META-MODELS FOR PREDICTING BLOOD BRAIN BARRIER PENETRATION BASED ON PHYSICOCHEMICAL DESCRIPTORS, LIKE H-BOND DONORS/ACCEPTORS AND PARTITION COEFFICIENTS

摘要

Descriptor based models, employing at least two descriptors, predict activities of compounds under consideration. Those activities may be biology-based activities such as the ability of the compound to cross the blood brain barrier. In one example, the model predicts a compound's solubility, its ability to be absorbed in the intestine, and its ability to cross the blood brain barrier. The descriptors of interest are typically physicochemical properties of the whole molecule. Examples include a log P or log D, molecular weight or related size-based descriptors, the number of hydrogen bond donors and/or hydrogen bond acceptors, formal charge, lipophilicity, and the like. In one embodiment, a compound is predicted to penetrate the BBB if the complessive number of H-bond donors and acceptors is smaller than six. In other embodiments, 2-D plots of the H-bond descriptor and a partitioning property are used.