mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-10 01:24:41 +00:00
Introduce new sequence matching logic and corpus handling
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.
This commit is contained in:
1 parent
f75e774bd5
commit
ad065f6853
10 files changed
+2265
-59
No files matched your search
+1208
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,255 @@
|
||||
AAAACTCGTGCCAGCCAC 3891 0
|
||||
AAACCCAAAGGACTTGGC 3890 0
|
||||
AAACGAACCCTTAATAGC 3875 0
|
||||
AAACTCGTGCCAGCCACC 3894 0
|
||||
AAACTGGGATTAGATACC 3896 0
|
||||
AAAGTCCTACGTGATCTG 3901 0
|
||||
AAATCATGATGCAAAAGG 3894 0
|
||||
AACAAACGAACCCTTAAT 3888 0
|
||||
AACATCGAGGTCGTAAAC 3893 0
|
||||
AACATGGTAAGTGTACCG 3894 0
|
||||
AACCAAAAACTCTTGGTG 3854 0
|
||||
AACCCAAAGGACTTGGCG 3888 0
|
||||
AACCCTTAATAGCGGCTG 3858 0
|
||||
AACCGCGGTGGCTGGCAC 3896 0
|
||||
AACGAACCCTTAATAGCG 3860 0
|
||||
AACGATTAAAGTCCTACG 3700 0
|
||||
AACGTCAGGTCGAGGTGT 3894 0
|
||||
AACTCAGATCACGTAGGA 3899 0
|
||||
AACTCGTGCCAGCCACCG 3893 0
|
||||
AACTGGGATTAGATACCC 3896 0
|
||||
AAGAGTTTTTGGTTCCTA 3848 0
|
||||
AAGCCTCGCCTGTTTACC 3876 0
|
||||
AAGGGTTCGTTTGTTCAA 3889 0
|
||||
AAGGTAGCGCAATCACTT 3889 0
|
||||
AAGTCCTACGTGATCTGA 3900 0
|
||||
AAGTCGTAACATGGTAAG 3893 0
|
||||
AAGTGCACCTTCCGGTAC 3888 0
|
||||
AAGTGTACCGGAAGGTGC 3889 0
|
||||
AATAGCGGCTGCACCATT 3839 0
|
||||
AATCACTTGTCTTTTAAA 3856 0
|
||||
AATCATGATGCAAAAGGT 3893 0
|
||||
AATCCAGGTCAGTTTCTA 3903 0
|
||||
AATCGTTGAACAAACGAA 3876 0
|
||||
AATGTAGCCCATTTCTTC 3871 0
|
||||
ACAAACGAACCCTTAATA 3885 0
|
||||
ACAAACTGGGATTAGATA 3893 0
|
||||
ACAAGTGATTGCGCTACC 3889 0
|
||||
ACACACCGCCCGTCACTC 3891 0
|
||||
ACACCGCCCGTCACTCTC 3890 0
|
||||
ACACTTACCATGTTACGA 3893 0
|
||||
ACATCCTAATGGTGCAGC 3858 0
|
||||
ACATCGAGGTCGTAAACC 3894 0
|
||||
ACATGGTAAGTGTACCGG 3894 0
|
||||
ACCAAAAACTCTTGGTGC 3875 0
|
||||
ACCAAGAGTTTTTGGTTC 3857 0
|
||||
ACCATGTTACGACTTGCC 3891 0
|
||||
ACCATTAGGATGTCCTGA 3891 0
|
||||
ACCCAAAGGACTTGGCGG 3886 0
|
||||
ACCCGTCTCTGTGGCAAA 3892 0
|
||||
ACCCTAGGGATAACAGCG 3895 0
|
||||
ACCCTTAATAGCGGCTGC 3861 0
|
||||
ACCGCCCGTCACTCTCCC 3893 0
|
||||
ACCGCGGTGGCTGGCACG 3895 0
|
||||
ACCGGAAGGTGCACTTGG 3887 0
|
||||
ACCTCGATGTTGGATCAG 3891 0
|
||||
ACCTTCCGGTACACTTAC 3893 0
|
||||
ACGAACCCTTAATAGCGG 3859 0
|
||||
ACGACCTCGATGTTGGAT 3889 0
|
||||
ACGATTAAAGTCCTACGT 3701 0
|
||||
ACGTCAGGTCGAGGTGTA 3894 0
|
||||
ACGTGATCTGAGTTCAGA 3901 0
|
||||
ACTCAGATCACGTAGGAC 3899 0
|
||||
ACTCGTGCCAGCCACCGC 3894 0
|
||||
ACTCTTTTGCCACAGAGA 3867 0
|
||||
ACTGGGATTAGATACCCC 3896 0
|
||||
ACTTACCATGTTACGACT 3894 0
|
||||
ACTTTAATCGTTGAACAA 3876 0
|
||||
AGAACAGGCTCCTCTAGG 3893 0
|
||||
AGACAAGTGATTGCGCTA 3883 0
|
||||
AGAGGAGCCTGTTCTAGA 3876 0
|
||||
AGAGTGACGGGCGGTGTG 3890 0
|
||||
AGAGTTTTTGGTTCCTAA 3851 0
|
||||
AGATAGAAACTGACCTGG 3900 0
|
||||
AGATCACGTAGGACTTTA 3901 0
|
||||
AGCCGCTATTAAGGGTTC 3856 0
|
||||
AGCCTCGCCTGTTTACCA 3889 0
|
||||
AGCCTGTTCTAGAACCGA 3871 0
|
||||
AGCGGCTGCACCATTAGG 3846 0
|
||||
AGGAACCAAAAACTCTTG 3842 0
|
||||
AGGACATCCTAATGGTGC 3866 0
|
||||
AGGACTTTAATCGTTGAA 3688 0
|
||||
AGGAGCCTGTTCTAGAAC 3874 0
|
||||
AGGATGTCCTGATCCAAC 3897 0
|
||||
AGGCAAGTCGTAACATGG 3868 0
|
||||
AGGCGATGTTTTTGGTAA 3894 0
|
||||
AGGGATAACAGCGCAATC 3896 0
|
||||
AGGGGAGGCAAGTCGTAA 3890 0
|
||||
AGGGGGTTTACGACCTCG 3894 0
|
||||
AGGGTTCGTTTGTTCAAC 3888 0
|
||||
AGGTAGCGCAATCACTTG 3888 0
|
||||
AGTCCTACGTGATCTGAG 3900 0
|
||||
AGTGGGGTATCTAATCCC 3896 0
|
||||
AGTTACCCTAGGGATAAC 3895 0
|
||||
AGTTTTTGGTTCCTAAGA 3848 0
|
||||
ATAGAAACTGACCTGGAT 3901 0
|
||||
ATAGCGGCTGCACCATTA 3837 0
|
||||
ATAGTGGGGTATCTAATC 3895 0
|
||||
ATCACGTAGGACTTTAAT 3880 0
|
||||
ATCACTTGTCTTTTAAAT 3856 0
|
||||
ATCAGGACATCCTAATGG 3892 0
|
||||
ATCATGATGCAAAAGGTA 3894 0
|
||||
ATCCTAATGGTGCAGCCG 3852 0
|
||||
ATCGAGGTCGTAAACCCC 3894 0
|
||||
ATCGGTTCTAGAACAGGC 3862 0
|
||||
ATCGTTGAACAAACGAAC 3877 0
|
||||
ATCTGAGTTCAGACCGGA 3902 0
|
||||
ATGATGCAAAAGGTACGA 3891 0
|
||||
ATGGTAAGTGTACCGGAA 3895 0
|
||||
ATGGTGCAGCCGCTATTA 3840 0
|
||||
ATGTAGCCCATTTCTTCC 3871 0
|
||||
ATGTCCTGATCCAACATC 3892 0
|
||||
ATGTTACGACTTGCCTCC 3864 0
|
||||
ATGTTGGATCAGGACATC 3893 0
|
||||
ATGTTTTTGGTAAACAGG 3887 0
|
||||
ATTAGATACCCCACTATG 3896 0
|
||||
ATTAGGATGTCCTGATCC 3893 0
|
||||
ATTGCGCTGTTATCCCTA 3896 0
|
||||
CAAAAACTCTTGGTGCAA 3886 0
|
||||
CAAACGAACCCTTAATAG 3882 0
|
||||
CAAACTGGGATTAGATAC 3895 0
|
||||
CAACATCGAGGTCGTAAA 3894 0
|
||||
CAACGATTAAAGTCCTAC 3691 0
|
||||
CAAGTCGTAACATGGTAA 3893 0
|
||||
CAAGTGCACCTTCCGGTA 3888 0
|
||||
CACCATTAGGATGTCCTG 3890 0
|
||||
CACCGCCCGTCACTCTCC 3888 0
|
||||
CACCTTCCGGTACACTTA 3891 0
|
||||
CACGTAGGACTTTAATCG 3702 0
|
||||
CACTCTTTTGCCACAGAG 3856 0
|
||||
CACTTACCATGTTACGAC 3894 0
|
||||
CATCCTAATGGTGCAGCC 3852 0
|
||||
CATCGAGGTCGTAAACCC 3894 0
|
||||
CATGATGCAAAAGGTACG 3890 0
|
||||
CATGGTAAGTGTACCGGA 3894 0
|
||||
CATGTTACGACTTGCCTC 3866 0
|
||||
CATTAGGATGTCCTGATC 3893 0
|
||||
CCAAAAACTCTTGGTGCA 3883 0
|
||||
CCAACATCGAGGTCGTAA 3894 0
|
||||
CCAAGAGTTTTTGGTTCC 3844 0
|
||||
CCACTCTTTTGCCACAGA 3879 0
|
||||
CCCACTCTTTTGCCACAG 3879 0
|
||||
CCCGTCTCTGTGGCAAAA 3894 0
|
||||
CCCTAGGGATAACAGCGC 3898 0
|
||||
CCCTTAATAGCGGCTGCA 3853 0
|
||||
CCGCCCGTCACTCTCCCC 3890 0
|
||||
CCGCGGTGGCTGGCACGA 3895 0
|
||||
CCGGTAAAACTCGTGCCA 3847 0
|
||||
CCGGTCTGAACTCAGATC 3904 0
|
||||
CCGTCTCTGTGGCAAAAG 3894 0
|
||||
CCTACGTGATCTGAGTTC 3899 0
|
||||
CCTAGGGATAACAGCGCA 3896 0
|
||||
CCTCGATGTTGGATCAGG 3892 0
|
||||
CCTCGCCTGTTTACCAAA 3892 0
|
||||
CCTGTTCTAGAACCGATA 3862 0
|
||||
CCTTAATAGCGGCTGCAC 3850 0
|
||||
CCTTCCGGTACACTTACC 3893 0
|
||||
CGAACCCTTAATAGCGGC 3855 0
|
||||
CGACCTCGATGTTGGATC 3890 0
|
||||
CGACGGCGGTATATAGGC 3890 0
|
||||
CGATGTTGGATCAGGACA 3892 0
|
||||
CGATGTTTTTGGTAAACA 3886 0
|
||||
CGCCTGTTTACCAAAAAC 3889 0
|
||||
CGCGGTGGCTGGCACGAG 3894 0
|
||||
CGCTTAGCTGTTAACTAA 3864 0
|
||||
CGGTAAAACTCGTGCCAG 3856 0
|
||||
CGGTCTGAACTCAGATCA 3904 0
|
||||
CGGTTCTAGAACAGGCTC 3873 0
|
||||
CGTAACATGGTAAGTGTA 3892 0
|
||||
CGTCAGGTCGAGGTGTAG 3893 0
|
||||
CGTCTCTGTGGCAAAAGA 3891 0
|
||||
CGTGATCTGAGTTCAGAC 3902 0
|
||||
CGTTGAACAAACGAACCC 3887 0
|
||||
CGTTTGTTCAACGATTAA 3877 0
|
||||
CTAAATCATGATGCAAAA 3896 0
|
||||
CTAATGGTGCAGCCGCTA 3840 0
|
||||
CTACGTGATCTGAGTTCA 3899 0
|
||||
CTAGAACAGGCTCCTCTA 3877 0
|
||||
CTAGAGGAGCCTGTTCTA 3891 0
|
||||
CTAGGGATAACAGCGCAA 3897 0
|
||||
CTCCGGTCTGAACTCAGA 3903 0
|
||||
CTCGATGTTGGATCAGGA 3892 0
|
||||
CTCGCCTGTTTACCAAAA 3892 0
|
||||
CTCGTACCTTTTGCATCA 3889 0
|
||||
CTCTTTTGCCACAGAGAC 3869 0
|
||||
CTGAACTCAGATCACGTA 3900 0
|
||||
CTGCACCATTAGGATGTC 3861 0
|
||||
CTGGGATTAGATACCCCA 3895 0
|
||||
CTGTTATCCCTAGGGTAA 3897 0
|
||||
CTGTTTACCAAAAACATC 3886 0
|
||||
CTTAATAGCGGCTGCACC 3848 0
|
||||
CTTAGCTGTTAACTAAGA 3878 0
|
||||
CTTAGGAACCAAAAACTC 3847 0
|
||||
CTTAGTTAACAGCTAAGC 3875 0
|
||||
CTTCCGGTACACTTACCA 3891 0
|
||||
CTTGGATTTGCACCAAGA 3899 0
|
||||
CTTTAATCGTTGAACAAA 3876 0
|
||||
CTTTTGCATCATGATTTA 3896 0
|
||||
GAACAAACGAACCCTTAA 3890 0
|
||||
GAAGGAACTCGGCAAACA 3889 0
|
||||
GACAAGTGATTGCGCTAC 3889 0
|
||||
GACCTCGATGTTGGATCA 3890 0
|
||||
GACTTTAATCGTTGAACA 3686 0
|
||||
GAGGAGCCTGTTCTAGAA 3876 0
|
||||
GAGGCGATGTTTTTGGTA 3893 0
|
||||
GATAGAAACTGACCTGGA 3900 0
|
||||
GATCACGTAGGACTTTAA 3900 0
|
||||
GATTAAAGTCCTACGTGA 3704 0
|
||||
GCAAGTCGTAACATGGTA 3891 0
|
||||
GCATAGTGGGGTATCTAA 3896 0
|
||||
GCCGGTAAAACTCGTGCC 3827 0
|
||||
GCCTCGCCTGTTTACCAA 3890 0
|
||||
GCCTGTTTACCAAAAACA 3889 0
|
||||
GCGATGTTTTTGGTAAAC 3888 0
|
||||
GCGCTTAGCTGTTAACTA 3899 0
|
||||
GCGGCTGCACCATTAGGA 3850 0
|
||||
GCTAAATCATGATGCAAA 3893 0
|
||||
GCTACACCTCGACCTGAC 3893 0
|
||||
GCTGGCACGAGTTTTACC 3881 0
|
||||
GCTGTTATCCCTAGGGTA 3896 0
|
||||
GGACATCCTAATGGTGCA 3865 0
|
||||
GGACTTTAATCGTTGAAC 3687 0
|
||||
GGAGCCTGTTCTAGAACC 3874 0
|
||||
GGATGTCCTGATCCAACA 3895 0
|
||||
GGATTAGATACCCCACTA 3896 0
|
||||
GGATTGCGCTGTTATCCC 3895 0
|
||||
GGCGATGTTTTTGGTAAA 3890 0
|
||||
GGCTGGCACGAGTTTTAC 3880 0
|
||||
GGGAAGAAATGGGCTACA 3872 0
|
||||
GGGAGGCAAGTCGTAACA 3891 0
|
||||
GGGGAGGCAAGTCGTAAC 3890 0
|
||||
GGGGGTTTACGACCTCGA 3894 0
|
||||
GGTACACTTACCATGTTA 3893 0
|
||||
GGTCTGAACTCAGATCAC 3902 0
|
||||
GGTCTTAGGAACCAAAAA 3862 0
|
||||
GGTTCGTTTGTTCAACGA 3877 0
|
||||
GTAACATGGTAAGTGTAC 3893 0
|
||||
GTACCTTTTGCATCATGA 3892 0
|
||||
GTCCTGATCCAACATCGA 3892 0
|
||||
GTCTTAGGAACCAAAAAC 3853 0
|
||||
GTGGGGTATCTAATCCCA 3895 0
|
||||
GTTACCCTAGGGATAACA 3896 0
|
||||
GTTTGTTCAACGATTAAA 3877 0
|
||||
TAAAACTCGTGCCAGCCA 3887 0
|
||||
TAACCGCGGTGGCTGGCA 3895 0
|
||||
TAAGGGTTCGTTTGTTCA 3889 0
|
||||
TAATCGTTGAACAAACGA 3876 0
|
||||
TACGACCTCGATGTTGGA 3892 0
|
||||
TAGGACTTTAATCGTTGA 3689 0
|
||||
TAGGATGTCCTGATCCAA 3897 0
|
||||
TCCCACTCTTTTGCCACA 3866 0
|
||||
TCGCCTGTTTACCAAAAA 3891 0
|
||||
TGGATCAGGACATCCTAA 3894 0
|
||||
TGGTCTTAGGAACCAAAA 3862 0
|
||||
TGGTGCAGCCGCTATTAA 3847 0
|
||||
TTGGTCTTAGGAACCAAA 3862 0
|
||||
|
Reference in new issue
Block a user