gengpt2_1024 / tokenizer.json
vojtam's picture
Upload tokenizer.json
4b8a34b verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": false
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": false,
"use_regex": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<|endoftext|>": 0,
"[PAD]": 1,
"A": 2,
"C": 3,
"G": 4,
"T": 5,
"Ċ": 6,
"TT": 7,
"AA": 8,
"TG": 9,
"AG": 10,
"CC": 11,
"TC": 12,
"AC": 13,
"GG": 14,
"ATT": 15,
"AT": 16,
"ATG": 17,
"GC": 18,
"TAA": 19,
"TCC": 20,
"ACC": 21,
"AAAA": 22,
"AGG": 23,
"AGC": 24,
"TTC": 25,
"ATC": 26,
"AAG": 27,
"TTTT": 28,
"TGC": 29,
"TGG": 30,
"AAC": 31,
"TTG": 32,
"TAG": 33,
"TAC": 34,
"CCC": 35,
"TATT": 36,
"TGGG": 37,
"AGAA": 38,
"TAT": 39,
"AGGG": 40,
"TTTC": 41,
"AGGC": 42,
"AGCC": 43,
"TGTG": 44,
"ATAA": 45,
"ATTC": 46,
"TTGG": 47,
"ACAC": 48,
"AAGG": 49,
"TCTC": 50,
"TCCC": 51,
"TATG": 52,
"TTTG": 53,
"TTCC": 54,
"AGAG": 55,
"ATGG": 56,
"AAAC": 57,
"AGTG": 58,
"ACCC": 59,
"TGCC": 60,
"AGAC": 61,
"ATTG": 62,
"ATCC": 63,
"ATGC": 64,
"ATAC": 65,
"TCAC": 66,
"TCTG": 67,
"TTAA": 68,
"TGAA": 69,
"TGGC": 70,
"TTGC": 71,
"TATC": 72,
"TAAG": 73,
"TAAC": 74,
"AAAG": 75,
"GGG": 76,
"AAGC": 77,
"TTAC": 78,
"GGC": 79,
"TAGC": 80,
"ATAT": 81,
"TACC": 82,
"AACC": 83,
"AATG": 84,
"TAGG": 85,
"GCC": 86,
"ATATT": 87,
"AGTC": 88,
"TTTTC": 89,
"TGAC": 90,
"AAAAC": 91,
"AATC": 92,
"TTTAA": 93,
"AAAAG": 94,
"ATAG": 95,
"TGTC": 96,
"TTATT": 97,
"TTTTG": 98,
"TGAG": 99,
"TTTCC": 100,
"AAATT": 101,
"ACAG": 102,
"AATT": 103,
"AATAA": 104,
"TCAG": 105,
"AGGCC": 106,
"AAATG": 107,
"TGGGC": 108,
"ACTC": 109,
"ACG": 110,
"ATTTC": 111,
"ACTG": 112,
"TTAG": 113,
"TGGCC": 114,
"AAAT": 115,
"ATCTC": 116,
"ACAA": 117,
"TATTC": 118,
"ATATG": 119,
"TGTAA": 120,
"ATTCC": 121,
"ACTT": 122,
"ATGCC": 123,
"AAAAAAAA": 124,
"TTCCC": 125,
"TTTGC": 126,
"TTTAG": 127,
"TGGGG": 128,
"TCCCC": 129,
"TTCTC": 130,
"TAAAA": 131,
"ACCCC": 132,
"AGAAG": 133,
"ACCTC": 134,
"AGGGC": 135,
"TTTTTTTT": 136,
"ACATT": 137,
"AGATG": 138,
"GGCC": 139,
"GTG": 140,
"AAGCC": 141,
"ATAAAA": 142,
"AGGAG": 143,
"ATGGC": 144,
"TTTAC": 145,
"ATTAC": 146,
"ATTGC": 147,
"TGGAG": 148,
"TCAA": 149,
"ACTGC": 150,
"TATTG": 151,
"AAGGC": 152,
"TTTGG": 153,
"TTGCC": 154,
"TTGGC": 155,
"AAATC": 156,
"AGAAC": 157,
"GGGC": 158,
"ATATC": 159,
"ACTCC": 160,
"AATTC": 161,
"ATAAC": 162,
"ATCCC": 163,
"AGGGG": 164,
"AAAGC": 165,
"TCG": 166,
"AGAGC": 167,
"ATGGG": 168,
"ATTTT": 169,
"TGAGG": 170,
"AAAGG": 171,
"TTGGG": 172,
"AGAAAA": 173,
"TCTCC": 174,
"TATCC": 175,
"ATTTG": 176,
"ACCAC": 177,
"ATAAG": 178,
"ATCAC": 179,
"TCTTC": 180,
"AGAGG": 181,
"TTTATT": 182,
"AGTAA": 183,
"TGTAG": 184,
"ATAGC": 185,
"AGCCC": 186,
"AGATT": 187,
"TGTGG": 188,
"AGTT": 189,
"TGTGC": 190,
"GGGG": 191,
"TATGC": 192,
"TGAAG": 193,
"TGCCC": 194,
"TGTT": 195,
"AGACC": 196,
"TCTT": 197,
"TCATT": 198,
"AAGGG": 199,
"TCTGC": 200,
"AGTTC": 201,
"AAACC": 202,
"ACATG": 203,
"ACTTC": 204,
"AATAG": 205,
"ACAGC": 206,
"TGATG": 207,
"AATAC": 208,
"AATGG": 209,
"AATGC": 210,
"TGATT": 211,
"TCAGC": 212,
"TGAGC": 213,
"TCAGG": 214,
"TGTTC": 215,
"TCTTG": 216,
"TTTTCC": 217,
"TATGG": 218,
"AGTGG": 219,
"TTAAAA": 220,
"TCCCAGC": 221,
"ATACC": 222,
"AGATC": 223,
"AACCC": 224,
"TACCC": 225,
"TGAAC": 226,
"AATCC": 227,
"TGTTG": 228,
"TAGCC": 229,
"TTAAC": 230,
"TTAAG": 231,
"TTATG": 232,
"ATAGG": 233,
"TTTAT": 234,
"AATTG": 235,
"AGTGC": 236,
"TGTCC": 237,
"TCTAA": 238,
"TAGGC": 239,
"AĊ": 240,
"TCATC": 241,
"TCAAG": 242,
"TTATC": 243,
"TCTTTT": 244,
"TCACC": 245,
"AATTTT": 246,
"AGAAGC": 247,
"ATTTTC": 248,
"AGTGGC": 249,
"CCCC": 250,
"ACTAA": 251,
"ACTAC": 252,
"AGTAG": 253,
"ATTGG": 254,
"AAATAA": 255,
"TCATG": 256,
"TGAGGC": 257,
"TCAGCC": 258,
"AGTTG": 259,
"ACAAC": 260,
"ATTTAA": 261,
"ACATC": 262,
"ACAGG": 263,
"AGTCC": 264,
"TCTGG": 265,
"ACAAG": 266,
"TCAAC": 267,
"TGACC": 268,
"ACACC": 269,
"TTAGC": 270,
"ATATAA": 271,
"TGAAAA": 272,
"TGTTTT": 273,
"AAAGAA": 274,
"AATAT": 275,
"TTGGCC": 276,
"TGATC": 277,
"ACTTG": 278,
"TGTAC": 279,
"TAAGG": 280,
"TAAGC": 281,
"ACAAAA": 282,
"AATATT": 283,
"AAACAC": 284,
"TAGGG": 285,
"TTTGTG": 286,
"ATTTTG": 287,
"TTACC": 288,
"TGTATT": 289,
"TTCG": 290,
"TCTAC": 291,
"TAATTTT": 292,
"TTAGG": 293,
"TAACC": 294,
"TĊ": 295,
"AGAAGG": 296,
"ACTGG": 297,
"ATTATT": 298,
"AGTAC": 299,
"AGCG": 300,
"AGTTTT": 301,
"TCTAG": 302,
"ACGG": 303,
"ACCATG": 304,
"TAATAA": 305,
"ATATTC": 306,
"GCCC": 307,
"TCCTG": 308,
"AAAAGC": 309,
"AAAACC": 310,
"TTCAC": 311,
"AAAAGG": 312,
"ACACACAC": 313,
"AGGAAG": 314,
"TCAGAA": 315,
"AGAGAA": 316,
"ACTAG": 317,
"AACG": 318,
"TCACTGC": 319,
"ATTTCC": 320,
"TGTCTC": 321,
"ACGC": 322,
"TTCCCC": 323,
"TGGGATTAC": 324,
"TGCG": 325,
"TGTAT": 326,
"TGTGTGTG": 327,
"AGGAGG": 328,
"TCTTTC": 329,
"AGGCTGG": 330,
"TCTGCC": 331,
"AAGAC": 332,
"ATCG": 333,
"ATTTTTT": 334,
"TCGC": 335,
"AGCAG": 336,
"ATATAC": 337,
"AAAGTGC": 338,
"AAATTC": 339,
"TTCAAG": 340,
"TCCG": 341,
"ACTTTT": 342,
"TCCTGCC": 343,
"AAAAATT": 344,
"AATTTC": 345,
"AGCCCC": 346,
"AGGTC": 347,
"TTGCCC": 348,
"TTTGCC": 349,
"AAAATAA": 350,
"AGCAGC": 351,
"ATAGAA": 352,
"TGGGGC": 353,
"ACCG": 354,
"AGTTTC": 355,
"TGAGAC": 356,
"AACAC": 357,
"TATATT": 358,
"TGTGGC": 359,
"AGGAGAA": 360,
"TTTCCC": 361,
"AAATAC": 362,
"AGGGGC": 363,
"TTTTGC": 364,
"TGTAATCCCAGC": 365,
"ATATTG": 366,
"TGGGCC": 367,
"TGGGGG": 368,
"TTCTTC": 369,
"TTTATG": 370,
"AAGAAG": 371,
"AAATGC": 372,
"AAATGG": 373,
"TAAAAC": 374,
"ATACAC": 375,
"AGGGCC": 376,
"TGAGAA": 377,
"AAGTGG": 378,
"AGCAC": 379,
"TGTTTC": 380,
"TCCTC": 381,
"TTTTGG": 382,
"ACTTTGGG": 383,
"TAAATG": 384,
"TGTGCC": 385,
"ACAGAA": 386,
"AAAGAC": 387,
"TTCTCC": 388,
"AGATGG": 389,
"AGTCTC": 390,
"AATGAA": 391,
"TGGAGTGC": 392,
"ATTTGC": 393,
"GTGG": 394,
"AGGCTGAGGC": 395,
"ATTTAC": 396,
"AACTC": 397,
"TTTGGC": 398,
"TATTCC": 399,
"TGATCC": 400,
"TTTAAG": 401,
"AGCTC": 402,
"GAG": 403,
"AGGAC": 404,
"AGGTGG": 405,
"TTTGGG": 406,
"TATAC": 407,
"TCCTCC": 408,
"TATATG": 409,
"TTATAA": 410,
"TAAAC": 411,
"TAAAAG": 412,
"AGATAA": 413,
"ATATGC": 414,
"ATTCCC": 415,
"TTCTGC": 416,
"TTTATC": 417,
"AAAGAG": 418,
"AAATTG": 419,
"TTGAAC": 420,
"TCAAAA": 421,
"TGATTC": 422,
"TGCTGC": 423,
"AGTGCC": 424,
"ATATCC": 425,
"TTATTC": 426,
"AATTAA": 427,
"ATATATAT": 428,
"AACAAC": 429,
"AAGAAAA": 430,
"AGTATT": 431,
"ATCTTC": 432,
"ATGGCC": 433,
"TACTC": 434,
"TCTGGC": 435,
"ATGATG": 436,
"ATTTATT": 437,
"ACTCCAGCC": 438,
"AGAGGC": 439,
"AGACAC": 440,
"ATCACC": 441,
"TGAAAC": 442,
"AAATCC": 443,
"ATCTCC": 444,
"AAGTC": 445,
"AATATC": 446,
"AAAGCC": 447,
"AATATG": 448,
"AATCTC": 449,
"GCG": 450,
"AACTCC": 451,
"TGCAC": 452,
"TGAAGG": 453,
"AGAGGG": 454,
"ATATGG": 455,
"TACG": 456,
"AGATTC": 457,
"TTGTTG": 458,
"TTGCAGTG": 459,
"ATGTC": 460,
"ACCTCC": 461,
"AAAGGG": 462,
"AGGAGC": 463,
"ATGAC": 464,
"TGCTC": 465,
"AGTAT": 466,
"ATTGCC": 467,
"TTTAAC": 468,
"AAAGGC": 469,
"TTTTTAA": 470,
"AAAGTG": 471,
"ATGTAA": 472,
"AATTTG": 473,
"TCCCAAAGTGC": 474,
"AAATATT": 475,
"TGGAAG": 476,
"TTGGGG": 477,
"AATTCC": 478,
"ATTTAG": 479,
"AAGGCC": 480,
"TTAAAC": 481,
"TCTTCC": 482,
"AGCTCC": 483,
"TTCTG": 484,
"ATAGAG": 485,
"TGGGATTACAGGC": 486,
"ATGAAG": 487,
"AATGGC": 488,
"TTAGAA": 489,
"AGCTGC": 490,
"AGGCCC": 491,
"TTGGGC": 492,
"TGCCCC": 493,
"AGGAAC": 494,
"ATCCCC": 495,
"TCTCCC": 496,
"TCCAC": 497,
"AATAAC": 498,
"AAAAAC": 499,
"TTAGCC": 500,
"TCACCC": 501,
"AAGAAC": 502,
"TTTAGTAG": 503,
"AGGCTGGAGTGC": 504,
"TAAATT": 505,
"TAAAAATAC": 506,
"ATGTG": 507,
"ATGTGG": 508,
"AAACCC": 509,
"TGAAGC": 510,
"ACCACC": 511,
"AGCAGG": 512,
"TCGG": 513,
"TTCAAC": 514,
"AGCAAG": 515,
"TCATTC": 516,
"ATCATC": 517,
"ATGGGG": 518,
"ATTTGG": 519,
"AAGGGG": 520,
"TTGAC": 521,
"TCTCG": 522,
"AGAGCC": 523,
"AGAACC": 524,
"ATAGTG": 525,
"AGGTGC": 526,
"ATGTGC": 527,
"CCCAGC": 528,
"TAGAC": 529,
"AATGTG": 530,
"TATAAAA": 531,
"AATTAC": 532,
"TGTTTG": 533,
"TTATTG": 534,
"AGTTTG": 535,
"TCTGTG": 536,
"TTTTTTG": 537,
"AATAAG": 538,
"ATAGGC": 539,
"ATGTTC": 540,
"TGATAA": 541,
"TGGCCC": 542,
"AAGGGC": 543,
"ATACCC": 544,
"ATAGAC": 545,
"ATCTGC": 546,
"ACAGAG": 547,
"TGAGCC": 548,
"ACTCTG": 549,
"ATGTTG": 550,
"TGTTCC": 551,
"TTCTTG": 552,
"TGGAGC": 553,
"TGTATG": 554,
"TCTATT": 555,
"TAGCTGGG": 556,
"ATCTTG": 557,
"TGTGGG": 558,
"AGGGGG": 559,
"TGGAC": 560,
"TTCTTTT": 561,
"TACAC": 562,
"TTCTAG": 563,
"TCTTTG": 564,
"AACATGG": 565,
"TTTACC": 566,
"AGATGC": 567,
"TTCTAA": 568,
"TCTTGC": 569,
"AGTTCC": 570,
"ACCGC": 571,
"ATTTTTC": 572,
"TAAGCC": 573,
"ATGAAC": 574,
"AACCCC": 575,
"ATGGGC": 576,
"ATTAAAA": 577,
"TCCTGC": 578,
"AAGTAA": 579,
"ATAAGC": 580,
"GGGCC": 581,
"AGCTAC": 582,
"AAAAAAAAAAAAAAAA": 583,
"ATCATG": 584,
"TCCTGCCTCAGCC": 585,
"TATTTATT": 586,
"TTCTGG": 587,
"AAGCG": 588,
"TCCCCC": 589,
"ACCCCC": 590,
"AGTTAA": 591,
"AGTGTG": 592,
"AGTGGG": 593,
"ATTTAT": 594,
"TGAGAG": 595,
"AATCAC": 596,
"TTGAACC": 597,
"ATAAGG": 598,
"TGGTGG": 599,
"TGCAGC": 600,
"TAGAAG": 601,
"TTTTTTTTTTTTTTTT": 602,
"TTCATC": 603,
"AAAAAAG": 604,
"ACTTTC": 605,
"TGATGG": 606,
"TGGAGG": 607,
"ATTAAC": 608,
"ACCTGC": 609,
"ATGCCC": 610,
"TTGTAA": 611,
"AAAAAAC": 612,
"TTGAAG": 613,
"TGAGGG": 614,
"TTCAGC": 615,
"AATGCC": 616,
"TGTCTG": 617,
"AGTATG": 618,
"TTTAGC": 619,
"ATCTAA": 620,
"AGATAC": 621,
"ATGTCC": 622,
"TAGAAC": 623,
"AGCCG": 624,
"AATTGC": 625,
"TTCATT": 626,
"TACTAAAAATAC": 627,
"GTCTC": 628,
"ATAAAAC": 629,
"TGGAAC": 630,
"TTAACC": 631,
"AAATATC": 632,
"AGGTAA": 633,
"TTAAGC": 634,
"AATCTG": 635,
"AGACCC": 636,
"TATATC": 637,
"AATCCC": 638,
"AGGAAAA": 639,
"TCCTGACCTC": 640,
"TACAAAA": 641,
"ACTGTG": 642,
"AGGCCG": 643,
"ATAACC": 644,
"AGGCGG": 645,
"AACCTCC": 646,
"TATTGC": 647,
"ATCAAC": 648,
"TCTGGG": 649,
"AGGTTC": 650,
"AGCAAC": 651,
"AAATAT": 652,
"AGTCTG": 653,
"TGGTGC": 654,
"TATAAC": 655,
"AAATAG": 656,
"ATCATT": 657,
"AGGATG": 658,
"TTATAC": 659,
"TGAACC": 660,
"TTTAGG": 661,
"GCCCC": 662,
"AGTAAC": 663,
"AATAGC": 664,
"TTTTTC": 665,
"ATAGCC": 666,
"AAGAGC": 667,
"AAGATG": 668,
"TTGTAG": 669,
"ACTGCACTCCAGCC": 670,
"TCCAGC": 671,
"ATAAATAA": 672,
"AGTCAC": 673,
"TTGTC": 674,
"GTGC": 675,
"TTCATG": 676,
"AATGGG": 677,
"ACTTCC": 678,
"ATAGGG": 679,
"TGGGCAAC": 680,
"ATTATG": 681,
"AATACC": 682,
"TGAGTG": 683,
"AAGCCC": 684,
"TACTAA": 685,
"TTCTTTC": 686,
"AGAAAAG": 687,
"TCAGGG": 688,
"AGTAAG": 689,
"ACCTTG": 690,
"TATCCC": 691,
"TGACAC": 692,
"TGTTGG": 693,
"TATGCC": 694,
"TAGGCC": 695,
"TGCAAG": 696,
"AGCTGG": 697,
"TTCTAC": 698,
"ACCAAC": 699,
"TTAAGG": 700,
"TCCCAAG": 701,
"TGCTCC": 702,
"ATTAAG": 703,
"ATGAGCC": 704,
"ACATTC": 705,
"TTATCC": 706,
"AGCATC": 707,
"ATAAAAG": 708,
"TTGTTTT": 709,
"TCACAC": 710,
"TCACAGAG": 711,
"AGTCCC": 712,
"AGACCAGCC": 713,
"AGGCTGAGGCAGGAGAA": 714,
"TGTCCC": 715,
"TTACAC": 716,
"ACCTAA": 717,
"AGAAAAC": 718,
"ACAGCC": 719,
"TCAGGC": 720,
"TGTATC": 721,
"ATTTTAA": 722,
"ACATGG": 723,
"TGATGC": 724,
"AGTTAC": 725,
"AGGTAG": 726,
"ATCAAG": 727,
"TGTTAA": 728,
"AGCTTC": 729,
"TCCTTC": 730,
"TATGGC": 731,
"AGCTAA": 732,
"TTTCTTTC": 733,
"AGGTTG": 734,
"ACAAAC": 735,
"TGTAATCCCAGCACTTTGGG": 736,
"AGCATT": 737,
"TGGCTCAC": 738,
"TCATGCC": 739,
"TCCTGG": 740,
"ACCAGCC": 741,
"TTAGAG": 742,
"AGATTG": 743,
"AATTATT": 744,
"TGCTTC": 745,
"TGTCAC": 746,
"AATTTAA": 747,
"CCCG": 748,
"ACAGGG": 749,
"TCAGAG": 750,
"AGATCC": 751,
"TGTAAG": 752,
"ATGAAAA": 753,
"ACCTGG": 754,
"TCTAT": 755,
"AAGATC": 756,
"TACCCC": 757,
"AGTAGC": 758,
"ATTATC": 759,
"ACCAGC": 760,
"TCAAAC": 761,
"TAATAC": 762,
"TCTCTCTC": 763,
"ATGTAC": 764,
"TCAAGC": 765,
"AGTATC": 766,
"TGTTGC": 767,
"TTTCCCC": 768,
"ACAGTG": 769,
"AGGTGTG": 770,
"TCATTG": 771,
"AAATAAAA": 772,
"TAGAAAA": 773,
"AGTTGG": 774,
"AATAGG": 775,
"ATTTCTC": 776,
"AACATC": 777,
"TCCTTG": 778,
"ACTTTG": 779,
"TCCTGAG": 780,
"TGTAAC": 781,
"AGTTGC": 782,
"AAACGGG": 783,
"AATTGG": 784,
"TTGAACCC": 785,
"ACAGGC": 786,
"TTATGC": 787,
"AACAAAA": 788,
"ACCTCCC": 789,
"GTGAGCC": 790,
"ATCTAC": 791,
"ACCAAG": 792,
"ATAGTC": 793,
"AACTTC": 794,
"ACCTTC": 795,
"ATGTAG": 796,
"ATAATAA": 797,
"GGGGC": 798,
"TCATCC": 799,
"ATGATC": 800,
"AAACG": 801,
"ACCATC": 802,
"TTACCC": 803,
"ACAGAC": 804,
"TCTTGG": 805,
"AGGTAC": 806,
"ACTAT": 807,
"TTGTATT": 808,
"TGCTGG": 809,
"TCAAGG": 810,
"TCAGGAG": 811,
"TCAGTG": 812,
"ATTTTTG": 813,
"AGGATC": 814,
"TATTGG": 815,
"ATTGGC": 816,
"ATTTTCC": 817,
"AGGATGG": 818,
"TTATATT": 819,
"TCCATG": 820,
"ACATGC": 821,
"AATTTTC": 822,
"AGAGAGAG": 823,
"ACACG": 824,
"ACATAA": 825,
"TGACCC": 826,
"TTTTTTTTTTTT": 827,
"TGGTAA": 828,
"TGTTAC": 829,
"AGGAGGC": 830,
"TTTTAAAA": 831,
"TTAGGG": 832,
"TCCCG": 833,
"TAGTAA": 834,
"AAGTGC": 835,
"ACCTAC": 836,
"AAAAAAAAAAAA": 837,
"AGACAGGG": 838,
"TCCATC": 839,
"TGGCG": 840,
"TTTCACCATG": 841,
"AGGCTGC": 842,
"ATGAGC": 843,
"AGAAAGAA": 844,
"TATGGG": 845,
"AGACG": 846,
"TATAAG": 847,
"AAAATAC": 848,
"ACTGGG": 849,
"TGAAACCCC": 850,
"TTCAGG": 851,
"ACTATT": 852,
"TGTTTTC": 853,
"TTATGG": 854,
"TCCTGGG": 855,
"AACTAA": 856,
"TCCTAA": 857,
"TTAGTG": 858,
"TTTGTGATG": 859,
"AGGCG": 860,
"TTTATTC": 861,
"TGATTG": 862,
"ACTGCC": 863,
"AAGAGG": 864,
"AACATT": 865,
"AGTAGG": 866,
"TCATAA": 867,
"AACTGC": 868,
"ACATCC": 869,
"TCATGG": 870,
"ATTCTCAGAA": 871,
"TTGTTC": 872,
"TCCCAGCTAC": 873,
"AACAGC": 874,
"TCCAAG": 875,
"TCAAAG": 876,
"TGAGTC": 877,
"ATGATT": 878,
"ACTCTC": 879,
"ATGAGG": 880,
"ACCTGCC": 881,
"TCGGCC": 882,
"ACATAC": 883,
"TCCAGG": 884,
"TTGTGC": 885,
"TAATTTTTGTATT": 886,
"GCGG": 887,
"ATTCG": 888,
"ATĊ": 889,
"TAAAAAA": 890,
"TGGGTGAC": 891,
"AAAGAAAA": 892,
"TTAGAC": 893,
"ATCTGG": 894,
"ATTTTAC": 895,
"TGCAGG": 896,
"TGATAC": 897,
"AAGTTC": 898,
"ACTGAA": 899,
"AGTTTTC": 900,
"AGCACC": 901,
"TGGGCG": 902,
"AACATG": 903,
"ACTCCC": 904,
"ACAATG": 905,
"AGCATG": 906,
"AACAAG": 907,
"AGATGGGG": 908,
"ACTATG": 909,
"TCATGC": 910,
"ACATTG": 911,
"AAAGAAG": 912,
"TCTATC": 913,
"ATTTCG": 914,
"TGCATG": 915,
"ATTGGG": 916,
"TTTGTAA": 917,
"AACTAC": 918,
"TTGTAC": 919,
"TGTAGG": 920,
"ATTTTTAA": 921,
"AGTACC": 922,
"TCTTAA": 923,
"AAACTCC": 924,
"AGATATT": 925,
"TAATTC": 926,
"TGGTAG": 927,
"TAGCTGGGACTAC": 928,
"TGGGAGG": 929,
"AATCTGC": 930,
"TCTTAC": 931,
"TTGAGG": 932,
"ACAAGG": 933,
"TTAAAAC": 934,
"TCTATG": 935,
"AATTTTG": 936,
"ATATATG": 937,
"ATCAGC": 938,
"TTTTTTC": 939,
"ATATAAAA": 940,
"TATTTTC": 941,
"ACACCC": 942,
"TCTGTCTC": 943,
"TGTAGC": 944,
"TTGAAAA": 945,
"TTGTGG": 946,
"AGGCCCC": 947,
"TTAGGC": 948,
"AAACAAAC": 949,
"ATATATT": 950,
"ATAAATG": 951,
"TTGTCC": 952,
"AGCTGAG": 953,
"AGCGC": 954,
"ACCACG": 955,
"TTTTTCC": 956,
"ATCGC": 957,
"AAGTAG": 958,
"TACATG": 959,
"ATGGTGGC": 960,
"AGGTCAGGAG": 961,
"ACTTGG": 962,
"TAAATC": 963,
"AGGAAGG": 964,
"ACTCAC": 965,
"TGTACC": 966,
"TTTTTTTC": 967,
"TAATGC": 968,
"TGGAAAA": 969,
"TAGTAG": 970,
"TGGATG": 971,
"TAAGGC": 972,
"ACTGGC": 973,
"TCAGAC": 974,
"TTGGAAACGGG": 975,
"ACAAAG": 976,
"ATTCAAC": 977,
"TTTCG": 978,
"TATTTTG": 979,
"TCAGTC": 980,
"TTTATTG": 981,
"AGGAAAC": 982,
"TGGTTC": 983,
"AGCTGGG": 984,
"TCTTTTC": 985,
"AGAAATG": 986,
"TGGATC": 987,
"TTATAG": 988,
"TATATAA": 989,
"TCACG": 990,
"ACTTGC": 991,
"ACCAGG": 992,
"TTTTGCC": 993,
"AAGTAC": 994,
"TAATAG": 995,
"AAAAATG": 996,
"AGATAG": 997,
"TCCAGCC": 998,
"TATAGC": 999,
"TCTACC": 1000,
"ATTTTATT": 1001,
"AAGTTG": 1002,
"ATCACTTG": 1003,
"AAGTCC": 1004,
"AAATTCC": 1005,
"AAAATGC": 1006,
"TCAATG": 1007,
"TTTTCCC": 1008,
"GGCTCACTGC": 1009,
"TATTTAA": 1010,
"TACTTC": 1011,
"ATACG": 1012,
"TACTGC": 1013,
"TAĊ": 1014,
"ATCTAG": 1015,
"ACCTAG": 1016,
"ATTAGG": 1017,
"ACTTAC": 1018,
"TTCTTCC": 1019,
"AGACGG": 1020,
"TTTTTATT": 1021,
"AGGCTGGAGTGCAGTGGC": 1022,
"TTAAAAG": 1023
},
"merges": [
[
"T",
"T"
],
[
"A",
"A"
],
[
"T",
"G"
],
[
"A",
"G"
],
[
"C",
"C"
],
[
"T",
"C"
],
[
"A",
"C"
],
[
"G",
"G"
],
[
"A",
"TT"
],
[
"A",
"T"
],
[
"A",
"TG"
],
[
"G",
"C"
],
[
"T",
"AA"
],
[
"T",
"CC"
],
[
"A",
"CC"
],
[
"AA",
"AA"
],
[
"AG",
"G"
],
[
"AG",
"C"
],
[
"TT",
"C"
],
[
"A",
"TC"
],
[
"AA",
"G"
],
[
"TT",
"TT"
],
[
"TG",
"C"
],
[
"TG",
"G"
],
[
"AA",
"C"
],
[
"TT",
"G"
],
[
"T",
"AG"
],
[
"T",
"AC"
],
[
"CC",
"C"
],
[
"T",
"ATT"
],
[
"TG",
"GG"
],
[
"AG",
"AA"
],
[
"T",
"AT"
],
[
"AG",
"GG"
],
[
"TT",
"TC"
],
[
"AG",
"GC"
],
[
"AG",
"CC"
],
[
"TG",
"TG"
],
[
"AT",
"AA"
],
[
"ATT",
"C"
],
[
"TT",
"GG"
],
[
"AC",
"AC"
],
[
"AA",
"GG"
],
[
"TC",
"TC"
],
[
"TCC",
"C"
],
[
"T",
"ATG"
],
[
"TT",
"TG"
],
[
"TT",
"CC"
],
[
"AG",
"AG"
],
[
"ATG",
"G"
],
[
"AA",
"AC"
],
[
"AG",
"TG"
],
[
"ACC",
"C"
],
[
"TG",
"CC"
],
[
"AG",
"AC"
],
[
"ATT",
"G"
],
[
"AT",
"CC"
],
[
"ATG",
"C"
],
[
"AT",
"AC"
],
[
"TC",
"AC"
],
[
"TC",
"TG"
],
[
"TT",
"AA"
],
[
"TG",
"AA"
],
[
"TG",
"GC"
],
[
"TT",
"GC"
],
[
"T",
"ATC"
],
[
"TAA",
"G"
],
[
"TAA",
"C"
],
[
"AA",
"AG"
],
[
"GG",
"G"
],
[
"AA",
"GC"
],
[
"TT",
"AC"
],
[
"GG",
"C"
],
[
"T",
"AGC"
],
[
"AT",
"AT"
],
[
"T",
"ACC"
],
[
"AA",
"CC"
],
[
"AA",
"TG"
],
[
"T",
"AGG"
],
[
"G",
"CC"
],
[
"AT",
"ATT"
],
[
"AG",
"TC"
],
[
"TT",
"TTC"
],
[
"TG",
"AC"
],
[
"AAAA",
"C"
],
[
"AA",
"TC"
],
[
"TT",
"TAA"
],
[
"AAAA",
"G"
],
[
"AT",
"AG"
],
[
"TG",
"TC"
],
[
"TT",
"ATT"
],
[
"TTTT",
"G"
],
[
"TG",
"AG"
],
[
"TT",
"TCC"
],
[
"AA",
"ATT"
],
[
"AC",
"AG"
],
[
"AA",
"TT"
],
[
"AA",
"TAA"
],
[
"TC",
"AG"
],
[
"AGG",
"CC"
],
[
"AA",
"ATG"
],
[
"TGGG",
"C"
],
[
"AC",
"TC"
],
[
"AC",
"G"
],
[
"ATT",
"TC"
],
[
"AC",
"TG"
],
[
"TT",
"AG"
],
[
"TGG",
"CC"
],
[
"AA",
"AT"
],
[
"ATC",
"TC"
],
[
"AC",
"AA"
],
[
"TATT",
"C"
],
[
"AT",
"ATG"
],
[
"TG",
"TAA"
],
[
"ATT",
"CC"
],
[
"AC",
"TT"
],
[
"ATG",
"CC"
],
[
"AAAA",
"AAAA"
],
[
"TT",
"CCC"
],
[
"TT",
"TGC"
],
[
"TT",
"TAG"
],
[
"TGGG",
"G"
],
[
"TCC",
"CC"
],
[
"TTC",
"TC"
],
[
"TAA",
"AA"
],
[
"ACC",
"CC"
],
[
"AG",
"AAG"
],
[
"ACC",
"TC"
],
[
"AGGG",
"C"
],
[
"TTTT",
"TTTT"
],
[
"AC",
"ATT"
],
[
"AG",
"ATG"
],
[
"GG",
"CC"
],
[
"G",
"TG"
],
[
"AAG",
"CC"
],
[
"AT",
"AAAA"
],
[
"AGG",
"AG"
],
[
"ATG",
"GC"
],
[
"TT",
"TAC"
],
[
"ATT",
"AC"
],
[
"ATT",
"GC"
],
[
"TGG",
"AG"
],
[
"TC",
"AA"
],
[
"AC",
"TGC"
],
[
"TATT",
"G"
],
[
"AAGG",
"C"
],
[
"TT",
"TGG"
],
[
"TTG",
"CC"
],
[
"TTGG",
"C"
],
[
"AA",
"ATC"
],
[
"AG",
"AAC"
],
[
"GG",
"GC"
],
[
"AT",
"ATC"
],
[
"AC",
"TCC"
],
[
"AA",
"TTC"
],
[
"AT",
"AAC"
],
[
"AT",
"CCC"
],
[
"AGGG",
"G"
],
[
"AA",
"AGC"
],
[
"TC",
"G"
],
[
"AG",
"AGC"
],
[
"ATG",
"GG"
],
[
"ATT",
"TT"
],
[
"TG",
"AGG"
],
[
"AA",
"AGG"
],
[
"TTGG",
"G"
],
[
"AG",
"AAAA"
],
[
"TC",
"TCC"
],
[
"TAT",
"CC"
],
[
"ATT",
"TG"
],
[
"ACC",
"AC"
],
[
"AT",
"AAG"
],
[
"ATC",
"AC"
],
[
"TC",
"TTC"
],
[
"AG",
"AGG"
],
[
"TT",
"TATT"
],
[
"AG",
"TAA"
],
[
"TG",
"TAG"
],
[
"AT",
"AGC"
],
[
"AG",
"CCC"
],
[
"AG",
"ATT"
],
[
"TG",
"TGG"
],
[
"AG",
"TT"
],
[
"TG",
"TGC"
],
[
"GG",
"GG"
],
[
"TATG",
"C"
],
[
"TG",
"AAG"
],
[
"TG",
"CCC"
],
[
"TG",
"TT"
],
[
"AG",
"ACC"
],
[
"TC",
"TT"
],
[
"TC",
"ATT"
],
[
"AAGG",
"G"
],
[
"TC",
"TGC"
],
[
"AG",
"TTC"
],
[
"AA",
"ACC"
],
[
"AC",
"ATG"
],
[
"AC",
"TTC"
],
[
"AA",
"TAG"
],
[
"AC",
"AGC"
],
[
"TG",
"ATG"
],
[
"AA",
"TAC"
],
[
"AA",
"TGG"
],
[
"AA",
"TGC"
],
[
"TG",
"ATT"
],
[
"TC",
"AGC"
],
[
"TG",
"AGC"
],
[
"TC",
"AGG"
],
[
"TG",
"TTC"
],
[
"TC",
"TTG"
],
[
"TTTT",
"CC"
],
[
"TATG",
"G"
],
[
"AG",
"TGG"
],
[
"TT",
"AAAA"
],
[
"TCCC",
"AGC"
],
[
"AT",
"ACC"
],
[
"AG",
"ATC"
],
[
"AA",
"CCC"
],
[
"T",
"ACCC"
],
[
"TG",
"AAC"
],
[
"AA",
"TCC"
],
[
"TG",
"TTG"
],
[
"TAG",
"CC"
],
[
"TT",
"AAC"
],
[
"TT",
"AAG"
],
[
"TT",
"ATG"
],
[
"AT",
"AGG"
],
[
"TT",
"TAT"
],
[
"AA",
"TTG"
],
[
"AG",
"TGC"
],
[
"TG",
"TCC"
],
[
"TC",
"TAA"
],
[
"TAG",
"GC"
],
[
"A",
"Ċ"
],
[
"TC",
"ATC"
],
[
"TC",
"AAG"
],
[
"TT",
"ATC"
],
[
"TC",
"TTTT"
],
[
"TC",
"ACC"
],
[
"AA",
"TTTT"
],
[
"AGAA",
"GC"
],
[
"ATT",
"TTC"
],
[
"AGTG",
"GC"
],
[
"CC",
"CC"
],
[
"AC",
"TAA"
],
[
"AC",
"TAC"
],
[
"AG",
"TAG"
],
[
"ATT",
"GG"
],
[
"AA",
"ATAA"
],
[
"TC",
"ATG"
],
[
"TG",
"AGGC"
],
[
"TC",
"AGCC"
],
[
"AG",
"TTG"
],
[
"AC",
"AAC"
],
[
"ATT",
"TAA"
],
[
"AC",
"ATC"
],
[
"AC",
"AGG"
],
[
"AG",
"TCC"
],
[
"TC",
"TGG"
],
[
"AC",
"AAG"
],
[
"TC",
"AAC"
],
[
"TG",
"ACC"
],
[
"AC",
"ACC"
],
[
"TT",
"AGC"
],
[
"AT",
"ATAA"
],
[
"TG",
"AAAA"
],
[
"TG",
"TTTT"
],
[
"AA",
"AGAA"
],
[
"AA",
"TAT"
],
[
"TTGG",
"CC"
],
[
"TG",
"ATC"
],
[
"AC",
"TTG"
],
[
"TG",
"TAC"
],
[
"TAA",
"GG"
],
[
"TAA",
"GC"
],
[
"AC",
"AAAA"
],
[
"AA",
"TATT"
],
[
"AA",
"ACAC"
],
[
"TAG",
"GG"
],
[
"TT",
"TGTG"
],
[
"ATT",
"TTG"
],
[
"TT",
"ACC"
],
[
"TG",
"TATT"
],
[
"TTC",
"G"
],
[
"TC",
"TAC"
],
[
"TAA",
"TTTT"
],
[
"TT",
"AGG"
],
[
"TAA",
"CC"
],
[
"T",
"Ċ"
],
[
"AGAA",
"GG"
],
[
"AC",
"TGG"
],
[
"ATT",
"ATT"
],
[
"AG",
"TAC"
],
[
"AGC",
"G"
],
[
"AG",
"TTTT"
],
[
"TC",
"TAG"
],
[
"AC",
"GG"
],
[
"ACC",
"ATG"
],
[
"TAA",
"TAA"
],
[
"AT",
"ATTC"
],
[
"G",
"CCC"
],
[
"TCC",
"TG"
],
[
"AAAA",
"GC"
],
[
"AAAA",
"CC"
],
[
"TTC",
"AC"
],
[
"AAAA",
"GG"
],
[
"ACAC",
"ACAC"
],
[
"AGG",
"AAG"
],
[
"TC",
"AGAA"
],
[
"AG",
"AGAA"
],
[
"AC",
"TAG"
],
[
"AAC",
"G"
],
[
"TCAC",
"TGC"
],
[
"ATT",
"TCC"
],
[
"TG",
"TCTC"
],
[
"AC",
"GC"
],
[
"TTCC",
"CC"
],
[
"TGGG",
"ATTAC"
],
[
"TGC",
"G"
],
[
"TG",
"TAT"
],
[
"TGTG",
"TGTG"
],
[
"AGG",
"AGG"
],
[
"TC",
"TTTC"
],
[
"AGGC",
"TGG"
],
[
"TC",
"TGCC"
],
[
"AAG",
"AC"
],
[
"ATC",
"G"
],
[
"ATT",
"TTTT"
],
[
"TC",
"GC"
],
[
"AGC",
"AG"
],
[
"AT",
"ATAC"
],
[
"AAAG",
"TGC"
],
[
"AA",
"ATTC"
],
[
"TTC",
"AAG"
],
[
"TCC",
"G"
],
[
"AC",
"TTTT"
],
[
"TCC",
"TGCC"
],
[
"AAAA",
"ATT"
],
[
"AA",
"TTTC"
],
[
"AGCC",
"CC"
],
[
"AGG",
"TC"
],
[
"TTG",
"CCC"
],
[
"TTTG",
"CC"
],
[
"AAAA",
"TAA"
],
[
"AGC",
"AGC"
],
[
"AT",
"AGAA"
],
[
"TGGG",
"GC"
],
[
"ACC",
"G"
],
[
"AG",
"TTTC"
],
[
"TG",
"AGAC"
],
[
"AAC",
"AC"
],
[
"TAT",
"ATT"
],
[
"TGTG",
"GC"
],
[
"AGG",
"AGAA"
],
[
"TT",
"TCCC"
],
[
"AA",
"ATAC"
],
[
"AGGG",
"GC"
],
[
"TTTT",
"GC"
],
[
"TGTAA",
"TCCCAGC"
],
[
"AT",
"ATTG"
],
[
"TGGG",
"CC"
],
[
"TGGG",
"GG"
],
[
"TTC",
"TTC"
],
[
"TT",
"TATG"
],
[
"AAG",
"AAG"
],
[
"AA",
"ATGC"
],
[
"AA",
"ATGG"
],
[
"TAA",
"AAC"
],
[
"AT",
"ACAC"
],
[
"AGGG",
"CC"
],
[
"TG",
"AGAA"
],
[
"AAG",
"TGG"
],
[
"AGC",
"AC"
],
[
"TG",
"TTTC"
],
[
"TCC",
"TC"
],
[
"TTTT",
"GG"
],
[
"ACTT",
"TGGG"
],
[
"TAA",
"ATG"
],
[
"TGTG",
"CC"
],
[
"AC",
"AGAA"
],
[
"AA",
"AGAC"
],
[
"TTC",
"TCC"
],
[
"AG",
"ATGG"
],
[
"AG",
"TCTC"
],
[
"AA",
"TGAA"
],
[
"TGGAG",
"TGC"
],
[
"ATT",
"TGC"
],
[
"G",
"TGG"
],
[
"AGGC",
"TGAGGC"
],
[
"ATT",
"TAC"
],
[
"AAC",
"TC"
],
[
"TTTG",
"GC"
],
[
"TATT",
"CC"
],
[
"TG",
"ATCC"
],
[
"TT",
"TAAG"
],
[
"AGC",
"TC"
],
[
"G",
"AG"
],
[
"AGG",
"AC"
],
[
"AGG",
"TGG"
],
[
"TT",
"TGGG"
],
[
"TAT",
"AC"
],
[
"TCC",
"TCC"
],
[
"TAT",
"ATG"
],
[
"TT",
"ATAA"
],
[
"TAA",
"AC"
],
[
"TAA",
"AAG"
],
[
"AG",
"ATAA"
],
[
"AT",
"ATGC"
],
[
"ATT",
"CCC"
],
[
"TTC",
"TGC"
],
[
"TT",
"TATC"
],
[
"AA",
"AGAG"
],
[
"AA",
"ATTG"
],
[
"TTG",
"AAC"
],
[
"TC",
"AAAA"
],
[
"TG",
"ATTC"
],
[
"TGC",
"TGC"
],
[
"AGTG",
"CC"
],
[
"AT",
"ATCC"
],
[
"TT",
"ATTC"
],
[
"AA",
"TTAA"
],
[
"ATAT",
"ATAT"
],
[
"AAC",
"AAC"
],
[
"AAG",
"AAAA"
],
[
"AG",
"TATT"
],
[
"ATC",
"TTC"
],
[
"ATGG",
"CC"
],
[
"TAC",
"TC"
],
[
"TCTG",
"GC"
],
[
"ATG",
"ATG"
],
[
"ATT",
"TATT"
],
[
"ACTCC",
"AGCC"
],
[
"AG",
"AGGC"
],
[
"AG",
"ACAC"
],
[
"ATC",
"ACC"
],
[
"TG",
"AAAC"
],
[
"AA",
"ATCC"
],
[
"ATC",
"TCC"
],
[
"AAG",
"TC"
],
[
"AA",
"TATC"
],
[
"AA",
"AGCC"
],
[
"AA",
"TATG"
],
[
"AA",
"TCTC"
],
[
"GC",
"G"
],
[
"AAC",
"TCC"
],
[
"TGC",
"AC"
],
[
"TG",
"AAGG"
],
[
"AG",
"AGGG"
],
[
"AT",
"ATGG"
],
[
"TAC",
"G"
],
[
"AG",
"ATTC"
],
[
"TTG",
"TTG"
],
[
"TTGC",
"AGTG"
],
[
"ATG",
"TC"
],
[
"ACC",
"TCC"
],
[
"AA",
"AGGG"
],
[
"AGG",
"AGC"
],
[
"ATG",
"AC"
],
[
"TGC",
"TC"
],
[
"AG",
"TAT"
],
[
"ATTG",
"CC"
],
[
"TT",
"TAAC"
],
[
"AA",
"AGGC"
],
[
"TTTT",
"TAA"
],
[
"AA",
"AGTG"
],
[
"ATG",
"TAA"
],
[
"AA",
"TTTG"
],
[
"TCCC",
"AAAGTGC"
],
[
"AA",
"ATATT"
],
[
"TGG",
"AAG"
],
[
"TTGG",
"GG"
],
[
"AA",
"TTCC"
],
[
"ATT",
"TAG"
],
[
"AAGG",
"CC"
],
[
"TT",
"AAAC"
],
[
"TC",
"TTCC"
],
[
"AGC",
"TCC"
],
[
"TTC",
"TG"
],
[
"AT",
"AGAG"
],
[
"TGGGATTAC",
"AGGC"
],
[
"ATG",
"AAG"
],
[
"AA",
"TGGC"
],
[
"TT",
"AGAA"
],
[
"AGC",
"TGC"
],
[
"AGG",
"CCC"
],
[
"TTGG",
"GC"
],
[
"TGCC",
"CC"
],
[
"AGG",
"AAC"
],
[
"ATCC",
"CC"
],
[
"TC",
"TCCC"
],
[
"TCC",
"AC"
],
[
"AA",
"TAAC"
],
[
"AAAA",
"AC"
],
[
"TT",
"AGCC"
],
[
"TC",
"ACCC"
],
[
"AAG",
"AAC"
],
[
"TTTAG",
"TAG"
],
[
"AGGC",
"TGGAGTGC"
],
[
"TAA",
"ATT"
],
[
"TAAAA",
"ATAC"
],
[
"ATG",
"TG"
],
[
"ATG",
"TGG"
],
[
"AA",
"ACCC"
],
[
"TGAA",
"GC"
],
[
"ACC",
"ACC"
],
[
"AGC",
"AGG"
],
[
"TC",
"GG"
],
[
"TTC",
"AAC"
],
[
"AGC",
"AAG"
],
[
"TC",
"ATTC"
],
[
"ATC",
"ATC"
],
[
"ATG",
"GGG"
],
[
"ATT",
"TGG"
],
[
"AAGG",
"GG"
],
[
"TTG",
"AC"
],
[
"TCTC",
"G"
],
[
"AG",
"AGCC"
],
[
"AGAA",
"CC"
],
[
"AT",
"AGTG"
],
[
"AGG",
"TGC"
],
[
"ATG",
"TGC"
],
[
"CCC",
"AGC"
],
[
"TAG",
"AC"
],
[
"AA",
"TGTG"
],
[
"TAT",
"AAAA"
],
[
"AA",
"TTAC"
],
[
"TG",
"TTTG"
],
[
"TT",
"ATTG"
],
[
"AG",
"TTTG"
],
[
"TC",
"TGTG"
],
[
"TTTT",
"TTG"
],
[
"AA",
"TAAG"
],
[
"AT",
"AGGC"
],
[
"ATG",
"TTC"
],
[
"TG",
"ATAA"
],
[
"TGG",
"CCC"
],
[
"AAGG",
"GC"
],
[
"AT",
"ACCC"
],
[
"AT",
"AGAC"
],
[
"ATC",
"TGC"
],
[
"AC",
"AGAG"
],
[
"TG",
"AGCC"
],
[
"AC",
"TCTG"
],
[
"ATG",
"TTG"
],
[
"TG",
"TTCC"
],
[
"TTC",
"TTG"
],
[
"TGG",
"AGC"
],
[
"TG",
"TATG"
],
[
"TC",
"TATT"
],
[
"TAGC",
"TGGG"
],
[
"ATC",
"TTG"
],
[
"TG",
"TGGG"
],
[
"AGGG",
"GG"
],
[
"TGG",
"AC"
],
[
"TTC",
"TTTT"
],
[
"TAC",
"AC"
],
[
"TTC",
"TAG"
],
[
"TC",
"TTTG"
],
[
"AAC",
"ATGG"
],
[
"TT",
"TACC"
],
[
"AG",
"ATGC"
],
[
"TTC",
"TAA"
],
[
"TC",
"TTGC"
],
[
"AG",
"TTCC"
],
[
"ACC",
"GC"
],
[
"ATT",
"TTTC"
],
[
"TAAG",
"CC"
],
[
"ATG",
"AAC"
],
[
"AACC",
"CC"
],
[
"ATG",
"GGC"
],
[
"ATT",
"AAAA"
],
[
"TCC",
"TGC"
],
[
"AAG",
"TAA"
],
[
"ATAA",
"GC"
],
[
"GGG",
"CC"
],
[
"AGC",
"TAC"
],
[
"AAAAAAAA",
"AAAAAAAA"
],
[
"ATC",
"ATG"
],
[
"TCCTGCC",
"TCAGCC"
],
[
"TATT",
"TATT"
],
[
"TTC",
"TGG"
],
[
"AAGC",
"G"
],
[
"TCC",
"CCC"
],
[
"ACC",
"CCC"
],
[
"AG",
"TTAA"
],
[
"AG",
"TGTG"
],
[
"AG",
"TGGG"
],
[
"ATT",
"TAT"
],
[
"TG",
"AGAG"
],
[
"AA",
"TCAC"
],
[
"TTG",
"AACC"
],
[
"ATAA",
"GG"
],
[
"TGG",
"TGG"
],
[
"TGC",
"AGC"
],
[
"TAG",
"AAG"
],
[
"TTTTTTTT",
"TTTTTTTT"
],
[
"TTC",
"ATC"
],
[
"AAAA",
"AAG"
],
[
"AC",
"TTTC"
],
[
"TG",
"ATGG"
],
[
"TGG",
"AGG"
],
[
"ATT",
"AAC"
],
[
"ACC",
"TGC"
],
[
"ATG",
"CCC"
],
[
"TTG",
"TAA"
],
[
"AAAA",
"AAC"
],
[
"TTG",
"AAG"
],
[
"TG",
"AGGG"
],
[
"TTC",
"AGC"
],
[
"AA",
"TGCC"
],
[
"TG",
"TCTG"
],
[
"AG",
"TATG"
],
[
"TT",
"TAGC"
],
[
"ATC",
"TAA"
],
[
"AG",
"ATAC"
],
[
"ATG",
"TCC"
],
[
"TAG",
"AAC"
],
[
"AGCC",
"G"
],
[
"AA",
"TTGC"
],
[
"TTC",
"ATT"
],
[
"TAC",
"TAAAAATAC"
],
[
"G",
"TCTC"
],
[
"AT",
"AAAAC"
],
[
"TGG",
"AAC"
],
[
"TTAA",
"CC"
],
[
"AAAT",
"ATC"
],
[
"AGG",
"TAA"
],
[
"TTAA",
"GC"
],
[
"AA",
"TCTG"
],
[
"AG",
"ACCC"
],
[
"TAT",
"ATC"
],
[
"AA",
"TCCC"
],
[
"AGG",
"AAAA"
],
[
"TCCTG",
"ACCTC"
],
[
"TAC",
"AAAA"
],
[
"AC",
"TGTG"
],
[
"AGGCC",
"G"
],
[
"ATAA",
"CC"
],
[
"AGGC",
"GG"
],
[
"AACC",
"TCC"
],
[
"TATT",
"GC"
],
[
"ATC",
"AAC"
],
[
"TC",
"TGGG"
],
[
"AGG",
"TTC"
],
[
"AGC",
"AAC"
],
[
"AA",
"ATAT"
],
[
"AG",
"TCTG"
],
[
"TGG",
"TGC"
],
[
"TAT",
"AAC"
],
[
"AA",
"ATAG"
],
[
"ATC",
"ATT"
],
[
"AGG",
"ATG"
],
[
"TT",
"ATAC"
],
[
"TGAA",
"CC"
],
[
"TT",
"TAGG"
],
[
"GCC",
"CC"
],
[
"AG",
"TAAC"
],
[
"AA",
"TAGC"
],
[
"TTTT",
"TC"
],
[
"AT",
"AGCC"
],
[
"AAG",
"AGC"
],
[
"AAG",
"ATG"
],
[
"TTG",
"TAG"
],
[
"ACTGC",
"ACTCCAGCC"
],
[
"TCC",
"AGC"
],
[
"ATAA",
"ATAA"
],
[
"AG",
"TCAC"
],
[
"TTG",
"TC"
],
[
"G",
"TGC"
],
[
"TTC",
"ATG"
],
[
"AA",
"TGGG"
],
[
"AC",
"TTCC"
],
[
"AT",
"AGGG"
],
[
"TGGGC",
"AAC"
],
[
"ATT",
"ATG"
],
[
"AA",
"TACC"
],
[
"TG",
"AGTG"
],
[
"AAG",
"CCC"
],
[
"TAC",
"TAA"
],
[
"TTC",
"TTTC"
],
[
"AG",
"AAAAG"
],
[
"TC",
"AGGG"
],
[
"AG",
"TAAG"
],
[
"ACC",
"TTG"
],
[
"TAT",
"CCC"
],
[
"TG",
"ACAC"
],
[
"TG",
"TTGG"
],
[
"TATG",
"CC"
],
[
"TAGG",
"CC"
],
[
"TGC",
"AAG"
],
[
"AGC",
"TGG"
],
[
"TTC",
"TAC"
],
[
"ACC",
"AAC"
],
[
"TT",
"AAGG"
],
[
"TCCC",
"AAG"
],
[
"TGC",
"TCC"
],
[
"ATT",
"AAG"
],
[
"ATG",
"AGCC"
],
[
"AC",
"ATTC"
],
[
"TT",
"ATCC"
],
[
"AGC",
"ATC"
],
[
"AT",
"AAAAG"
],
[
"TTG",
"TTTT"
],
[
"TC",
"ACAC"
],
[
"TCAC",
"AGAG"
],
[
"AG",
"TCCC"
],
[
"AGACC",
"AGCC"
],
[
"AGGCTGAGGC",
"AGGAGAA"
],
[
"TG",
"TCCC"
],
[
"TT",
"ACAC"
],
[
"ACC",
"TAA"
],
[
"AG",
"AAAAC"
],
[
"AC",
"AGCC"
],
[
"TC",
"AGGC"
],
[
"TG",
"TATC"
],
[
"ATT",
"TTAA"
],
[
"AC",
"ATGG"
],
[
"TG",
"ATGC"
],
[
"AG",
"TTAC"
],
[
"AGG",
"TAG"
],
[
"ATC",
"AAG"
],
[
"TG",
"TTAA"
],
[
"AGC",
"TTC"
],
[
"TCC",
"TTC"
],
[
"TATG",
"GC"
],
[
"AGC",
"TAA"
],
[
"TTTC",
"TTTC"
],
[
"AGG",
"TTG"
],
[
"AC",
"AAAC"
],
[
"TGTAATCCCAGC",
"ACTTTGGG"
],
[
"AGC",
"ATT"
],
[
"TGGC",
"TCAC"
],
[
"TC",
"ATGCC"
],
[
"TCC",
"TGG"
],
[
"ACC",
"AGCC"
],
[
"TT",
"AGAG"
],
[
"AG",
"ATTG"
],
[
"AA",
"TTATT"
],
[
"TGC",
"TTC"
],
[
"TG",
"TCAC"
],
[
"AA",
"TTTAA"
],
[
"CCC",
"G"
],
[
"AC",
"AGGG"
],
[
"TC",
"AGAG"
],
[
"AG",
"ATCC"
],
[
"TG",
"TAAG"
],
[
"ATG",
"AAAA"
],
[
"ACC",
"TGG"
],
[
"TC",
"TAT"
],
[
"AAG",
"ATC"
],
[
"TACC",
"CC"
],
[
"AG",
"TAGC"
],
[
"ATT",
"ATC"
],
[
"ACC",
"AGC"
],
[
"TC",
"AAAC"
],
[
"TAA",
"TAC"
],
[
"TCTC",
"TCTC"
],
[
"ATG",
"TAC"
],
[
"TC",
"AAGC"
],
[
"AG",
"TATC"
],
[
"TG",
"TTGC"
],
[
"TTTCC",
"CC"
],
[
"AC",
"AGTG"
],
[
"AGG",
"TGTG"
],
[
"TC",
"ATTG"
],
[
"AAAT",
"AAAA"
],
[
"TAG",
"AAAA"
],
[
"AG",
"TTGG"
],
[
"AA",
"TAGG"
],
[
"ATT",
"TCTC"
],
[
"AAC",
"ATC"
],
[
"TCC",
"TTG"
],
[
"AC",
"TTTG"
],
[
"TCC",
"TGAG"
],
[
"TG",
"TAAC"
],
[
"AG",
"TTGC"
],
[
"AAAC",
"GGG"
],
[
"AA",
"TTGG"
],
[
"TTG",
"AACCC"
],
[
"AC",
"AGGC"
],
[
"TT",
"ATGC"
],
[
"AAC",
"AAAA"
],
[
"ACC",
"TCCC"
],
[
"GTG",
"AGCC"
],
[
"ATC",
"TAC"
],
[
"ACC",
"AAG"
],
[
"AT",
"AGTC"
],
[
"AAC",
"TTC"
],
[
"ACC",
"TTC"
],
[
"ATG",
"TAG"
],
[
"ATAA",
"TAA"
],
[
"GG",
"GGC"
],
[
"TC",
"ATCC"
],
[
"ATG",
"ATC"
],
[
"AAAC",
"G"
],
[
"ACC",
"ATC"
],
[
"TT",
"ACCC"
],
[
"AC",
"AGAC"
],
[
"TC",
"TTGG"
],
[
"AGG",
"TAC"
],
[
"AC",
"TAT"
],
[
"TTG",
"TATT"
],
[
"TGC",
"TGG"
],
[
"TC",
"AAGG"
],
[
"TC",
"AGGAG"
],
[
"TC",
"AGTG"
],
[
"ATT",
"TTTG"
],
[
"AGG",
"ATC"
],
[
"TATT",
"GG"
],
[
"ATT",
"GGC"
],
[
"ATT",
"TTCC"
],
[
"AGG",
"ATGG"
],
[
"TT",
"ATATT"
],
[
"TCC",
"ATG"
],
[
"AC",
"ATGC"
],
[
"AA",
"TTTTC"
],
[
"AGAG",
"AGAG"
],
[
"ACAC",
"G"
],
[
"AC",
"ATAA"
],
[
"TG",
"ACCC"
],
[
"TTTTTTTT",
"TTTT"
],
[
"TGG",
"TAA"
],
[
"TG",
"TTAC"
],
[
"AGG",
"AGGC"
],
[
"TTTT",
"AAAA"
],
[
"TT",
"AGGG"
],
[
"TCCC",
"G"
],
[
"TAG",
"TAA"
],
[
"AAG",
"TGC"
],
[
"ACC",
"TAC"
],
[
"AAAAAAAA",
"AAAA"
],
[
"AGAC",
"AGGG"
],
[
"TCC",
"ATC"
],
[
"TGGC",
"G"
],
[
"TTTC",
"ACCATG"
],
[
"AGGC",
"TGC"
],
[
"ATG",
"AGC"
],
[
"AGAA",
"AGAA"
],
[
"TATG",
"GG"
],
[
"AGAC",
"G"
],
[
"TAT",
"AAG"
],
[
"AAAA",
"TAC"
],
[
"AC",
"TGGG"
],
[
"TGAA",
"ACCCC"
],
[
"TTC",
"AGG"
],
[
"AC",
"TATT"
],
[
"TG",
"TTTTC"
],
[
"TT",
"ATGG"
],
[
"TCC",
"TGGG"
],
[
"AAC",
"TAA"
],
[
"TCC",
"TAA"
],
[
"TT",
"AGTG"
],
[
"TTTGTG",
"ATG"
],
[
"AGGC",
"G"
],
[
"TT",
"TATTC"
],
[
"TG",
"ATTG"
],
[
"AC",
"TGCC"
],
[
"AAG",
"AGG"
],
[
"AAC",
"ATT"
],
[
"AG",
"TAGG"
],
[
"TC",
"ATAA"
],
[
"AAC",
"TGC"
],
[
"AC",
"ATCC"
],
[
"TC",
"ATGG"
],
[
"ATTC",
"TCAGAA"
],
[
"TTG",
"TTC"
],
[
"TCCCAGC",
"TAC"
],
[
"AAC",
"AGC"
],
[
"TCC",
"AAG"
],
[
"TC",
"AAAG"
],
[
"TG",
"AGTC"
],
[
"ATG",
"ATT"
],
[
"AC",
"TCTC"
],
[
"ATG",
"AGG"
],
[
"ACC",
"TGCC"
],
[
"TC",
"GGCC"
],
[
"AC",
"ATAC"
],
[
"TCC",
"AGG"
],
[
"TTG",
"TGC"
],
[
"TAATTTT",
"TGTATT"
],
[
"GC",
"GG"
],
[
"ATTC",
"G"
],
[
"AT",
"Ċ"
],
[
"TAA",
"AAAA"
],
[
"TGGG",
"TGAC"
],
[
"AAAG",
"AAAA"
],
[
"TT",
"AGAC"
],
[
"ATC",
"TGG"
],
[
"ATT",
"TTAC"
],
[
"TGC",
"AGG"
],
[
"TG",
"ATAC"
],
[
"AAG",
"TTC"
],
[
"AC",
"TGAA"
],
[
"AG",
"TTTTC"
],
[
"AGC",
"ACC"
],
[
"TGGGC",
"G"
],
[
"AAC",
"ATG"
],
[
"AC",
"TCCC"
],
[
"AC",
"AATG"
],
[
"AGC",
"ATG"
],
[
"AAC",
"AAG"
],
[
"AGATG",
"GGG"
],
[
"AC",
"TATG"
],
[
"TC",
"ATGC"
],
[
"AC",
"ATTG"
],
[
"AAAG",
"AAG"
],
[
"TC",
"TATC"
],
[
"ATTTC",
"G"
],
[
"TGC",
"ATG"
],
[
"ATT",
"GGG"
],
[
"TTTG",
"TAA"
],
[
"AAC",
"TAC"
],
[
"TTG",
"TAC"
],
[
"TG",
"TAGG"
],
[
"ATT",
"TTTAA"
],
[
"AG",
"TACC"
],
[
"TC",
"TTAA"
],
[
"AAAC",
"TCC"
],
[
"AG",
"ATATT"
],
[
"TAA",
"TTC"
],
[
"TGG",
"TAG"
],
[
"TAGCTGGG",
"ACTAC"
],
[
"TGGG",
"AGG"
],
[
"AATC",
"TGC"
],
[
"TC",
"TTAC"
],
[
"TTG",
"AGG"
],
[
"AC",
"AAGG"
],
[
"TT",
"AAAAC"
],
[
"TC",
"TATG"
],
[
"AA",
"TTTTG"
],
[
"ATAT",
"ATG"
],
[
"ATC",
"AGC"
],
[
"TTTT",
"TTC"
],
[
"ATAT",
"AAAA"
],
[
"TATT",
"TTC"
],
[
"AC",
"ACCC"
],
[
"TCTG",
"TCTC"
],
[
"TG",
"TAGC"
],
[
"TTG",
"AAAA"
],
[
"TTG",
"TGG"
],
[
"AGGCC",
"CC"
],
[
"TT",
"AGGC"
],
[
"AAAC",
"AAAC"
],
[
"ATAT",
"ATT"
],
[
"ATAA",
"ATG"
],
[
"TTG",
"TCC"
],
[
"AGC",
"TGAG"
],
[
"AGC",
"GC"
],
[
"ACC",
"ACG"
],
[
"TTTT",
"TCC"
],
[
"ATC",
"GC"
],
[
"AAG",
"TAG"
],
[
"TAC",
"ATG"
],
[
"ATGG",
"TGGC"
],
[
"AGGTC",
"AGGAG"
],
[
"AC",
"TTGG"
],
[
"TAA",
"ATC"
],
[
"AGG",
"AAGG"
],
[
"AC",
"TCAC"
],
[
"TG",
"TACC"
],
[
"TTTT",
"TTTC"
],
[
"TAA",
"TGC"
],
[
"TGG",
"AAAA"
],
[
"TAG",
"TAG"
],
[
"TGG",
"ATG"
],
[
"TAA",
"GGC"
],
[
"AC",
"TGGC"
],
[
"TC",
"AGAC"
],
[
"TTGG",
"AAACGGG"
],
[
"AC",
"AAAG"
],
[
"ATTC",
"AAC"
],
[
"TTTC",
"G"
],
[
"TATT",
"TTG"
],
[
"TC",
"AGTC"
],
[
"TT",
"TATTG"
],
[
"AGG",
"AAAC"
],
[
"TGG",
"TTC"
],
[
"AGC",
"TGGG"
],
[
"TC",
"TTTTC"
],
[
"AGAA",
"ATG"
],
[
"TGG",
"ATC"
],
[
"TT",
"ATAG"
],
[
"TAT",
"ATAA"
],
[
"TCAC",
"G"
],
[
"AC",
"TTGC"
],
[
"ACC",
"AGG"
],
[
"TTTT",
"GCC"
],
[
"AAG",
"TAC"
],
[
"TAA",
"TAG"
],
[
"AAAA",
"ATG"
],
[
"AG",
"ATAG"
],
[
"TCC",
"AGCC"
],
[
"TAT",
"AGC"
],
[
"TC",
"TACC"
],
[
"ATT",
"TTATT"
],
[
"AAG",
"TTG"
],
[
"ATCAC",
"TTG"
],
[
"AAG",
"TCC"
],
[
"AAATT",
"CC"
],
[
"AAAA",
"TGC"
],
[
"TC",
"AATG"
],
[
"TTTT",
"CCC"
],
[
"GGC",
"TCACTGC"
],
[
"TATT",
"TAA"
],
[
"TAC",
"TTC"
],
[
"ATAC",
"G"
],
[
"TAC",
"TGC"
],
[
"T",
"AĊ"
],
[
"ATC",
"TAG"
],
[
"ACC",
"TAG"
],
[
"ATT",
"AGG"
],
[
"AC",
"TTAC"
],
[
"TTC",
"TTCC"
],
[
"AGAC",
"GG"
],
[
"TTTT",
"TATT"
],
[
"AGGCTGGAGTGC",
"AGTGGC"
],
[
"TT",
"AAAAG"
]
]
}
}