Introduction

Drug metabolism plays a crucial role in understanding bioavailability and drug-drug interactions, as well as in the design of prodrugs and in avoiding undesirable toxic metabolites. Cytochrome P450s (CYPs) are the major class of enzymes responsible for metabolism of most drugs. We have employed our state-of the-art Artificial Neural Network Ensemble (ANNE) modeling methodology to develop in silico models for classifying drugs as substrates of nine CYP isoforms, 1A2, 2A6, 2B6, 2C8, 2C9, 2C19, 2D6, 2E1, and 3A4. Our models also predict CYP-specific likely sites of metabolic oxidation and the resulting metabolites.

By Marvin Waldman, Robert Fraczkiewicz, David Miller, Jinhua Zhang, and Robert D. Clark

CHI 2012  ACM SIGCHI Conference on Human Factors in Computing System in Austin, Texas, May 5-10, 2012