Prediction of Caco-2 cell permeability using a combination of MO-calculation and neural network

In the present study, we developed an approach involving a combination of molecular orbital (MO) calculation and neural network to predict Caco-2 cell permeability (logP(app)) from the molecular structure of compounds. For a total of 87 compounds with logP(app) values obtained from the literature, three-dimensional molecular structures were determined by MO-calculation, and then five molecular descriptors were obtained, namely, the dipole moment, polarizability, sum of charges of nitrogen atoms (sum(N)), oxygen atoms (sum(O)), and hydrogen atoms bonding to nitrogen or oxygen atoms (sum(H)). The correlation between these five molecular descriptors and logP(app) was analyzed using a feed-forward back-propagation neural network with a configuration of 5-4-1 for input, hidden, and output layers found suitable for predicting Caco-2 cell permeability. A leave-one-out cross-validation procedure revealed that the neural network model possesses a fairly good predictability as far as Caco-2 cell permeability is concerned (predictive root mean square error (RMSE)=0.507), and better than the simple and quadratic regression model (predictive RMSE=0.584 and 0.568, respectively).