TEST / tokenizer.json
Vlasta's picture
add tokenizer
db1d55d
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "[a-zA-Z]{100}"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "BertProcessing",
"sep": [
"[SEP]",
3
],
"cls": [
"[CLS]",
2
]
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "[UNK]",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"A": 5,
"C": 6,
"G": 7,
"T": 8,
"AA": 9,
"TT": 10,
"CC": 11,
"AG": 12,
"TG": 13,
"TC": 14,
"AC": 15,
"GG": 16,
"ATT": 17,
"AT": 18,
"GC": 19,
"ATG": 20,
"AAAA": 21,
"ACC": 22,
"AGG": 23,
"TCC": 24,
"TAA": 25,
"AGC": 26,
"TTTT": 27,
"AAG": 28,
"ATC": 29,
"AAC": 30,
"TGC": 31,
"TGG": 32,
"TTC": 33,
"TTG": 34,
"TAG": 35,
"TAC": 36,
"CCC": 37,
"TGGG": 38,
"TATT": 39,
"AGCC": 40,
"AGAA": 41,
"AGGC": 42,
"ATAA": 43,
"GGC": 44,
"TCTC": 45,
"GCC": 46,
"GGG": 47,
"TGGC": 48,
"TCAC": 49,
"ATAC": 50,
"TCCC": 51,
"TTCC": 52,
"AGAG": 53,
"TGCC": 54,
"ACCC": 55,
"TTTC": 56,
"TGAA": 57,
"ATTC": 58,
"ATGG": 59,
"TGAG": 60,
"ATCC": 61,
"ACAC": 62,
"ATGC": 63,
"TAAAA": 64,
"TAT": 65,
"AAAG": 66,
"TTGG": 67,
"TGTC": 68,
"ACAA": 69,
"TTGC": 70,
"ATTG": 71,
"TGTT": 72,
"TAGC": 73,
"TAGG": 74,
"AGGG": 75,
"TATG": 76,
"TAAG": 77,
"AAAC": 78,
"TATC": 79,
"AAGG": 80,
"AGAC": 81,
"TGTG": 82,
"AATT": 83,
"AGTC": 84,
"AAAAG": 85,
"AATC": 86,
"ACTT": 87,
"TAAC": 88,
"AGTT": 89,
"AGTG": 90,
"AAAAC": 91,
"TACC": 92,
"AAATT": 93,
"AAGC": 94,
"AACC": 95,
"TTTG": 96,
"TGAC": 97,
"ACG": 98,
"AAAAAAAA": 99,
"ATCTC": 100,
"CCCC": 101,
"ATTTT": 102,
"TCTT": 103,
"ATGGC": 104,
"TGGGC": 105,
"ACAG": 106,
"ACTC": 107,
"ATGGG": 108,
"TTAG": 109,
"ACCCC": 110,
"GGGC": 111,
"ATTTC": 112,
"TTTTC": 113,
"AATG": 114,
"AATAA": 115,
"GGCC": 116,
"ATAG": 117,
"AGGTC": 118,
"TTTTTT": 119,
"GCCC": 120,
"AAATG": 121,
"AAACC": 122,
"TGAAG": 123,
"ATTCC": 124,
"ATTAC": 125,
"ACCAC": 126,
"TGGCC": 127,
"AGAGG": 128,
"TGTAA": 129,
"TCTG": 130,
"ACTCC": 131,
"TTTTG": 132,
"AAGTG": 133,
"AACAC": 134,
"TGGGG": 135,
"AAGGC": 136,
"TTTAA": 137,
"TCAG": 138,
"ATTGC": 139,
"ATATT": 140,
"ATAGG": 141,
"TGGAG": 142,
"TATAA": 143,
"TATAC": 144,
"AGATG": 145,
"ACTG": 146,
"ACTGC": 147,
"ATAAC": 148,
"ATCCC": 149,
"ACCTC": 150,
"TCCCC": 151,
"AAGAA": 152,
"AAGTC": 153,
"ATCTT": 154,
"TTCTC": 155,
"TGCCTC": 156,
"TACCC": 157,
"AAAGG": 158,
"AAAGC": 159,
"TTTGC": 160,
"AGAAAA": 161,
"AGTAA": 162,
"GGGG": 163,
"ATATG": 164,
"ACCTCC": 165,
"AGGCC": 166,
"TTTTTTTT": 167,
"TAGCC": 168,
"GTG": 169,
"TTAC": 170,
"TTTAG": 171,
"AGAGC": 172,
"AGATC": 173,
"AGGGC": 174,
"TGAAAA": 175,
"TCTTG": 176,
"ATACC": 177,
"TTGAA": 178,
"TATTC": 179,
"AGGCTG": 180,
"TTCCCC": 181,
"ATTACAGGC": 182,
"GAG": 183,
"TA": 184,
"AGAAG": 185,
"AGAAC": 186,
"TCTTC": 187,
"ACATT": 188,
"ATTTG": 189,
"ATTGG": 190,
"ATAAAA": 191,
"ATGCC": 192,
"TCCAG": 193,
"TAAAC": 194,
"AGCAGC": 195,
"TTGCC": 196,
"TGGGATTACAGGC": 197,
"TCTCG": 198,
"AATTTT": 199,
"AATAG": 200,
"TTTCC": 201,
"TTGGG": 202,
"AGTGG": 203,
"AGTTC": 204,
"ACATG": 205,
"ACATC": 206,
"ATAGAA": 207,
"ATATAA": 208,
"AAAAAA": 209,
"ACCAGCC": 210,
"AGCTG": 211,
"AGCTC": 212,
"TGGAGG": 213,
"TATTTATT": 214,
"TGGCTC": 215,
"TCCCAGC": 216,
"GTC": 217,
"GTGG": 218,
"AAGGG": 219,
"AAACAC": 220,
"TTAAG": 221,
"TTCCC": 222,
"AGTGTT": 223,
"TGAAC": 224,
"TGTTG": 225,
"TGTAG": 226,
"TGTAC": 227,
"TCATT": 228,
"ACAGG": 229,
"ACTTC": 230,
"ACTTG": 231,
"ATTTTC": 232,
"ATAGC": 233,
"ATAAG": 234,
"AAAAAC": 235,
"ACCATG": 236,
"AGGAGG": 237,
"TCCTC": 238,
"TCCTGCCTC": 239,
"TAATTTT": 240,
"AACATT": 241,
"TGCAA": 242,
"TATTG": 243,
"TATTCC": 244,
"TCACTGC": 245,
"TGAAGC": 246,
"AGGCTGAGGC": 247,
"TATGG": 248,
"TTATAA": 249,
"CCAGG": 250,
"TGTATT": 251,
"TCG": 252,
"TCTAA": 253,
"ATATC": 254,
"GCGG": 255,
"ATGTT": 256,
"ATGAC": 257,
"AGGAA": 258,
"TAATAC": 259,
"AGCTT": 260,
"AGCTCC": 261,
"AAGAC": 262,
"AAGATC": 263,
"TTCTCC": 264,
"TTCTAA": 265,
"TACAC": 266,
"TACTAAAA": 267,
"TGGGGG": 268,
"AGAAAG": 269,
"AGAAGC": 270,
"AGGCTGG": 271,
"GCCGCC": 272,
"ATACAAAA": 273,
"TTTCTAC": 274,
"AAAGTGC": 275,
"ATTGTC": 276,
"TCCTGCCTCAGCC": 277,
"CAA": 278,
"GAC": 279,
"TATCC": 280,
"AATGG": 281,
"AATCTC": 282,
"AAATTC": 283,
"AATATC": 284,
"AGA": 285,
"AGACC": 286,
"AGTCC": 287,
"AGTGC": 288,
"AGCCC": 289,
"AGTCTC": 290,
"AGTGCC": 291,
"AGACAA": 292,
"TGATT": 293,
"TGAGG": 294,
"TGTTTT": 295,
"TCAAAA": 296,
"TCTTTT": 297,
"ACAT": 298,
"ACTAC": 299,
"GGAC": 300,
"GGAGC": 301,
"ATTAA": 302,
"ATTATT": 303,
"ATTATG": 304,
"ATTTCC": 305,
"ATTTTGG": 306,
"ATGACC": 307,
"ATGAAC": 308,
"ATGCCC": 309,
"AAAACC": 310,
"ACCACC": 311,
"AGGAGAA": 312,
"TCCTG": 313,
"TCCATG": 314,
"TCCACC": 315,
"TAATC": 316,
"TAAGC": 317,
"AGCG": 318,
"AGCAC": 319,
"AGCAGG": 320,
"AAGCC": 321,
"AACAA": 322,
"AACTT": 323,
"AACATGG": 324,
"TGCG": 325,
"TGCTT": 326,
"TGGAA": 327,
"TGGTGG": 328,
"TTCAC": 329,
"TTGAG": 330,
"TTGTG": 331,
"TTGTAG": 332,
"TTGCCC": 333,
"TAGTAG": 334,
"TAGGGC": 335,
"CCCAC": 336,
"TATTGC": 337,
"AGCCAC": 338,
"AGCCAGG": 339,
"ATAATT": 340,
"GGCTCACTGC": 341,
"GGGTGG": 342,
"ACCCTC": 343,
"TTTCTTTT": 344,
"TATAAAA": 345,
"TTGGCC": 346,
"TAGCTGGG": 347,
"ACTTTGGG": 348,
"AAAAAAAAAAAAAAAA": 349,
"TGGGCAAC": 350,
"AGGTCAGG": 351,
"GTCC": 352,
"GTGTC": 353,
"AAAT": 354,
"AAATAA": 355,
"AATGGC": 356,
"AAATAC": 357,
"AATATG": 358,
"TTAA": 359,
"TTGGC": 360,
"TTTATC": 361,
"AGTCAC": 362,
"TGA": 363,
"TGAGC": 364,
"TGCCC": 365,
"TGATAA": 366,
"TGATGC": 367,
"TGATTG": 368,
"TGTATG": 369,
"TGTTTTC": 370,
"TCTGG": 371,
"TCTTGC": 372,
"ACGC": 373,
"ACTGG": 374,
"GGCCC": 375,
"ATTTGC": 376,
"ATTTAG": 377,
"ATTTAC": 378,
"ATTTATT": 379,
"ATAT": 380,
"ATACCC": 381,
"GCTGGAG": 382,
"ACCGC": 383,
"TCCAC": 384,
"TCCAAAA": 385,
"TAAATC": 386,
"AGCAA": 387,
"AGCATG": 388,
"AGCTTC": 389,
"TTTTGG": 390,
"TTTTAGC": 391,
"AAGAGG": 392,
"AAGTTC": 393,
"ATCAC": 394,
"ATCTAG": 395,
"AACTAA": 396,
"TGCAAAA": 397,
"TGCTAC": 398,
"TGCTAAG": 399,
"TGGATT": 400,
"TGGACTT": 401,
"TTCTTC": 402,
"TTGTC": 403,
"TAGAAAA": 404,
"TAGAGAC": 405,
"TACTG": 406,
"CCCAGG": 407,
"CCCAGCC": 408,
"TATTTT": 409,
"TCACTC": 410,
"TCACTTC": 411,
"TCCCTC": 412,
"AGAGTGAG": 413,
"TTTCTTC": 414,
"ATTCTGG": 415,
"TGAGACCAGCC": 416,
"ATCCCC": 417,
"TTGCAGTG": 418,
"TAGGTC": 419,
"AGGGCC": 420,
"AAGGCC": 421,
"AATTAC": 422,
"ATGGGCC": 423,
"ACTCCAGCC": 424,
"AAGTGATCC": 425,
"AGGCCG": 426,
"TTTTTTTTTTTT": 427,
"AGGCTGAGGCAGGAGAA": 428,
"TACTAAAAATACAAAA": 429,
"AAAGTGCTGGGATTACAGGC": 430,
"GAAC": 431,
"GTCTC": 432,
"AAATC": 433,
"AATGC": 434,
"AATTC": 435,
"AATAC": 436,
"AATATT": 437,
"AATGAG": 438,
"AATGTC": 439,
"AAATAGG": 440,
"TTATG": 441,
"TTAAC": 442,
"TTTATT": 443,
"TTATAC": 444,
"TTACCC": 445,
"TTATTC": 446,
"TTTAAAA": 447,
"CCG": 448,
"CCAC": 449,
"CCATC": 450,
"AGATT": 451,
"AGTAG": 452,
"AGAGAA": 453,
"AGATAA": 454,
"AGGGG": 455,
"AGTGGC": 456,
"AGATAC": 457,
"AGTAAAA": 458,
"TGATG": 459,
"TGTCC": 460,
"TGTGC": 461,
"TGTTC": 462,
"TGTCTC": 463,
"TGTGGC": 464,
"TGTCCC": 465,
"TGATTC": 466,
"TCGC": 467,
"TCATG": 468,
"TCTAG": 469,
"TCTAC": 470,
"ACGG": 471,
"ACTGGG": 472,
"ACATAC": 473,
"ACTGCC": 474,
"ACATGG": 475,
"ACTAAAA": 476,
"GGGGC": 477,
"GGCCCC": 478,
"ATTTTG": 479,
"ATTCCC": 480,
"ATTGGG": 481,
"ATTACAA": 482,
"ATTTTGC": 483,
"ATTTAGG": 484,
"ATTTATC": 485,
"ATTAGTC": 486,
"ATAGGC": 487,
"ATATCC": 488,
"ATACCCC": 489,
"GCG": 490,
"GCTGC": 491,
"ATGTC": 492,
"ATGATC": 493,
"ATGGCC": 494,
"ATGAAAG": 495,
"ATGTAAG": 496,
"AAAATT": 497,
"AAAAGG": 498,
"AAAAGC": 499,
"AAAAAAG": 500,
"AAAAATC": 501,
"AAAAAAC": 502,
"AAAATATT": 503,
"ACCAAG": 504,
"ACCTAG": 505,
"ACCTATT": 506,
"AGGAG": 507,
"AGGAAAA": 508,
"AGGTAA": 509,
"AGGTGC": 510,
"AGGTAC": 511,
"AGGAGAG": 512,
"TCCTAG": 513,
"TCCTCCC": 514,
"TCCACCTCC": 515,
"TAATT": 516,
"TAACC": 517,
"TAATAA": 518,
"TAAATAA": 519,
"TAAGCC": 520,
"TAATAT": 521,
"AGCACC": 522,
"AGCTAC": 523,
"AGCGCC": 524,
"AGCTTCC": 525,
"AGCTAATTTT": 526,
"TTTTAAAA": 527,
"TTTTTAAAA": 528,
"AAGTAC": 529,
"ATCG": 530,
"ATCAAC": 531,
"ATCTTC": 532,
"ATCTAAAA": 533,
"AACAG": 534,
"AACTC": 535,
"AACAGC": 536,
"AACATTC": 537,
"AACTAAAA": 538,
"TGCTG": 539,
"TGCTC": 540,
"TGCTGCC": 541,
"TGCAGTG": 542,
"TGCAGTGG": 543,
"TGGTT": 544,
"TGGAAC": 545,
"TGGTTTC": 546,
"TGGAATT": 547,
"TTGTT": 548,
"TTGTATT": 549,
"TAGTTTT": 550,
"TACAGC": 551,
"TACTTC": 552,
"TGGGCC": 553,
"TGGGTGG": 554,
"TGGGGCC": 555,
"AGCCCC": 556,
"AGCCTCCC": 557,
"AGCCGGGC": 558,
"AGCCAAGATC": 559,
"AGAATT": 560,
"AGAAAC": 561,
"AGAAGG": 562,
"AGAAGGC": 563,
"GGCG": 564,
"TCTCTC": 565,
"GCCTCC": 566,
"TGGCTAAC": 567,
"TCACACC": 568,
"TCACTTG": 569,
"AGAGAT": 570,
"AGAGAGAG": 571,
"TGCCAC": 572,
"ACCCACC": 573,
"ACCCGCC": 574,
"TTTCACCATG": 575,
"TGAAACCCC": 576,
"ATTCTCCTGCCTCAGCC": 577,
"TGAGATG": 578,
"ACACATG": 579,
"ACACAAAA": 580,
"TAAAAC": 581,
"TTGGGC": 582,
"TGTCTAA": 583,
"TTGCTCC": 584,
"ATTGATCC": 585,
"TAGCTGGGATTACAGGC": 586,
"AAACGG": 587,
"AAACACC": 588,
"AGTCTATT": 589,
"ACTTCCC": 590,
"TAACTGC": 591,
"TACCATG": 592,
"AAATTTC": 593,
"ATCTCATG": 594,
"TCTTAGC": 595,
"TGGGCGC": 596,
"AGAGGAAAA": 597,
"AGATGGGG": 598,
"TTTAGTAGAGAC": 599,
"TCTCGAAC": 600,
"TCCCAGCACTTTGGG": 601,
"TTCACGCC": 602,
"GGCTCACTGCAACC": 603,
"TAGCTGGGACTAC": 604,
"ACTCCAGCCTGGGCAAC": 605,
"CAG": 606,
"GTT": 607,
"GATG": 608,
"GTAA": 609,
"GAGC": 610,
"GTTG": 611,
"GTAC": 612,
"GTGAA": 613,
"GTAGG": 614,
"GTACC": 615,
"GACTCC": 616,
"GATCCC": 617,
"GTGCCTC": 618,
"TATGC": 619,
"AATTG": 620,
"AAAGCC": 621,
"AAAGAA": 622,
"AAAGAG": 623,
"AATTTC": 624,
"AAATCC": 625,
"AATAAAA": 626,
"AAATGGC": 627,
"AAAGGTC": 628,
"AATATAA": 629,
"TTATT": 630,
"TTTAC": 631,
"TTTGGG": 632,
"TTTGAA": 633,
"TTTGTC": 634,
"TTATTG": 635,
"TTTGTT": 636,
"TTTAGC": 637,
"TTAAAC": 638,
"TTAGTT": 639,
"TTTACC": 640,
"TTAACC": 641,
"TTACG": 642,
"TTATTGC": 643,
"TTTATTC": 644,
"CCAAAG": 645,
"AGT": 646,
"AGTTCC": 647,
"AGATTC": 648,
"AGACAC": 649,
"AGTTGG": 650,
"AGTGTC": 651,
"AGTTGC": 652,
"AGAAAAC": 653,
"AGATTTT": 654,
"AGATGGG": 655,
"AGATTTC": 656,
"AGAACAC": 657,
"AGTATTGC": 658,
"TGAT": 659,
"TGTGGG": 660,
"TGAGCC": 661,
"TGAGGC": 662,
"TGTGCC": 663,
"TGATCC": 664,
"TGACAC": 665,
"TGTAT": 666,
"TGACAA": 667,
"TGATAGG": 668,
"TGTATAC": 669,
"TGAGGTCAGG": 670,
"TCACC": 671,
"TCAGG": 672,
"TCAAG": 673,
"TCATGG": 674,
"TCATCC": 675,
"TCAAAC": 676,
"TCAATT": 677,
"TCAATC": 678,
"TCTGAC": 679,
"TCAAGTGATCC": 680,
"ACT": 681,
"ACTTTT": 682,
"ACTATT": 683,
"ACTCAC": 684,
"ACTGAG": 685,
"ACATGC": 686,
"ACATGGG": 687,
"ACTTTTTT": 688,
"ACAACAC": 689,
"ACTACCC": 690,
"ACTAATAC": 691,
"GGAG": 692,
"GGAGG": 693,
"GGATC": 694,
"GGTGGC": 695,
"GGTTGG": 696,
"GGAAAC": 697,
"GGACTC": 698,
"GGAAAAAAG": 699,
"ATTA": 700,
"ATTAG": 701,
"ATTTAA": 702,
"ATTTGGG": 703,
"ATTTCAC": 704,
"ATTACCC": 705,
"ATTTTTC": 706,
"ATTTGAG": 707,
"ATTACAG": 708,
"ATTTATAC": 709,
"ATTAAAGG": 710,
"ATTTATTTATT": 711,
"ATA": 712,
"ATAGAG": 713,
"ATATGC": 714,
"ATAAAAC": 715,
"ATATAG": 716,
"GCGGC": 717,
"GCTGGC": 718,
"GCAAGG": 719,
"GCACCAC": 720,
"ATGTAA": 721,
"ATGTGG": 722,
"ATGTTG": 723,
"ATGTAC": 724,
"ATGAGCC": 725,
"ATGTGCC": 726,
"ATGATCC": 727,
"ATGAAAC": 728,
"ATGTCTT": 729,
"ATGAATG": 730,
"ATGTGAAAA": 731,
"AAAAATG": 732,
"AAAATTC": 733,
"AAAACCC": 734,
"ACCAT": 735,
"ACCTTC": 736,
"ACCATCC": 737,
"ACCACAC": 738,
"ACCACAA": 739,
"ACCTGTT": 740,
"ACCTGTG": 741,
"ACCTTCTC": 742,
"ACCTGAGGTCAGG": 743,
"AGGT": 744,
"AGGAAG": 745,
"AGGAAC": 746,
"AGGTGG": 747,
"AGGCCC": 748,
"AGGTAGG": 749,
"AGGAAAAG": 750,
"AGGTGAC": 751,
"AGGAAACC": 752,
"TCCG": 753,
"TCCATC": 754,
"TCCAAC": 755,
"TCCAGGC": 756,
"TCCTTTAA": 757,
"TCCGCCTCC": 758,
"TAAGG": 759,
"TAAATG": 760,
"TAACCC": 761,
"TAATGAAG": 762,
"AGCA": 763,
"AGCT": 764,
"AGCAT": 765,
"AGCATC": 766,
"AGCAGGC": 767,
"AGCAAAG": 768,
"AGCTAGC": 769,
"AGCTATG": 770,
"AGCAAGG": 771,
"AGCAATAG": 772,
"AGCTCACTGC": 773,
"TTTTCC": 774,
"TTTTAT": 775,
"TTTTAATAA": 776,
"TTTTTTTTTT": 777,
"AAGTAA": 778,
"AAGCCC": 779,
"AAGTATT": 780,
"AAGAGAA": 781,
"AAGATAC": 782,
"AAGTTCC": 783,
"AAGTTTC": 784,
"AAGAGGG": 785,
"AAGAGTC": 786,
"AAGACTT": 787,
"AAGACTC": 788,
"AAGACTCC": 789,
"ATCAGCC": 790,
"ATCTCAC": 791,
"ATCACAC": 792,
"ATCTAGG": 793,
"ATCAGGG": 794,
"ATCACTT": 795,
"ATCACG": 796,
"AACTAG": 797,
"AACTGCC": 798,
"AACACTT": 799,
"TGCGC": 800,
"TGCTGC": 801,
"TGCATAC": 802,
"TGCATCC": 803,
"TGGAT": 804,
"TGGTAA": 805,
"TGGATCC": 806,
"TGGAGAC": 807,
"TGGTGTG": 808,
"TGGTTTTC": 809,
"TTCTG": 810,
"TTCACC": 811,
"TTCATC": 812,
"TTGA": 813,
"TTGAAC": 814,
"TTGAGCC": 815,
"TTGTCTC": 816,
"TTGATGC": 817,
"TTGTTGC": 818,
"TTGAATT": 819,
"TTGAATAA": 820,
"TAGTC": 821,
"TAGCCC": 822,
"TAGGCTGGAG": 823,
"TACGG": 824,
"TACTACC": 825,
"TACACTG": 826,
"TACTTGGG": 827,
"TACTGGGGCC": 828,
"CCCG": 829,
"CCCAAG": 830,
"CCCTTTC": 831,
"CCCGGCC": 832,
"CCCACCTC": 833,
"CCCAAAGAA": 834,
"TGGGTGC": 835,
"TGGGTTC": 836,
"TGGGAGGC": 837,
"TGGGTCCCC": 838,
"TGGGTTCACGCC": 839,
"TATTAC": 840,
"TATTTTCC": 841,
"TATTTTGC": 842,
"AGCCATC": 843,
"AGCCTCCAG": 844,
"AGAAAT": 845,
"AGAATGC": 846,
"AGAATTC": 847,
"AGAAAGAG": 848,
"AGAAGGCC": 849,
"AGGCTAT": 850,
"AGGCAGAGG": 851,
"AGGCTGGAG": 852,
"AGGCAGATC": 853,
"AGGCAGAAG": 854,
"ATAAATAA": 855,
"ATAATTAG": 856,
"ATAATCAG": 857,
"GGCT": 858,
"GGCGAG": 859,
"GCCTTGG": 860,
"GCCACTGC": 861,
"GGGATG": 862,
"GGGTGC": 863,
"GGGACCC": 864,
"GGGACAG": 865,
"GGGAATG": 866,
"GGGAGGCTGAGGC": 867,
"TGGCTAC": 868,
"TGGCTGAA": 869,
"TGGCTGGGG": 870,
"TGGCTTGAA": 871,
"TGGCTAATTTT": 872,
"TGGCGTGAA": 873,
"TCACAATC": 874,
"ATACAGGC": 875,
"TCCCGCC": 876,
"TCCCTGAA": 877,
"TCCCAAAGTGCTGGGATTACAGGC": 878,
"TTCCATTC": 879,
"AGAGT": 880,
"AGAGGG": 881,
"AGAGAGAC": 882,
"TGCCAGG": 883,
"TGCCTTG": 884,
"ACCCAGC": 885,
"ACCCATAC": 886,
"TTTCTAG": 887,
"TGAAT": 888,
"TGAAAC": 889,
"TGAAGGC": 890,
"TGAAACCC": 891,
"TGAAATTTAG": 892,
"ATTCTAA": 893,
"ATGGTCC": 894,
"ATGGAAG": 895,
"ATGGTAG": 896,
"ATGGAGTCTC": 897,
"TGAGTATT": 898,
"TGAGATGG": 899,
"TGAGACAA": 900,
"ATGCAAG": 901,
"ATGCAATAA": 902,
"TATAGG": 903,
"TATATGC": 904,
"AAAGAGGC": 905,
"AAAGTAT": 906,
"TTGGTC": 907,
"TGTCTTCC": 908,
"TGTCGCCC": 909,
"ACAAAC": 910,
"ACAATATTTT": 911,
"TTGCAG": 912,
"TTGCTGC": 913,
"ATTGTATT": 914,
"ATTGAGAG": 915,
"ATTGTTTTC": 916,
"TGTTTGGG": 917,
"TGTTTATT": 918,
"TGTTGGG": 919,
"AGGGGCC": 920,
"AGGGTTTCACCATG": 921,
"TATGAGC": 922,
"AAGGAAAA": 923,
"AAGGAGAGC": 924,
"AATTAGCC": 925,
"AGTCTAG": 926,
"AAAAGAAATT": 927,
"AATCATGC": 928,
"AATCTGAC": 929,
"TAACTC": 930,
"AGTTTCC": 931,
"AGTTTAGG": 932,
"AGTTTGAGACCAGCC": 933,
"AGTGAAAA": 934,
"AGTGTAG": 935,
"AAAACACC": 936,
"AAAACAGAC": 937,
"TACCTC": 938,
"AAGCG": 939,
"AAGCAA": 940,
"AAGCATGC": 941,
"AAGCACTG": 942,
"AACCCC": 943,
"TTTGAGG": 944,
"TTTGCCC": 945,
"ACGA": 946,
"AAAAAAAAAAAA": 947,
"ATCTCATC": 948,
"ATCTCTGC": 949,
"CCCCG": 950,
"CCCCCC": 951,
"ATTTTCCC": 952,
"ATTTTATTG": 953,
"TCTTTAAG": 954,
"ATGGCAGCAGGC": 955,
"TGGGCATGG": 956,
"ATGGGTAG": 957,
"TTAGTGC": 958,
"ACCCCTGGC": 959,
"GGGCGG": 960,
"ATTTCTTG": 961,
"TTTTTTTGAG": 962,
"GCCCGCCGCC": 963,
"AAATGAAC": 964,
"TGAAGTTGG": 965,
"ATTCCATG": 966,
"ACCACTAC": 967,
"ACCACAGAA": 968,
"TGGCCAACATGG": 969,
"TGTAATCTC": 970,
"TCTGTCTC": 971,
"TTTTGTT": 972,
"AACACTGAC": 973,
"TGGGGAGTC": 974,
"TTTAAGC": 975,
"ATAGGAGTTGG": 976,
"TATAAAGAA": 977,
"AGATGCC": 978,
"ACTGCCC": 979,
"ATAACTTC": 980,
"TCCCCGC": 981,
"AAGTCATGTCTT": 982,
"AGGGCGC": 983,
"TCTTGAAC": 984,
"TTGAAAGCC": 985,
"GAGTAGCTGGGATTACAGGC": 986,
"AATTTTAC": 987,
"TTTCCCCC": 988,
"ACATGAAATG": 989,
"ACATCATC": 990,
"TCCCAGCTACTTGGG": 991,
"TTAAGAG": 992,
"AGTGTTGGG": 993,
"ACTTCAAG": 994,
"ATTTTCTGG": 995,
"AGGAATGTG": 996,
"TACACTGAA": 997,
"AGGCTGGTCTCGAAC": 998,
"AGGCTGGTCTTGAAC": 999
},
"merges": [
"A A",
"T T",
"C C",
"A G",
"T G",
"T C",
"A C",
"G G",
"A TT",
"A T",
"G C",
"A TG",
"AA AA",
"A CC",
"AG G",
"T CC",
"T AA",
"AG C",
"TT TT",
"AA G",
"A TC",
"AA C",
"TG C",
"TG G",
"TT C",
"TT G",
"T AG",
"T AC",
"CC C",
"TG GG",
"T ATT",
"AG CC",
"AG AA",
"AG GC",
"AT AA",
"GG C",
"TC TC",
"G CC",
"GG G",
"TG GC",
"TC AC",
"AT AC",
"TCC C",
"TT CC",
"AG AG",
"TG CC",
"ACC C",
"TT TC",
"TG AA",
"ATT C",
"ATG G",
"TG AG",
"AT CC",
"AC AC",
"ATG C",
"T AAAA",
"T AT",
"AA AG",
"TT GG",
"TG TC",
"AC AA",
"TT GC",
"ATT G",
"TG TT",
"T AGC",
"T AGG",
"AG GG",
"T ATG",
"TAA G",
"AA AC",
"T ATC",
"AA GG",
"AG AC",
"TG TG",
"AA TT",
"AG TC",
"AAAA G",
"AA TC",
"AC TT",
"TAA C",
"AG TT",
"AG TG",
"AAAA C",
"T ACC",
"AA ATT",
"AA GC",
"AA CC",
"TT TG",
"TG AC",
"AC G",
"AAAA AAAA",
"ATC TC",
"CC CC",
"ATT TT",
"TC TT",
"ATG GC",
"TGGG C",
"AC AG",
"AC TC",
"ATG GG",
"TT AG",
"ACC CC",
"GG GC",
"ATT TC",
"TTTT C",
"AA TG",
"AA TAA",
"GG CC",
"AT AG",
"AGG TC",
"TTTT TT",
"G CCC",
"AA ATG",
"AA ACC",
"TG AAG",
"ATT CC",
"ATT AC",
"ACC AC",
"TGG CC",
"AG AGG",
"TG TAA",
"TC TG",
"AC TCC",
"TTTT G",
"AAG TG",
"AAC AC",
"TGGG G",
"AA GGC",
"TT TAA",
"TC AG",
"ATT GC",
"AT ATT",
"AT AGG",
"TGG AG",
"T ATAA",
"T ATAC",
"AG ATG",
"AC TG",
"AC TGC",
"AT AAC",
"AT CCC",
"ACC TC",
"TCC CC",
"AAG AA",
"AAG TC",
"ATC TT",
"TTC TC",
"TGCC TC",
"T ACCC",
"AA AGG",
"AA AGC",
"TT TGC",
"AG AAAA",
"AG TAA",
"GG GG",
"AT ATG",
"ACC TCC",
"AGG CC",
"TTTT TTTT",
"TAG CC",
"G TG",
"TT AC",
"TT TAG",
"AG AGC",
"AG ATC",
"AG GGC",
"TG AAAA",
"TC TTG",
"AT ACC",
"TTG AA",
"TATT C",
"AGGC TG",
"TTCC CC",
"ATTAC AGGC",
"G AG",
"T A",
"AG AAG",
"AG AAC",
"TC TTC",
"AC ATT",
"ATT TG",
"ATT GG",
"AT AAAA",
"ATG CC",
"TCC AG",
"TAA AC",
"AGC AGC",
"TTG CC",
"TGGG ATTACAGGC",
"TCTC G",
"AA TTTT",
"AA TAG",
"TT TCC",
"TT GGG",
"AG TGG",
"AG TTC",
"AC ATG",
"AC ATC",
"AT AGAA",
"AT ATAA",
"AAAA AA",
"ACC AGCC",
"AGC TG",
"AGC TC",
"TGG AGG",
"TATT TATT",
"TGGC TC",
"TCCC AGC",
"G TC",
"G TGG",
"AA GGG",
"AA ACAC",
"TT AAG",
"TT CCC",
"AG TGTT",
"TG AAC",
"TG TTG",
"TG TAG",
"TG TAC",
"TC ATT",
"AC AGG",
"AC TTC",
"AC TTG",
"ATT TTC",
"AT AGC",
"AT AAG",
"AAAA AC",
"ACC ATG",
"AGG AGG",
"TCC TC",
"TCC TGCCTC",
"TAA TTTT",
"AAC ATT",
"TGC AA",
"TATT G",
"TATT CC",
"TCAC TGC",
"TGAA GC",
"AGGCTG AGGC",
"T ATGG",
"TT ATAA",
"CC AGG",
"TG TATT",
"TC G",
"TC TAA",
"AT ATC",
"GC GG",
"ATG TT",
"ATG AC",
"AGG AA",
"TAA TAC",
"AGC TT",
"AGC TCC",
"AAG AC",
"AAG ATC",
"TTC TCC",
"TTC TAA",
"TAC AC",
"TAC TAAAA",
"TGGG GG",
"AGAA AG",
"AGAA GC",
"AGGC TGG",
"GCC GCC",
"ATAC AAAA",
"TTTC TAC",
"AAAG TGC",
"ATTG TC",
"TCCTGCCTC AGCC",
"C AA",
"G AC",
"T ATCC",
"AA TGG",
"AA TCTC",
"AA ATTC",
"AA TATC",
"AG A",
"AG ACC",
"AG TCC",
"AG TGC",
"AG CCC",
"AG TCTC",
"AG TGCC",
"AG ACAA",
"TG ATT",
"TG AGG",
"TG TTTT",
"TC AAAA",
"TC TTTT",
"AC AT",
"AC TAC",
"GG AC",
"GG AGC",
"ATT AA",
"ATT ATT",
"ATT ATG",
"ATT TCC",
"ATT TTGG",
"ATG ACC",
"ATG AAC",
"ATG CCC",
"AAAA CC",
"ACC ACC",
"AGG AGAA",
"TCC TG",
"TCC ATG",
"TCC ACC",
"TAA TC",
"TAA GC",
"AGC G",
"AGC AC",
"AGC AGG",
"AAG CC",
"AAC AA",
"AAC TT",
"AAC ATGG",
"TGC G",
"TGC TT",
"TGG AA",
"TGG TGG",
"TTC AC",
"TTG AG",
"TTG TG",
"TTG TAG",
"TTG CCC",
"TAG TAG",
"TAG GGC",
"CCC AC",
"TATT GC",
"AGCC AC",
"AGCC AGG",
"ATAA TT",
"GGC TCACTGC",
"GGG TGG",
"ACCC TC",
"TTTC TTTT",
"TAT AAAA",
"TTGG CC",
"TAGC TGGG",
"ACTT TGGG",
"AAAAAAAA AAAAAAAA",
"TGGGC AAC",
"AGGTC AGG",
"G TCC",
"G TGTC",
"AA AT",
"AA ATAA",
"AA TGGC",
"AA ATAC",
"AA TATG",
"TT AA",
"TT GGC",
"TT TATC",
"AG TCAC",
"TG A",
"TG AGC",
"TG CCC",
"TG ATAA",
"TG ATGC",
"TG ATTG",
"TG TATG",
"TG TTTTC",
"TC TGG",
"TC TTGC",
"AC GC",
"AC TGG",
"GG CCC",
"ATT TGC",
"ATT TAG",
"ATT TAC",
"ATT TATT",
"AT AT",
"AT ACCC",
"GC TGGAG",
"ACC GC",
"TCC AC",
"TCC AAAA",
"TAA ATC",
"AGC AA",
"AGC ATG",
"AGC TTC",
"TTTT GG",
"TTTT AGC",
"AAG AGG",
"AAG TTC",
"ATC AC",
"ATC TAG",
"AAC TAA",
"TGC AAAA",
"TGC TAC",
"TGC TAAG",
"TGG ATT",
"TGG ACTT",
"TTC TTC",
"TTG TC",
"TAG AAAA",
"TAG AGAC",
"TAC TG",
"CCC AGG",
"CCC AGCC",
"TATT TT",
"TCAC TC",
"TCAC TTC",
"TCCC TC",
"AGAG TGAG",
"TTTC TTC",
"ATTC TGG",
"TGAG ACCAGCC",
"ATCC CC",
"TTGC AGTG",
"TAGG TC",
"AGGG CC",
"AAGG CC",
"AATT AC",
"ATGGG CC",
"ACTCC AGCC",
"AAGTG ATCC",
"AGGCC G",
"TTTTTTTT TTTT",
"AGGCTGAGGC AGGAGAA",
"TACTAAAA ATACAAAA",
"AAAGTGC TGGGATTACAGGC",
"G AAC",
"G TCTC",
"AA ATC",
"AA TGC",
"AA TTC",
"AA TAC",
"AA TATT",
"AA TGAG",
"AA TGTC",
"AA ATAGG",
"TT ATG",
"TT AAC",
"TT TATT",
"TT ATAC",
"TT ACCC",
"TT ATTC",
"TT TAAAA",
"CC G",
"CC AC",
"CC ATC",
"AG ATT",
"AG TAG",
"AG AGAA",
"AG ATAA",
"AG GGG",
"AG TGGC",
"AG ATAC",
"AG TAAAA",
"TG ATG",
"TG TCC",
"TG TGC",
"TG TTC",
"TG TCTC",
"TG TGGC",
"TG TCCC",
"TG ATTC",
"TC GC",
"TC ATG",
"TC TAG",
"TC TAC",
"AC GG",
"AC TGGG",
"AC ATAC",
"AC TGCC",
"AC ATGG",
"AC TAAAA",
"GG GGC",
"GG CCCC",
"ATT TTG",
"ATT CCC",
"ATT GGG",
"ATT ACAA",
"ATT TTGC",
"ATT TAGG",
"ATT TATC",
"ATT AGTC",
"AT AGGC",
"AT ATCC",
"AT ACCCC",
"GC G",
"GC TGC",
"ATG TC",
"ATG ATC",
"ATG GCC",
"ATG AAAG",
"ATG TAAG",
"AAAA TT",
"AAAA GG",
"AAAA GC",
"AAAA AAG",
"AAAA ATC",
"AAAA AAC",
"AAAA TATT",
"ACC AAG",
"ACC TAG",
"ACC TATT",
"AGG AG",
"AGG AAAA",
"AGG TAA",
"AGG TGC",
"AGG TAC",
"AGG AGAG",
"TCC TAG",
"TCC TCCC",
"TCC ACCTCC",
"TAA TT",
"TAA CC",
"TAA TAA",
"TAA ATAA",
"TAA GCC",
"TAA TAT",
"AGC ACC",
"AGC TAC",
"AGC GCC",
"AGC TTCC",
"AGC TAATTTT",
"TTTT AAAA",
"TTTT TAAAA",
"AAG TAC",
"ATC G",
"ATC AAC",
"ATC TTC",
"ATC TAAAA",
"AAC AG",
"AAC TC",
"AAC AGC",
"AAC ATTC",
"AAC TAAAA",
"TGC TG",
"TGC TC",
"TGC TGCC",
"TGC AGTG",
"TGC AGTGG",
"TGG TT",
"TGG AAC",
"TGG TTTC",
"TGG AATT",
"TTG TT",
"TTG TATT",
"TAG TTTT",
"TAC AGC",
"TAC TTC",
"TGGG CC",
"TGGG TGG",
"TGGG GCC",
"AGCC CC",
"AGCC TCCC",
"AGCC GGGC",
"AGCC AAGATC",
"AGAA TT",
"AGAA AC",
"AGAA GG",
"AGAA GGC",
"GGC G",
"TCTC TC",
"GCC TCC",
"TGGC TAAC",
"TCAC ACC",
"TCAC TTG",
"AGAG AT",
"AGAG AGAG",
"TGCC AC",
"ACCC ACC",
"ACCC GCC",
"TTTC ACCATG",
"TGAA ACCCC",
"ATTC TCCTGCCTCAGCC",
"TGAG ATG",
"ACAC ATG",
"ACAC AAAA",
"TAAAA C",
"TTGG GC",
"TGTC TAA",
"TTGC TCC",
"ATTG ATCC",
"TAGC TGGGATTACAGGC",
"AAAC GG",
"AAAC ACC",
"AGTC TATT",
"ACTT CCC",
"TAAC TGC",
"TACC ATG",
"AAATT TC",
"ATCTC ATG",
"TCTT AGC",
"TGGGC GC",
"AGAGG AAAA",
"AGATG GGG",
"TTTAG TAGAGAC",
"TCTCG AAC",
"TCCCAGC ACTTTGGG",
"TTCAC GCC",
"GGCTCACTGC AACC",
"TAGCTGGG ACTAC",
"ACTCCAGCC TGGGCAAC",
"C AG",
"G TT",
"G ATG",
"G TAA",
"G AGC",
"G TTG",
"G TAC",
"G TGAA",
"G TAGG",
"G TACC",
"G ACTCC",
"G ATCCC",
"G TGCCTC",
"T ATGC",
"AA TTG",
"AA AGCC",
"AA AGAA",
"AA AGAG",
"AA TTTC",
"AA ATCC",
"AA TAAAA",
"AA ATGGC",
"AA AGGTC",
"AA TATAA",
"TT ATT",
"TT TAC",
"TT TGGG",
"TT TGAA",
"TT TGTC",
"TT ATTG",
"TT TGTT",
"TT TAGC",
"TT AAAC",
"TT AGTT",
"TT TACC",
"TT AACC",
"TT ACG",
"TT ATTGC",
"TT TATTC",
"CC AAAG",
"AG T",
"AG TTCC",
"AG ATTC",
"AG ACAC",
"AG TTGG",
"AG TGTC",
"AG TTGC",
"AG AAAAC",
"AG ATTTT",
"AG ATGGG",
"AG ATTTC",
"AG AACAC",
"AG TATTGC",
"TG AT",
"TG TGGG",
"TG AGCC",
"TG AGGC",
"TG TGCC",
"TG ATCC",
"TG ACAC",
"TG TAT",
"TG ACAA",
"TG ATAGG",
"TG TATAC",
"TG AGGTCAGG",
"TC ACC",
"TC AGG",
"TC AAG",
"TC ATGG",
"TC ATCC",
"TC AAAC",
"TC AATT",
"TC AATC",
"TC TGAC",
"TC AAGTGATCC",
"AC T",
"AC TTTT",
"AC TATT",
"AC TCAC",
"AC TGAG",
"AC ATGC",
"AC ATGGG",
"AC TTTTTT",
"AC AACAC",
"AC TACCC",
"AC TAATAC",
"GG AG",
"GG AGG",
"GG ATC",
"GG TGGC",
"GG TTGG",
"GG AAAC",
"GG ACTC",
"GG AAAAAAG",
"ATT A",
"ATT AG",
"ATT TAA",
"ATT TGGG",
"ATT TCAC",
"ATT ACCC",
"ATT TTTC",
"ATT TGAG",
"ATT ACAG",
"ATT TATAC",
"ATT AAAGG",
"ATT TATTTATT",
"AT A",
"AT AGAG",
"AT ATGC",
"AT AAAAC",
"AT ATAG",
"GC GGC",
"GC TGGC",
"GC AAGG",
"GC ACCAC",
"ATG TAA",
"ATG TGG",
"ATG TTG",
"ATG TAC",
"ATG AGCC",
"ATG TGCC",
"ATG ATCC",
"ATG AAAC",
"ATG TCTT",
"ATG AATG",
"ATG TGAAAA",
"AAAA ATG",
"AAAA TTC",
"AAAA CCC",
"ACC AT",
"ACC TTC",
"ACC ATCC",
"ACC ACAC",
"ACC ACAA",
"ACC TGTT",
"ACC TGTG",
"ACC TTCTC",
"ACC TGAGGTCAGG",
"AGG T",
"AGG AAG",
"AGG AAC",
"AGG TGG",
"AGG CCC",
"AGG TAGG",
"AGG AAAAG",
"AGG TGAC",
"AGG AAACC",
"TCC G",
"TCC ATC",
"TCC AAC",
"TCC AGGC",
"TCC TTTAA",
"TCC GCCTCC",
"TAA GG",
"TAA ATG",
"TAA CCC",
"TAA TGAAG",
"AGC A",
"AGC T",
"AGC AT",
"AGC ATC",
"AGC AGGC",
"AGC AAAG",
"AGC TAGC",
"AGC TATG",
"AGC AAGG",
"AGC AATAG",
"AGC TCACTGC",
"TTTT CC",
"TTTT AT",
"TTTT AATAA",
"TTTT TTTTTT",
"AAG TAA",
"AAG CCC",
"AAG TATT",
"AAG AGAA",
"AAG ATAC",
"AAG TTCC",
"AAG TTTC",
"AAG AGGG",
"AAG AGTC",
"AAG ACTT",
"AAG ACTC",
"AAG ACTCC",
"ATC AGCC",
"ATC TCAC",
"ATC ACAC",
"ATC TAGG",
"ATC AGGG",
"ATC ACTT",
"ATC ACG",
"AAC TAG",
"AAC TGCC",
"AAC ACTT",
"TGC GC",
"TGC TGC",
"TGC ATAC",
"TGC ATCC",
"TGG AT",
"TGG TAA",
"TGG ATCC",
"TGG AGAC",
"TGG TGTG",
"TGG TTTTC",
"TTC TG",
"TTC ACC",
"TTC ATC",
"TTG A",
"TTG AAC",
"TTG AGCC",
"TTG TCTC",
"TTG ATGC",
"TTG TTGC",
"TTG AATT",
"TTG AATAA",
"TAG TC",
"TAG CCC",
"TAG GCTGGAG",
"TAC GG",
"TAC TACC",
"TAC ACTG",
"TAC TTGGG",
"TAC TGGGGCC",
"CCC G",
"CCC AAG",
"CCC TTTC",
"CCC GGCC",
"CCC ACCTC",
"CCC AAAGAA",
"TGGG TGC",
"TGGG TTC",
"TGGG AGGC",
"TGGG TCCCC",
"TGGG TTCACGCC",
"TATT AC",
"TATT TTCC",
"TATT TTGC",
"AGCC ATC",
"AGCC TCCAG",
"AGAA AT",
"AGAA TGC",
"AGAA TTC",
"AGAA AGAG",
"AGAA GGCC",
"AGGC TAT",
"AGGC AGAGG",
"AGGC TGGAG",
"AGGC AGATC",
"AGGC AGAAG",
"ATAA ATAA",
"ATAA TTAG",
"ATAA TCAG",
"GGC T",
"GGC GAG",
"GCC TTGG",
"GCC ACTGC",
"GGG ATG",
"GGG TGC",
"GGG ACCC",
"GGG ACAG",
"GGG AATG",
"GGG AGGCTGAGGC",
"TGGC TAC",
"TGGC TGAA",
"TGGC TGGGG",
"TGGC TTGAA",
"TGGC TAATTTT",
"TGGC GTGAA",
"TCAC AATC",
"ATAC AGGC",
"TCCC GCC",
"TCCC TGAA",
"TCCC AAAGTGCTGGGATTACAGGC",
"TTCC ATTC",
"AGAG T",
"AGAG GG",
"AGAG AGAC",
"TGCC AGG",
"TGCC TTG",
"ACCC AGC",
"ACCC ATAC",
"TTTC TAG",
"TGAA T",
"TGAA AC",
"TGAA GGC",
"TGAA ACCC",
"TGAA ATTTAG",
"ATTC TAA",
"ATGG TCC",
"ATGG AAG",
"ATGG TAG",
"ATGG AGTCTC",
"TGAG TATT",
"TGAG ATGG",
"TGAG ACAA",
"ATGC AAG",
"ATGC AATAA",
"TAT AGG",
"TAT ATGC",
"AAAG AGGC",
"AAAG TAT",
"TTGG TC",
"TGTC TTCC",
"TGTC GCCC",
"ACAA AC",
"ACAA TATTTT",
"TTGC AG",
"TTGC TGC",
"ATTG TATT",
"ATTG AGAG",
"ATTG TTTTC",
"TGTT TGGG",
"TGTT TATT",
"TGTT GGG",
"AGGG GCC",
"AGGG TTTCACCATG",
"TATG AGC",
"AAGG AAAA",
"AAGG AGAGC",
"AATT AGCC",
"AGTC TAG",
"AAAAG AAATT",
"AATC ATGC",
"AATC TGAC",
"TAAC TC",
"AGTT TCC",
"AGTT TAGG",
"AGTT TGAGACCAGCC",
"AGTG AAAA",
"AGTG TAG",
"AAAAC ACC",
"AAAAC AGAC",
"TACC TC",
"AAGC G",
"AAGC AA",
"AAGC ATGC",
"AAGC ACTG",
"AACC CC",
"TTTG AGG",
"TTTG CCC",
"ACG A",
"AAAAAAAA AAAA",
"ATCTC ATC",
"ATCTC TGC",
"CCCC G",
"CCCC CC",
"ATTTT CCC",
"ATTTT ATTG",
"TCTT TAAG",
"ATGGC AGCAGGC",
"TGGGC ATGG",
"ATGGG TAG",
"TTAG TGC",
"ACCCC TGGC",
"GGGC GG",
"ATTTC TTG",
"TTTTTT TGAG",
"GCCC GCCGCC",
"AAATG AAC",
"TGAAG TTGG",
"ATTCC ATG",
"ACCAC TAC",
"ACCAC AGAA",
"TGGCC AACATGG",
"TGTAA TCTC",
"TCTG TCTC",
"TTTTG TT",
"AACAC TGAC",
"TGGGG AGTC",
"TTTAA GC",
"ATAGG AGTTGG",
"TATAA AGAA",
"AGATG CC",
"ACTG CCC",
"ATAAC TTC",
"TCCCC GC",
"AAGTC ATGTCTT",
"AGGGC GC",
"TCTTG AAC",
"TTGAA AGCC",
"GAG TAGCTGGGATTACAGGC",
"AATTTT AC",
"TTTCC CCC",
"ACATG AAATG",
"ACATC ATC",
"TCCCAGC TACTTGGG",
"TTAAG AG",
"AGTGTT GGG",
"ACTTC AAG",
"ATTTTC TGG",
"AGGAA TGTG",
"TACAC TGAA",
"AGGCTGG TCTCGAAC",
"AGGCTGG TCTTGAAC"
]
}
}