Dataset size and data distribution for the HLM, RRCK, and MDR assays that were used to build the categorical models
The datasets are divided into training and test datasets that were used to build the model and test the predictivity of the in silico model, respectively.
| Assay | Training Set Number in High, Moderate, and Low Categories | Test Set Number in High, Moderate, and Low Categories |
|---|---|---|
| HLM stability | 20,445, 18,545, 10,978 | 10,236, 9466, 5282 |
| RRCK permeability | 13,887, 6656, 4446 | 13,491, 6924, 4580 |
| MDR P-gp efflux | 10,820, 14,175 | 7972, 10,441 |