Quantitative structure-property relationship (QSPR) models for predicting the physicochemical properties of polychlorinated biphenyls (PCBs) using deep belief network

Abstract

Octanol/water partition coefficient (log P), octanol/air partition coefficient (log K_OA) and bioconcentration factor (log BCF) are important physiochemical properties of organic substances. Quantitative structure-property relationship (QSPR) models are a promising alternative method of reducing and replacing experimental steps in determination of log P, log K_OA and log BCF. In the current study, we propose a new QSPR model based on a deep belief network (DBN) to predict the physicochemical properties of polychlorinated biphenyls (PCBs). The prediction accuracy of the proposed model was compared to the results of previous reported models. The predictive ability of the DBN model, validated with a test set, is clearly superior to the other models. All results showed that the proposed model is robust and satisfactory, and can effectively predict the physiochemical properties of PCBs without highly reliable experimental values.

Keywords: DRAGON molecular descriptors; Deep belief network (DBN); Polychlorinated biphenyls (PCBs); Quantitative structure-property relationship (QSPR).