PREDICTING MAXIMUM BIOACTIVITY BY EFFECTIVE INVERSION OF NEURAL NETWORKS USING GENETIC ALGORITHMS

Authors
BURDEN FR ROSEWARNE BS WINKLER DA
Citation
Fr. Burden et al., PREDICTING MAXIMUM BIOACTIVITY BY EFFECTIVE INVERSION OF NEURAL NETWORKS USING GENETIC ALGORITHMS, Chemometrics and intelligent laboratory systems, 38(2), 1997, pp. 127-137
Citations number
11
Categorie Soggetti
Computer Application, Chemistry & Engineering","Instument & Instrumentation","Chemistry Analytical","Computer Science Artificial Intelligence","Robotics & Automatic Control
Journal title
Chemometrics and intelligent laboratory systems → ACNP
ISSN journal
01697439
Volume
38
Issue
2
Year of publication
1997
Pages
127 - 137
Database
ISI
SICI code
0169-7439(1997)38:2<127:PMBBEI>2.0.ZU;2-P
Abstract
Recently neural networks have been applied with some success to the st udy of quantitative structure activity relationships. One limitation o f their use is that, while they are able to predict the biological act ivity of a new molecule from its physicochemical properties, it is dif ficult to get them to solve the more interesting problem of predicting the required molecular properties of a more active molecule. This pap er proposes one method for solving this problem by using genetic algor ithms and explores their potential as a method for solving this proble m. Suggestions for more potent dihydrofolate reductase inhibitors are made. (C) 1997 Elsevier Science B.V.