Discrimination and molecular design of new theoretical hypolipaemic agentsusing the molecular connectivity functions

The molecular topology model and discriminant analysis have been applied to the prediction and QSAR interpretation of some pharmacological properties of hypolipaemic drugs using multivariable regression equations with their s tatistical parameters. Regression analysis showed that the molecular topolo gy model predicts these properties. The corresponding stability (cross-vali dation) studies done on the selected prediction models confirmed the goodne ss of the fits. The method used for hypolipaemic activity selection was a l inear discriminant analysis (LDA). We make use of the pharmacological distr ibution diagrams (PDDs) as a visualizing technique for the identification a nd design of new hypolipaemic agents.