|
The six benchmark datasets that uesed to train and test the proposed model are provided on this page. Benchmark dataset S1 contains 1554 4mC site containing sequences and 1554 non-4mC site containing sequences of C. elegans. Benchmark dataset S2 contains 1769 4mC site containing sequences and 1769 non-4mC site containing sequences of D. melanogaster. Benchmark dataset S3 contains 1978 4mC site containing sequences and 1978 non-4mC site containing sequences of A.thaliana. Benchmark dataset S4 contains 388 4mC site containing sequences and 388 non-4mC site containing sequences of E. coli. Benchmark dataset S5 contains 906 4mC site containing sequences and 906 non-4mC site containing sequences of G. subterraneus. Benchmark dataset S6 contains 569 4mC site containing sequences and 569 non-4mC site containing sequences of G. pickeringii.
|