tokenizer/merges.txt DELETED
@@ -1,1006 +0,0 @@
1
- #version: 0.2
2
- G G
3
- A A
4
- U U
5
- C C
6
- A G
7
- U G
8
- A C
9
- U C
10
- U GG
11
- G C
12
- A GG
13
- U AA
14
- AG C
15
- A UU
16
- A CC
17
- A UG
18
- U CC
19
- G AA
20
- U AC
21
- UG C
22
- A UC
23
- U AG
24
- UU C
25
- AA C
26
- GG C
27
- UU G
28
- AA G
29
- GG G
30
- CC C
31
- A U
32
- UG AA
33
- AC G
34
- A UGG
35
- UAA C
36
- GC G
37
- UC G
38
- AGG C
39
- UG AG
40
- UGG C
41
- AUG C
42
- AG CC
43
- UG CC
44
- A UCC
45
- GG AA
46
- A UAA
47
- U ACC
48
- UU UU
49
- AC GG
50
- AGG G
51
- U AUU
52
- AG AA
53
- UU GG
54
- G CC
55
- U AGC
56
- UC AA
57
- UU AA
58
- GAA C
59
- AC AA
60
- U AGG
61
- UGG G
62
- ACC C
63
- UGG GG
64
- UG AC
65
- A UAC
66
- GC GG
67
- AGG AA
68
- UU CC
69
- AGC G
70
- UCC C
71
- GC AA
72
- AG AC
73
- GG CC
74
- AUU C
75
- UU UC
76
- UU GC
77
- AA AA
78
- AG AG
79
- CC G
80
- UAC G
81
- AC AC
82
- A UAG
83
- GG GG
84
- UG UC
85
- UAA G
86
- U AUC
87
- UU UG
88
- AG UC
89
- AUU G
90
- GGC G
91
- AA AC
92
- AAG UC
93
- AUG AA
94
- UG UG
95
- UC UC
96
- UGG AA
97
- ACC G
98
- AG UG
99
- UGG GC
100
- UU AC
101
- UC GC
102
- UUC GG
103
- UGC G
104
- U AUG
105
- UUC G
106
- UU UAA
107
- UC GG
108
- UU AG
109
- UC UG
110
- UCC G
111
- AAC G
112
- GAA G
113
- AG UGG
114
- UC AC
115
- A UAAC
116
- UG AGG
117
- AUGG C
118
- AG AGG
119
- AG AU
120
- AUG CC
121
- ACC AA
122
- U AGGC
123
- GG GC
124
- AUU AA
125
- GG UGAA
126
- UAC GGG
127
- AUC G
128
- AAG CC
129
- UU GAA
130
- U AU
131
- UAC AC
132
- GC GAA
133
- CC UU
134
- CCC G
135
- AUGC G
136
- AC UC
137
- UG UU
138
- GGC UAAC
139
- AA GG
140
- UC AG
141
- AC GC
142
- UG UAGC
143
- UGAC GC
144
- UGAG AC
145
- UU CCC
146
- GCG UAA
147
- AGC AGCC
148
- AUGG G
149
- AGGC AGC
150
- AG UGGC
151
- AGG GC
152
- UAC AA
153
- UC AGC
154
- AUU GG
155
- GAA GGC
156
- GCGG UAA
157
- AC GAA
158
- UU AAG
159
- UGCC AGCAGCC
160
- CC CC
161
- UG UCG
162
- UU GGG
163
- UGC AA
164
- AGC AA
165
- AUCC C
166
- UACGGG AGGCAGC
167
- AC GGG
168
- UU AAC
169
- UUC GGG
170
- AC UG
171
- UUG CC
172
- ACC GG
173
- UAG AG
174
- UUG UAA
175
- UAG UCC
176
- AGG AUU
177
- UAA GG
178
- UGCCAGCAGCC GCGGUAA
179
- UCC UACGGGAGGCAGC
180
- AGG GG
181
- GC ACAA
182
- AU AUU
183
- AU AUC
184
- AG UU
185
- UAA UACC
186
- UAA AA
187
- UAC GG
188
- AGG AAC
189
- UG CCC
190
- UUG AC
191
- GAA GC
192
- UGG CC
193
- UC UU
194
- U AGGG
195
- AG CCC
196
- UGAGAC ACGG
197
- AUU AGC
198
- AUAA G
199
- GC UGGC
200
- AGG CC
201
- AC UU
202
- AGCG UGGGG
203
- AGC AAAC
204
- ACC CC
205
- AGGAA GG
206
- UAA CC
207
- UUG ACGG
208
- AGGAUU AGAU
209
- AC AG
210
- AGAC UCCUACGGGAGGCAGC
211
- UGG UC
212
- GGC GG
213
- GC GC
214
- UACC C
215
- UGG AGC
216
- AUG UGG
217
- AGUGG GGAA
218
- UGUAGC GGUGAA
219
- GGG CC
220
- UAG UAA
221
- UCC GG
222
- N N
223
- Ġ G
224
- UG AAG
225
- UAG CC
226
- AC AUGC
227
- UC AAC
228
- AG UAC
229
- AGG AUG
230
- AGGAUUAGAU ACCC
231
- AG UGC
232
- U AUGG
233
- ACG CC
234
- UAG UUGG
235
- UG UAA
236
- AA CC
237
- AC UGC
238
- UAUU GG
239
- UGG GCGUAA
240
- UU UUC
241
- UGAG UAAC
242
- UGC UGC
243
- UAG AA
244
- AUU CC
245
- UAA GC
246
- U AUAA
247
- ACG UC
248
- AA GC
249
- AG AAG
250
- AGC GCAA
251
- UG ACGG
252
- AGC GC
253
- UU UUG
254
- UGC AAC
255
- GG UG
256
- UCAGC UCG
257
- UGG UAGUCC
258
- UU UCC
259
- AGC GG
260
- AG AAC
261
- UG AAC
262
- UGG AAC
263
- UUC AA
264
- AG AUU
265
- AC UCC
266
- AG AUG
267
- UU AUU
268
- UGG GAA
269
- AG AGC
270
- AUC AA
271
- GGCUAAC UACG
272
- AGC AAC
273
- AGCGUGGGG AGCAAAC
274
- AGGAUUAGAUACCC UGGUAGUCC
275
- AC AUU
276
- UAA ACG
277
- UG AGGC
278
- UG UGAA
279
- GAA GG
280
- AUGCG UAG
281
- UU GGC
282
- UAGG GG
283
- AG UGAA
284
- AGG GAA
285
- UG AUC
286
- UGGG AC
287
- UUAAG UCCC
288
- ACCG CCCG
289
- GAAC GCUGGC
290
- AAGUC GAAC
291
- AGC GAA
292
- AGC UC
293
- UCAA AGGAA
294
- UCAA CC
295
- GCC UGGGG
296
- CCC UU
297
- UCC CC
298
- UGCC G
299
- UG AUCC
300
- UGAG AUG
301
- UU ACC
302
- AGACUCCUACGGGAGGCAGC AGUGGGGAA
303
- UCG CC
304
- GGG AC
305
- AGGC G
306
- AGGAAGG UGGGG
307
- GGG CCC
308
- UAUU C
309
- UACG UUCCC
310
- UCAAAGGAA UUGACGG
311
- AU ACC
312
- UGAGACACGG CCC
313
- AU AGC
314
- UC AUU
315
- UACAC ACCGCCCG
316
- UC GAA
317
- AU AGG
318
- AUC GG
319
- UU UGG
320
- UG AUGC
321
- UGC GAA
322
- UAG AGG
323
- GCACAA GCGG
324
- AAG UCG
325
- UGGC G
326
- UC GGAA
327
- GGCG ACG
328
- UG AUG
329
- UAGC G
330
- AUAC G
331
- AACG AGCGCAA
332
- UCAGCUCG UGUCG
333
- CCUU ACC
334
- UUGGG UUAAGUCCC
335
- ACG UGC
336
- AC UGG
337
- AG UAA
338
- GCAA GG
339
- UG UGG
340
- UCAGCUCGUGUCG UGAGAUG
341
- U AUCC
342
- AG UUC
343
- AG ACC
344
- ACC AGUGGC
345
- AU AUG
346
- UC AGG
347
- UC UUC
348
- GC AACGAGCGCAA
349
- UUAC UGGGCGUAA
350
- UG AUU
351
- UU AUCC
352
- UG ACC
353
- UC AUC
354
- U AUGC
355
- UAG UC
356
- GCC G
357
- AUC AGC
358
- AUUC G
359
- UAAUACC GC
360
- UGG GGG
361
- AAC GCGAA
362
- AC AGG
363
- UGC GG
364
- GGCUAAC UCCG
365
- AUGUGG UUUAA
366
- AGGAAGGUGGGG AUG
367
- GCC GCG
368
- UCGC UAGUAA
369
- UGAA AC
370
- AC GGC
371
- UUG UACACACCGCCCG
372
- UGGAA UUCC
373
- UCAGCUCGUGUCGUGAGAUG UUGGGUUAAGUCCC
374
- GAA AGCC
375
- AUU GC
376
- UGGUC UGAG
377
- UC GGC
378
- UCC AA
379
- AUUAGC UAGUUGG
380
- UAGGC GG
381
- AG UUG
382
- GAAC GGG
383
- UC ACC
384
- UAA AAC
385
- UC UGG
386
- UAUU G
387
- UUCGGG UUGUAA
388
- AC UUC
389
- ACGUGC UACAA
390
- GAA AA
391
- Ġ C
392
- UC UGC
393
- UU UGC
394
- UACC G
395
- UGCAAC UCG
396
- AUGGC UGUCG
397
- UUG UUGG
398
- UG UGC
399
- AACGCGAA GAA
400
- UG UUC
401
- AG AGGG
402
- AUCC G
403
- GCG UUG
404
- AAC AA
405
- UU GGAA
406
- AU AU
407
- UC UCC
408
- AG AUC
409
- ACG CCG
410
- UUAA CC
411
- AGGC GG
412
- ACAUGC AAGUCGAAC
413
- UGG UGC
414
- UAA UAC
415
- UACC AA
416
- GG CCC
417
- AGC AC
418
- UGAA CC
419
- ACAC UGGGAC
420
- AUC AGG
421
- UGAGUAAC ACG
422
- GCG UG
423
- U AUAC
424
- UUG UC
425
- GAA UC
426
- UU AGC
427
- UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCC GCAACGAGCGCAA
428
- AGCAAC GCCGCG
429
- AG UAGG
430
- UAAC G
431
- GCACAAGCGG UGGAGC
432
- UU UAG
433
- AGG GGG
434
- UACAC ACGUGCUACAA
435
- GGC GC
436
- UGAG AGGG
437
- UGC GC
438
- AGCC G
439
- UGAA UACGUUCCC
440
- UU UAC
441
- NN NN
442
- GGCUAACUCCG UGCCAGCAGCCGCGGUAA
443
- AUGG AA
444
- UGGGC GC
445
- UGGGC GAAAGCC
446
- U AUAG
447
- GAA GGCC
448
- GGC AGC
449
- AUC GC
450
- UG UUG
451
- ACCC G
452
- GGCUAACUACG UGCCAGCAGCCGCGGUAA
453
- AG UCC
454
- AUC AGCC
455
- UG UCC
456
- UCAAAGGAAUUGACGG GGGCCC
457
- UGACGC UGAGGC
458
- UG AGC
459
- UUCC G
460
- AAG AC
461
- GAAC G
462
- AACGCGAAGAA CCUUACC
463
- UGGC GAAGGC
464
- AAC GC
465
- GG AUU
466
- ACACUGGGAC UGAGACACGGCCC
467
- AGCC AUGCC
468
- AUG AC
469
- GCACAAGCGGUGGAGC AUGUGGUUUAA
470
- GCG CC
471
- UG AUGG
472
- UGCUGC AUGGCUGUCG
473
- AGG UC
474
- AUG UC
475
- GCC CC
476
- UG ACG
477
- GGGCC UUGUACACACCGCCCG
478
- ACC UC
479
- GG GGC
480
- UCAC ACC
481
- AUUGG GCGUAA
482
- UAAC AAGG
483
- UUAA AA
484
- ACC GC
485
- UGUAGCGGUGAA AUGCGUAG
486
- UUGG GC
487
- UAAC GGC
488
- ACGCCG UAAACG
489
- GAA AC
490
- AGC UAAC
491
- AUAA AA
492
- AGCGUGGGGAGCAAAC AGGAUUAGAUACCCUGGUAGUCC
493
- AGC GAAC
494
- UCC UC
495
- AGAA AA
496
- UGAA GG
497
- UAUU GCACAA
498
- UGGGCGC AAGCC
499
- UUUU GG
500
- UGGUCUGAG AGGAUG
501
- AUC AG
502
- ACCAA GGCGACG
503
- GAACGCUGGC GGC
504
- GGCUAACUACGUGCCAGCAGCCGCGGUAA UACG
505
- UGAGACACGG UCC
506
- AGAA GC
507
- UCCC G
508
- UUC GGAA
509
- ACGG CC
510
- U AUGAA
511
- UGACGC UGAGG
512
- AUC AUU
513
- ACCAGUGGC GAAGGC
514
- ACCAA GGC
515
- U A
516
- UU UGAC
517
- AC AAC
518
- AUG UGAA
519
- UGUAGCGGUGAA AUGC
520
- UG UAG
521
- UGG GAAC
522
- AUC AUC
523
- GGCC G
524
- UAA UC
525
- GGCUAACUCCGUGCCAGCAGCCGCGGUAA UACGG
526
- UAA AGC
527
- UGGC UC
528
- AGAC UGCC
529
- UG UAC
530
- UUG AG
531
- GG UC
532
- ACAC UGGAAC
533
- UAAUACC GG
534
- UCC GGAA
535
- UUAA UCGGAA
536
- GCCUGGGG AGUAC
537
- AUAA CC
538
- AG UCG
539
- AUGG GC
540
- GGG UC
541
- AG UUCGG
542
- AGGAAGGUGGGGAUG ACGUC
543
- UGAG AA
544
- AUCC CC
545
- GCGG UGAAUACGUUCCC
546
- UGG AGG
547
- AGAG UUUG
548
- UGCAA GCG
549
- UU UAUU
550
- UGG AC
551
- UGAG UAA
552
- GAAGC ACC
553
- AGCCAUGCC GCG
554
- GGC AA
555
- UUG UCG
556
- UAUUGG ACAA
557
- UUGG GG
558
- AUC UC
559
- GAA AGC
560
- UGAA AA
561
- AC AGC
562
- UG AUGAA
563
- GCCUGGGGAGUAC GGCC
564
- GAA CC
565
- UGG GCC
566
- AG AGAA
567
- AUGG GG
568
- AGG CCC
569
- AUAAC G
570
- AUGCG UAGAG
571
- GAA GGCG
572
- UC GGG
573
- UGGC AA
574
- AGCC CC
575
- UC GCGG
576
- GG ACGGG
577
- UCG UAACAAGG
578
- AGC UUGC
579
- UUUU AA
580
- AGCG ACGCC
581
- UUAAUCGGAA UUACUGGGCGUAA
582
- GGAA GG
583
- AC AUC
584
- UGAGUAAC GCG
585
- UU AUG
586
- GCCUGGGG AG
587
- UAG CCG
588
- UGGGG UAA
589
- UUCG AUGC
590
- CCC UUG
591
- CCC GG
592
- UU UGAA
593
- GCAA GGC
594
- AUGG CCCUU
595
- AUU UC
596
- AGG AC
597
- GAACGCUGGC GGCG
598
- GGCGG ACGGG
599
- UUAA GC
600
- U AUGGG
601
- UU AUC
602
- AU AUUC
603
- UGG AG
604
- AAGUC AUC
605
- UGG GGC
606
- AGUC UGCAACUCG
607
- ACCC GC
608
- AG AUGG
609
- GGAA UCGCUAGUAA
610
- UUC UC
611
- AUU AAG
612
- ACG UCAA
613
- CC AA
614
- UUUU GC
615
- UCAA AA
616
- AUG AAG
617
- AUG AAC
618
- AG UAG
619
- AC ACC
620
- UGC UUAAC
621
- ACACUGGAAC UGAGACACGGUCC
622
- ACACUGGGACUGAGACACGGCCC AGACUCCUACGGGAGGCAGCAGUGGGGAA
623
- AC UGGG
624
- UAUC AGC
625
- UGGUGC AUGG
626
- ACAUGC AAGUCG
627
- UAC GAA
628
- UU AUUGGGCGUAA
629
- CCC AA
630
- AUG AUU
631
- AAC GG
632
- UU UCG
633
- AC UUG
634
- AGG AGG
635
- AAAA AA
636
- UUGAA AC
637
- GGGCCUUGUACACACCGCCCG UCACACC
638
- AGGG UGCG
639
- UAAGC ACC
640
- UGC GGC
641
- UGGC GC
642
- UGC AUU
643
- UUUU CC
644
- UCCC AA
645
- UU AGG
646
- AGCG UUG
647
- UGAA GAAGGCC
648
- UCC GC
649
- UU UGGG
650
- UUC GGGG
651
- Ġ AGAGUUUG
652
- UUAUCC GGAUU
653
- UG UUGG
654
- UAGG AA
655
- UGAA GC
656
- Ġ CC
657
- UGC AC
658
- AGUGGC GAACGGG
659
- UAA AC
660
- AC GAACGCUGGCGGCG
661
- UU AAGUC
662
- UGGGG GAA
663
- AUU GAA
664
- AGG UGCUGCAUGGCUGUCG
665
- UAUC G
666
- UUG ACC
667
- UAUU CC
668
- AGUG AGGAA
669
- ACC ACC
670
- UU GCG
671
- ACAA AA
672
- AGG AAG
673
- UAU AUU
674
- UAAUAC AUGC
675
- ACAUU GGGAC
676
- AUGCC CCUU
677
- UGCC CC
678
- AC UAC
679
- AC AAG
680
- GG GAA
681
- AGAA GAAGCACC
682
- UGC GGG
683
- UUC AG
684
- UAGCC GGCC
685
- UUC GAAGC
686
- AGCC AC
687
- AGCAACGCCGCG UGAG
688
- AUU GAACGCUGGCGGC
689
- UAGC UGGUCUGAGAGGAUG
690
- UU GCAA
691
- AUG AAGUC
692
- UAGAGG UGAA
693
- UUGCC AGC
694
- UUAA AAC
695
- AC UAA
696
- UGAG AGG
697
- UC UUG
698
- ACCGG UGGCGAAGGC
699
- AGCC AA
700
- Ġ UACG
701
- AUG CCC
702
- UAGG GC
703
- ACGCCGUAAACG AUG
704
- AG UUGG
705
- UG AGGG
706
- AUU UAA
707
- UGACGG UACC
708
- UC UAA
709
- UGG GGAA
710
- GG AC
711
- UGG UGUAGCGGUGAAAUGC
712
- UC AAG
713
- AG UGGG
714
- AUAC AA
715
- GCUGGC GGCG
716
- GG AG
717
- UAAC ACAUGCAAGUCGAAC
718
- GCG AGG
719
- ACC UGAGAGGG
720
- ACCAGUGGCGAAGGC GGC
721
- UUUU UUUU
722
- UCGC AAG
723
- ACGG UACC
724
- AUG UG
725
- UAC GC
726
- UGCC GC
727
- AU AUAA
728
- GCG UGAG
729
- UAGC GAA
730
- GGUG ACAA
731
- AUU AUU
732
- AG ACG
733
- AA UAA
734
- UCAAAGGAAUUGACGGGGGCCC GCACAAGCGGUGGAGCAUGUGGUUUAA
735
- UUCGG AUUG
736
- AGC UCC
737
- UG UGGC
738
- GGAA UUCC
739
- AUUCG UAG
740
- GG AAC
741
- UGAC AC
742
- UU AGGG
743
- UAGGC GGC
744
- AG UUUU
745
- UGGGC UACACACGUGCUACAA
746
- UGG UUC
747
- ACGUCAA AUCAUC
748
- UGAAG UCGUAACAAGG
749
- AUCC AA
750
- NNNN NNNN
751
- AUC AC
752
- GGGC UCAACC
753
- UAAC GCG
754
- AUG UCC
755
- UUCGG AUCG
756
- UGGGGGAA ACCC
757
- GCC GG
758
- AGGC AA
759
- GGC UAA
760
- UGAUC GGCC
761
- UAGAGGUGAA AUUCGUAG
762
- UG AUAC
763
- AUG ACC
764
- UGAG CC
765
- UGAGG UAA
766
- UC UAC
767
- UGACGCUGAGGC GCGAA
768
- AUU UU
769
- UC GCG
770
- AGC AGG
771
- AUU AG
772
- UCC CCC
773
- UC UGCC
774
- UACCAA GGCGACG
775
- GAA GAA
776
- ĠAGAGUUUG AUCC
777
- GGUGACAA ACCGG
778
- GCAA UGGGCGAAAGCC
779
- UGUAGCGGUGAA AUGCGUAGAG
780
- AGG ACG
781
- AC UGCC
782
- AUGGC GAAGGC
783
- UGG UG
784
- AUGG CC
785
- UC AUG
786
- AGC AUC
787
- GG GGG
788
- AG ACGG
789
- U AUAAC
790
- AGCUAAC GC
791
- U AUAAG
792
- UUG UU
793
- AUGC AA
794
- UUGAC AUCC
795
- AUUC AA
796
- ĠG ACGAACGCUGGCGGCG
797
- GGCUAACUACG UG
798
- AGUGGC GGACGGG
799
- UGGG UAGC
800
- UGAUCC AGCCAUGCCGCG
801
- UUC AC
802
- AGG GGC
803
- UAG AGC
804
- ACC AGCC
805
- GCCUGGGGAG UACGG
806
- ACG CCC
807
- UGCUUAAC ACAUGCAAGUCGAAC
808
- UGGUGCAUGG UUGUCG
809
- UAAC GG
810
- UAAUACCGC AUACG
811
- UGUAGCGGUGAAAUGCGUAG AUAUC
812
- AGCC GCC
813
- GCCUGGGGAGUACGGCC GCAAGG
814
- GGGG GC
815
- UG UGAC
816
- AUU UAC
817
- AGAA GAA
818
- UAUU GC
819
- UUCGAUGC AACGCGAAGAACCUUACC
820
- GGUGAA UACGUUCCC
821
- UAGC AA
822
- ACG UU
823
- UAUUGG UCAA
824
- AU AUGC
825
- AUAG CC
826
- UG UUUU
827
- GGG UUUAA
828
- AGCAA UGCC
829
- UACC CC
830
- UAGG UGG
831
- AGC AUU
832
- AUGAA GC
833
- AGGC GC
834
- UGCC GG
835
- AAGUCAUC AUGGCCCUU
836
- UGCC UAAUACAUGC
837
- CCC GCG
838
- AGCGUGGGGAGCAAAC AGG
839
- ACCAGUGGC GAAGGCG
840
- UGCAAGCG UUAAUCGGAAUUACUGGGCGUAA
841
- UGG UAA
842
- UU UGGC
843
- UAGUCC GG
844
- UACC GG
845
- UG AAGUC
846
- UCAA GC
847
- AGCGUGGGG AGCGAAC
848
- UCG AUG
849
- UAA GAA
850
- U AUGGC
851
- AGCC GG
852
- UGG UGG
853
- ACCC AA
854
- ACC AC
855
- CCC GC
856
- AGAA GG
857
- UUC UUC
858
- GG ACCC
859
- AGG UAG
860
- AG AGGAA
861
- UUC GGC
862
- UCUC AGUUCGG
863
- AUUAA GC
864
- UAC GGGG
865
- UGC UCC
866
- GC AGAU
867
- AGACUCCUACGGGAGGCAGC AGUAGG
868
- AGC UAA
869
- AUCAGG AGGAAC
870
- AUU AC
871
- UC UAG
872
- UAUU AA
873
- AGG UGGUGCAUGGUUGUCG
874
- AGG AGGAAC
875
- ACGUCAAAUCAUC AUGCCCCUU
876
- GCGG CC
877
- UGG AUG
878
- AUU AGAU
879
- UGC AGC
880
- UU UGAG
881
- UGAA GAAGG
882
- UAA UAA
883
- UU UGUC
884
- UGAGG UAACGGC
885
- AUAG AA
886
- AAC UC
887
- UGG GCG
888
- AG UUUC
889
- AUG UUC
890
- UGG ACC
891
- UUCC CC
892
- AG UUGC
893
- UGAA AGCCC
894
- UGC AGG
895
- AAG UCCUC
896
- UG ACCG
897
- UGG AUC
898
- AAG AGG
899
- AUU GCGAA
900
- ACG AUG
901
- UGG AAAC
902
- AUAA GC
903
- GG UGGAA
904
- UGACGCUGAGG AGCGAA
905
- GAAC GC
906
- GAAUC UUCC
907
- UUC GC
908
- ACCUGAGAGGG UGAUCGGCC
909
- ACACUGGAACUGAGACACGGUCC AGACUCCUACGGGAGGCAGCAGUGGGGAA
910
- GGCUAAC UUCG
911
- AG AGAC
912
- AG AGGC
913
- UAC UC
914
- UAAC GGCCC
915
- UUG AGUGC
916
- AAC AC
917
- AG UGCC
918
- AGCGC GCG
919
- UG UGCC
920
- AGC AGC
921
- ACCC GAA
922
- ACAA CC
923
- GGG AGGAAC
924
- ACC UGGGG
925
- ACGAA AGUC
926
- UC AUGC
927
- ACGG GG
928
- AU AUGG
929
- UC UUUU
930
- GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGG AGGG
931
- UU AGAG
932
- UGAUGC AGCGACGCC
933
- UG UAGG
934
- GC AUGG
935
- AGAA AGCCAC
936
- UGG AUU
937
- UUGC AGAA
938
- UU UCCC
939
- UG UUAA
940
- UU GAAG
941
- UCAA CCG
942
- UGG UAG
943
- GGCUAACUACGUGCCAGCAGCCGCGGUAAUACG UAGG
944
- GAA AGG
945
- UG AGGAA
946
- UU ACCAAGGC
947
- UGUAGC AGUGAA
948
- UAGCCGGCC UGAGAGGG
949
- UGG UAC
950
- UCGCGG AUCAGC
951
- GGAA ACG
952
- UGUG UGAAGAAGGCC
953
- GGCC ACAUUGGGAC
954
- AUC UCC
955
- AGGGC GCG
956
- UG UGGG
957
- UAAC GC
958
- ACC UCC
959
- GGGCCUUGUACACACCGCCCGUCACACC AUGGG
960
- UU UCAA
961
- UGG UCGG
962
- AGGG AC
963
- UAGGC G
964
- UG UAAG
965
- UGG AGGAA
966
- UUGACGG UACC
967
- AGUGAGGAA UAUUGGUCAA
968
- UG ACAA
969
- AUU UUC
970
- AGGUGGUGCAUGGUUGUCG UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA
971
- AGC ACC
972
- AGAA CC
973
- AUGAAGUC GGAAUCGCUAGUAA
974
- GG UCC
975
- AG UGAC
976
- AG AGCC
977
- UGC UC
978
- AC AUG
979
- UAUG CC
980
- AUUAGC UAG
981
- UCAA CCC
982
- AU AUAC
983
- UAA ACC
984
- AU AUCC
985
- UU AUUC
986
- UAC AGAGGG
987
- UUC GAA
988
- UU GAAC
989
- AG UAAC
990
- AGC GGC
991
- UCC UCC
992
- AGC UCG
993
- UUCGAAGC AACGCGAAGAACCUUACC
994
- U AUCCC
995
- GCGUUG UCCGGAA
996
- UGG CCC
997
- AG UACG
998
- ACGGCC UUCGGGUUGUAA
999
- AAG ACC
1000
- UAUUGG GCGUAA
1001
- AA GAA
1002
- UU UAAG
1003
- UUCGGAA UUACUGGGCGUAA
1004
- UGAG AUAC
1005
- UC UUGC
1006
- AG UUAA
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/special_tokens_map.json DELETED
@@ -1,5 +0,0 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
5
- }
 
 
 
 
 
 
tokenizer/tokenizer.json DELETED
@@ -1,2078 +0,0 @@
1
- {
2
- "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
5
- "added_tokens": [
6
- {
7
- "id": 0,
8
- "content": "<|endoftext|>",
9
- "single_word": false,
10
- "lstrip": false,
11
- "rstrip": false,
12
- "normalized": false,
13
- "special": true
14
- }
15
- ],
16
- "normalizer": null,
17
- "pre_tokenizer": {
18
- "type": "ByteLevel",
19
- "add_prefix_space": true,
20
- "trim_offsets": true,
21
- "use_regex": true
22
- },
23
- "post_processor": {
24
- "type": "ByteLevel",
25
- "add_prefix_space": true,
26
- "trim_offsets": true,
27
- "use_regex": true
28
- },
29
- "decoder": {
30
- "type": "ByteLevel",
31
- "add_prefix_space": true,
32
- "trim_offsets": true,
33
- "use_regex": true
34
- },
35
- "model": {
36
- "type": "BPE",
37
- "dropout": null,
38
- "unk_token": null,
39
- "continuing_subword_prefix": null,
40
- "end_of_word_suffix": null,
41
- "fuse_unk": false,
42
- "byte_fallback": false,
43
- "ignore_merges": false,
44
- "vocab": {
45
- "<|endoftext|>": 0,
46
- "A": 1,
47
- "B": 2,
48
- "C": 3,
49
- "D": 4,
50
- "G": 5,
51
- "H": 6,
52
- "K": 7,
53
- "M": 8,
54
- "N": 9,
55
- "R": 10,
56
- "S": 11,
57
- "U": 12,
58
- "V": 13,
59
- "W": 14,
60
- "X": 15,
61
- "Y": 16,
62
- "Ċ": 17,
63
- "Ġ": 18,
64
- "GG": 19,
65
- "AA": 20,
66
- "UU": 21,
67
- "CC": 22,
68
- "AG": 23,
69
- "UG": 24,
70
- "AC": 25,
71
- "UC": 26,
72
- "UGG": 27,
73
- "GC": 28,
74
- "AGG": 29,
75
- "UAA": 30,
76
- "AGC": 31,
77
- "AUU": 32,
78
- "ACC": 33,
79
- "AUG": 34,
80
- "UCC": 35,
81
- "GAA": 36,
82
- "UAC": 37,
83
- "UGC": 38,
84
- "AUC": 39,
85
- "UAG": 40,
86
- "UUC": 41,
87
- "AAC": 42,
88
- "GGC": 43,
89
- "UUG": 44,
90
- "AAG": 45,
91
- "GGG": 46,
92
- "CCC": 47,
93
- "AU": 48,
94
- "UGAA": 49,
95
- "ACG": 50,
96
- "AUGG": 51,
97
- "UAAC": 52,
98
- "GCG": 53,
99
- "UCG": 54,
100
- "AGGC": 55,
101
- "UGAG": 56,
102
- "UGGC": 57,
103
- "AUGC": 58,
104
- "AGCC": 59,
105
- "UGCC": 60,
106
- "AUCC": 61,
107
- "GGAA": 62,
108
- "AUAA": 63,
109
- "UACC": 64,
110
- "UUUU": 65,
111
- "ACGG": 66,
112
- "AGGG": 67,
113
- "UAUU": 68,
114
- "AGAA": 69,
115
- "UUGG": 70,
116
- "GCC": 71,
117
- "UAGC": 72,
118
- "UCAA": 73,
119
- "UUAA": 74,
120
- "GAAC": 75,
121
- "ACAA": 76,
122
- "UAGG": 77,
123
- "UGGG": 78,
124
- "ACCC": 79,
125
- "UGGGG": 80,
126
- "UGAC": 81,
127
- "AUAC": 82,
128
- "GCGG": 83,
129
- "AGGAA": 84,
130
- "UUCC": 85,
131
- "AGCG": 86,
132
- "UCCC": 87,
133
- "GCAA": 88,
134
- "AGAC": 89,
135
- "GGCC": 90,
136
- "AUUC": 91,
137
- "UUUC": 92,
138
- "UUGC": 93,
139
- "AAAA": 94,
140
- "AGAG": 95,
141
- "CCG": 96,
142
- "UACG": 97,
143
- "ACAC": 98,
144
- "AUAG": 99,
145
- "GGGG": 100,
146
- "UGUC": 101,
147
- "UAAG": 102,
148
- "UAUC": 103,
149
- "UUUG": 104,
150
- "AGUC": 105,
151
- "AUUG": 106,
152
- "GGCG": 107,
153
- "AAAC": 108,
154
- "AAGUC": 109,
155
- "AUGAA": 110,
156
- "UGUG": 111,
157
- "UCUC": 112,
158
- "UGGAA": 113,
159
- "ACCG": 114,
160
- "AGUG": 115,
161
- "UGGGC": 116,
162
- "UUAC": 117,
163
- "UCGC": 118,
164
- "UUCGG": 119,
165
- "UGCG": 120,
166
- "UAUG": 121,
167
- "UUCG": 122,
168
- "UUUAA": 123,
169
- "UCGG": 124,
170
- "UUAG": 125,
171
- "UCUG": 126,
172
- "UCCG": 127,
173
- "AACG": 128,
174
- "GAAG": 129,
175
- "AGUGG": 130,
176
- "UCAC": 131,
177
- "AUAAC": 132,
178
- "UGAGG": 133,
179
- "AUGGC": 134,
180
- "AGAGG": 135,
181
- "AGAU": 136,
182
- "AUGCC": 137,
183
- "ACCAA": 138,
184
- "UAGGC": 139,
185
- "GGGC": 140,
186
- "AUUAA": 141,
187
- "GGUGAA": 142,
188
- "UACGGG": 143,
189
- "AUCG": 144,
190
- "AAGCC": 145,
191
- "UUGAA": 146,
192
- "UAU": 147,
193
- "UACAC": 148,
194
- "GCGAA": 149,
195
- "CCUU": 150,
196
- "CCCG": 151,
197
- "AUGCG": 152,
198
- "ACUC": 153,
199
- "UGUU": 154,
200
- "GGCUAAC": 155,
201
- "AAGG": 156,
202
- "UCAG": 157,
203
- "ACGC": 158,
204
- "UGUAGC": 159,
205
- "UGACGC": 160,
206
- "UGAGAC": 161,
207
- "UUCCC": 162,
208
- "GCGUAA": 163,
209
- "AGCAGCC": 164,
210
- "AUGGG": 165,
211
- "AGGCAGC": 166,
212
- "AGUGGC": 167,
213
- "AGGGC": 168,
214
- "UACAA": 169,
215
- "UCAGC": 170,
216
- "AUUGG": 171,
217
- "GAAGGC": 172,
218
- "GCGGUAA": 173,
219
- "ACGAA": 174,
220
- "UUAAG": 175,
221
- "UGCCAGCAGCC": 176,
222
- "CCCC": 177,
223
- "UGUCG": 178,
224
- "UUGGG": 179,
225
- "UGCAA": 180,
226
- "AGCAA": 181,
227
- "AUCCC": 182,
228
- "UACGGGAGGCAGC": 183,
229
- "ACGGG": 184,
230
- "UUAAC": 185,
231
- "UUCGGG": 186,
232
- "ACUG": 187,
233
- "UUGCC": 188,
234
- "ACCGG": 189,
235
- "UAGAG": 190,
236
- "UUGUAA": 191,
237
- "UAGUCC": 192,
238
- "AGGAUU": 193,
239
- "UAAGG": 194,
240
- "UGCCAGCAGCCGCGGUAA": 195,
241
- "UCCUACGGGAGGCAGC": 196,
242
- "AGGGG": 197,
243
- "GCACAA": 198,
244
- "AUAUU": 199,
245
- "AUAUC": 200,
246
- "AGUU": 201,
247
- "UAAUACC": 202,
248
- "UAAAA": 203,
249
- "UACGG": 204,
250
- "AGGAAC": 205,
251
- "UGCCC": 206,
252
- "UUGAC": 207,
253
- "GAAGC": 208,
254
- "UGGCC": 209,
255
- "UCUU": 210,
256
- "UAGGG": 211,
257
- "AGCCC": 212,
258
- "UGAGACACGG": 213,
259
- "AUUAGC": 214,
260
- "AUAAG": 215,
261
- "GCUGGC": 216,
262
- "AGGCC": 217,
263
- "ACUU": 218,
264
- "AGCGUGGGG": 219,
265
- "AGCAAAC": 220,
266
- "ACCCC": 221,
267
- "AGGAAGG": 222,
268
- "UAACC": 223,
269
- "UUGACGG": 224,
270
- "AGGAUUAGAU": 225,
271
- "ACAG": 226,
272
- "AGACUCCUACGGGAGGCAGC": 227,
273
- "UGGUC": 228,
274
- "GGCGG": 229,
275
- "GCGC": 230,
276
- "UACCC": 231,
277
- "UGGAGC": 232,
278
- "AUGUGG": 233,
279
- "AGUGGGGAA": 234,
280
- "UGUAGCGGUGAA": 235,
281
- "GGGCC": 236,
282
- "UAGUAA": 237,
283
- "UCCGG": 238,
284
- "NN": 239,
285
- "ĠG": 240,
286
- "UGAAG": 241,
287
- "UAGCC": 242,
288
- "ACAUGC": 243,
289
- "UCAAC": 244,
290
- "AGUAC": 245,
291
- "AGGAUG": 246,
292
- "AGGAUUAGAUACCC": 247,
293
- "AGUGC": 248,
294
- "UAUGG": 249,
295
- "ACGCC": 250,
296
- "UAGUUGG": 251,
297
- "UGUAA": 252,
298
- "AACC": 253,
299
- "ACUGC": 254,
300
- "UAUUGG": 255,
301
- "UGGGCGUAA": 256,
302
- "UUUUC": 257,
303
- "UGAGUAAC": 258,
304
- "UGCUGC": 259,
305
- "UAGAA": 260,
306
- "AUUCC": 261,
307
- "UAAGC": 262,
308
- "UAUAA": 263,
309
- "ACGUC": 264,
310
- "AAGC": 265,
311
- "AGAAG": 266,
312
- "AGCGCAA": 267,
313
- "UGACGG": 268,
314
- "AGCGC": 269,
315
- "UUUUG": 270,
316
- "UGCAAC": 271,
317
- "GGUG": 272,
318
- "UCAGCUCG": 273,
319
- "UGGUAGUCC": 274,
320
- "UUUCC": 275,
321
- "AGCGG": 276,
322
- "AGAAC": 277,
323
- "UGAAC": 278,
324
- "UGGAAC": 279,
325
- "UUCAA": 280,
326
- "AGAUU": 281,
327
- "ACUCC": 282,
328
- "AGAUG": 283,
329
- "UUAUU": 284,
330
- "UGGGAA": 285,
331
- "AGAGC": 286,
332
- "AUCAA": 287,
333
- "GGCUAACUACG": 288,
334
- "AGCAAC": 289,
335
- "AGCGUGGGGAGCAAAC": 290,
336
- "AGGAUUAGAUACCCUGGUAGUCC": 291,
337
- "ACAUU": 292,
338
- "UAAACG": 293,
339
- "UGAGGC": 294,
340
- "UGUGAA": 295,
341
- "GAAGG": 296,
342
- "AUGCGUAG": 297,
343
- "UUGGC": 298,
344
- "UAGGGG": 299,
345
- "AGUGAA": 300,
346
- "AGGGAA": 301,
347
- "UGAUC": 302,
348
- "UGGGAC": 303,
349
- "UUAAGUCCC": 304,
350
- "ACCGCCCG": 305,
351
- "GAACGCUGGC": 306,
352
- "AAGUCGAAC": 307,
353
- "AGCGAA": 308,
354
- "AGCUC": 309,
355
- "UCAAAGGAA": 310,
356
- "UCAACC": 311,
357
- "GCCUGGGG": 312,
358
- "CCCUU": 313,
359
- "UCCCC": 314,
360
- "UGCCG": 315,
361
- "UGAUCC": 316,
362
- "UGAGAUG": 317,
363
- "UUACC": 318,
364
- "AGACUCCUACGGGAGGCAGCAGUGGGGAA": 319,
365
- "UCGCC": 320,
366
- "GGGAC": 321,
367
- "AGGCG": 322,
368
- "AGGAAGGUGGGG": 323,
369
- "GGGCCC": 324,
370
- "UAUUC": 325,
371
- "UACGUUCCC": 326,
372
- "UCAAAGGAAUUGACGG": 327,
373
- "AUACC": 328,
374
- "UGAGACACGGCCC": 329,
375
- "AUAGC": 330,
376
- "UCAUU": 331,
377
- "UACACACCGCCCG": 332,
378
- "UCGAA": 333,
379
- "AUAGG": 334,
380
- "AUCGG": 335,
381
- "UUUGG": 336,
382
- "UGAUGC": 337,
383
- "UGCGAA": 338,
384
- "UAGAGG": 339,
385
- "GCACAAGCGG": 340,
386
- "AAGUCG": 341,
387
- "UGGCG": 342,
388
- "UCGGAA": 343,
389
- "GGCGACG": 344,
390
- "UGAUG": 345,
391
- "UAGCG": 346,
392
- "AUACG": 347,
393
- "AACGAGCGCAA": 348,
394
- "UCAGCUCGUGUCG": 349,
395
- "CCUUACC": 350,
396
- "UUGGGUUAAGUCCC": 351,
397
- "ACGUGC": 352,
398
- "ACUGG": 353,
399
- "AGUAA": 354,
400
- "GCAAGG": 355,
401
- "UGUGG": 356,
402
- "UCAGCUCGUGUCGUGAGAUG": 357,
403
- "UAUCC": 358,
404
- "AGUUC": 359,
405
- "AGACC": 360,
406
- "ACCAGUGGC": 361,
407
- "AUAUG": 362,
408
- "UCAGG": 363,
409
- "UCUUC": 364,
410
- "GCAACGAGCGCAA": 365,
411
- "UUACUGGGCGUAA": 366,
412
- "UGAUU": 367,
413
- "UUAUCC": 368,
414
- "UGACC": 369,
415
- "UCAUC": 370,
416
- "UAUGC": 371,
417
- "UAGUC": 372,
418
- "GCCG": 373,
419
- "AUCAGC": 374,
420
- "AUUCG": 375,
421
- "UAAUACCGC": 376,
422
- "UGGGGG": 377,
423
- "AACGCGAA": 378,
424
- "ACAGG": 379,
425
- "UGCGG": 380,
426
- "GGCUAACUCCG": 381,
427
- "AUGUGGUUUAA": 382,
428
- "AGGAAGGUGGGGAUG": 383,
429
- "GCCGCG": 384,
430
- "UCGCUAGUAA": 385,
431
- "UGAAAC": 386,
432
- "ACGGC": 387,
433
- "UUGUACACACCGCCCG": 388,
434
- "UGGAAUUCC": 389,
435
- "UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCC": 390,
436
- "GAAAGCC": 391,
437
- "AUUGC": 392,
438
- "UGGUCUGAG": 393,
439
- "UCGGC": 394,
440
- "UCCAA": 395,
441
- "AUUAGCUAGUUGG": 396,
442
- "UAGGCGG": 397,
443
- "AGUUG": 398,
444
- "GAACGGG": 399,
445
- "UCACC": 400,
446
- "UAAAAC": 401,
447
- "UCUGG": 402,
448
- "UAUUG": 403,
449
- "UUCGGGUUGUAA": 404,
450
- "ACUUC": 405,
451
- "ACGUGCUACAA": 406,
452
- "GAAAA": 407,
453
- "ĠC": 408,
454
- "UCUGC": 409,
455
- "UUUGC": 410,
456
- "UACCG": 411,
457
- "UGCAACUCG": 412,
458
- "AUGGCUGUCG": 413,
459
- "UUGUUGG": 414,
460
- "UGUGC": 415,
461
- "AACGCGAAGAA": 416,
462
- "UGUUC": 417,
463
- "AGAGGG": 418,
464
- "AUCCG": 419,
465
- "GCGUUG": 420,
466
- "AACAA": 421,
467
- "UUGGAA": 422,
468
- "AUAU": 423,
469
- "UCUCC": 424,
470
- "AGAUC": 425,
471
- "ACGCCG": 426,
472
- "UUAACC": 427,
473
- "AGGCGG": 428,
474
- "ACAUGCAAGUCGAAC": 429,
475
- "UGGUGC": 430,
476
- "UAAUAC": 431,
477
- "UACCAA": 432,
478
- "GGCCC": 433,
479
- "AGCAC": 434,
480
- "UGAACC": 435,
481
- "ACACUGGGAC": 436,
482
- "AUCAGG": 437,
483
- "UGAGUAACACG": 438,
484
- "GCGUG": 439,
485
- "UAUAC": 440,
486
- "UUGUC": 441,
487
- "GAAUC": 442,
488
- "UUAGC": 443,
489
- "UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA": 444,
490
- "AGCAACGCCGCG": 445,
491
- "AGUAGG": 446,
492
- "UAACG": 447,
493
- "GCACAAGCGGUGGAGC": 448,
494
- "UUUAG": 449,
495
- "AGGGGG": 450,
496
- "UACACACGUGCUACAA": 451,
497
- "GGCGC": 452,
498
- "UGAGAGGG": 453,
499
- "UGCGC": 454,
500
- "AGCCG": 455,
501
- "UGAAUACGUUCCC": 456,
502
- "UUUAC": 457,
503
- "NNNN": 458,
504
- "GGCUAACUCCGUGCCAGCAGCCGCGGUAA": 459,
505
- "AUGGAA": 460,
506
- "UGGGCGC": 461,
507
- "UGGGCGAAAGCC": 462,
508
- "UAUAG": 463,
509
- "GAAGGCC": 464,
510
- "GGCAGC": 465,
511
- "AUCGC": 466,
512
- "UGUUG": 467,
513
- "ACCCG": 468,
514
- "GGCUAACUACGUGCCAGCAGCCGCGGUAA": 469,
515
- "AGUCC": 470,
516
- "AUCAGCC": 471,
517
- "UGUCC": 472,
518
- "UCAAAGGAAUUGACGGGGGCCC": 473,
519
- "UGACGCUGAGGC": 474,
520
- "UGAGC": 475,
521
- "UUCCG": 476,
522
- "AAGAC": 477,
523
- "GAACG": 478,
524
- "AACGCGAAGAACCUUACC": 479,
525
- "UGGCGAAGGC": 480,
526
- "AACGC": 481,
527
- "GGAUU": 482,
528
- "ACACUGGGACUGAGACACGGCCC": 483,
529
- "AGCCAUGCC": 484,
530
- "AUGAC": 485,
531
- "GCACAAGCGGUGGAGCAUGUGGUUUAA": 486,
532
- "GCGCC": 487,
533
- "UGAUGG": 488,
534
- "UGCUGCAUGGCUGUCG": 489,
535
- "AGGUC": 490,
536
- "AUGUC": 491,
537
- "GCCCC": 492,
538
- "UGACG": 493,
539
- "GGGCCUUGUACACACCGCCCG": 494,
540
- "ACCUC": 495,
541
- "GGGGC": 496,
542
- "UCACACC": 497,
543
- "AUUGGGCGUAA": 498,
544
- "UAACAAGG": 499,
545
- "UUAAAA": 500,
546
- "ACCGC": 501,
547
- "UGUAGCGGUGAAAUGCGUAG": 502,
548
- "UUGGGC": 503,
549
- "UAACGGC": 504,
550
- "ACGCCGUAAACG": 505,
551
- "GAAAC": 506,
552
- "AGCUAAC": 507,
553
- "AUAAAA": 508,
554
- "AGCGUGGGGAGCAAACAGGAUUAGAUACCCUGGUAGUCC": 509,
555
- "AGCGAAC": 510,
556
- "UCCUC": 511,
557
- "AGAAAA": 512,
558
- "UGAAGG": 513,
559
- "UAUUGCACAA": 514,
560
- "UGGGCGCAAGCC": 515,
561
- "UUUUGG": 516,
562
- "UGGUCUGAGAGGAUG": 517,
563
- "AUCAG": 518,
564
- "ACCAAGGCGACG": 519,
565
- "GAACGCUGGCGGC": 520,
566
- "GGCUAACUACGUGCCAGCAGCCGCGGUAAUACG": 521,
567
- "UGAGACACGGUCC": 522,
568
- "AGAAGC": 523,
569
- "UCCCG": 524,
570
- "UUCGGAA": 525,
571
- "ACGGCC": 526,
572
- "UAUGAA": 527,
573
- "UGACGCUGAGG": 528,
574
- "AUCAUU": 529,
575
- "ACCAGUGGCGAAGGC": 530,
576
- "ACCAAGGC": 531,
577
- "UA": 532,
578
- "UUUGAC": 533,
579
- "ACAAC": 534,
580
- "AUGUGAA": 535,
581
- "UGUAGCGGUGAAAUGC": 536,
582
- "UGUAG": 537,
583
- "UGGGAAC": 538,
584
- "AUCAUC": 539,
585
- "GGCCG": 540,
586
- "UAAUC": 541,
587
- "GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGG": 542,
588
- "UAAAGC": 543,
589
- "UGGCUC": 544,
590
- "AGACUGCC": 545,
591
- "UGUAC": 546,
592
- "UUGAG": 547,
593
- "GGUC": 548,
594
- "ACACUGGAAC": 549,
595
- "UAAUACCGG": 550,
596
- "UCCGGAA": 551,
597
- "UUAAUCGGAA": 552,
598
- "GCCUGGGGAGUAC": 553,
599
- "AUAACC": 554,
600
- "AGUCG": 555,
601
- "AUGGGC": 556,
602
- "GGGUC": 557,
603
- "AGUUCGG": 558,
604
- "AGGAAGGUGGGGAUGACGUC": 559,
605
- "UGAGAA": 560,
606
- "AUCCCC": 561,
607
- "GCGGUGAAUACGUUCCC": 562,
608
- "UGGAGG": 563,
609
- "AGAGUUUG": 564,
610
- "UGCAAGCG": 565,
611
- "UUUAUU": 566,
612
- "UGGAC": 567,
613
- "UGAGUAA": 568,
614
- "GAAGCACC": 569,
615
- "AGCCAUGCCGCG": 570,
616
- "GGCAA": 571,
617
- "UUGUCG": 572,
618
- "UAUUGGACAA": 573,
619
- "UUGGGG": 574,
620
- "AUCUC": 575,
621
- "GAAAGC": 576,
622
- "UGAAAA": 577,
623
- "ACAGC": 578,
624
- "UGAUGAA": 579,
625
- "GCCUGGGGAGUACGGCC": 580,
626
- "GAACC": 581,
627
- "UGGGCC": 582,
628
- "AGAGAA": 583,
629
- "AUGGGG": 584,
630
- "AGGCCC": 585,
631
- "AUAACG": 586,
632
- "AUGCGUAGAG": 587,
633
- "GAAGGCG": 588,
634
- "UCGGG": 589,
635
- "UGGCAA": 590,
636
- "AGCCCC": 591,
637
- "UCGCGG": 592,
638
- "GGACGGG": 593,
639
- "UCGUAACAAGG": 594,
640
- "AGCUUGC": 595,
641
- "UUUUAA": 596,
642
- "AGCGACGCC": 597,
643
- "UUAAUCGGAAUUACUGGGCGUAA": 598,
644
- "GGAAGG": 599,
645
- "ACAUC": 600,
646
- "UGAGUAACGCG": 601,
647
- "UUAUG": 602,
648
- "GCCUGGGGAG": 603,
649
- "UAGCCG": 604,
650
- "UGGGGUAA": 605,
651
- "UUCGAUGC": 606,
652
- "CCCUUG": 607,
653
- "CCCGG": 608,
654
- "UUUGAA": 609,
655
- "GCAAGGC": 610,
656
- "AUGGCCCUU": 611,
657
- "AUUUC": 612,
658
- "AGGAC": 613,
659
- "GAACGCUGGCGGCG": 614,
660
- "GGCGGACGGG": 615,
661
- "UUAAGC": 616,
662
- "UAUGGG": 617,
663
- "UUAUC": 618,
664
- "AUAUUC": 619,
665
- "UGGAG": 620,
666
- "AAGUCAUC": 621,
667
- "UGGGGC": 622,
668
- "AGUCUGCAACUCG": 623,
669
- "ACCCGC": 624,
670
- "AGAUGG": 625,
671
- "GGAAUCGCUAGUAA": 626,
672
- "UUCUC": 627,
673
- "AUUAAG": 628,
674
- "ACGUCAA": 629,
675
- "CCAA": 630,
676
- "UUUUGC": 631,
677
- "UCAAAA": 632,
678
- "AUGAAG": 633,
679
- "AUGAAC": 634,
680
- "AGUAG": 635,
681
- "ACACC": 636,
682
- "UGCUUAAC": 637,
683
- "ACACUGGAACUGAGACACGGUCC": 638,
684
- "ACACUGGGACUGAGACACGGCCCAGACUCCUACGGGAGGCAGCAGUGGGGAA": 639,
685
- "ACUGGG": 640,
686
- "UAUCAGC": 641,
687
- "UGGUGCAUGG": 642,
688
- "ACAUGCAAGUCG": 643,
689
- "UACGAA": 644,
690
- "UUAUUGGGCGUAA": 645,
691
- "CCCAA": 646,
692
- "AUGAUU": 647,
693
- "AACGG": 648,
694
- "UUUCG": 649,
695
- "ACUUG": 650,
696
- "AGGAGG": 651,
697
- "AAAAAA": 652,
698
- "UUGAAAC": 653,
699
- "GGGCCUUGUACACACCGCCCGUCACACC": 654,
700
- "AGGGUGCG": 655,
701
- "UAAGCACC": 656,
702
- "UGCGGC": 657,
703
- "UGGCGC": 658,
704
- "UGCAUU": 659,
705
- "UUUUCC": 660,
706
- "UCCCAA": 661,
707
- "UUAGG": 662,
708
- "AGCGUUG": 663,
709
- "UGAAGAAGGCC": 664,
710
- "UCCGC": 665,
711
- "UUUGGG": 666,
712
- "UUCGGGG": 667,
713
- "ĠAGAGUUUG": 668,
714
- "UUAUCCGGAUU": 669,
715
- "UGUUGG": 670,
716
- "UAGGAA": 671,
717
- "UGAAGC": 672,
718
- "ĠCC": 673,
719
- "UGCAC": 674,
720
- "AGUGGCGAACGGG": 675,
721
- "UAAAC": 676,
722
- "ACGAACGCUGGCGGCG": 677,
723
- "UUAAGUC": 678,
724
- "UGGGGGAA": 679,
725
- "AUUGAA": 680,
726
- "AGGUGCUGCAUGGCUGUCG": 681,
727
- "UAUCG": 682,
728
- "UUGACC": 683,
729
- "UAUUCC": 684,
730
- "AGUGAGGAA": 685,
731
- "ACCACC": 686,
732
- "UUGCG": 687,
733
- "ACAAAA": 688,
734
- "AGGAAG": 689,
735
- "UAUAUU": 690,
736
- "UAAUACAUGC": 691,
737
- "ACAUUGGGAC": 692,
738
- "AUGCCCCUU": 693,
739
- "UGCCCC": 694,
740
- "ACUAC": 695,
741
- "ACAAG": 696,
742
- "GGGAA": 697,
743
- "AGAAGAAGCACC": 698,
744
- "UGCGGG": 699,
745
- "UUCAG": 700,
746
- "UAGCCGGCC": 701,
747
- "UUCGAAGC": 702,
748
- "AGCCAC": 703,
749
- "AGCAACGCCGCGUGAG": 704,
750
- "AUUGAACGCUGGCGGC": 705,
751
- "UAGCUGGUCUGAGAGGAUG": 706,
752
- "UUGCAA": 707,
753
- "AUGAAGUC": 708,
754
- "UAGAGGUGAA": 709,
755
- "UUGCCAGC": 710,
756
- "UUAAAAC": 711,
757
- "ACUAA": 712,
758
- "UGAGAGG": 713,
759
- "UCUUG": 714,
760
- "ACCGGUGGCGAAGGC": 715,
761
- "AGCCAA": 716,
762
- "ĠUACG": 717,
763
- "AUGCCC": 718,
764
- "UAGGGC": 719,
765
- "ACGCCGUAAACGAUG": 720,
766
- "AGUUGG": 721,
767
- "UGAGGG": 722,
768
- "AUUUAA": 723,
769
- "UGACGGUACC": 724,
770
- "UCUAA": 725,
771
- "UGGGGAA": 726,
772
- "GGAC": 727,
773
- "UGGUGUAGCGGUGAAAUGC": 728,
774
- "UCAAG": 729,
775
- "AGUGGG": 730,
776
- "AUACAA": 731,
777
- "GCUGGCGGCG": 732,
778
- "GGAG": 733,
779
- "UAACACAUGCAAGUCGAAC": 734,
780
- "GCGAGG": 735,
781
- "ACCUGAGAGGG": 736,
782
- "ACCAGUGGCGAAGGCGGC": 737,
783
- "UUUUUUUU": 738,
784
- "UCGCAAG": 739,
785
- "ACGGUACC": 740,
786
- "AUGUG": 741,
787
- "UACGC": 742,
788
- "UGCCGC": 743,
789
- "AUAUAA": 744,
790
- "GCGUGAG": 745,
791
- "UAGCGAA": 746,
792
- "GGUGACAA": 747,
793
- "AUUAUU": 748,
794
- "AGACG": 749,
795
- "AAUAA": 750,
796
- "UCAAAGGAAUUGACGGGGGCCCGCACAAGCGGUGGAGCAUGUGGUUUAA": 751,
797
- "UUCGGAUUG": 752,
798
- "AGCUCC": 753,
799
- "UGUGGC": 754,
800
- "GGAAUUCC": 755,
801
- "AUUCGUAG": 756,
802
- "GGAAC": 757,
803
- "UGACAC": 758,
804
- "UUAGGG": 759,
805
- "UAGGCGGC": 760,
806
- "AGUUUU": 761,
807
- "UGGGCUACACACGUGCUACAA": 762,
808
- "UGGUUC": 763,
809
- "ACGUCAAAUCAUC": 764,
810
- "UGAAGUCGUAACAAGG": 765,
811
- "AUCCAA": 766,
812
- "NNNNNNNN": 767,
813
- "AUCAC": 768,
814
- "GGGCUCAACC": 769,
815
- "UAACGCG": 770,
816
- "AUGUCC": 771,
817
- "UUCGGAUCG": 772,
818
- "UGGGGGAAACCC": 773,
819
- "GCCGG": 774,
820
- "AGGCAA": 775,
821
- "GGCUAA": 776,
822
- "UGAUCGGCC": 777,
823
- "UAGAGGUGAAAUUCGUAG": 778,
824
- "UGAUAC": 779,
825
- "AUGACC": 780,
826
- "UGAGCC": 781,
827
- "UGAGGUAA": 782,
828
- "UCUAC": 783,
829
- "UGACGCUGAGGCGCGAA": 784,
830
- "AUUUU": 785,
831
- "UCGCG": 786,
832
- "AGCAGG": 787,
833
- "AUUAG": 788,
834
- "UCCCCC": 789,
835
- "UCUGCC": 790,
836
- "UACCAAGGCGACG": 791,
837
- "GAAGAA": 792,
838
- "ĠAGAGUUUGAUCC": 793,
839
- "GGUGACAAACCGG": 794,
840
- "GCAAUGGGCGAAAGCC": 795,
841
- "UGUAGCGGUGAAAUGCGUAGAG": 796,
842
- "AGGACG": 797,
843
- "ACUGCC": 798,
844
- "AUGGCGAAGGC": 799,
845
- "UGGUG": 800,
846
- "AUGGCC": 801,
847
- "UCAUG": 802,
848
- "AGCAUC": 803,
849
- "GGGGG": 804,
850
- "AGACGG": 805,
851
- "UAUAAC": 806,
852
- "AGCUAACGC": 807,
853
- "UAUAAG": 808,
854
- "UUGUU": 809,
855
- "AUGCAA": 810,
856
- "UUGACAUCC": 811,
857
- "AUUCAA": 812,
858
- "ĠGACGAACGCUGGCGGCG": 813,
859
- "GGCUAACUACGUG": 814,
860
- "AGUGGCGGACGGG": 815,
861
- "UGGGUAGC": 816,
862
- "UGAUCCAGCCAUGCCGCG": 817,
863
- "UUCAC": 818,
864
- "AGGGGC": 819,
865
- "UAGAGC": 820,
866
- "ACCAGCC": 821,
867
- "GCCUGGGGAGUACGG": 822,
868
- "ACGCCC": 823,
869
- "UGCUUAACACAUGCAAGUCGAAC": 824,
870
- "UGGUGCAUGGUUGUCG": 825,
871
- "UAACGG": 826,
872
- "UAAUACCGCAUACG": 827,
873
- "UGUAGCGGUGAAAUGCGUAGAUAUC": 828,
874
- "AGCCGCC": 829,
875
- "GCCUGGGGAGUACGGCCGCAAGG": 830,
876
- "GGGGGC": 831,
877
- "UGUGAC": 832,
878
- "AUUUAC": 833,
879
- "AGAAGAA": 834,
880
- "UAUUGC": 835,
881
- "UUCGAUGCAACGCGAAGAACCUUACC": 836,
882
- "GGUGAAUACGUUCCC": 837,
883
- "UAGCAA": 838,
884
- "ACGUU": 839,
885
- "UAUUGGUCAA": 840,
886
- "AUAUGC": 841,
887
- "AUAGCC": 842,
888
- "UGUUUU": 843,
889
- "GGGUUUAA": 844,
890
- "AGCAAUGCC": 845,
891
- "UACCCC": 846,
892
- "UAGGUGG": 847,
893
- "AGCAUU": 848,
894
- "AUGAAGC": 849,
895
- "AGGCGC": 850,
896
- "UGCCGG": 851,
897
- "AAGUCAUCAUGGCCCUU": 852,
898
- "UGCCUAAUACAUGC": 853,
899
- "CCCGCG": 854,
900
- "AGCGUGGGGAGCAAACAGG": 855,
901
- "ACCAGUGGCGAAGGCG": 856,
902
- "UGCAAGCGUUAAUCGGAAUUACUGGGCGUAA": 857,
903
- "UGGUAA": 858,
904
- "UUUGGC": 859,
905
- "UAGUCCGG": 860,
906
- "UACCGG": 861,
907
- "UGAAGUC": 862,
908
- "UCAAGC": 863,
909
- "AGCGUGGGGAGCGAAC": 864,
910
- "UCGAUG": 865,
911
- "UAAGAA": 866,
912
- "UAUGGC": 867,
913
- "AGCCGG": 868,
914
- "UGGUGG": 869,
915
- "ACCCAA": 870,
916
- "ACCAC": 871,
917
- "CCCGC": 872,
918
- "AGAAGG": 873,
919
- "UUCUUC": 874,
920
- "GGACCC": 875,
921
- "AGGUAG": 876,
922
- "AGAGGAA": 877,
923
- "UUCGGC": 878,
924
- "UCUCAGUUCGG": 879,
925
- "AUUAAGC": 880,
926
- "UACGGGG": 881,
927
- "UGCUCC": 882,
928
- "GCAGAU": 883,
929
- "AGACUCCUACGGGAGGCAGCAGUAGG": 884,
930
- "AGCUAA": 885,
931
- "AUCAGGAGGAAC": 886,
932
- "AUUAC": 887,
933
- "UCUAG": 888,
934
- "UAUUAA": 889,
935
- "AGGUGGUGCAUGGUUGUCG": 890,
936
- "AGGAGGAAC": 891,
937
- "ACGUCAAAUCAUCAUGCCCCUU": 892,
938
- "GCGGCC": 893,
939
- "UGGAUG": 894,
940
- "AUUAGAU": 895,
941
- "UGCAGC": 896,
942
- "UUUGAG": 897,
943
- "UGAAGAAGG": 898,
944
- "UAAUAA": 899,
945
- "UUUGUC": 900,
946
- "UGAGGUAACGGC": 901,
947
- "AUAGAA": 902,
948
- "AACUC": 903,
949
- "UGGGCG": 904,
950
- "AGUUUC": 905,
951
- "AUGUUC": 906,
952
- "UGGACC": 907,
953
- "UUCCCC": 908,
954
- "AGUUGC": 909,
955
- "UGAAAGCCC": 910,
956
- "UGCAGG": 911,
957
- "AAGUCCUC": 912,
958
- "UGACCG": 913,
959
- "UGGAUC": 914,
960
- "AAGAGG": 915,
961
- "AUUGCGAA": 916,
962
- "ACGAUG": 917,
963
- "UGGAAAC": 918,
964
- "AUAAGC": 919,
965
- "GGUGGAA": 920,
966
- "UGACGCUGAGGAGCGAA": 921,
967
- "GAACGC": 922,
968
- "GAAUCUUCC": 923,
969
- "UUCGC": 924,
970
- "ACCUGAGAGGGUGAUCGGCC": 925,
971
- "ACACUGGAACUGAGACACGGUCCAGACUCCUACGGGAGGCAGCAGUGGGGAA": 926,
972
- "GGCUAACUUCG": 927,
973
- "AGAGAC": 928,
974
- "AGAGGC": 929,
975
- "UACUC": 930,
976
- "UAACGGCCC": 931,
977
- "UUGAGUGC": 932,
978
- "AACAC": 933,
979
- "AGUGCC": 934,
980
- "AGCGCGCG": 935,
981
- "UGUGCC": 936,
982
- "AGCAGC": 937,
983
- "ACCCGAA": 938,
984
- "ACAACC": 939,
985
- "GGGAGGAAC": 940,
986
- "ACCUGGGG": 941,
987
- "ACGAAAGUC": 942,
988
- "UCAUGC": 943,
989
- "ACGGGG": 944,
990
- "AUAUGG": 945,
991
- "UCUUUU": 946,
992
- "GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGGAGGG": 947,
993
- "UUAGAG": 948,
994
- "UGAUGCAGCGACGCC": 949,
995
- "UGUAGG": 950,
996
- "GCAUGG": 951,
997
- "AGAAAGCCAC": 952,
998
- "UGGAUU": 953,
999
- "UUGCAGAA": 954,
1000
- "UUUCCC": 955,
1001
- "UGUUAA": 956,
1002
- "UUGAAG": 957,
1003
- "UCAACCG": 958,
1004
- "UGGUAG": 959,
1005
- "GGCUAACUACGUGCCAGCAGCCGCGGUAAUACGUAGG": 960,
1006
- "GAAAGG": 961,
1007
- "UGAGGAA": 962,
1008
- "UUACCAAGGC": 963,
1009
- "UGUAGCAGUGAA": 964,
1010
- "UAGCCGGCCUGAGAGGG": 965,
1011
- "UGGUAC": 966,
1012
- "UCGCGGAUCAGC": 967,
1013
- "GGAAACG": 968,
1014
- "UGUGUGAAGAAGGCC": 969,
1015
- "GGCCACAUUGGGAC": 970,
1016
- "AUCUCC": 971,
1017
- "AGGGCGCG": 972,
1018
- "UGUGGG": 973,
1019
- "UAACGC": 974,
1020
- "ACCUCC": 975,
1021
- "GGGCCUUGUACACACCGCCCGUCACACCAUGGG": 976,
1022
- "UUUCAA": 977,
1023
- "UGGUCGG": 978,
1024
- "AGGGAC": 979,
1025
- "UAGGCG": 980,
1026
- "UGUAAG": 981,
1027
- "UGGAGGAA": 982,
1028
- "UUGACGGUACC": 983,
1029
- "AGUGAGGAAUAUUGGUCAA": 984,
1030
- "UGACAA": 985,
1031
- "AUUUUC": 986,
1032
- "AGGUGGUGCAUGGUUGUCGUCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA": 987,
1033
- "AGCACC": 988,
1034
- "AGAACC": 989,
1035
- "AUGAAGUCGGAAUCGCUAGUAA": 990,
1036
- "GGUCC": 991,
1037
- "AGUGAC": 992,
1038
- "AGAGCC": 993,
1039
- "UGCUC": 994,
1040
- "ACAUG": 995,
1041
- "UAUGCC": 996,
1042
- "AUUAGCUAG": 997,
1043
- "UCAACCC": 998,
1044
- "AUAUAC": 999,
1045
- "UAAACC": 1000,
1046
- "AUAUCC": 1001,
1047
- "UUAUUC": 1002,
1048
- "UACAGAGGG": 1003,
1049
- "UUCGAA": 1004,
1050
- "UUGAAC": 1005,
1051
- "AGUAAC": 1006,
1052
- "AGCGGC": 1007,
1053
- "UCCUCC": 1008,
1054
- "AGCUCG": 1009,
1055
- "UUCGAAGCAACGCGAAGAACCUUACC": 1010,
1056
- "UAUCCC": 1011,
1057
- "GCGUUGUCCGGAA": 1012,
1058
- "UGGCCC": 1013,
1059
- "AGUACG": 1014,
1060
- "ACGGCCUUCGGGUUGUAA": 1015,
1061
- "AAGACC": 1016,
1062
- "UAUUGGGCGUAA": 1017,
1063
- "AAGAA": 1018,
1064
- "UUUAAG": 1019,
1065
- "UUCGGAAUUACUGGGCGUAA": 1020,
1066
- "UGAGAUAC": 1021,
1067
- "UCUUGC": 1022,
1068
- "AGUUAA": 1023
1069
- },
1070
- "merges": [
1071
- "G G",
1072
- "A A",
1073
- "U U",
1074
- "C C",
1075
- "A G",
1076
- "U G",
1077
- "A C",
1078
- "U C",
1079
- "U GG",
1080
- "G C",
1081
- "A GG",
1082
- "U AA",
1083
- "AG C",
1084
- "A UU",
1085
- "A CC",
1086
- "A UG",
1087
- "U CC",
1088
- "G AA",
1089
- "U AC",
1090
- "UG C",
1091
- "A UC",
1092
- "U AG",
1093
- "UU C",
1094
- "AA C",
1095
- "GG C",
1096
- "UU G",
1097
- "AA G",
1098
- "GG G",
1099
- "CC C",
1100
- "A U",
1101
- "UG AA",
1102
- "AC G",
1103
- "A UGG",
1104
- "UAA C",
1105
- "GC G",
1106
- "UC G",
1107
- "AGG C",
1108
- "UG AG",
1109
- "UGG C",
1110
- "AUG C",
1111
- "AG CC",
1112
- "UG CC",
1113
- "A UCC",
1114
- "GG AA",
1115
- "A UAA",
1116
- "U ACC",
1117
- "UU UU",
1118
- "AC GG",
1119
- "AGG G",
1120
- "U AUU",
1121
- "AG AA",
1122
- "UU GG",
1123
- "G CC",
1124
- "U AGC",
1125
- "UC AA",
1126
- "UU AA",
1127
- "GAA C",
1128
- "AC AA",
1129
- "U AGG",
1130
- "UGG G",
1131
- "ACC C",
1132
- "UGG GG",
1133
- "UG AC",
1134
- "A UAC",
1135
- "GC GG",
1136
- "AGG AA",
1137
- "UU CC",
1138
- "AGC G",
1139
- "UCC C",
1140
- "GC AA",
1141
- "AG AC",
1142
- "GG CC",
1143
- "AUU C",
1144
- "UU UC",
1145
- "UU GC",
1146
- "AA AA",
1147
- "AG AG",
1148
- "CC G",
1149
- "UAC G",
1150
- "AC AC",
1151
- "A UAG",
1152
- "GG GG",
1153
- "UG UC",
1154
- "UAA G",
1155
- "U AUC",
1156
- "UU UG",
1157
- "AG UC",
1158
- "AUU G",
1159
- "GGC G",
1160
- "AA AC",
1161
- "AAG UC",
1162
- "AUG AA",
1163
- "UG UG",
1164
- "UC UC",
1165
- "UGG AA",
1166
- "ACC G",
1167
- "AG UG",
1168
- "UGG GC",
1169
- "UU AC",
1170
- "UC GC",
1171
- "UUC GG",
1172
- "UGC G",
1173
- "U AUG",
1174
- "UUC G",
1175
- "UU UAA",
1176
- "UC GG",
1177
- "UU AG",
1178
- "UC UG",
1179
- "UCC G",
1180
- "AAC G",
1181
- "GAA G",
1182
- "AG UGG",
1183
- "UC AC",
1184
- "A UAAC",
1185
- "UG AGG",
1186
- "AUGG C",
1187
- "AG AGG",
1188
- "AG AU",
1189
- "AUG CC",
1190
- "ACC AA",
1191
- "U AGGC",
1192
- "GG GC",
1193
- "AUU AA",
1194
- "GG UGAA",
1195
- "UAC GGG",
1196
- "AUC G",
1197
- "AAG CC",
1198
- "UU GAA",
1199
- "U AU",
1200
- "UAC AC",
1201
- "GC GAA",
1202
- "CC UU",
1203
- "CCC G",
1204
- "AUGC G",
1205
- "AC UC",
1206
- "UG UU",
1207
- "GGC UAAC",
1208
- "AA GG",
1209
- "UC AG",
1210
- "AC GC",
1211
- "UG UAGC",
1212
- "UGAC GC",
1213
- "UGAG AC",
1214
- "UU CCC",
1215
- "GCG UAA",
1216
- "AGC AGCC",
1217
- "AUGG G",
1218
- "AGGC AGC",
1219
- "AG UGGC",
1220
- "AGG GC",
1221
- "UAC AA",
1222
- "UC AGC",
1223
- "AUU GG",
1224
- "GAA GGC",
1225
- "GCGG UAA",
1226
- "AC GAA",
1227
- "UU AAG",
1228
- "UGCC AGCAGCC",
1229
- "CC CC",
1230
- "UG UCG",
1231
- "UU GGG",
1232
- "UGC AA",
1233
- "AGC AA",
1234
- "AUCC C",
1235
- "UACGGG AGGCAGC",
1236
- "AC GGG",
1237
- "UU AAC",
1238
- "UUC GGG",
1239
- "AC UG",
1240
- "UUG CC",
1241
- "ACC GG",
1242
- "UAG AG",
1243
- "UUG UAA",
1244
- "UAG UCC",
1245
- "AGG AUU",
1246
- "UAA GG",
1247
- "UGCCAGCAGCC GCGGUAA",
1248
- "UCC UACGGGAGGCAGC",
1249
- "AGG GG",
1250
- "GC ACAA",
1251
- "AU AUU",
1252
- "AU AUC",
1253
- "AG UU",
1254
- "UAA UACC",
1255
- "UAA AA",
1256
- "UAC GG",
1257
- "AGG AAC",
1258
- "UG CCC",
1259
- "UUG AC",
1260
- "GAA GC",
1261
- "UGG CC",
1262
- "UC UU",
1263
- "U AGGG",
1264
- "AG CCC",
1265
- "UGAGAC ACGG",
1266
- "AUU AGC",
1267
- "AUAA G",
1268
- "GC UGGC",
1269
- "AGG CC",
1270
- "AC UU",
1271
- "AGCG UGGGG",
1272
- "AGC AAAC",
1273
- "ACC CC",
1274
- "AGGAA GG",
1275
- "UAA CC",
1276
- "UUG ACGG",
1277
- "AGGAUU AGAU",
1278
- "AC AG",
1279
- "AGAC UCCUACGGGAGGCAGC",
1280
- "UGG UC",
1281
- "GGC GG",
1282
- "GC GC",
1283
- "UACC C",
1284
- "UGG AGC",
1285
- "AUG UGG",
1286
- "AGUGG GGAA",
1287
- "UGUAGC GGUGAA",
1288
- "GGG CC",
1289
- "UAG UAA",
1290
- "UCC GG",
1291
- "N N",
1292
- "Ġ G",
1293
- "UG AAG",
1294
- "UAG CC",
1295
- "AC AUGC",
1296
- "UC AAC",
1297
- "AG UAC",
1298
- "AGG AUG",
1299
- "AGGAUUAGAU ACCC",
1300
- "AG UGC",
1301
- "U AUGG",
1302
- "ACG CC",
1303
- "UAG UUGG",
1304
- "UG UAA",
1305
- "AA CC",
1306
- "AC UGC",
1307
- "UAUU GG",
1308
- "UGG GCGUAA",
1309
- "UU UUC",
1310
- "UGAG UAAC",
1311
- "UGC UGC",
1312
- "UAG AA",
1313
- "AUU CC",
1314
- "UAA GC",
1315
- "U AUAA",
1316
- "ACG UC",
1317
- "AA GC",
1318
- "AG AAG",
1319
- "AGC GCAA",
1320
- "UG ACGG",
1321
- "AGC GC",
1322
- "UU UUG",
1323
- "UGC AAC",
1324
- "GG UG",
1325
- "UCAGC UCG",
1326
- "UGG UAGUCC",
1327
- "UU UCC",
1328
- "AGC GG",
1329
- "AG AAC",
1330
- "UG AAC",
1331
- "UGG AAC",
1332
- "UUC AA",
1333
- "AG AUU",
1334
- "AC UCC",
1335
- "AG AUG",
1336
- "UU AUU",
1337
- "UGG GAA",
1338
- "AG AGC",
1339
- "AUC AA",
1340
- "GGCUAAC UACG",
1341
- "AGC AAC",
1342
- "AGCGUGGGG AGCAAAC",
1343
- "AGGAUUAGAUACCC UGGUAGUCC",
1344
- "AC AUU",
1345
- "UAA ACG",
1346
- "UG AGGC",
1347
- "UG UGAA",
1348
- "GAA GG",
1349
- "AUGCG UAG",
1350
- "UU GGC",
1351
- "UAGG GG",
1352
- "AG UGAA",
1353
- "AGG GAA",
1354
- "UG AUC",
1355
- "UGGG AC",
1356
- "UUAAG UCCC",
1357
- "ACCG CCCG",
1358
- "GAAC GCUGGC",
1359
- "AAGUC GAAC",
1360
- "AGC GAA",
1361
- "AGC UC",
1362
- "UCAA AGGAA",
1363
- "UCAA CC",
1364
- "GCC UGGGG",
1365
- "CCC UU",
1366
- "UCC CC",
1367
- "UGCC G",
1368
- "UG AUCC",
1369
- "UGAG AUG",
1370
- "UU ACC",
1371
- "AGACUCCUACGGGAGGCAGC AGUGGGGAA",
1372
- "UCG CC",
1373
- "GGG AC",
1374
- "AGGC G",
1375
- "AGGAAGG UGGGG",
1376
- "GGG CCC",
1377
- "UAUU C",
1378
- "UACG UUCCC",
1379
- "UCAAAGGAA UUGACGG",
1380
- "AU ACC",
1381
- "UGAGACACGG CCC",
1382
- "AU AGC",
1383
- "UC AUU",
1384
- "UACAC ACCGCCCG",
1385
- "UC GAA",
1386
- "AU AGG",
1387
- "AUC GG",
1388
- "UU UGG",
1389
- "UG AUGC",
1390
- "UGC GAA",
1391
- "UAG AGG",
1392
- "GCACAA GCGG",
1393
- "AAG UCG",
1394
- "UGGC G",
1395
- "UC GGAA",
1396
- "GGCG ACG",
1397
- "UG AUG",
1398
- "UAGC G",
1399
- "AUAC G",
1400
- "AACG AGCGCAA",
1401
- "UCAGCUCG UGUCG",
1402
- "CCUU ACC",
1403
- "UUGGG UUAAGUCCC",
1404
- "ACG UGC",
1405
- "AC UGG",
1406
- "AG UAA",
1407
- "GCAA GG",
1408
- "UG UGG",
1409
- "UCAGCUCGUGUCG UGAGAUG",
1410
- "U AUCC",
1411
- "AG UUC",
1412
- "AG ACC",
1413
- "ACC AGUGGC",
1414
- "AU AUG",
1415
- "UC AGG",
1416
- "UC UUC",
1417
- "GC AACGAGCGCAA",
1418
- "UUAC UGGGCGUAA",
1419
- "UG AUU",
1420
- "UU AUCC",
1421
- "UG ACC",
1422
- "UC AUC",
1423
- "U AUGC",
1424
- "UAG UC",
1425
- "GCC G",
1426
- "AUC AGC",
1427
- "AUUC G",
1428
- "UAAUACC GC",
1429
- "UGG GGG",
1430
- "AAC GCGAA",
1431
- "AC AGG",
1432
- "UGC GG",
1433
- "GGCUAAC UCCG",
1434
- "AUGUGG UUUAA",
1435
- "AGGAAGGUGGGG AUG",
1436
- "GCC GCG",
1437
- "UCGC UAGUAA",
1438
- "UGAA AC",
1439
- "AC GGC",
1440
- "UUG UACACACCGCCCG",
1441
- "UGGAA UUCC",
1442
- "UCAGCUCGUGUCGUGAGAUG UUGGGUUAAGUCCC",
1443
- "GAA AGCC",
1444
- "AUU GC",
1445
- "UGGUC UGAG",
1446
- "UC GGC",
1447
- "UCC AA",
1448
- "AUUAGC UAGUUGG",
1449
- "UAGGC GG",
1450
- "AG UUG",
1451
- "GAAC GGG",
1452
- "UC ACC",
1453
- "UAA AAC",
1454
- "UC UGG",
1455
- "UAUU G",
1456
- "UUCGGG UUGUAA",
1457
- "AC UUC",
1458
- "ACGUGC UACAA",
1459
- "GAA AA",
1460
- "Ġ C",
1461
- "UC UGC",
1462
- "UU UGC",
1463
- "UACC G",
1464
- "UGCAAC UCG",
1465
- "AUGGC UGUCG",
1466
- "UUG UUGG",
1467
- "UG UGC",
1468
- "AACGCGAA GAA",
1469
- "UG UUC",
1470
- "AG AGGG",
1471
- "AUCC G",
1472
- "GCG UUG",
1473
- "AAC AA",
1474
- "UU GGAA",
1475
- "AU AU",
1476
- "UC UCC",
1477
- "AG AUC",
1478
- "ACG CCG",
1479
- "UUAA CC",
1480
- "AGGC GG",
1481
- "ACAUGC AAGUCGAAC",
1482
- "UGG UGC",
1483
- "UAA UAC",
1484
- "UACC AA",
1485
- "GG CCC",
1486
- "AGC AC",
1487
- "UGAA CC",
1488
- "ACAC UGGGAC",
1489
- "AUC AGG",
1490
- "UGAGUAAC ACG",
1491
- "GCG UG",
1492
- "U AUAC",
1493
- "UUG UC",
1494
- "GAA UC",
1495
- "UU AGC",
1496
- "UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCC GCAACGAGCGCAA",
1497
- "AGCAAC GCCGCG",
1498
- "AG UAGG",
1499
- "UAAC G",
1500
- "GCACAAGCGG UGGAGC",
1501
- "UU UAG",
1502
- "AGG GGG",
1503
- "UACAC ACGUGCUACAA",
1504
- "GGC GC",
1505
- "UGAG AGGG",
1506
- "UGC GC",
1507
- "AGCC G",
1508
- "UGAA UACGUUCCC",
1509
- "UU UAC",
1510
- "NN NN",
1511
- "GGCUAACUCCG UGCCAGCAGCCGCGGUAA",
1512
- "AUGG AA",
1513
- "UGGGC GC",
1514
- "UGGGC GAAAGCC",
1515
- "U AUAG",
1516
- "GAA GGCC",
1517
- "GGC AGC",
1518
- "AUC GC",
1519
- "UG UUG",
1520
- "ACCC G",
1521
- "GGCUAACUACG UGCCAGCAGCCGCGGUAA",
1522
- "AG UCC",
1523
- "AUC AGCC",
1524
- "UG UCC",
1525
- "UCAAAGGAAUUGACGG GGGCCC",
1526
- "UGACGC UGAGGC",
1527
- "UG AGC",
1528
- "UUCC G",
1529
- "AAG AC",
1530
- "GAAC G",
1531
- "AACGCGAAGAA CCUUACC",
1532
- "UGGC GAAGGC",
1533
- "AAC GC",
1534
- "GG AUU",
1535
- "ACACUGGGAC UGAGACACGGCCC",
1536
- "AGCC AUGCC",
1537
- "AUG AC",
1538
- "GCACAAGCGGUGGAGC AUGUGGUUUAA",
1539
- "GCG CC",
1540
- "UG AUGG",
1541
- "UGCUGC AUGGCUGUCG",
1542
- "AGG UC",
1543
- "AUG UC",
1544
- "GCC CC",
1545
- "UG ACG",
1546
- "GGGCC UUGUACACACCGCCCG",
1547
- "ACC UC",
1548
- "GG GGC",
1549
- "UCAC ACC",
1550
- "AUUGG GCGUAA",
1551
- "UAAC AAGG",
1552
- "UUAA AA",
1553
- "ACC GC",
1554
- "UGUAGCGGUGAA AUGCGUAG",
1555
- "UUGG GC",
1556
- "UAAC GGC",
1557
- "ACGCCG UAAACG",
1558
- "GAA AC",
1559
- "AGC UAAC",
1560
- "AUAA AA",
1561
- "AGCGUGGGGAGCAAAC AGGAUUAGAUACCCUGGUAGUCC",
1562
- "AGC GAAC",
1563
- "UCC UC",
1564
- "AGAA AA",
1565
- "UGAA GG",
1566
- "UAUU GCACAA",
1567
- "UGGGCGC AAGCC",
1568
- "UUUU GG",
1569
- "UGGUCUGAG AGGAUG",
1570
- "AUC AG",
1571
- "ACCAA GGCGACG",
1572
- "GAACGCUGGC GGC",
1573
- "GGCUAACUACGUGCCAGCAGCCGCGGUAA UACG",
1574
- "UGAGACACGG UCC",
1575
- "AGAA GC",
1576
- "UCCC G",
1577
- "UUC GGAA",
1578
- "ACGG CC",
1579
- "U AUGAA",
1580
- "UGACGC UGAGG",
1581
- "AUC AUU",
1582
- "ACCAGUGGC GAAGGC",
1583
- "ACCAA GGC",
1584
- "U A",
1585
- "UU UGAC",
1586
- "AC AAC",
1587
- "AUG UGAA",
1588
- "UGUAGCGGUGAA AUGC",
1589
- "UG UAG",
1590
- "UGG GAAC",
1591
- "AUC AUC",
1592
- "GGCC G",
1593
- "UAA UC",
1594
- "GGCUAACUCCGUGCCAGCAGCCGCGGUAA UACGG",
1595
- "UAA AGC",
1596
- "UGGC UC",
1597
- "AGAC UGCC",
1598
- "UG UAC",
1599
- "UUG AG",
1600
- "GG UC",
1601
- "ACAC UGGAAC",
1602
- "UAAUACC GG",
1603
- "UCC GGAA",
1604
- "UUAA UCGGAA",
1605
- "GCCUGGGG AGUAC",
1606
- "AUAA CC",
1607
- "AG UCG",
1608
- "AUGG GC",
1609
- "GGG UC",
1610
- "AG UUCGG",
1611
- "AGGAAGGUGGGGAUG ACGUC",
1612
- "UGAG AA",
1613
- "AUCC CC",
1614
- "GCGG UGAAUACGUUCCC",
1615
- "UGG AGG",
1616
- "AGAG UUUG",
1617
- "UGCAA GCG",
1618
- "UU UAUU",
1619
- "UGG AC",
1620
- "UGAG UAA",
1621
- "GAAGC ACC",
1622
- "AGCCAUGCC GCG",
1623
- "GGC AA",
1624
- "UUG UCG",
1625
- "UAUUGG ACAA",
1626
- "UUGG GG",
1627
- "AUC UC",
1628
- "GAA AGC",
1629
- "UGAA AA",
1630
- "AC AGC",
1631
- "UG AUGAA",
1632
- "GCCUGGGGAGUAC GGCC",
1633
- "GAA CC",
1634
- "UGG GCC",
1635
- "AG AGAA",
1636
- "AUGG GG",
1637
- "AGG CCC",
1638
- "AUAAC G",
1639
- "AUGCG UAGAG",
1640
- "GAA GGCG",
1641
- "UC GGG",
1642
- "UGGC AA",
1643
- "AGCC CC",
1644
- "UC GCGG",
1645
- "GG ACGGG",
1646
- "UCG UAACAAGG",
1647
- "AGC UUGC",
1648
- "UUUU AA",
1649
- "AGCG ACGCC",
1650
- "UUAAUCGGAA UUACUGGGCGUAA",
1651
- "GGAA GG",
1652
- "AC AUC",
1653
- "UGAGUAAC GCG",
1654
- "UU AUG",
1655
- "GCCUGGGG AG",
1656
- "UAG CCG",
1657
- "UGGGG UAA",
1658
- "UUCG AUGC",
1659
- "CCC UUG",
1660
- "CCC GG",
1661
- "UU UGAA",
1662
- "GCAA GGC",
1663
- "AUGG CCCUU",
1664
- "AUU UC",
1665
- "AGG AC",
1666
- "GAACGCUGGC GGCG",
1667
- "GGCGG ACGGG",
1668
- "UUAA GC",
1669
- "U AUGGG",
1670
- "UU AUC",
1671
- "AU AUUC",
1672
- "UGG AG",
1673
- "AAGUC AUC",
1674
- "UGG GGC",
1675
- "AGUC UGCAACUCG",
1676
- "ACCC GC",
1677
- "AG AUGG",
1678
- "GGAA UCGCUAGUAA",
1679
- "UUC UC",
1680
- "AUU AAG",
1681
- "ACG UCAA",
1682
- "CC AA",
1683
- "UUUU GC",
1684
- "UCAA AA",
1685
- "AUG AAG",
1686
- "AUG AAC",
1687
- "AG UAG",
1688
- "AC ACC",
1689
- "UGC UUAAC",
1690
- "ACACUGGAAC UGAGACACGGUCC",
1691
- "ACACUGGGACUGAGACACGGCCC AGACUCCUACGGGAGGCAGCAGUGGGGAA",
1692
- "AC UGGG",
1693
- "UAUC AGC",
1694
- "UGGUGC AUGG",
1695
- "ACAUGC AAGUCG",
1696
- "UAC GAA",
1697
- "UU AUUGGGCGUAA",
1698
- "CCC AA",
1699
- "AUG AUU",
1700
- "AAC GG",
1701
- "UU UCG",
1702
- "AC UUG",
1703
- "AGG AGG",
1704
- "AAAA AA",
1705
- "UUGAA AC",
1706
- "GGGCCUUGUACACACCGCCCG UCACACC",
1707
- "AGGG UGCG",
1708
- "UAAGC ACC",
1709
- "UGC GGC",
1710
- "UGGC GC",
1711
- "UGC AUU",
1712
- "UUUU CC",
1713
- "UCCC AA",
1714
- "UU AGG",
1715
- "AGCG UUG",
1716
- "UGAA GAAGGCC",
1717
- "UCC GC",
1718
- "UU UGGG",
1719
- "UUC GGGG",
1720
- "Ġ AGAGUUUG",
1721
- "UUAUCC GGAUU",
1722
- "UG UUGG",
1723
- "UAGG AA",
1724
- "UGAA GC",
1725
- "Ġ CC",
1726
- "UGC AC",
1727
- "AGUGGC GAACGGG",
1728
- "UAA AC",
1729
- "AC GAACGCUGGCGGCG",
1730
- "UU AAGUC",
1731
- "UGGGG GAA",
1732
- "AUU GAA",
1733
- "AGG UGCUGCAUGGCUGUCG",
1734
- "UAUC G",
1735
- "UUG ACC",
1736
- "UAUU CC",
1737
- "AGUG AGGAA",
1738
- "ACC ACC",
1739
- "UU GCG",
1740
- "ACAA AA",
1741
- "AGG AAG",
1742
- "UAU AUU",
1743
- "UAAUAC AUGC",
1744
- "ACAUU GGGAC",
1745
- "AUGCC CCUU",
1746
- "UGCC CC",
1747
- "AC UAC",
1748
- "AC AAG",
1749
- "GG GAA",
1750
- "AGAA GAAGCACC",
1751
- "UGC GGG",
1752
- "UUC AG",
1753
- "UAGCC GGCC",
1754
- "UUC GAAGC",
1755
- "AGCC AC",
1756
- "AGCAACGCCGCG UGAG",
1757
- "AUU GAACGCUGGCGGC",
1758
- "UAGC UGGUCUGAGAGGAUG",
1759
- "UU GCAA",
1760
- "AUG AAGUC",
1761
- "UAGAGG UGAA",
1762
- "UUGCC AGC",
1763
- "UUAA AAC",
1764
- "AC UAA",
1765
- "UGAG AGG",
1766
- "UC UUG",
1767
- "ACCGG UGGCGAAGGC",
1768
- "AGCC AA",
1769
- "Ġ UACG",
1770
- "AUG CCC",
1771
- "UAGG GC",
1772
- "ACGCCGUAAACG AUG",
1773
- "AG UUGG",
1774
- "UG AGGG",
1775
- "AUU UAA",
1776
- "UGACGG UACC",
1777
- "UC UAA",
1778
- "UGG GGAA",
1779
- "GG AC",
1780
- "UGG UGUAGCGGUGAAAUGC",
1781
- "UC AAG",
1782
- "AG UGGG",
1783
- "AUAC AA",
1784
- "GCUGGC GGCG",
1785
- "GG AG",
1786
- "UAAC ACAUGCAAGUCGAAC",
1787
- "GCG AGG",
1788
- "ACC UGAGAGGG",
1789
- "ACCAGUGGCGAAGGC GGC",
1790
- "UUUU UUUU",
1791
- "UCGC AAG",
1792
- "ACGG UACC",
1793
- "AUG UG",
1794
- "UAC GC",
1795
- "UGCC GC",
1796
- "AU AUAA",
1797
- "GCG UGAG",
1798
- "UAGC GAA",
1799
- "GGUG ACAA",
1800
- "AUU AUU",
1801
- "AG ACG",
1802
- "AA UAA",
1803
- "UCAAAGGAAUUGACGGGGGCCC GCACAAGCGGUGGAGCAUGUGGUUUAA",
1804
- "UUCGG AUUG",
1805
- "AGC UCC",
1806
- "UG UGGC",
1807
- "GGAA UUCC",
1808
- "AUUCG UAG",
1809
- "GG AAC",
1810
- "UGAC AC",
1811
- "UU AGGG",
1812
- "UAGGC GGC",
1813
- "AG UUUU",
1814
- "UGGGC UACACACGUGCUACAA",
1815
- "UGG UUC",
1816
- "ACGUCAA AUCAUC",
1817
- "UGAAG UCGUAACAAGG",
1818
- "AUCC AA",
1819
- "NNNN NNNN",
1820
- "AUC AC",
1821
- "GGGC UCAACC",
1822
- "UAAC GCG",
1823
- "AUG UCC",
1824
- "UUCGG AUCG",
1825
- "UGGGGGAA ACCC",
1826
- "GCC GG",
1827
- "AGGC AA",
1828
- "GGC UAA",
1829
- "UGAUC GGCC",
1830
- "UAGAGGUGAA AUUCGUAG",
1831
- "UG AUAC",
1832
- "AUG ACC",
1833
- "UGAG CC",
1834
- "UGAGG UAA",
1835
- "UC UAC",
1836
- "UGACGCUGAGGC GCGAA",
1837
- "AUU UU",
1838
- "UC GCG",
1839
- "AGC AGG",
1840
- "AUU AG",
1841
- "UCC CCC",
1842
- "UC UGCC",
1843
- "UACCAA GGCGACG",
1844
- "GAA GAA",
1845
- "ĠAGAGUUUG AUCC",
1846
- "GGUGACAA ACCGG",
1847
- "GCAA UGGGCGAAAGCC",
1848
- "UGUAGCGGUGAA AUGCGUAGAG",
1849
- "AGG ACG",
1850
- "AC UGCC",
1851
- "AUGGC GAAGGC",
1852
- "UGG UG",
1853
- "AUGG CC",
1854
- "UC AUG",
1855
- "AGC AUC",
1856
- "GG GGG",
1857
- "AG ACGG",
1858
- "U AUAAC",
1859
- "AGCUAAC GC",
1860
- "U AUAAG",
1861
- "UUG UU",
1862
- "AUGC AA",
1863
- "UUGAC AUCC",
1864
- "AUUC AA",
1865
- "ĠG ACGAACGCUGGCGGCG",
1866
- "GGCUAACUACG UG",
1867
- "AGUGGC GGACGGG",
1868
- "UGGG UAGC",
1869
- "UGAUCC AGCCAUGCCGCG",
1870
- "UUC AC",
1871
- "AGG GGC",
1872
- "UAG AGC",
1873
- "ACC AGCC",
1874
- "GCCUGGGGAG UACGG",
1875
- "ACG CCC",
1876
- "UGCUUAAC ACAUGCAAGUCGAAC",
1877
- "UGGUGCAUGG UUGUCG",
1878
- "UAAC GG",
1879
- "UAAUACCGC AUACG",
1880
- "UGUAGCGGUGAAAUGCGUAG AUAUC",
1881
- "AGCC GCC",
1882
- "GCCUGGGGAGUACGGCC GCAAGG",
1883
- "GGGG GC",
1884
- "UG UGAC",
1885
- "AUU UAC",
1886
- "AGAA GAA",
1887
- "UAUU GC",
1888
- "UUCGAUGC AACGCGAAGAACCUUACC",
1889
- "GGUGAA UACGUUCCC",
1890
- "UAGC AA",
1891
- "ACG UU",
1892
- "UAUUGG UCAA",
1893
- "AU AUGC",
1894
- "AUAG CC",
1895
- "UG UUUU",
1896
- "GGG UUUAA",
1897
- "AGCAA UGCC",
1898
- "UACC CC",
1899
- "UAGG UGG",
1900
- "AGC AUU",
1901
- "AUGAA GC",
1902
- "AGGC GC",
1903
- "UGCC GG",
1904
- "AAGUCAUC AUGGCCCUU",
1905
- "UGCC UAAUACAUGC",
1906
- "CCC GCG",
1907
- "AGCGUGGGGAGCAAAC AGG",
1908
- "ACCAGUGGC GAAGGCG",
1909
- "UGCAAGCG UUAAUCGGAAUUACUGGGCGUAA",
1910
- "UGG UAA",
1911
- "UU UGGC",
1912
- "UAGUCC GG",
1913
- "UACC GG",
1914
- "UG AAGUC",
1915
- "UCAA GC",
1916
- "AGCGUGGGG AGCGAAC",
1917
- "UCG AUG",
1918
- "UAA GAA",
1919
- "U AUGGC",
1920
- "AGCC GG",
1921
- "UGG UGG",
1922
- "ACCC AA",
1923
- "ACC AC",
1924
- "CCC GC",
1925
- "AGAA GG",
1926
- "UUC UUC",
1927
- "GG ACCC",
1928
- "AGG UAG",
1929
- "AG AGGAA",
1930
- "UUC GGC",
1931
- "UCUC AGUUCGG",
1932
- "AUUAA GC",
1933
- "UAC GGGG",
1934
- "UGC UCC",
1935
- "GC AGAU",
1936
- "AGACUCCUACGGGAGGCAGC AGUAGG",
1937
- "AGC UAA",
1938
- "AUCAGG AGGAAC",
1939
- "AUU AC",
1940
- "UC UAG",
1941
- "UAUU AA",
1942
- "AGG UGGUGCAUGGUUGUCG",
1943
- "AGG AGGAAC",
1944
- "ACGUCAAAUCAUC AUGCCCCUU",
1945
- "GCGG CC",
1946
- "UGG AUG",
1947
- "AUU AGAU",
1948
- "UGC AGC",
1949
- "UU UGAG",
1950
- "UGAA GAAGG",
1951
- "UAA UAA",
1952
- "UU UGUC",
1953
- "UGAGG UAACGGC",
1954
- "AUAG AA",
1955
- "AAC UC",
1956
- "UGG GCG",
1957
- "AG UUUC",
1958
- "AUG UUC",
1959
- "UGG ACC",
1960
- "UUCC CC",
1961
- "AG UUGC",
1962
- "UGAA AGCCC",
1963
- "UGC AGG",
1964
- "AAG UCCUC",
1965
- "UG ACCG",
1966
- "UGG AUC",
1967
- "AAG AGG",
1968
- "AUU GCGAA",
1969
- "ACG AUG",
1970
- "UGG AAAC",
1971
- "AUAA GC",
1972
- "GG UGGAA",
1973
- "UGACGCUGAGG AGCGAA",
1974
- "GAAC GC",
1975
- "GAAUC UUCC",
1976
- "UUC GC",
1977
- "ACCUGAGAGGG UGAUCGGCC",
1978
- "ACACUGGAACUGAGACACGGUCC AGACUCCUACGGGAGGCAGCAGUGGGGAA",
1979
- "GGCUAAC UUCG",
1980
- "AG AGAC",
1981
- "AG AGGC",
1982
- "UAC UC",
1983
- "UAAC GGCCC",
1984
- "UUG AGUGC",
1985
- "AAC AC",
1986
- "AG UGCC",
1987
- "AGCGC GCG",
1988
- "UG UGCC",
1989
- "AGC AGC",
1990
- "ACCC GAA",
1991
- "ACAA CC",
1992
- "GGG AGGAAC",
1993
- "ACC UGGGG",
1994
- "ACGAA AGUC",
1995
- "UC AUGC",
1996
- "ACGG GG",
1997
- "AU AUGG",
1998
- "UC UUUU",
1999
- "GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGG AGGG",
2000
- "UU AGAG",
2001
- "UGAUGC AGCGACGCC",
2002
- "UG UAGG",
2003
- "GC AUGG",
2004
- "AGAA AGCCAC",
2005
- "UGG AUU",
2006
- "UUGC AGAA",
2007
- "UU UCCC",
2008
- "UG UUAA",
2009
- "UU GAAG",
2010
- "UCAA CCG",
2011
- "UGG UAG",
2012
- "GGCUAACUACGUGCCAGCAGCCGCGGUAAUACG UAGG",
2013
- "GAA AGG",
2014
- "UG AGGAA",
2015
- "UU ACCAAGGC",
2016
- "UGUAGC AGUGAA",
2017
- "UAGCCGGCC UGAGAGGG",
2018
- "UGG UAC",
2019
- "UCGCGG AUCAGC",
2020
- "GGAA ACG",
2021
- "UGUG UGAAGAAGGCC",
2022
- "GGCC ACAUUGGGAC",
2023
- "AUC UCC",
2024
- "AGGGC GCG",
2025
- "UG UGGG",
2026
- "UAAC GC",
2027
- "ACC UCC",
2028
- "GGGCCUUGUACACACCGCCCGUCACACC AUGGG",
2029
- "UU UCAA",
2030
- "UGG UCGG",
2031
- "AGGG AC",
2032
- "UAGGC G",
2033
- "UG UAAG",
2034
- "UGG AGGAA",
2035
- "UUGACGG UACC",
2036
- "AGUGAGGAA UAUUGGUCAA",
2037
- "UG ACAA",
2038
- "AUU UUC",
2039
- "AGGUGGUGCAUGGUUGUCG UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA",
2040
- "AGC ACC",
2041
- "AGAA CC",
2042
- "AUGAAGUC GGAAUCGCUAGUAA",
2043
- "GG UCC",
2044
- "AG UGAC",
2045
- "AG AGCC",
2046
- "UGC UC",
2047
- "AC AUG",
2048
- "UAUG CC",
2049
- "AUUAGC UAG",
2050
- "UCAA CCC",
2051
- "AU AUAC",
2052
- "UAA ACC",
2053
- "AU AUCC",
2054
- "UU AUUC",
2055
- "UAC AGAGGG",
2056
- "UUC GAA",
2057
- "UU GAAC",
2058
- "AG UAAC",
2059
- "AGC GGC",
2060
- "UCC UCC",
2061
- "AGC UCG",
2062
- "UUCGAAGC AACGCGAAGAACCUUACC",
2063
- "U AUCCC",
2064
- "GCGUUG UCCGGAA",
2065
- "UGG CCC",
2066
- "AG UACG",
2067
- "ACGGCC UUCGGGUUGUAA",
2068
- "AAG ACC",
2069
- "UAUUGG GCGUAA",
2070
- "AA GAA",
2071
- "UU UAAG",
2072
- "UUCGGAA UUACUGGGCGUAA",
2073
- "UGAG AUAC",
2074
- "UC UUGC",
2075
- "AG UUAA"
2076
- ]
2077
- }
2078
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/tokenizer_config.json DELETED
@@ -1,18 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- }
12
- },
13
- "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": true,
15
- "eos_token": "<|endoftext|>",
16
- "model_max_length": 1024,
17
- "tokenizer_class": "GPT2Tokenizer"
18
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/vocab.json DELETED
@@ -1 +0,0 @@
1
- {"<|endoftext|>":0,"A":1,"B":2,"C":3,"D":4,"G":5,"H":6,"K":7,"M":8,"N":9,"R":10,"S":11,"U":12,"V":13,"W":14,"X":15,"Y":16,"Ċ":17,"Ġ":18,"GG":19,"AA":20,"UU":21,"CC":22,"AG":23,"UG":24,"AC":25,"UC":26,"UGG":27,"GC":28,"AGG":29,"UAA":30,"AGC":31,"AUU":32,"ACC":33,"AUG":34,"UCC":35,"GAA":36,"UAC":37,"UGC":38,"AUC":39,"UAG":40,"UUC":41,"AAC":42,"GGC":43,"UUG":44,"AAG":45,"GGG":46,"CCC":47,"AU":48,"UGAA":49,"ACG":50,"AUGG":51,"UAAC":52,"GCG":53,"UCG":54,"AGGC":55,"UGAG":56,"UGGC":57,"AUGC":58,"AGCC":59,"UGCC":60,"AUCC":61,"GGAA":62,"AUAA":63,"UACC":64,"UUUU":65,"ACGG":66,"AGGG":67,"UAUU":68,"AGAA":69,"UUGG":70,"GCC":71,"UAGC":72,"UCAA":73,"UUAA":74,"GAAC":75,"ACAA":76,"UAGG":77,"UGGG":78,"ACCC":79,"UGGGG":80,"UGAC":81,"AUAC":82,"GCGG":83,"AGGAA":84,"UUCC":85,"AGCG":86,"UCCC":87,"GCAA":88,"AGAC":89,"GGCC":90,"AUUC":91,"UUUC":92,"UUGC":93,"AAAA":94,"AGAG":95,"CCG":96,"UACG":97,"ACAC":98,"AUAG":99,"GGGG":100,"UGUC":101,"UAAG":102,"UAUC":103,"UUUG":104,"AGUC":105,"AUUG":106,"GGCG":107,"AAAC":108,"AAGUC":109,"AUGAA":110,"UGUG":111,"UCUC":112,"UGGAA":113,"ACCG":114,"AGUG":115,"UGGGC":116,"UUAC":117,"UCGC":118,"UUCGG":119,"UGCG":120,"UAUG":121,"UUCG":122,"UUUAA":123,"UCGG":124,"UUAG":125,"UCUG":126,"UCCG":127,"AACG":128,"GAAG":129,"AGUGG":130,"UCAC":131,"AUAAC":132,"UGAGG":133,"AUGGC":134,"AGAGG":135,"AGAU":136,"AUGCC":137,"ACCAA":138,"UAGGC":139,"GGGC":140,"AUUAA":141,"GGUGAA":142,"UACGGG":143,"AUCG":144,"AAGCC":145,"UUGAA":146,"UAU":147,"UACAC":148,"GCGAA":149,"CCUU":150,"CCCG":151,"AUGCG":152,"ACUC":153,"UGUU":154,"GGCUAAC":155,"AAGG":156,"UCAG":157,"ACGC":158,"UGUAGC":159,"UGACGC":160,"UGAGAC":161,"UUCCC":162,"GCGUAA":163,"AGCAGCC":164,"AUGGG":165,"AGGCAGC":166,"AGUGGC":167,"AGGGC":168,"UACAA":169,"UCAGC":170,"AUUGG":171,"GAAGGC":172,"GCGGUAA":173,"ACGAA":174,"UUAAG":175,"UGCCAGCAGCC":176,"CCCC":177,"UGUCG":178,"UUGGG":179,"UGCAA":180,"AGCAA":181,"AUCCC":182,"UACGGGAGGCAGC":183,"ACGGG":184,"UUAAC":185,"UUCGGG":186,"ACUG":187,"UUGCC":188,"ACCGG":189,"UAGAG":190,"UUGUAA":191,"UAGUCC":192,"AGGAUU":193,"UAAGG":194,"UGCCAGCAGCCGCGGUAA":195,"UCCUACGGGAGGCAGC":196,"AGGGG":197,"GCACAA":198,"AUAUU":199,"AUAUC":200,"AGUU":201,"UAAUACC":202,"UAAAA":203,"UACGG":204,"AGGAAC":205,"UGCCC":206,"UUGAC":207,"GAAGC":208,"UGGCC":209,"UCUU":210,"UAGGG":211,"AGCCC":212,"UGAGACACGG":213,"AUUAGC":214,"AUAAG":215,"GCUGGC":216,"AGGCC":217,"ACUU":218,"AGCGUGGGG":219,"AGCAAAC":220,"ACCCC":221,"AGGAAGG":222,"UAACC":223,"UUGACGG":224,"AGGAUUAGAU":225,"ACAG":226,"AGACUCCUACGGGAGGCAGC":227,"UGGUC":228,"GGCGG":229,"GCGC":230,"UACCC":231,"UGGAGC":232,"AUGUGG":233,"AGUGGGGAA":234,"UGUAGCGGUGAA":235,"GGGCC":236,"UAGUAA":237,"UCCGG":238,"NN":239,"ĠG":240,"UGAAG":241,"UAGCC":242,"ACAUGC":243,"UCAAC":244,"AGUAC":245,"AGGAUG":246,"AGGAUUAGAUACCC":247,"AGUGC":248,"UAUGG":249,"ACGCC":250,"UAGUUGG":251,"UGUAA":252,"AACC":253,"ACUGC":254,"UAUUGG":255,"UGGGCGUAA":256,"UUUUC":257,"UGAGUAAC":258,"UGCUGC":259,"UAGAA":260,"AUUCC":261,"UAAGC":262,"UAUAA":263,"ACGUC":264,"AAGC":265,"AGAAG":266,"AGCGCAA":267,"UGACGG":268,"AGCGC":269,"UUUUG":270,"UGCAAC":271,"GGUG":272,"UCAGCUCG":273,"UGGUAGUCC":274,"UUUCC":275,"AGCGG":276,"AGAAC":277,"UGAAC":278,"UGGAAC":279,"UUCAA":280,"AGAUU":281,"ACUCC":282,"AGAUG":283,"UUAUU":284,"UGGGAA":285,"AGAGC":286,"AUCAA":287,"GGCUAACUACG":288,"AGCAAC":289,"AGCGUGGGGAGCAAAC":290,"AGGAUUAGAUACCCUGGUAGUCC":291,"ACAUU":292,"UAAACG":293,"UGAGGC":294,"UGUGAA":295,"GAAGG":296,"AUGCGUAG":297,"UUGGC":298,"UAGGGG":299,"AGUGAA":300,"AGGGAA":301,"UGAUC":302,"UGGGAC":303,"UUAAGUCCC":304,"ACCGCCCG":305,"GAACGCUGGC":306,"AAGUCGAAC":307,"AGCGAA":308,"AGCUC":309,"UCAAAGGAA":310,"UCAACC":311,"GCCUGGGG":312,"CCCUU":313,"UCCCC":314,"UGCCG":315,"UGAUCC":316,"UGAGAUG":317,"UUACC":318,"AGACUCCUACGGGAGGCAGCAGUGGGGAA":319,"UCGCC":320,"GGGAC":321,"AGGCG":322,"AGGAAGGUGGGG":323,"GGGCCC":324,"UAUUC":325,"UACGUUCCC":326,"UCAAAGGAAUUGACGG":327,"AUACC":328,"UGAGACACGGCCC":329,"AUAGC":330,"UCAUU":331,"UACACACCGCCCG":332,"UCGAA":333,"AUAGG":334,"AUCGG":335,"UUUGG":336,"UGAUGC":337,"UGCGAA":338,"UAGAGG":339,"GCACAAGCGG":340,"AAGUCG":341,"UGGCG":342,"UCGGAA":343,"GGCGACG":344,"UGAUG":345,"UAGCG":346,"AUACG":347,"AACGAGCGCAA":348,"UCAGCUCGUGUCG":349,"CCUUACC":350,"UUGGGUUAAGUCCC":351,"ACGUGC":352,"ACUGG":353,"AGUAA":354,"GCAAGG":355,"UGUGG":356,"UCAGCUCGUGUCGUGAGAUG":357,"UAUCC":358,"AGUUC":359,"AGACC":360,"ACCAGUGGC":361,"AUAUG":362,"UCAGG":363,"UCUUC":364,"GCAACGAGCGCAA":365,"UUACUGGGCGUAA":366,"UGAUU":367,"UUAUCC":368,"UGACC":369,"UCAUC":370,"UAUGC":371,"UAGUC":372,"GCCG":373,"AUCAGC":374,"AUUCG":375,"UAAUACCGC":376,"UGGGGG":377,"AACGCGAA":378,"ACAGG":379,"UGCGG":380,"GGCUAACUCCG":381,"AUGUGGUUUAA":382,"AGGAAGGUGGGGAUG":383,"GCCGCG":384,"UCGCUAGUAA":385,"UGAAAC":386,"ACGGC":387,"UUGUACACACCGCCCG":388,"UGGAAUUCC":389,"UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCC":390,"GAAAGCC":391,"AUUGC":392,"UGGUCUGAG":393,"UCGGC":394,"UCCAA":395,"AUUAGCUAGUUGG":396,"UAGGCGG":397,"AGUUG":398,"GAACGGG":399,"UCACC":400,"UAAAAC":401,"UCUGG":402,"UAUUG":403,"UUCGGGUUGUAA":404,"ACUUC":405,"ACGUGCUACAA":406,"GAAAA":407,"ĠC":408,"UCUGC":409,"UUUGC":410,"UACCG":411,"UGCAACUCG":412,"AUGGCUGUCG":413,"UUGUUGG":414,"UGUGC":415,"AACGCGAAGAA":416,"UGUUC":417,"AGAGGG":418,"AUCCG":419,"GCGUUG":420,"AACAA":421,"UUGGAA":422,"AUAU":423,"UCUCC":424,"AGAUC":425,"ACGCCG":426,"UUAACC":427,"AGGCGG":428,"ACAUGCAAGUCGAAC":429,"UGGUGC":430,"UAAUAC":431,"UACCAA":432,"GGCCC":433,"AGCAC":434,"UGAACC":435,"ACACUGGGAC":436,"AUCAGG":437,"UGAGUAACACG":438,"GCGUG":439,"UAUAC":440,"UUGUC":441,"GAAUC":442,"UUAGC":443,"UCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA":444,"AGCAACGCCGCG":445,"AGUAGG":446,"UAACG":447,"GCACAAGCGGUGGAGC":448,"UUUAG":449,"AGGGGG":450,"UACACACGUGCUACAA":451,"GGCGC":452,"UGAGAGGG":453,"UGCGC":454,"AGCCG":455,"UGAAUACGUUCCC":456,"UUUAC":457,"NNNN":458,"GGCUAACUCCGUGCCAGCAGCCGCGGUAA":459,"AUGGAA":460,"UGGGCGC":461,"UGGGCGAAAGCC":462,"UAUAG":463,"GAAGGCC":464,"GGCAGC":465,"AUCGC":466,"UGUUG":467,"ACCCG":468,"GGCUAACUACGUGCCAGCAGCCGCGGUAA":469,"AGUCC":470,"AUCAGCC":471,"UGUCC":472,"UCAAAGGAAUUGACGGGGGCCC":473,"UGACGCUGAGGC":474,"UGAGC":475,"UUCCG":476,"AAGAC":477,"GAACG":478,"AACGCGAAGAACCUUACC":479,"UGGCGAAGGC":480,"AACGC":481,"GGAUU":482,"ACACUGGGACUGAGACACGGCCC":483,"AGCCAUGCC":484,"AUGAC":485,"GCACAAGCGGUGGAGCAUGUGGUUUAA":486,"GCGCC":487,"UGAUGG":488,"UGCUGCAUGGCUGUCG":489,"AGGUC":490,"AUGUC":491,"GCCCC":492,"UGACG":493,"GGGCCUUGUACACACCGCCCG":494,"ACCUC":495,"GGGGC":496,"UCACACC":497,"AUUGGGCGUAA":498,"UAACAAGG":499,"UUAAAA":500,"ACCGC":501,"UGUAGCGGUGAAAUGCGUAG":502,"UUGGGC":503,"UAACGGC":504,"ACGCCGUAAACG":505,"GAAAC":506,"AGCUAAC":507,"AUAAAA":508,"AGCGUGGGGAGCAAACAGGAUUAGAUACCCUGGUAGUCC":509,"AGCGAAC":510,"UCCUC":511,"AGAAAA":512,"UGAAGG":513,"UAUUGCACAA":514,"UGGGCGCAAGCC":515,"UUUUGG":516,"UGGUCUGAGAGGAUG":517,"AUCAG":518,"ACCAAGGCGACG":519,"GAACGCUGGCGGC":520,"GGCUAACUACGUGCCAGCAGCCGCGGUAAUACG":521,"UGAGACACGGUCC":522,"AGAAGC":523,"UCCCG":524,"UUCGGAA":525,"ACGGCC":526,"UAUGAA":527,"UGACGCUGAGG":528,"AUCAUU":529,"ACCAGUGGCGAAGGC":530,"ACCAAGGC":531,"UA":532,"UUUGAC":533,"ACAAC":534,"AUGUGAA":535,"UGUAGCGGUGAAAUGC":536,"UGUAG":537,"UGGGAAC":538,"AUCAUC":539,"GGCCG":540,"UAAUC":541,"GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGG":542,"UAAAGC":543,"UGGCUC":544,"AGACUGCC":545,"UGUAC":546,"UUGAG":547,"GGUC":548,"ACACUGGAAC":549,"UAAUACCGG":550,"UCCGGAA":551,"UUAAUCGGAA":552,"GCCUGGGGAGUAC":553,"AUAACC":554,"AGUCG":555,"AUGGGC":556,"GGGUC":557,"AGUUCGG":558,"AGGAAGGUGGGGAUGACGUC":559,"UGAGAA":560,"AUCCCC":561,"GCGGUGAAUACGUUCCC":562,"UGGAGG":563,"AGAGUUUG":564,"UGCAAGCG":565,"UUUAUU":566,"UGGAC":567,"UGAGUAA":568,"GAAGCACC":569,"AGCCAUGCCGCG":570,"GGCAA":571,"UUGUCG":572,"UAUUGGACAA":573,"UUGGGG":574,"AUCUC":575,"GAAAGC":576,"UGAAAA":577,"ACAGC":578,"UGAUGAA":579,"GCCUGGGGAGUACGGCC":580,"GAACC":581,"UGGGCC":582,"AGAGAA":583,"AUGGGG":584,"AGGCCC":585,"AUAACG":586,"AUGCGUAGAG":587,"GAAGGCG":588,"UCGGG":589,"UGGCAA":590,"AGCCCC":591,"UCGCGG":592,"GGACGGG":593,"UCGUAACAAGG":594,"AGCUUGC":595,"UUUUAA":596,"AGCGACGCC":597,"UUAAUCGGAAUUACUGGGCGUAA":598,"GGAAGG":599,"ACAUC":600,"UGAGUAACGCG":601,"UUAUG":602,"GCCUGGGGAG":603,"UAGCCG":604,"UGGGGUAA":605,"UUCGAUGC":606,"CCCUUG":607,"CCCGG":608,"UUUGAA":609,"GCAAGGC":610,"AUGGCCCUU":611,"AUUUC":612,"AGGAC":613,"GAACGCUGGCGGCG":614,"GGCGGACGGG":615,"UUAAGC":616,"UAUGGG":617,"UUAUC":618,"AUAUUC":619,"UGGAG":620,"AAGUCAUC":621,"UGGGGC":622,"AGUCUGCAACUCG":623,"ACCCGC":624,"AGAUGG":625,"GGAAUCGCUAGUAA":626,"UUCUC":627,"AUUAAG":628,"ACGUCAA":629,"CCAA":630,"UUUUGC":631,"UCAAAA":632,"AUGAAG":633,"AUGAAC":634,"AGUAG":635,"ACACC":636,"UGCUUAAC":637,"ACACUGGAACUGAGACACGGUCC":638,"ACACUGGGACUGAGACACGGCCCAGACUCCUACGGGAGGCAGCAGUGGGGAA":639,"ACUGGG":640,"UAUCAGC":641,"UGGUGCAUGG":642,"ACAUGCAAGUCG":643,"UACGAA":644,"UUAUUGGGCGUAA":645,"CCCAA":646,"AUGAUU":647,"AACGG":648,"UUUCG":649,"ACUUG":650,"AGGAGG":651,"AAAAAA":652,"UUGAAAC":653,"GGGCCUUGUACACACCGCCCGUCACACC":654,"AGGGUGCG":655,"UAAGCACC":656,"UGCGGC":657,"UGGCGC":658,"UGCAUU":659,"UUUUCC":660,"UCCCAA":661,"UUAGG":662,"AGCGUUG":663,"UGAAGAAGGCC":664,"UCCGC":665,"UUUGGG":666,"UUCGGGG":667,"ĠAGAGUUUG":668,"UUAUCCGGAUU":669,"UGUUGG":670,"UAGGAA":671,"UGAAGC":672,"ĠCC":673,"UGCAC":674,"AGUGGCGAACGGG":675,"UAAAC":676,"ACGAACGCUGGCGGCG":677,"UUAAGUC":678,"UGGGGGAA":679,"AUUGAA":680,"AGGUGCUGCAUGGCUGUCG":681,"UAUCG":682,"UUGACC":683,"UAUUCC":684,"AGUGAGGAA":685,"ACCACC":686,"UUGCG":687,"ACAAAA":688,"AGGAAG":689,"UAUAUU":690,"UAAUACAUGC":691,"ACAUUGGGAC":692,"AUGCCCCUU":693,"UGCCCC":694,"ACUAC":695,"ACAAG":696,"GGGAA":697,"AGAAGAAGCACC":698,"UGCGGG":699,"UUCAG":700,"UAGCCGGCC":701,"UUCGAAGC":702,"AGCCAC":703,"AGCAACGCCGCGUGAG":704,"AUUGAACGCUGGCGGC":705,"UAGCUGGUCUGAGAGGAUG":706,"UUGCAA":707,"AUGAAGUC":708,"UAGAGGUGAA":709,"UUGCCAGC":710,"UUAAAAC":711,"ACUAA":712,"UGAGAGG":713,"UCUUG":714,"ACCGGUGGCGAAGGC":715,"AGCCAA":716,"ĠUACG":717,"AUGCCC":718,"UAGGGC":719,"ACGCCGUAAACGAUG":720,"AGUUGG":721,"UGAGGG":722,"AUUUAA":723,"UGACGGUACC":724,"UCUAA":725,"UGGGGAA":726,"GGAC":727,"UGGUGUAGCGGUGAAAUGC":728,"UCAAG":729,"AGUGGG":730,"AUACAA":731,"GCUGGCGGCG":732,"GGAG":733,"UAACACAUGCAAGUCGAAC":734,"GCGAGG":735,"ACCUGAGAGGG":736,"ACCAGUGGCGAAGGCGGC":737,"UUUUUUUU":738,"UCGCAAG":739,"ACGGUACC":740,"AUGUG":741,"UACGC":742,"UGCCGC":743,"AUAUAA":744,"GCGUGAG":745,"UAGCGAA":746,"GGUGACAA":747,"AUUAUU":748,"AGACG":749,"AAUAA":750,"UCAAAGGAAUUGACGGGGGCCCGCACAAGCGGUGGAGCAUGUGGUUUAA":751,"UUCGGAUUG":752,"AGCUCC":753,"UGUGGC":754,"GGAAUUCC":755,"AUUCGUAG":756,"GGAAC":757,"UGACAC":758,"UUAGGG":759,"UAGGCGGC":760,"AGUUUU":761,"UGGGCUACACACGUGCUACAA":762,"UGGUUC":763,"ACGUCAAAUCAUC":764,"UGAAGUCGUAACAAGG":765,"AUCCAA":766,"NNNNNNNN":767,"AUCAC":768,"GGGCUCAACC":769,"UAACGCG":770,"AUGUCC":771,"UUCGGAUCG":772,"UGGGGGAAACCC":773,"GCCGG":774,"AGGCAA":775,"GGCUAA":776,"UGAUCGGCC":777,"UAGAGGUGAAAUUCGUAG":778,"UGAUAC":779,"AUGACC":780,"UGAGCC":781,"UGAGGUAA":782,"UCUAC":783,"UGACGCUGAGGCGCGAA":784,"AUUUU":785,"UCGCG":786,"AGCAGG":787,"AUUAG":788,"UCCCCC":789,"UCUGCC":790,"UACCAAGGCGACG":791,"GAAGAA":792,"ĠAGAGUUUGAUCC":793,"GGUGACAAACCGG":794,"GCAAUGGGCGAAAGCC":795,"UGUAGCGGUGAAAUGCGUAGAG":796,"AGGACG":797,"ACUGCC":798,"AUGGCGAAGGC":799,"UGGUG":800,"AUGGCC":801,"UCAUG":802,"AGCAUC":803,"GGGGG":804,"AGACGG":805,"UAUAAC":806,"AGCUAACGC":807,"UAUAAG":808,"UUGUU":809,"AUGCAA":810,"UUGACAUCC":811,"AUUCAA":812,"ĠGACGAACGCUGGCGGCG":813,"GGCUAACUACGUG":814,"AGUGGCGGACGGG":815,"UGGGUAGC":816,"UGAUCCAGCCAUGCCGCG":817,"UUCAC":818,"AGGGGC":819,"UAGAGC":820,"ACCAGCC":821,"GCCUGGGGAGUACGG":822,"ACGCCC":823,"UGCUUAACACAUGCAAGUCGAAC":824,"UGGUGCAUGGUUGUCG":825,"UAACGG":826,"UAAUACCGCAUACG":827,"UGUAGCGGUGAAAUGCGUAGAUAUC":828,"AGCCGCC":829,"GCCUGGGGAGUACGGCCGCAAGG":830,"GGGGGC":831,"UGUGAC":832,"AUUUAC":833,"AGAAGAA":834,"UAUUGC":835,"UUCGAUGCAACGCGAAGAACCUUACC":836,"GGUGAAUACGUUCCC":837,"UAGCAA":838,"ACGUU":839,"UAUUGGUCAA":840,"AUAUGC":841,"AUAGCC":842,"UGUUUU":843,"GGGUUUAA":844,"AGCAAUGCC":845,"UACCCC":846,"UAGGUGG":847,"AGCAUU":848,"AUGAAGC":849,"AGGCGC":850,"UGCCGG":851,"AAGUCAUCAUGGCCCUU":852,"UGCCUAAUACAUGC":853,"CCCGCG":854,"AGCGUGGGGAGCAAACAGG":855,"ACCAGUGGCGAAGGCG":856,"UGCAAGCGUUAAUCGGAAUUACUGGGCGUAA":857,"UGGUAA":858,"UUUGGC":859,"UAGUCCGG":860,"UACCGG":861,"UGAAGUC":862,"UCAAGC":863,"AGCGUGGGGAGCGAAC":864,"UCGAUG":865,"UAAGAA":866,"UAUGGC":867,"AGCCGG":868,"UGGUGG":869,"ACCCAA":870,"ACCAC":871,"CCCGC":872,"AGAAGG":873,"UUCUUC":874,"GGACCC":875,"AGGUAG":876,"AGAGGAA":877,"UUCGGC":878,"UCUCAGUUCGG":879,"AUUAAGC":880,"UACGGGG":881,"UGCUCC":882,"GCAGAU":883,"AGACUCCUACGGGAGGCAGCAGUAGG":884,"AGCUAA":885,"AUCAGGAGGAAC":886,"AUUAC":887,"UCUAG":888,"UAUUAA":889,"AGGUGGUGCAUGGUUGUCG":890,"AGGAGGAAC":891,"ACGUCAAAUCAUCAUGCCCCUU":892,"GCGGCC":893,"UGGAUG":894,"AUUAGAU":895,"UGCAGC":896,"UUUGAG":897,"UGAAGAAGG":898,"UAAUAA":899,"UUUGUC":900,"UGAGGUAACGGC":901,"AUAGAA":902,"AACUC":903,"UGGGCG":904,"AGUUUC":905,"AUGUUC":906,"UGGACC":907,"UUCCCC":908,"AGUUGC":909,"UGAAAGCCC":910,"UGCAGG":911,"AAGUCCUC":912,"UGACCG":913,"UGGAUC":914,"AAGAGG":915,"AUUGCGAA":916,"ACGAUG":917,"UGGAAAC":918,"AUAAGC":919,"GGUGGAA":920,"UGACGCUGAGGAGCGAA":921,"GAACGC":922,"GAAUCUUCC":923,"UUCGC":924,"ACCUGAGAGGGUGAUCGGCC":925,"ACACUGGAACUGAGACACGGUCCAGACUCCUACGGGAGGCAGCAGUGGGGAA":926,"GGCUAACUUCG":927,"AGAGAC":928,"AGAGGC":929,"UACUC":930,"UAACGGCCC":931,"UUGAGUGC":932,"AACAC":933,"AGUGCC":934,"AGCGCGCG":935,"UGUGCC":936,"AGCAGC":937,"ACCCGAA":938,"ACAACC":939,"GGGAGGAAC":940,"ACCUGGGG":941,"ACGAAAGUC":942,"UCAUGC":943,"ACGGGG":944,"AUAUGG":945,"UCUUUU":946,"GGCUAACUCCGUGCCAGCAGCCGCGGUAAUACGGAGGG":947,"UUAGAG":948,"UGAUGCAGCGACGCC":949,"UGUAGG":950,"GCAUGG":951,"AGAAAGCCAC":952,"UGGAUU":953,"UUGCAGAA":954,"UUUCCC":955,"UGUUAA":956,"UUGAAG":957,"UCAACCG":958,"UGGUAG":959,"GGCUAACUACGUGCCAGCAGCCGCGGUAAUACGUAGG":960,"GAAAGG":961,"UGAGGAA":962,"UUACCAAGGC":963,"UGUAGCAGUGAA":964,"UAGCCGGCCUGAGAGGG":965,"UGGUAC":966,"UCGCGGAUCAGC":967,"GGAAACG":968,"UGUGUGAAGAAGGCC":969,"GGCCACAUUGGGAC":970,"AUCUCC":971,"AGGGCGCG":972,"UGUGGG":973,"UAACGC":974,"ACCUCC":975,"GGGCCUUGUACACACCGCCCGUCACACCAUGGG":976,"UUUCAA":977,"UGGUCGG":978,"AGGGAC":979,"UAGGCG":980,"UGUAAG":981,"UGGAGGAA":982,"UUGACGGUACC":983,"AGUGAGGAAUAUUGGUCAA":984,"UGACAA":985,"AUUUUC":986,"AGGUGGUGCAUGGUUGUCGUCAGCUCGUGUCGUGAGAUGUUGGGUUAAGUCCCGCAACGAGCGCAA":987,"AGCACC":988,"AGAACC":989,"AUGAAGUCGGAAUCGCUAGUAA":990,"GGUCC":991,"AGUGAC":992,"AGAGCC":993,"UGCUC":994,"ACAUG":995,"UAUGCC":996,"AUUAGCUAG":997,"UCAACCC":998,"AUAUAC":999,"UAAACC":1000,"AUAUCC":1001,"UUAUUC":1002,"UACAGAGGG":1003,"UUCGAA":1004,"UUGAAC":1005,"AGUAAC":1006,"AGCGGC":1007,"UCCUCC":1008,"AGCUCG":1009,"UUCGAAGCAACGCGAAGAACCUUACC":1010,"UAUCCC":1011,"GCGUUGUCCGGAA":1012,"UGGCCC":1013,"AGUACG":1014,"ACGGCCUUCGGGUUGUAA":1015,"AAGACC":1016,"UAUUGGGCGUAA":1017,"AAGAA":1018,"UUUAAG":1019,"UUCGGAAUUACUGGGCGUAA":1020,"UGAGAUAC":1021,"UCUUGC":1022,"AGUUAA":1023}