Quantitative structure-activity relationships (QSAR) study of flavonoid derivatives for inhibition of cytochrome P450 1A2

The quantitative structure-activity relationships (QSAR) studies on flavono id derivatives as cytochrome P450 1A2 inhibitors were performed using multi ple linear regression analysis (MLR) and neural networks (NN). The results of MLR and NN show that Hammett constant, the highest occupied molecular or bital energy (HOMO), the nonoverlap steric volume? the partial charge of C- 3 carbon atom, and the HOMO pi coefficients of C-3, C-3' and C-4' carbon at oms of flavonoids play an important role in inhibitory activity. The correl ations between the descriptors and the activities were improved by neural n etworks although the descriptors of optimum MLR model were used in the netw orks, which implies that the descriptors used in MLR model include nonlinea r relationships. Moreover, neural networks using descriptors selected by th e pruning method gave higher r(2) value than neural networks using MLR desc riptors.