A novel QSAR model for evaluating and predicting the inhibition activity of dipeptidyl aspartyl fluoromethylketones

Abstract

A linear quantitative structure activity relationship model is obtained using Multiple Linear Regression (MLR) analysis as applied to a series of 49 dipeptidyl aspartyl fluoromethylketone derivatives with inhibitory activity of the caspase enzyme. For the selection of the best descriptors, the elimination selection stepwise regression method is utilized. The accuracy of the proposed MLR model is illustrated using the following evaluation techniques: cross validation, validation through an external test set, and Y-randomization. Furthermore, the domain of applicability which indicates the area of reliable predictions is defined. © 2006 Wiley-VCH Verlag GmbH & Co. KGaA.