Neural System for in silico Drug-Drug Interaction Screening
Sebastian Polak, Jerzy Brandys, Aleksander Mendyk · 2006
Drug usage is always associated with risk. Drugs interactions are considered to be one of the potential sources of undesirable action of drugs. Such a situation enforced U.S. Food and Drug Administration (FDA) as well as European Medicines Agency (EMEA) to issue a guidance for industry and researchers for in vivo and in vitro drug interactions studies. The authors proposed neural networks based in silico system for potential drug-drug interactions screening with use of simple physico-chemical data describing each chemical substance particle. Initial results where 77% of classification rate in generalization test was found suggest that computational intelligence based systems could be effective in this area.