|
iEnhancer-2L: a two-layer predictor for identifying enhancers and their strength by pseudo k-tuple nucleotide composition |
The benchmark dataset contains 742 strong enhancers, 742 weak enhancers and 1,484 non-enhancers. None of the sequences included has >= 80% pairwise sequence identity with any other in each subset. You can download the dataset here Supplementary Information S1.
The original and normalized numerical values of the six DNA dinucleotide physical structural properties used in the paper can be download here Supplementary Information S2.
