Enhancing search space diversity in multi-objective evolutionary drug molecule design using niching

• DOI: 10.1145/1569901.1569932
• Publication Date: 2009-07-21T13:32:17Z
• Authors: Johannes W. Kruis...; Alexander Aleman; Michael T.M. Emme...; Ad P. IJzerman; Andreas Bender; Thomas Baeck; Eelke van der Horst
• Keywords: Identification

There exist several applications of multi-objective evolutionary algorithms for drug design, however, a common drawback in recent approaches is that the diversity resulting molecule populations relatively low. This paper seeks to overcome this problem by introducing niching as technique enhance search space diversity. A single population approach with dynamic niche identification studied application domain. In order apply molecular spaces metric measuring dissimilarity molecules will be introduced. The validated case studies and compared results an NSGA-II algorithm without space.