTC",
1954
+ "AGAG T",
1955
+ "AGAG GG",
1956
+ "AGAG AGAC",
1957
+ "TGCC AGG",
1958
+ "TGCC TTG",
1959
+ "ACCC AGC",
1960
+ "ACCC ATAC",
1961
+ "TTTC TAG",
1962
+ "TGAA T",
1963
+ "TGAA AC",
1964
+ "TGAA GGC",
1965
+ "TGAA ACCC",
1966
+ "TGAA ATTTAG",
1967
+ "ATTC TAA",
1968
+ "ATGG TCC",
1969
+ "ATGG AAG",
1970
+ "ATGG TAG",
1971
+ "ATGG AGTCTC",
1972
+ "TGAG TATT",
1973
+ "TGAG ATGG",
1974
+ "TGAG ACAA",
1975
+ "ATGC AAG",
1976
+ "ATGC AATAA",
1977
+ "TAT AGG",
1978
+ "TAT ATGC",
1979
+ "AAAG AGGC",
1980
+ "AAAG TAT",
1981
+ "TTGG TC",
1982
+ "TGTC TTCC",
1983
+ "TGTC GCCC",
1984
+ "ACAA AC",
1985
+ "ACAA TATTTT",
1986
+ "TTGC AG",
1987
+ "TTGC TGC",
1988
+ "ATTG TATT",
1989
+ "ATTG AGAG",
1990
+ "ATTG TTTTC",
1991
+ "TGTT TGGG",
1992
+ "TGTT TATT",
1993
+ "TGTT GGG",
1994
+ "AGGG GCC",
1995
+ "AGGG TTTCACCATG",
1996
+ "TATG AGC",
1997
+ "AAGG AAAA",
1998
+ "AAGG AGAGC",
1999
+ "AATT AGCC",
2000
+ "AGTC TAG",
2001
+ "AAAAG AAATT",
2002
+ "AATC ATGC",
2003
+ "AATC TGAC",
2004
+ "TAAC TC",
2005
+ "AGTT TCC",
2006
+ "AGTT TAGG",
2007
+ "AGTT TGAGACCAGCC",
2008
+ "AGTG AAAA",
2009
+ "AGTG TAG",
2010
+ "AAAAC ACC",
2011
+ "AAAAC AGAC",
2012
+ "TACC TC",
2013
+ "AAGC G",
2014
+ "AAGC AA",
2015
+ "AAGC ATGC",
2016
+ "AAGC ACTG",
2017
+ "AACC CC",
2018
+ "TTTG AGG",
2019
+ "TTTG CCC",
2020
+ "ACG A",
2021
+ "AAAAAAAA AAAA",
2022
+ "ATCTC ATC",
2023
+ "ATCTC TGC",
2024
+ "CCCC G",
2025
+ "CCCC CC",
2026
+ "ATTTT CCC",
2027
+ "ATTTT ATTG",
2028
+ "TCTT TAAG",
2029
+ "ATGGC AGCAGGC",
2030
+ "TGGGC ATGG",
2031
+ "ATGGG TAG",
2032
+ "TTAG TGC",
2033
+ "ACCCC TGGC",
2034
+ "GGGC GG",
2035
+ "ATTTC TTG",
2036
+ "TTTTTT TGAG",
2037
+ "GCCC GCCGCC",
2038
+ "AAATG AAC",
2039
+ "TGAAG TTGG",
2040
+ "ATTCC ATG",
2041
+ "ACCAC TAC",
2042
+ "ACCAC AGAA",
2043
+ "TGGCC AACATGG",
2044
+ "TGTAA TCTC",
2045
+ "TCTG TCTC",
2046
+ "TTTTG TT",
2047
+ "AACAC TGAC",
2048
+ "TGGGG AGTC",
2049
+ "TTTAA GC",
2050
+ "ATAGG AGTTGG",
2051
+ "TATAA AGAA",
2052
+ "AGATG CC",
2053
+ "ACTG CCC",
2054
+ "ATAAC TTC",
2055
+ "TCCCC GC",
2056
+ "AAGTC ATGTCTT",
2057
+ "AGGGC GC",
2058
+ "TCTTG AAC",
2059
+ "TTGAA AGCC",
2060
+ "GAG TAGCTGGGATTACAGGC",
2061
+ "AATTTT AC",
2062
+ "TTTCC CCC",
2063
+ "ACATG AAATG",
2064
+ "ACATC ATC",
2065
+ "TCCCAGC TACTTGGG",
2066
+ "TTAAG AG",
2067
+ "AGTGTT GGG",
2068
+ "ACTTC AAG",
2069
+ "ATTTTC TGG",
2070
+ "AGGAA TGTG",
2071
+ "TACAC TGAA",
2072
+ "AGGCTGG TCTCGAAC",
2073
+ "AGGCTGG TCTTGAAC"
2074
+ ]
2075
+ }
2076
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 512,
5
+ "pad_token": "[PAD]",
6
+ "padding_side": "right",
7
+ "sep_token": "[SEP]",
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "truncation_side": "right",
10
+ "unk_token": "[UNK]"
11
+ }