Ligand-based virtual screening and in silico design of new antimalarial compounds using nonstochastic and stochastic total and atom-type quadratic maps

A simple linear discriminant-based quantitative structure-activity relationship (QSAR) models were developed for the classification and prediction of antimalarial activity using some of the topological molecular computer design-computer aided 'rational' drug design (TOMOCOMD-CARDD) fingerprints. A database of 1562 organic chemicals having great structural variability, 597 of them antimalarial agents and 965 compounds having other clinical uses, was analyzed. This series of compounds was processed by a k-means cluster analysis in order to design training and predicting sets. It was concluded that the approach described seems to be a promising QSAR tool for the molecular discovery of classes of antimalarial drugs.