Authors: Noriko Etani
Our first research goal is to predict drug side effect which is one of screening methods in drug discovery. This paper proposes prediction model of side effect in drug discovery using big data based on data mining methods at the intersection of statistics, machine learning and database systems, and shows its implementation to simply develop web services as a prototype system for drug discovery by object reuse. This implementation shows that the side effect prediction model is practical. Moreover, we introduces Model-driven architecture (MDA) into our research process for data modeling to find a service overview and a system overview.
Keywords: PLS regression analysis; discriminant analysis; support vector machine; Web Application; prediction model; side effect; drug discovery; veracity; Big Data; Model-driven architecture (MDA)