Upload vocab_dedup.txt with huggingface_hub
Browse files- vocab_dedup.txt +901 -0
vocab_dedup.txt
ADDED
|
@@ -0,0 +1,901 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
CCAATCAG
|
| 2 |
+
GGTTGGGCTT
|
| 3 |
+
AATCGATT
|
| 4 |
+
TGAAACCTGAT
|
| 5 |
+
ATTGCATAA
|
| 6 |
+
CTAATTAG
|
| 7 |
+
CCAATAAA
|
| 8 |
+
CTGTCA
|
| 9 |
+
GCGTGGGCG
|
| 10 |
+
GGCCAAGCCCC
|
| 11 |
+
ATCAGGTGAT
|
| 12 |
+
CATTGGCC
|
| 13 |
+
GAGTTCA
|
| 14 |
+
ACCGAACAAT
|
| 15 |
+
TTTTATTGC
|
| 16 |
+
CTCACCTCC
|
| 17 |
+
GCCTGAGGC
|
| 18 |
+
GACACGTGCC
|
| 19 |
+
GATGACTCA
|
| 20 |
+
GTAAACAAA
|
| 21 |
+
CCCAAGGGA
|
| 22 |
+
GGG
|
| 23 |
+
CCTAGCAAC
|
| 24 |
+
TGGCCCCA
|
| 25 |
+
GCGGAAGT
|
| 26 |
+
GATGAGTCAT
|
| 27 |
+
AAGGAAGT
|
| 28 |
+
CGTTTA
|
| 29 |
+
TGAGTCA
|
| 30 |
+
TATGCAAAT
|
| 31 |
+
TGCCGCA
|
| 32 |
+
CTTTCTC
|
| 33 |
+
TAATTAG
|
| 34 |
+
AAACAGGAAGT
|
| 35 |
+
GTGGGCGTGG
|
| 36 |
+
AACATATGGT
|
| 37 |
+
ACAGTAGC
|
| 38 |
+
GCCACGCCCAC
|
| 39 |
+
ACCCGGAAGT
|
| 40 |
+
CATTAATTAA
|
| 41 |
+
ATTGTTT
|
| 42 |
+
AACAGATGGT
|
| 43 |
+
ATT
|
| 44 |
+
TTCCAGGAAA
|
| 45 |
+
TAATCGATA
|
| 46 |
+
ATGACTCA
|
| 47 |
+
TTAACTCTT
|
| 48 |
+
TAATCAATTA
|
| 49 |
+
ATTGTTCGGT
|
| 50 |
+
AGGCACAGC
|
| 51 |
+
GGAACAGCA
|
| 52 |
+
N
|
| 53 |
+
CTTCCT
|
| 54 |
+
TCGTAA
|
| 55 |
+
CCACGCCCCC
|
| 56 |
+
AGGCCTCGGC
|
| 57 |
+
TAATTTGCATA
|
| 58 |
+
GTACCCGCAT
|
| 59 |
+
ACCTACCG
|
| 60 |
+
TATGTCGCGATA
|
| 61 |
+
TTTTACGAG
|
| 62 |
+
GCAATTA
|
| 63 |
+
TCTTATCT
|
| 64 |
+
AGGTCTGGA
|
| 65 |
+
ATTAATTATGCA
|
| 66 |
+
CGC
|
| 67 |
+
TATCTGGGCA
|
| 68 |
+
GACCACCCA
|
| 69 |
+
ATGACATCAT
|
| 70 |
+
CACCTG
|
| 71 |
+
GAA
|
| 72 |
+
AGCAGCTGCT
|
| 73 |
+
CTGACTCAGC
|
| 74 |
+
ATGATGTCAT
|
| 75 |
+
TTGCACAA
|
| 76 |
+
CCATTGTTCT
|
| 77 |
+
TGCAGTGATTT
|
| 78 |
+
TGGAAA
|
| 79 |
+
TCCCTTGGG
|
| 80 |
+
GGTTTCG
|
| 81 |
+
CTCCAGAA
|
| 82 |
+
TTGACTTTT
|
| 83 |
+
TCAGGTT
|
| 84 |
+
TTAATTAG
|
| 85 |
+
CCGTTAACGGT
|
| 86 |
+
ACAATAG
|
| 87 |
+
TGTAAC
|
| 88 |
+
AATGTAACAA
|
| 89 |
+
AAATCACTGCA
|
| 90 |
+
GAG
|
| 91 |
+
AATTA
|
| 92 |
+
CACTCAA
|
| 93 |
+
CAATAAA
|
| 94 |
+
TTCCAGGAA
|
| 95 |
+
ACAGCTGT
|
| 96 |
+
CAACTG
|
| 97 |
+
TAATCCC
|
| 98 |
+
ACAATGG
|
| 99 |
+
CTTATCT
|
| 100 |
+
TAAGTG
|
| 101 |
+
AGGTGTTAATG
|
| 102 |
+
TTTATTG
|
| 103 |
+
ATGAGGTCAT
|
| 104 |
+
ATGACTCAGCA
|
| 105 |
+
CGGCCTCA
|
| 106 |
+
TGCTGTTCC
|
| 107 |
+
GCGTG
|
| 108 |
+
CGA
|
| 109 |
+
ACAGCAGA
|
| 110 |
+
GACGC
|
| 111 |
+
TGCGGCA
|
| 112 |
+
CCT
|
| 113 |
+
TGACTCAT
|
| 114 |
+
TTACGTCAT
|
| 115 |
+
GTAAACAT
|
| 116 |
+
GGTTTCTGTT
|
| 117 |
+
TTAATGA
|
| 118 |
+
TGCATAATTAAT
|
| 119 |
+
TAATTAC
|
| 120 |
+
AACAGCTGAT
|
| 121 |
+
CCCCTCCCCC
|
| 122 |
+
TACGTA
|
| 123 |
+
TGGGTGGTC
|
| 124 |
+
CAATTA
|
| 125 |
+
AGTTCAAGGTCA
|
| 126 |
+
ATGACGTCA
|
| 127 |
+
CGTCAGCACTTT
|
| 128 |
+
ATCAAAGG
|
| 129 |
+
TCAAGGTCA
|
| 130 |
+
TTTCAGTTTCA
|
| 131 |
+
CCGGAAGTG
|
| 132 |
+
CCACGCCCAC
|
| 133 |
+
ACACGTGCC
|
| 134 |
+
AAAAATCAATAA
|
| 135 |
+
AAAGGTCA
|
| 136 |
+
TATCGATTA
|
| 137 |
+
CCACGCCC
|
| 138 |
+
CGG
|
| 139 |
+
TGACTCA
|
| 140 |
+
TTATGCAAT
|
| 141 |
+
GCAACAGGTG
|
| 142 |
+
GCCACGTCATC
|
| 143 |
+
GCCACGCCCCC
|
| 144 |
+
GTCACGTGAC
|
| 145 |
+
TAAACG
|
| 146 |
+
ATGTAAACA
|
| 147 |
+
AAACCGGTT
|
| 148 |
+
GTCGTAAAA
|
| 149 |
+
GGGTCCTGGG
|
| 150 |
+
TGC
|
| 151 |
+
ACATATGTC
|
| 152 |
+
ACATTCCA
|
| 153 |
+
CACTTCCGGT
|
| 154 |
+
ATGACCTTGA
|
| 155 |
+
GAACAAAG
|
| 156 |
+
GGCCAATG
|
| 157 |
+
GCTACTGT
|
| 158 |
+
TGAGTCAT
|
| 159 |
+
CACCTGTTGA
|
| 160 |
+
ACCGGAAGTG
|
| 161 |
+
TCATTAA
|
| 162 |
+
CCTTGAGCC
|
| 163 |
+
CGTCCGC
|
| 164 |
+
CAGGGGGC
|
| 165 |
+
CTA
|
| 166 |
+
TGACAGCTGTCA
|
| 167 |
+
AGA
|
| 168 |
+
CACGTGCC
|
| 169 |
+
TGTCAGGGGGC
|
| 170 |
+
ATCACCCCAT
|
| 171 |
+
GCCACGTG
|
| 172 |
+
ATTGCACAAT
|
| 173 |
+
TAATTG
|
| 174 |
+
AAACCATTA
|
| 175 |
+
TACAAAGTA
|
| 176 |
+
TAGTTAA
|
| 177 |
+
TCGGTGGTCG
|
| 178 |
+
TTTCCA
|
| 179 |
+
GGGGCGGGG
|
| 180 |
+
ACAGTCTGT
|
| 181 |
+
TGACCTTGAACT
|
| 182 |
+
TTGAGGTT
|
| 183 |
+
ATCACGTGAT
|
| 184 |
+
GTTGCTAGG
|
| 185 |
+
ATGGCGG
|
| 186 |
+
GGGGGCGTGGC
|
| 187 |
+
GCTGTGATTT
|
| 188 |
+
AGATAAG
|
| 189 |
+
GCCCGGGGGC
|
| 190 |
+
CCACGTGG
|
| 191 |
+
TGACCTT
|
| 192 |
+
ATC
|
| 193 |
+
ATGGGGTGAT
|
| 194 |
+
ATGCCAAC
|
| 195 |
+
AGGTGTGAAG
|
| 196 |
+
TGACCT
|
| 197 |
+
GGATTATCT
|
| 198 |
+
GTTGCATAA
|
| 199 |
+
TAATCGATTA
|
| 200 |
+
TGATTTATG
|
| 201 |
+
TTCTGGAG
|
| 202 |
+
TGATTGC
|
| 203 |
+
GCCGAGGCCT
|
| 204 |
+
[PAD]
|
| 205 |
+
TATTGATTT
|
| 206 |
+
GTAAACAA
|
| 207 |
+
TGACGTCA
|
| 208 |
+
GTGGGCGTGGC
|
| 209 |
+
AGCTCATTA
|
| 210 |
+
ACCGAAACT
|
| 211 |
+
TGCCAA
|
| 212 |
+
ATGACGTCAT
|
| 213 |
+
TTTTCCAT
|
| 214 |
+
GAT
|
| 215 |
+
TCCCAGCC
|
| 216 |
+
TGTACAGTA
|
| 217 |
+
TTGACAG
|
| 218 |
+
CTTTGTT
|
| 219 |
+
TTAATTAATG
|
| 220 |
+
TGAACTC
|
| 221 |
+
TTTTATA
|
| 222 |
+
CCCAGCCT
|
| 223 |
+
CTC
|
| 224 |
+
CACGTGA
|
| 225 |
+
TCCAC
|
| 226 |
+
CTTGGCA
|
| 227 |
+
TTTTATTGCC
|
| 228 |
+
TAATGGTTT
|
| 229 |
+
CCA
|
| 230 |
+
AACAATGG
|
| 231 |
+
CATCAATCA
|
| 232 |
+
TAATTGC
|
| 233 |
+
TCTGCTGT
|
| 234 |
+
GCCCAGGCTG
|
| 235 |
+
ACTTCCTGT
|
| 236 |
+
TGATGTCA
|
| 237 |
+
TAG
|
| 238 |
+
TGTTTGTTTAA
|
| 239 |
+
AAAGGTCAAGGG
|
| 240 |
+
TCCTGTTTAC
|
| 241 |
+
TGCCAAG
|
| 242 |
+
TATGCAAATTA
|
| 243 |
+
GCTGAGTCAG
|
| 244 |
+
AAAAAAAA
|
| 245 |
+
CATATGTT
|
| 246 |
+
CAG
|
| 247 |
+
TAATTGATTA
|
| 248 |
+
CACGTG
|
| 249 |
+
CAA
|
| 250 |
+
CAGTTTCAAGG
|
| 251 |
+
AGATAAGG
|
| 252 |
+
CACGTGT
|
| 253 |
+
TTTCCATT
|
| 254 |
+
GGAATGT
|
| 255 |
+
[SEP]
|
| 256 |
+
GCACCTGT
|
| 257 |
+
GCGGACG
|
| 258 |
+
AATTGATACAT
|
| 259 |
+
ATGCAAA
|
| 260 |
+
TGGGGATT
|
| 261 |
+
CCATCTGT
|
| 262 |
+
TTCCTGGAA
|
| 263 |
+
ATGACCTCAT
|
| 264 |
+
ACAGATGG
|
| 265 |
+
ACATTCCAG
|
| 266 |
+
ATCAAAG
|
| 267 |
+
GCCCCCGGGC
|
| 268 |
+
GCACCTGCC
|
| 269 |
+
ATGACGTAA
|
| 270 |
+
AACATATGTT
|
| 271 |
+
TTATCTTATCT
|
| 272 |
+
ACGCCCACGCA
|
| 273 |
+
TAC
|
| 274 |
+
AACATCTGGAT
|
| 275 |
+
GCTGTTCTTATC
|
| 276 |
+
GGGGGCGTGG
|
| 277 |
+
AAAGTGCTGACG
|
| 278 |
+
AGGTCGTAAAA
|
| 279 |
+
ATGCCAGAC
|
| 280 |
+
GTCTAGACA
|
| 281 |
+
GCCACACCCAC
|
| 282 |
+
ATCAGGTTTCA
|
| 283 |
+
TGACACCTGTCA
|
| 284 |
+
TTAAGTGGTT
|
| 285 |
+
AACCGGTTT
|
| 286 |
+
TTACGTAA
|
| 287 |
+
TGTCTAGAC
|
| 288 |
+
AACATCTGT
|
| 289 |
+
ATTTGCATA
|
| 290 |
+
GATGACGTCAT
|
| 291 |
+
TGGGCCC
|
| 292 |
+
TCCTCCC
|
| 293 |
+
ATAGTAGGT
|
| 294 |
+
AGCAATTAA
|
| 295 |
+
TTTGAAT
|
| 296 |
+
AACAAAG
|
| 297 |
+
TTT
|
| 298 |
+
CCATTGTT
|
| 299 |
+
GGCAGGTGC
|
| 300 |
+
GCGTC
|
| 301 |
+
TGGCGCC
|
| 302 |
+
TTTACAGCG
|
| 303 |
+
T
|
| 304 |
+
ACCATATGGT
|
| 305 |
+
AGGAAG
|
| 306 |
+
CCATTTTG
|
| 307 |
+
ACC
|
| 308 |
+
GGCACGTG
|
| 309 |
+
TGCCCTGGGGC
|
| 310 |
+
ATTCCCC
|
| 311 |
+
TGTTTACAT
|
| 312 |
+
TGTGGATT
|
| 313 |
+
TATCGATC
|
| 314 |
+
GTGGGTGTGGC
|
| 315 |
+
CGCCCACGC
|
| 316 |
+
TCGTGAC
|
| 317 |
+
TGAACTTT
|
| 318 |
+
CTAAAAATAG
|
| 319 |
+
TAAGTGG
|
| 320 |
+
GGCACGTGTC
|
| 321 |
+
CAAAGTCCA
|
| 322 |
+
GGGCGTGGTC
|
| 323 |
+
CTATAAATAGC
|
| 324 |
+
AACAGAAACC
|
| 325 |
+
GCGCGTGA
|
| 326 |
+
CCTTTGAT
|
| 327 |
+
AAGGTGTGAA
|
| 328 |
+
ATGGAAA
|
| 329 |
+
TTCTGGGAA
|
| 330 |
+
GGCACGTGT
|
| 331 |
+
TAA
|
| 332 |
+
TTTTATTGG
|
| 333 |
+
GATAA
|
| 334 |
+
CTAATCT
|
| 335 |
+
GTAATTAG
|
| 336 |
+
CAAAATGG
|
| 337 |
+
GGAAATTCCC
|
| 338 |
+
TAAACAGGAAG
|
| 339 |
+
TGACATCA
|
| 340 |
+
CATTAACACCT
|
| 341 |
+
TAGCAACG
|
| 342 |
+
TTTTACGAC
|
| 343 |
+
GGGGCTTGGCC
|
| 344 |
+
CACCTGTTGC
|
| 345 |
+
TTTTACGACCT
|
| 346 |
+
CGT
|
| 347 |
+
TAATCAAATTAT
|
| 348 |
+
TAAGGCGTCTT
|
| 349 |
+
TTGTTACATT
|
| 350 |
+
TCAAGGTCAT
|
| 351 |
+
ACCACGTGGT
|
| 352 |
+
TTGCGGTT
|
| 353 |
+
ATAGGGTATCA
|
| 354 |
+
TTTTACGACC
|
| 355 |
+
CCAATCA
|
| 356 |
+
TTCCAAGAA
|
| 357 |
+
AGTGCTT
|
| 358 |
+
GGGGAAT
|
| 359 |
+
TGGGGCCA
|
| 360 |
+
CGGAAGTAATTA
|
| 361 |
+
TAT
|
| 362 |
+
GCTGTGCCT
|
| 363 |
+
ATCAATCAA
|
| 364 |
+
AACCACTTAA
|
| 365 |
+
CATGTG
|
| 366 |
+
TAATTACTTCCG
|
| 367 |
+
CTTTGATCT
|
| 368 |
+
GGCTGTTC
|
| 369 |
+
TTTCCAT
|
| 370 |
+
TTAAACAAACA
|
| 371 |
+
ATGACTCAT
|
| 372 |
+
AAGTAGGTCA
|
| 373 |
+
GCTGTTACCCT
|
| 374 |
+
CAGATGG
|
| 375 |
+
CCATTGT
|
| 376 |
+
CTAATTAA
|
| 377 |
+
AACCTGTT
|
| 378 |
+
ATTGCATCAT
|
| 379 |
+
CCCGCCCCGC
|
| 380 |
+
TGCAATCCC
|
| 381 |
+
ACAGGAAGT
|
| 382 |
+
GCGTGACC
|
| 383 |
+
GGATTA
|
| 384 |
+
ATG
|
| 385 |
+
ATATACCAT
|
| 386 |
+
TGACA
|
| 387 |
+
CCATTAG
|
| 388 |
+
GATCGATA
|
| 389 |
+
CCATTGTTTT
|
| 390 |
+
AACAAT
|
| 391 |
+
TGGCGCCC
|
| 392 |
+
CCTTTGATCT
|
| 393 |
+
CTTTGT
|
| 394 |
+
GTC
|
| 395 |
+
TTATTGATTTTT
|
| 396 |
+
ACCTACTAT
|
| 397 |
+
CGGTAGGT
|
| 398 |
+
CTGGAATGT
|
| 399 |
+
TGATACCCTAT
|
| 400 |
+
GAAACAGAAA
|
| 401 |
+
CCG
|
| 402 |
+
TTATTAG
|
| 403 |
+
CTATAAATAG
|
| 404 |
+
AGATAAGATAA
|
| 405 |
+
GTAAACAGGA
|
| 406 |
+
TAAAAAT
|
| 407 |
+
TAATTTAATTA
|
| 408 |
+
GCCCCAGGGCA
|
| 409 |
+
TGT
|
| 410 |
+
CAT
|
| 411 |
+
TAATTAA
|
| 412 |
+
AAACCACAA
|
| 413 |
+
ATTTTTA
|
| 414 |
+
AAGGTCA
|
| 415 |
+
GCAGCTGCG
|
| 416 |
+
TTCCTGAGAA
|
| 417 |
+
AAACAAT
|
| 418 |
+
TGCCACGTCATC
|
| 419 |
+
CTGTCAA
|
| 420 |
+
ACAGAAGC
|
| 421 |
+
GTCTGG
|
| 422 |
+
AAAACAATGG
|
| 423 |
+
TAATTAAATTA
|
| 424 |
+
CTTCACACCT
|
| 425 |
+
TGGGAA
|
| 426 |
+
TGAAACTGAAA
|
| 427 |
+
ACAGGTGT
|
| 428 |
+
AACAGCTGTT
|
| 429 |
+
CCC
|
| 430 |
+
TACTGTACA
|
| 431 |
+
CACGTGGC
|
| 432 |
+
AGATCAAAGG
|
| 433 |
+
TTTAAT
|
| 434 |
+
GGAAATCCC
|
| 435 |
+
ACCATATGG
|
| 436 |
+
ATTGTT
|
| 437 |
+
ACAGACTGT
|
| 438 |
+
TTTGCAT
|
| 439 |
+
AGAACAATGG
|
| 440 |
+
CGTTGCTA
|
| 441 |
+
CTATTTTTAG
|
| 442 |
+
CTCATTA
|
| 443 |
+
CGAAACC
|
| 444 |
+
ATCACCTGAT
|
| 445 |
+
CACGT
|
| 446 |
+
GACAGGTGC
|
| 447 |
+
GACATATGT
|
| 448 |
+
ACCATCTGTT
|
| 449 |
+
GCTTCTGT
|
| 450 |
+
TTG
|
| 451 |
+
TTGAGTG
|
| 452 |
+
TTC
|
| 453 |
+
CCAATAAAA
|
| 454 |
+
CCAGAC
|
| 455 |
+
CCACTTGA
|
| 456 |
+
TTCCTGTT
|
| 457 |
+
CCCCGCCCC
|
| 458 |
+
TTCTTGGAA
|
| 459 |
+
GGTCTCTA
|
| 460 |
+
CTGACCA
|
| 461 |
+
GTTCCAG
|
| 462 |
+
ATTAATA
|
| 463 |
+
CCTTGAAACTG
|
| 464 |
+
CAGTTG
|
| 465 |
+
[UNK]
|
| 466 |
+
CACTTCCTGT
|
| 467 |
+
TGATACA
|
| 468 |
+
GCAATTAG
|
| 469 |
+
TTTTTTTT
|
| 470 |
+
GCT
|
| 471 |
+
CTCGAACCC
|
| 472 |
+
TATAAAA
|
| 473 |
+
GATGACGTGGCA
|
| 474 |
+
CCGTGTAGAC
|
| 475 |
+
CACTTCCTG
|
| 476 |
+
GAACAGCC
|
| 477 |
+
TGCCCAGATA
|
| 478 |
+
AAA
|
| 479 |
+
CCAAGAAGAAT
|
| 480 |
+
TTCCCGCCA
|
| 481 |
+
ACCATTTGTC
|
| 482 |
+
CCTCTCTG
|
| 483 |
+
GTAATAAAA
|
| 484 |
+
ACACCTGT
|
| 485 |
+
TGTGGGAAAAGC
|
| 486 |
+
GGCAATAAAA
|
| 487 |
+
TGCCC
|
| 488 |
+
TGGCGGGAA
|
| 489 |
+
GGGCGTGG
|
| 490 |
+
ACTTCCGC
|
| 491 |
+
TAATTAATT
|
| 492 |
+
AATTCTA
|
| 493 |
+
CCGCCAT
|
| 494 |
+
TGATTGATG
|
| 495 |
+
CTT
|
| 496 |
+
TGGCACGTGCC
|
| 497 |
+
ACGTG
|
| 498 |
+
ATGCGGGTAC
|
| 499 |
+
GCAGGTGC
|
| 500 |
+
TGTCA
|
| 501 |
+
TGTTTAC
|
| 502 |
+
TGCTGAGTCAGC
|
| 503 |
+
GGGAGG
|
| 504 |
+
AAGCTT
|
| 505 |
+
AACATATGTC
|
| 506 |
+
CCCTTGCCTC
|
| 507 |
+
TAATGA
|
| 508 |
+
ATGTTTAC
|
| 509 |
+
TGATTAAATTA
|
| 510 |
+
TGTTTACA
|
| 511 |
+
CAATATT
|
| 512 |
+
ACAGATGTT
|
| 513 |
+
CTGCGCCTGCGC
|
| 514 |
+
AATCCACA
|
| 515 |
+
TTACGA
|
| 516 |
+
TTAATTGCT
|
| 517 |
+
CTCGTAAAA
|
| 518 |
+
GGGGGG
|
| 519 |
+
GCACGTGG
|
| 520 |
+
CTTCCTGTTTA
|
| 521 |
+
CACTTCCGG
|
| 522 |
+
TGCTGCCC
|
| 523 |
+
CAC
|
| 524 |
+
[MASK]
|
| 525 |
+
AAATCACAGC
|
| 526 |
+
CTTTGAT
|
| 527 |
+
ATTAAA
|
| 528 |
+
CTAATCGGT
|
| 529 |
+
GGTGGTCG
|
| 530 |
+
AAACCGGTTT
|
| 531 |
+
CAGGAAGTG
|
| 532 |
+
GGA
|
| 533 |
+
AACAGGTT
|
| 534 |
+
GCGCAGGCGCAG
|
| 535 |
+
CTTTGTTC
|
| 536 |
+
TAAGTAAACAA
|
| 537 |
+
ATTGCGCAAT
|
| 538 |
+
TGGTCAG
|
| 539 |
+
TATGAGTTCTCG
|
| 540 |
+
CAGAGAGG
|
| 541 |
+
CTTCCGGT
|
| 542 |
+
A
|
| 543 |
+
AGATTAG
|
| 544 |
+
AGGTCA
|
| 545 |
+
TCG
|
| 546 |
+
CTGTGGTTT
|
| 547 |
+
TGCAGAGCCC
|
| 548 |
+
ATTTCCGGT
|
| 549 |
+
AGACCACCCA
|
| 550 |
+
CACGC
|
| 551 |
+
AGGTGTGAA
|
| 552 |
+
CCCTTGACCTTT
|
| 553 |
+
GGTCGTAAAA
|
| 554 |
+
GATAAGAACAGC
|
| 555 |
+
GGCTCAAGG
|
| 556 |
+
AGG
|
| 557 |
+
ACT
|
| 558 |
+
AACAGGAA
|
| 559 |
+
CTAATTGC
|
| 560 |
+
AACCCGGAAGT
|
| 561 |
+
GCTAATTAGC
|
| 562 |
+
GGGGGCGGGGG
|
| 563 |
+
ACCCGGATGT
|
| 564 |
+
GTAATTA
|
| 565 |
+
GCACGT
|
| 566 |
+
GGGTTCGAG
|
| 567 |
+
ATAACGGT
|
| 568 |
+
CGAACAATG
|
| 569 |
+
GGCACGTGCC
|
| 570 |
+
GCG
|
| 571 |
+
TGCCCTGC
|
| 572 |
+
CCACTTA
|
| 573 |
+
AGGTGTGA
|
| 574 |
+
C
|
| 575 |
+
ATGAGTCA
|
| 576 |
+
AGGTTTCTT
|
| 577 |
+
AAG
|
| 578 |
+
CAGATG
|
| 579 |
+
TAATT
|
| 580 |
+
TTTGTTTAC
|
| 581 |
+
GTCACGTG
|
| 582 |
+
ACTTCCTGTTT
|
| 583 |
+
TATTAAT
|
| 584 |
+
ACA
|
| 585 |
+
ATTAATTATTCA
|
| 586 |
+
CCTGCTGTG
|
| 587 |
+
TGCCTGA
|
| 588 |
+
CACTTGA
|
| 589 |
+
ACTTCCTT
|
| 590 |
+
CCCCGCCC
|
| 591 |
+
CATTGTTCG
|
| 592 |
+
CACATG
|
| 593 |
+
TACGTCA
|
| 594 |
+
GCAGGTG
|
| 595 |
+
CCTCCCCCAC
|
| 596 |
+
GGGCA
|
| 597 |
+
CGAGAACTCATA
|
| 598 |
+
CGACCACCGA
|
| 599 |
+
CCGCGCAC
|
| 600 |
+
TGACCTAATT
|
| 601 |
+
TAATTTAATCA
|
| 602 |
+
TGCACCTGT
|
| 603 |
+
TGA
|
| 604 |
+
ACACGTG
|
| 605 |
+
AAAAGTCAA
|
| 606 |
+
ACCGGAAGT
|
| 607 |
+
AATTAATTA
|
| 608 |
+
TTCTCAGGAA
|
| 609 |
+
TTGAGTGG
|
| 610 |
+
GACATATGTT
|
| 611 |
+
TCCAGACCT
|
| 612 |
+
AGGCTTTCCCAC
|
| 613 |
+
GGGGATTCCCC
|
| 614 |
+
AAACAGGAAG
|
| 615 |
+
GGGATTA
|
| 616 |
+
TCATTA
|
| 617 |
+
ATCAAGGTCA
|
| 618 |
+
GTCATGTGAC
|
| 619 |
+
TAGAATT
|
| 620 |
+
GGCTGGGA
|
| 621 |
+
CACCTGC
|
| 622 |
+
GGAGGTGAG
|
| 623 |
+
TTAATTAATGCG
|
| 624 |
+
TTCACACCT
|
| 625 |
+
CCATCTG
|
| 626 |
+
TGACCTACTT
|
| 627 |
+
CCCCCGCCCCC
|
| 628 |
+
ATGTATCAATT
|
| 629 |
+
ACG
|
| 630 |
+
CTATTGT
|
| 631 |
+
TACTTTGTA
|
| 632 |
+
TCTCGCGAGA
|
| 633 |
+
CCATATGGT
|
| 634 |
+
TGTAAACA
|
| 635 |
+
ACCGTTA
|
| 636 |
+
GGGGAATCCCC
|
| 637 |
+
ACCGGAAAT
|
| 638 |
+
GCCACGTCAC
|
| 639 |
+
AAATCAATA
|
| 640 |
+
TAACGGT
|
| 641 |
+
TTAAGAGCTCA
|
| 642 |
+
CACAGCAGG
|
| 643 |
+
CGCATTAATTAA
|
| 644 |
+
GCCTCAGGC
|
| 645 |
+
ACCGGAAG
|
| 646 |
+
GGC
|
| 647 |
+
CCTTATCT
|
| 648 |
+
GGGCAGCA
|
| 649 |
+
TTTATTGC
|
| 650 |
+
TCAGGCA
|
| 651 |
+
CACGTGAC
|
| 652 |
+
GCTTTTCCCACA
|
| 653 |
+
ATAATTTGATTA
|
| 654 |
+
CCCCTCCC
|
| 655 |
+
AGGCTGGG
|
| 656 |
+
TCACGCGC
|
| 657 |
+
GGGCCCCC
|
| 658 |
+
GCCCCCTG
|
| 659 |
+
AAC
|
| 660 |
+
CTAGACA
|
| 661 |
+
TCACCCCA
|
| 662 |
+
ACCGTTAACGG
|
| 663 |
+
CATCTG
|
| 664 |
+
GTG
|
| 665 |
+
AACATATG
|
| 666 |
+
AACCTCAA
|
| 667 |
+
AGATAAGA
|
| 668 |
+
AATTAGGTCA
|
| 669 |
+
CGCAGCTGC
|
| 670 |
+
GAC
|
| 671 |
+
TTA
|
| 672 |
+
GCAATAAAA
|
| 673 |
+
GTAAACAGGAAG
|
| 674 |
+
TGATTCAATCA
|
| 675 |
+
AACCGCAA
|
| 676 |
+
GACCACGCCC
|
| 677 |
+
CCCAGGACCC
|
| 678 |
+
TTCCCGCC
|
| 679 |
+
TGATTGAATCA
|
| 680 |
+
GTGACGTGGC
|
| 681 |
+
TTTATTGG
|
| 682 |
+
GCGGGAA
|
| 683 |
+
GACAAATGGT
|
| 684 |
+
GGCGGGAA
|
| 685 |
+
GGGGGCCC
|
| 686 |
+
CTGTCACTCA
|
| 687 |
+
ATGAGTCAT
|
| 688 |
+
TGACCTTGA
|
| 689 |
+
TTTGGCGCCAAA
|
| 690 |
+
CTAAATAAACAA
|
| 691 |
+
TAATTA
|
| 692 |
+
TTGATTGAT
|
| 693 |
+
CTTCCTGTTT
|
| 694 |
+
CAGCTG
|
| 695 |
+
GGGATTGCA
|
| 696 |
+
AAGAGTTAA
|
| 697 |
+
TGGACTTTG
|
| 698 |
+
TTGTTTACTTA
|
| 699 |
+
AAGAAACCT
|
| 700 |
+
TCAACAGGTG
|
| 701 |
+
ACGTGC
|
| 702 |
+
ACATCTGG
|
| 703 |
+
GCAGGGCA
|
| 704 |
+
CTGATTGG
|
| 705 |
+
ATGACGTCATC
|
| 706 |
+
AAAGTTCA
|
| 707 |
+
CGGAAGTG
|
| 708 |
+
CCTGCTG
|
| 709 |
+
CCACTCAA
|
| 710 |
+
ACCGATTAG
|
| 711 |
+
CTG
|
| 712 |
+
ATATTTACATA
|
| 713 |
+
GATGACGTGGC
|
| 714 |
+
ACAAAG
|
| 715 |
+
TGACCTTT
|
| 716 |
+
TTCCCGC
|
| 717 |
+
TGGGTGGTCT
|
| 718 |
+
TGAATAATTAAT
|
| 719 |
+
TTATGCAAC
|
| 720 |
+
GCAATAAA
|
| 721 |
+
ATGATGCAAT
|
| 722 |
+
ACCATATGTT
|
| 723 |
+
AATGGAAA
|
| 724 |
+
GCTATTTATAG
|
| 725 |
+
TAATCC
|
| 726 |
+
GTT
|
| 727 |
+
ACTTCCGGGT
|
| 728 |
+
GCCCCGCCC
|
| 729 |
+
CAGCCTGGGC
|
| 730 |
+
AAAATGCTGAC
|
| 731 |
+
TGTATCA
|
| 732 |
+
GGCGCCA
|
| 733 |
+
ACTTCCGGT
|
| 734 |
+
ATGGTATAT
|
| 735 |
+
AACCTGA
|
| 736 |
+
TGACAG
|
| 737 |
+
AATATTG
|
| 738 |
+
GCAATCA
|
| 739 |
+
GCGGGGCGGG
|
| 740 |
+
CCGCCGCTCC
|
| 741 |
+
CATAAATCA
|
| 742 |
+
TTCCCA
|
| 743 |
+
CTAATTAC
|
| 744 |
+
CATGACTCAT
|
| 745 |
+
TGACAGGTGTCA
|
| 746 |
+
CCCCACCC
|
| 747 |
+
GGGAATTTCC
|
| 748 |
+
G
|
| 749 |
+
ACATTCC
|
| 750 |
+
GCA
|
| 751 |
+
CTATTTATAG
|
| 752 |
+
TTCACACCTT
|
| 753 |
+
CACTCAC
|
| 754 |
+
AGGGTAACAGC
|
| 755 |
+
GGGAGGA
|
| 756 |
+
GGGCGGGG
|
| 757 |
+
TGAGTGACAG
|
| 758 |
+
TTTCCTGGAA
|
| 759 |
+
GAGAAAG
|
| 760 |
+
AGATCAAAG
|
| 761 |
+
CAGCAGG
|
| 762 |
+
CTTCCTGTTTAC
|
| 763 |
+
AGATGGAGAAC
|
| 764 |
+
AAGACGCCTTA
|
| 765 |
+
TGGGGTGA
|
| 766 |
+
GGGCGCCA
|
| 767 |
+
TGAGTGACAGG
|
| 768 |
+
GGCACGTGCCA
|
| 769 |
+
TGAGCTCTTAA
|
| 770 |
+
TTACGTAAC
|
| 771 |
+
TAATGAG
|
| 772 |
+
GACACGTGC
|
| 773 |
+
GTAACCTGA
|
| 774 |
+
GCACGTGTC
|
| 775 |
+
GTGCGCGG
|
| 776 |
+
TTAATTAA
|
| 777 |
+
GCCCCCTGACA
|
| 778 |
+
GTTACGTAA
|
| 779 |
+
GAGATTACAGCA
|
| 780 |
+
CGACCACC
|
| 781 |
+
GGGGGAGGGG
|
| 782 |
+
ATGGAAAA
|
| 783 |
+
TGGAATGT
|
| 784 |
+
GTGGA
|
| 785 |
+
CTAATGG
|
| 786 |
+
TTGTTTAC
|
| 787 |
+
TCCAGGTTTTC
|
| 788 |
+
GGT
|
| 789 |
+
GGTCA
|
| 790 |
+
GGGCTCTGCA
|
| 791 |
+
GGGCCCA
|
| 792 |
+
ATCAGCTGTT
|
| 793 |
+
CTAATTA
|
| 794 |
+
TTATC
|
| 795 |
+
TCACGTG
|
| 796 |
+
ACCCGCAT
|
| 797 |
+
GGGAGGGG
|
| 798 |
+
ACCGTTAT
|
| 799 |
+
ATGAGTCATG
|
| 800 |
+
ATAAACAAT
|
| 801 |
+
AGATAATCC
|
| 802 |
+
ATTCAAA
|
| 803 |
+
ATA
|
| 804 |
+
GTCACGA
|
| 805 |
+
CCTTTGATCTTT
|
| 806 |
+
TTAACTA
|
| 807 |
+
TTAATTA
|
| 808 |
+
AAGCCCAACC
|
| 809 |
+
GTCTGGCAT
|
| 810 |
+
CACTTCCG
|
| 811 |
+
GTGAGTG
|
| 812 |
+
TGAGTCATC
|
| 813 |
+
GTGGGAAAGCCT
|
| 814 |
+
TAATGAGCT
|
| 815 |
+
GTGGGGGGGG
|
| 816 |
+
GTAAACA
|
| 817 |
+
TGCGTGGGCGT
|
| 818 |
+
TCACACCT
|
| 819 |
+
ACATCCGGGT
|
| 820 |
+
GCAGCTGC
|
| 821 |
+
ACAGGAAGTG
|
| 822 |
+
GTCAGCATTTT
|
| 823 |
+
TGACGTCAT
|
| 824 |
+
AAAGATCAAAGG
|
| 825 |
+
TGACC
|
| 826 |
+
GTGGGGGAGG
|
| 827 |
+
CCCCCCCCAC
|
| 828 |
+
CCACGTGC
|
| 829 |
+
AAGCACT
|
| 830 |
+
TCA
|
| 831 |
+
TCAAGTG
|
| 832 |
+
TGAGGCCG
|
| 833 |
+
CGCTGTAAA
|
| 834 |
+
CCTCCC
|
| 835 |
+
TTGTTTATTTAG
|
| 836 |
+
AAACCACAG
|
| 837 |
+
TTTCTGTTTC
|
| 838 |
+
AATCCCCA
|
| 839 |
+
GCC
|
| 840 |
+
AGC
|
| 841 |
+
GCACCTGTC
|
| 842 |
+
GGGCGGGGC
|
| 843 |
+
GCACCTGC
|
| 844 |
+
ATTGTGCAAT
|
| 845 |
+
GCTGACTCAGCA
|
| 846 |
+
TCT
|
| 847 |
+
[CLS]
|
| 848 |
+
TCCCCTGGGGA
|
| 849 |
+
GTCTACACGG
|
| 850 |
+
TTCCCAGAA
|
| 851 |
+
TCAAGTGG
|
| 852 |
+
TATCGCGACATA
|
| 853 |
+
TCAGGTTAC
|
| 854 |
+
CCTGTCACTCA
|
| 855 |
+
TGTCTAG
|
| 856 |
+
CAGGTG
|
| 857 |
+
TAGAGACC
|
| 858 |
+
ACTTCCGGGTT
|
| 859 |
+
AAT
|
| 860 |
+
ATTGTTTAT
|
| 861 |
+
GTTACA
|
| 862 |
+
GGTCACGC
|
| 863 |
+
TTGTGCAA
|
| 864 |
+
ATGCGGGT
|
| 865 |
+
ATGACTCATC
|
| 866 |
+
GGAGCGGCGG
|
| 867 |
+
TCC
|
| 868 |
+
TTGGCA
|
| 869 |
+
GTA
|
| 870 |
+
GTACGTGCG
|
| 871 |
+
GTCACATGAC
|
| 872 |
+
CACTTA
|
| 873 |
+
TGG
|
| 874 |
+
GGGATTTCC
|
| 875 |
+
GAGGCAAGGG
|
| 876 |
+
ACAGGTGC
|
| 877 |
+
CCAGATGT
|
| 878 |
+
TATGTAAATAT
|
| 879 |
+
TGATTGG
|
| 880 |
+
GGGTGGGG
|
| 881 |
+
TTTTATTAC
|
| 882 |
+
AGT
|
| 883 |
+
GCACGTGC
|
| 884 |
+
ATCCAGATGTT
|
| 885 |
+
TGCTGAGTCAT
|
| 886 |
+
CCCCCC
|
| 887 |
+
ATTCTTCTTGG
|
| 888 |
+
TTGTGGTTT
|
| 889 |
+
CTAATAA
|
| 890 |
+
ACAGGTGCA
|
| 891 |
+
AGTTTCGGT
|
| 892 |
+
CGCACGTAC
|
| 893 |
+
TCCCCAGGGGA
|
| 894 |
+
TGCTGTAATCTC
|
| 895 |
+
CTGGAAC
|
| 896 |
+
GAAAACCTGGA
|
| 897 |
+
GTGACGTCAC
|
| 898 |
+
GTTGGCAT
|
| 899 |
+
GTTCTCCATCT
|
| 900 |
+
TGACGTA
|
| 901 |
+
TGACCTTGAT
|