Abstract

A reliable quantitative model for estimation of reactivities of Diels-Alder reactions has been developed. A linear and a nonlinear method were used to predict kinetic parameters. Cheaply computed descriptors (including chemical graph indices, intermolecular binding distances, molecular surface areas and electrostatic potentials (ESP), ESP atom value autocorrelation functions, topological (2D) or topographical parameters) with artificial neural networks as well as calculated IR-spectra (Sybyl’s EVA) with partial least square regression were used to build the QSAR equations. Both sets of descriptors are invariant to roto-translation.
 

*To whom correspondence should be addressed. He has recently joint  Basilea Pharmaceutica Ltd (POB 3255, 65/316, 4002 Basel, Switzerland; http://www.basileapharma.com,  e-mail: andras.borosy@roche.com)