Prediction of Caco-2 cell permeability using partial least squares multivariate analysis

The permeability across Caco-2 cell monolayers of structurally diverse compounds were predicted using computed molecular descriptors and multivariate Partial Least Squares (PLS). The molecular descriptors including log polarization, log solvent accessible surface area, hydration energy heat of formation, and dipole moment were calculated with Hyperchem and ChemPlus QSAR programs for Windows. Other physicochemical properties such as hydrogen acceptor for oxygen atoms, hydrogen acceptor for nitrogen atoms, hydrogen bond donors, hydrogen bond forming ability, molecular weight, and log distribution coefficient were also used as descriptors. Cross validation with internal test set and prediction with external test set indicated the usefulness of the derived model for Caco-2 cell permeability. Hydrogen bonding is one of the important factors associated with permeability. While increased logo and hydration energy facilitate permeability, an increased dipole moment of molecules has a negative effect on permeability.