Improved Naïve Bayesian Modeling of Numerical Data for Absorption, Distribution, Metabolism and Excretion (ADME) Property Prediction
文摘
We have implemented a naïve Bayesian classifier which models continuous numerical data using a Gaussiandistribution. Several cases of interest in the area of absorption, distribution, metabolism, and excretionprediction are presented which demonstrate that this approach is superior to the implementation of naïveBayesian classifiers in which continuous chemical descriptors are modeled as binary data. We demonstratethat this enhanced performance, upon comparison with other implementations, is independent of the descriptorsets chosen. We also compare the performance of three implementations of naïve Bayesian classifiers withother previously described models.