A Genetic Algorithm- Back Propagation Artificial Neural Network Model to Quantify the Affinity of Flavonoids Toward P-Glycoprotein

Jibin      Shen; Ying      Cui; Jun      Gu; Yaxiao      Li; Lingzhi      Li

Abstract

Flavonoids, the most diverse class of plant secondary metabolites, exhibit high affinity toward the purified cytosolic NBD2(C-terminal nucleotide-binding domain) of P-glycoprotein (P-gp). To explore the affinity of flavonoids for P-gp, quantitative structure-activity relationships (QSARs) models were developed using back-propagation artificial neural networks (BPANN) and multiple linear regression (MLR). Molecular descriptors were calculated using PaDELDescriptor, and the number of descriptors was then reduced using a genetic algorithm (GA) and stepwise regression. The MLR (R²=0.855, q²=0.8138, R_ext ²=0.6916), 14-3-1 BPANN (R²=0.8514, q²=0.7695, R_ext ²=0.8142), 14-4-1 BPANN (R²=0.9199, q²=0.7733, R_ext ² =0.8731), and 14-5-1 BPANN (R²=0.8660, q²=0.7432, R_ext ² =0.8292) models all showed good robustness. While BPANN models exceeded significantly MLR in predictable performance for their flexible characters, could be used to predict the affinity of flavonoids for P-gp and applied in further drug screening.