Classification of 1,4-dihydropyridine calcium channel antagonists using the hyperbox approach

Abstract

The early prediction of activity-related characteristics of drug candidates is an important problem in drug design. Activity levels of drug candidates are classified as low or high depending on their IC50 values. Because the experimental determination of IC50 values for a vast number of molecules is both time-consuming and expensive, computational approaches are employed. In this work, we present a novel approach to classify the activities of drug molecules. We use the hyperbox classification method in combination with partial least-squares regression to determine the most relevant molecular descriptors of the drug molecules for an efficient classification. The effectiveness of the approach is illustrated on DHP derivatives. The results indicate that the proposed approach outperforms other approaches reported in the literature.