mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-09 09:24:41 +00:00
This commit introduces the core matching functionality, including parallel corpus loading, the `Corpus` data structure, and implementations for `matchNaive` and `matchApat`. It also defines new matching rules, variant handling, and comprehensive unit and integration tests to validate the new logic and parameter handling.
6.5 KiB
6.5 KiB
| 1 | AAAACTCGTGCCAGCCAC | 3891 | 0 |
|---|---|---|---|
| 2 | AAACCCAAAGGACTTGGC | 3890 | 0 |
| 3 | AAACGAACCCTTAATAGC | 3875 | 0 |
| 4 | AAACTCGTGCCAGCCACC | 3894 | 0 |
| 5 | AAACTGGGATTAGATACC | 3896 | 0 |
| 6 | AAAGTCCTACGTGATCTG | 3901 | 0 |
| 7 | AAATCATGATGCAAAAGG | 3894 | 0 |
| 8 | AACAAACGAACCCTTAAT | 3888 | 0 |
| 9 | AACATCGAGGTCGTAAAC | 3893 | 0 |
| 10 | AACATGGTAAGTGTACCG | 3894 | 0 |
| 11 | AACCAAAAACTCTTGGTG | 3854 | 0 |
| 12 | AACCCAAAGGACTTGGCG | 3888 | 0 |
| 13 | AACCCTTAATAGCGGCTG | 3858 | 0 |
| 14 | AACCGCGGTGGCTGGCAC | 3896 | 0 |
| 15 | AACGAACCCTTAATAGCG | 3860 | 0 |
| 16 | AACGATTAAAGTCCTACG | 3700 | 0 |
| 17 | AACGTCAGGTCGAGGTGT | 3894 | 0 |
| 18 | AACTCAGATCACGTAGGA | 3899 | 0 |
| 19 | AACTCGTGCCAGCCACCG | 3893 | 0 |
| 20 | AACTGGGATTAGATACCC | 3896 | 0 |
| 21 | AAGAGTTTTTGGTTCCTA | 3848 | 0 |
| 22 | AAGCCTCGCCTGTTTACC | 3876 | 0 |
| 23 | AAGGGTTCGTTTGTTCAA | 3889 | 0 |
| 24 | AAGGTAGCGCAATCACTT | 3889 | 0 |
| 25 | AAGTCCTACGTGATCTGA | 3900 | 0 |
| 26 | AAGTCGTAACATGGTAAG | 3893 | 0 |
| 27 | AAGTGCACCTTCCGGTAC | 3888 | 0 |
| 28 | AAGTGTACCGGAAGGTGC | 3889 | 0 |
| 29 | AATAGCGGCTGCACCATT | 3839 | 0 |
| 30 | AATCACTTGTCTTTTAAA | 3856 | 0 |
| 31 | AATCATGATGCAAAAGGT | 3893 | 0 |
| 32 | AATCCAGGTCAGTTTCTA | 3903 | 0 |
| 33 | AATCGTTGAACAAACGAA | 3876 | 0 |
| 34 | AATGTAGCCCATTTCTTC | 3871 | 0 |
| 35 | ACAAACGAACCCTTAATA | 3885 | 0 |
| 36 | ACAAACTGGGATTAGATA | 3893 | 0 |
| 37 | ACAAGTGATTGCGCTACC | 3889 | 0 |
| 38 | ACACACCGCCCGTCACTC | 3891 | 0 |
| 39 | ACACCGCCCGTCACTCTC | 3890 | 0 |
| 40 | ACACTTACCATGTTACGA | 3893 | 0 |
| 41 | ACATCCTAATGGTGCAGC | 3858 | 0 |
| 42 | ACATCGAGGTCGTAAACC | 3894 | 0 |
| 43 | ACATGGTAAGTGTACCGG | 3894 | 0 |
| 44 | ACCAAAAACTCTTGGTGC | 3875 | 0 |
| 45 | ACCAAGAGTTTTTGGTTC | 3857 | 0 |
| 46 | ACCATGTTACGACTTGCC | 3891 | 0 |
| 47 | ACCATTAGGATGTCCTGA | 3891 | 0 |
| 48 | ACCCAAAGGACTTGGCGG | 3886 | 0 |
| 49 | ACCCGTCTCTGTGGCAAA | 3892 | 0 |
| 50 | ACCCTAGGGATAACAGCG | 3895 | 0 |
| 51 | ACCCTTAATAGCGGCTGC | 3861 | 0 |
| 52 | ACCGCCCGTCACTCTCCC | 3893 | 0 |
| 53 | ACCGCGGTGGCTGGCACG | 3895 | 0 |
| 54 | ACCGGAAGGTGCACTTGG | 3887 | 0 |
| 55 | ACCTCGATGTTGGATCAG | 3891 | 0 |
| 56 | ACCTTCCGGTACACTTAC | 3893 | 0 |
| 57 | ACGAACCCTTAATAGCGG | 3859 | 0 |
| 58 | ACGACCTCGATGTTGGAT | 3889 | 0 |
| 59 | ACGATTAAAGTCCTACGT | 3701 | 0 |
| 60 | ACGTCAGGTCGAGGTGTA | 3894 | 0 |
| 61 | ACGTGATCTGAGTTCAGA | 3901 | 0 |
| 62 | ACTCAGATCACGTAGGAC | 3899 | 0 |
| 63 | ACTCGTGCCAGCCACCGC | 3894 | 0 |
| 64 | ACTCTTTTGCCACAGAGA | 3867 | 0 |
| 65 | ACTGGGATTAGATACCCC | 3896 | 0 |
| 66 | ACTTACCATGTTACGACT | 3894 | 0 |
| 67 | ACTTTAATCGTTGAACAA | 3876 | 0 |
| 68 | AGAACAGGCTCCTCTAGG | 3893 | 0 |
| 69 | AGACAAGTGATTGCGCTA | 3883 | 0 |
| 70 | AGAGGAGCCTGTTCTAGA | 3876 | 0 |
| 71 | AGAGTGACGGGCGGTGTG | 3890 | 0 |
| 72 | AGAGTTTTTGGTTCCTAA | 3851 | 0 |
| 73 | AGATAGAAACTGACCTGG | 3900 | 0 |
| 74 | AGATCACGTAGGACTTTA | 3901 | 0 |
| 75 | AGCCGCTATTAAGGGTTC | 3856 | 0 |
| 76 | AGCCTCGCCTGTTTACCA | 3889 | 0 |
| 77 | AGCCTGTTCTAGAACCGA | 3871 | 0 |
| 78 | AGCGGCTGCACCATTAGG | 3846 | 0 |
| 79 | AGGAACCAAAAACTCTTG | 3842 | 0 |
| 80 | AGGACATCCTAATGGTGC | 3866 | 0 |
| 81 | AGGACTTTAATCGTTGAA | 3688 | 0 |
| 82 | AGGAGCCTGTTCTAGAAC | 3874 | 0 |
| 83 | AGGATGTCCTGATCCAAC | 3897 | 0 |
| 84 | AGGCAAGTCGTAACATGG | 3868 | 0 |
| 85 | AGGCGATGTTTTTGGTAA | 3894 | 0 |
| 86 | AGGGATAACAGCGCAATC | 3896 | 0 |
| 87 | AGGGGAGGCAAGTCGTAA | 3890 | 0 |
| 88 | AGGGGGTTTACGACCTCG | 3894 | 0 |
| 89 | AGGGTTCGTTTGTTCAAC | 3888 | 0 |
| 90 | AGGTAGCGCAATCACTTG | 3888 | 0 |
| 91 | AGTCCTACGTGATCTGAG | 3900 | 0 |
| 92 | AGTGGGGTATCTAATCCC | 3896 | 0 |
| 93 | AGTTACCCTAGGGATAAC | 3895 | 0 |
| 94 | AGTTTTTGGTTCCTAAGA | 3848 | 0 |
| 95 | ATAGAAACTGACCTGGAT | 3901 | 0 |
| 96 | ATAGCGGCTGCACCATTA | 3837 | 0 |
| 97 | ATAGTGGGGTATCTAATC | 3895 | 0 |
| 98 | ATCACGTAGGACTTTAAT | 3880 | 0 |
| 99 | ATCACTTGTCTTTTAAAT | 3856 | 0 |
| 100 | ATCAGGACATCCTAATGG | 3892 | 0 |
| 101 | ATCATGATGCAAAAGGTA | 3894 | 0 |
| 102 | ATCCTAATGGTGCAGCCG | 3852 | 0 |
| 103 | ATCGAGGTCGTAAACCCC | 3894 | 0 |
| 104 | ATCGGTTCTAGAACAGGC | 3862 | 0 |
| 105 | ATCGTTGAACAAACGAAC | 3877 | 0 |
| 106 | ATCTGAGTTCAGACCGGA | 3902 | 0 |
| 107 | ATGATGCAAAAGGTACGA | 3891 | 0 |
| 108 | ATGGTAAGTGTACCGGAA | 3895 | 0 |
| 109 | ATGGTGCAGCCGCTATTA | 3840 | 0 |
| 110 | ATGTAGCCCATTTCTTCC | 3871 | 0 |
| 111 | ATGTCCTGATCCAACATC | 3892 | 0 |
| 112 | ATGTTACGACTTGCCTCC | 3864 | 0 |
| 113 | ATGTTGGATCAGGACATC | 3893 | 0 |
| 114 | ATGTTTTTGGTAAACAGG | 3887 | 0 |
| 115 | ATTAGATACCCCACTATG | 3896 | 0 |
| 116 | ATTAGGATGTCCTGATCC | 3893 | 0 |
| 117 | ATTGCGCTGTTATCCCTA | 3896 | 0 |
| 118 | CAAAAACTCTTGGTGCAA | 3886 | 0 |
| 119 | CAAACGAACCCTTAATAG | 3882 | 0 |
| 120 | CAAACTGGGATTAGATAC | 3895 | 0 |
| 121 | CAACATCGAGGTCGTAAA | 3894 | 0 |
| 122 | CAACGATTAAAGTCCTAC | 3691 | 0 |
| 123 | CAAGTCGTAACATGGTAA | 3893 | 0 |
| 124 | CAAGTGCACCTTCCGGTA | 3888 | 0 |
| 125 | CACCATTAGGATGTCCTG | 3890 | 0 |
| 126 | CACCGCCCGTCACTCTCC | 3888 | 0 |
| 127 | CACCTTCCGGTACACTTA | 3891 | 0 |
| 128 | CACGTAGGACTTTAATCG | 3702 | 0 |
| 129 | CACTCTTTTGCCACAGAG | 3856 | 0 |
| 130 | CACTTACCATGTTACGAC | 3894 | 0 |
| 131 | CATCCTAATGGTGCAGCC | 3852 | 0 |
| 132 | CATCGAGGTCGTAAACCC | 3894 | 0 |
| 133 | CATGATGCAAAAGGTACG | 3890 | 0 |
| 134 | CATGGTAAGTGTACCGGA | 3894 | 0 |
| 135 | CATGTTACGACTTGCCTC | 3866 | 0 |
| 136 | CATTAGGATGTCCTGATC | 3893 | 0 |
| 137 | CCAAAAACTCTTGGTGCA | 3883 | 0 |
| 138 | CCAACATCGAGGTCGTAA | 3894 | 0 |
| 139 | CCAAGAGTTTTTGGTTCC | 3844 | 0 |
| 140 | CCACTCTTTTGCCACAGA | 3879 | 0 |
| 141 | CCCACTCTTTTGCCACAG | 3879 | 0 |
| 142 | CCCGTCTCTGTGGCAAAA | 3894 | 0 |
| 143 | CCCTAGGGATAACAGCGC | 3898 | 0 |
| 144 | CCCTTAATAGCGGCTGCA | 3853 | 0 |
| 145 | CCGCCCGTCACTCTCCCC | 3890 | 0 |
| 146 | CCGCGGTGGCTGGCACGA | 3895 | 0 |
| 147 | CCGGTAAAACTCGTGCCA | 3847 | 0 |
| 148 | CCGGTCTGAACTCAGATC | 3904 | 0 |
| 149 | CCGTCTCTGTGGCAAAAG | 3894 | 0 |
| 150 | CCTACGTGATCTGAGTTC | 3899 | 0 |
| 151 | CCTAGGGATAACAGCGCA | 3896 | 0 |
| 152 | CCTCGATGTTGGATCAGG | 3892 | 0 |
| 153 | CCTCGCCTGTTTACCAAA | 3892 | 0 |
| 154 | CCTGTTCTAGAACCGATA | 3862 | 0 |
| 155 | CCTTAATAGCGGCTGCAC | 3850 | 0 |
| 156 | CCTTCCGGTACACTTACC | 3893 | 0 |
| 157 | CGAACCCTTAATAGCGGC | 3855 | 0 |
| 158 | CGACCTCGATGTTGGATC | 3890 | 0 |
| 159 | CGACGGCGGTATATAGGC | 3890 | 0 |
| 160 | CGATGTTGGATCAGGACA | 3892 | 0 |
| 161 | CGATGTTTTTGGTAAACA | 3886 | 0 |
| 162 | CGCCTGTTTACCAAAAAC | 3889 | 0 |
| 163 | CGCGGTGGCTGGCACGAG | 3894 | 0 |
| 164 | CGCTTAGCTGTTAACTAA | 3864 | 0 |
| 165 | CGGTAAAACTCGTGCCAG | 3856 | 0 |
| 166 | CGGTCTGAACTCAGATCA | 3904 | 0 |
| 167 | CGGTTCTAGAACAGGCTC | 3873 | 0 |
| 168 | CGTAACATGGTAAGTGTA | 3892 | 0 |
| 169 | CGTCAGGTCGAGGTGTAG | 3893 | 0 |
| 170 | CGTCTCTGTGGCAAAAGA | 3891 | 0 |
| 171 | CGTGATCTGAGTTCAGAC | 3902 | 0 |
| 172 | CGTTGAACAAACGAACCC | 3887 | 0 |
| 173 | CGTTTGTTCAACGATTAA | 3877 | 0 |
| 174 | CTAAATCATGATGCAAAA | 3896 | 0 |
| 175 | CTAATGGTGCAGCCGCTA | 3840 | 0 |
| 176 | CTACGTGATCTGAGTTCA | 3899 | 0 |
| 177 | CTAGAACAGGCTCCTCTA | 3877 | 0 |
| 178 | CTAGAGGAGCCTGTTCTA | 3891 | 0 |
| 179 | CTAGGGATAACAGCGCAA | 3897 | 0 |
| 180 | CTCCGGTCTGAACTCAGA | 3903 | 0 |
| 181 | CTCGATGTTGGATCAGGA | 3892 | 0 |
| 182 | CTCGCCTGTTTACCAAAA | 3892 | 0 |
| 183 | CTCGTACCTTTTGCATCA | 3889 | 0 |
| 184 | CTCTTTTGCCACAGAGAC | 3869 | 0 |
| 185 | CTGAACTCAGATCACGTA | 3900 | 0 |
| 186 | CTGCACCATTAGGATGTC | 3861 | 0 |
| 187 | CTGGGATTAGATACCCCA | 3895 | 0 |
| 188 | CTGTTATCCCTAGGGTAA | 3897 | 0 |
| 189 | CTGTTTACCAAAAACATC | 3886 | 0 |
| 190 | CTTAATAGCGGCTGCACC | 3848 | 0 |
| 191 | CTTAGCTGTTAACTAAGA | 3878 | 0 |
| 192 | CTTAGGAACCAAAAACTC | 3847 | 0 |
| 193 | CTTAGTTAACAGCTAAGC | 3875 | 0 |
| 194 | CTTCCGGTACACTTACCA | 3891 | 0 |
| 195 | CTTGGATTTGCACCAAGA | 3899 | 0 |
| 196 | CTTTAATCGTTGAACAAA | 3876 | 0 |
| 197 | CTTTTGCATCATGATTTA | 3896 | 0 |
| 198 | GAACAAACGAACCCTTAA | 3890 | 0 |
| 199 | GAAGGAACTCGGCAAACA | 3889 | 0 |
| 200 | GACAAGTGATTGCGCTAC | 3889 | 0 |
| 201 | GACCTCGATGTTGGATCA | 3890 | 0 |
| 202 | GACTTTAATCGTTGAACA | 3686 | 0 |
| 203 | GAGGAGCCTGTTCTAGAA | 3876 | 0 |
| 204 | GAGGCGATGTTTTTGGTA | 3893 | 0 |
| 205 | GATAGAAACTGACCTGGA | 3900 | 0 |
| 206 | GATCACGTAGGACTTTAA | 3900 | 0 |
| 207 | GATTAAAGTCCTACGTGA | 3704 | 0 |
| 208 | GCAAGTCGTAACATGGTA | 3891 | 0 |
| 209 | GCATAGTGGGGTATCTAA | 3896 | 0 |
| 210 | GCCGGTAAAACTCGTGCC | 3827 | 0 |
| 211 | GCCTCGCCTGTTTACCAA | 3890 | 0 |
| 212 | GCCTGTTTACCAAAAACA | 3889 | 0 |
| 213 | GCGATGTTTTTGGTAAAC | 3888 | 0 |
| 214 | GCGCTTAGCTGTTAACTA | 3899 | 0 |
| 215 | GCGGCTGCACCATTAGGA | 3850 | 0 |
| 216 | GCTAAATCATGATGCAAA | 3893 | 0 |
| 217 | GCTACACCTCGACCTGAC | 3893 | 0 |
| 218 | GCTGGCACGAGTTTTACC | 3881 | 0 |
| 219 | GCTGTTATCCCTAGGGTA | 3896 | 0 |
| 220 | GGACATCCTAATGGTGCA | 3865 | 0 |
| 221 | GGACTTTAATCGTTGAAC | 3687 | 0 |
| 222 | GGAGCCTGTTCTAGAACC | 3874 | 0 |
| 223 | GGATGTCCTGATCCAACA | 3895 | 0 |
| 224 | GGATTAGATACCCCACTA | 3896 | 0 |
| 225 | GGATTGCGCTGTTATCCC | 3895 | 0 |
| 226 | GGCGATGTTTTTGGTAAA | 3890 | 0 |
| 227 | GGCTGGCACGAGTTTTAC | 3880 | 0 |
| 228 | GGGAAGAAATGGGCTACA | 3872 | 0 |
| 229 | GGGAGGCAAGTCGTAACA | 3891 | 0 |
| 230 | GGGGAGGCAAGTCGTAAC | 3890 | 0 |
| 231 | GGGGGTTTACGACCTCGA | 3894 | 0 |
| 232 | GGTACACTTACCATGTTA | 3893 | 0 |
| 233 | GGTCTGAACTCAGATCAC | 3902 | 0 |
| 234 | GGTCTTAGGAACCAAAAA | 3862 | 0 |
| 235 | GGTTCGTTTGTTCAACGA | 3877 | 0 |
| 236 | GTAACATGGTAAGTGTAC | 3893 | 0 |
| 237 | GTACCTTTTGCATCATGA | 3892 | 0 |
| 238 | GTCCTGATCCAACATCGA | 3892 | 0 |
| 239 | GTCTTAGGAACCAAAAAC | 3853 | 0 |
| 240 | GTGGGGTATCTAATCCCA | 3895 | 0 |
| 241 | GTTACCCTAGGGATAACA | 3896 | 0 |
| 242 | GTTTGTTCAACGATTAAA | 3877 | 0 |
| 243 | TAAAACTCGTGCCAGCCA | 3887 | 0 |
| 244 | TAACCGCGGTGGCTGGCA | 3895 | 0 |
| 245 | TAAGGGTTCGTTTGTTCA | 3889 | 0 |
| 246 | TAATCGTTGAACAAACGA | 3876 | 0 |
| 247 | TACGACCTCGATGTTGGA | 3892 | 0 |
| 248 | TAGGACTTTAATCGTTGA | 3689 | 0 |
| 249 | TAGGATGTCCTGATCCAA | 3897 | 0 |
| 250 | TCCCACTCTTTTGCCACA | 3866 | 0 |
| 251 | TCGCCTGTTTACCAAAAA | 3891 | 0 |
| 252 | TGGATCAGGACATCCTAA | 3894 | 0 |
| 253 | TGGTCTTAGGAACCAAAA | 3862 | 0 |
| 254 | TGGTGCAGCCGCTATTAA | 3847 | 0 |
| 255 | TTGGTCTTAGGAACCAAA | 3862 | 0 |