QSAR/QSPR studies using probabilistic neural networks and generalized regression neural networks. J Chem Inf Comput Sci 2002;42(6):1460-70
Date
11/26/2002Pubmed ID
12444744DOI
10.1021/ci020039iScopus ID
2-s2.0-0036827084 (requires institutional sign-in at Scopus site) 64 CitationsAbstract
The Probabilistic Neural Network (PNN) and its close relative, the Generalized Regression Neural Network (GRNN), are presented as simple yet powerful neural network techniques for use in Quantitative Structure-Activity Relationship (QSAR) and Quantitative Structure-Property Relationship (QSPR) studies. The PNN methodology is applicable to classification problems, and the GRNN is applicable to continuous function mapping problems. The basic underlying theory behind these probability-based methods is presented along with two applications of the PNN/GRNN methodology. The PNN model presented identifies molecules as potential soluble epoxide hydrolase inhibitors using a binary classification scheme. The GRNN model presented predicts the aqueous solubility of nitrogen- and oxygen-containing small organic molecules. For each application, the network inputs consist of a small set of descriptors that encode structural features at the molecular level. Each of these studies has also been previously addressed in this research group using more traditional techniques such as k-nearest neighbor classification, multiple linear regression, and multilayer feed-forward neural networks. In each case, the predictive power of the PNN and GRNN models was found to be comparable to that of the more traditional techniques but requiring significantly fewer input descriptors.
Author List
Mosier PD, Jurs PCAuthor
Philip Mosier PhD Assistant Professor in the School of Pharmacy Administration department at Medical College of WisconsinMESH terms used to index this publication - Major topics in bold
Bayes TheoremEnzyme Inhibitors
Epoxide Hydrolases
Humans
Models, Chemical
Probability
Quantitative Structure-Activity Relationship
Regression Analysis
Solubility
