| Abstract
| - Inhibitors of the enzyme farnesyltransferase show potential as novel anticancer agents. Thereare many known inhibitors, but efforts to build predictive SAR models have been hamperedby the structural diversity and flexibility of inhibitors. We have undertaken for the first timea QSAR study of the potency and selectivity of a large, diverse data set of farnesyltransferaseinhibitors. We used novel molecular descriptors based on binned atomic properties andinvariants of molecular matrices and a robust, nonlinear QSAR mapping paradigm, theBayesian regularized neural network. We have built robust QSAR models of farnesyltransferaseinhibition, geranylgeranyltransferase inhibition, and in vivo data. We have derived a novelselectivity index that allows us to model potency and selectivity simultaneously and have builtrobust QSAR models using this index that have the potential to discover new potent andselective inhibitors.
|
