A new topological method that makes it possible to predict the properties of molecules on the basis of their chemical structures is applied in the present study to quinolone antimicrobial agents. This method uses neural networks in which training algorithms are used as well as different concepts and methods of artificial intelligence with a suitable set of topological descriptors. This makes it possible to determine the minimal inhibitory concentration (MIC) of quinolones. Analysis of the results shows that the experimental and calculated values are highly similar. It is possible to obtain a QSAR interpretation of the information contained in the network after the training has been carried out.

The molecular topology model and discriminant analysis have been applied to the prediction of some pharmacological properties of hypoglycemic drugs using multiple regression equations with their statistical parameters. Regression analysis showed that the molecular topology model predicts these properties. The corresponding stability (cross-validation) studies performed on the selected prediction models confirmed the goodness of the fits. The method used for hypoglycemic activity selection was a linear discriminant analysis (LDA). We make use of the pharmacological distribution diagrams (PDDs) as a visualizing technique for the identification and selection of new hypoglycemic agents, and we tested on rats the predictive ability of the model.