Machine learning-driven QSAR models for prediction of Metabolic mechanisms and Thyroid hormone disrupting effects of emerging pollutants in human body: a case study of Bisphenol analogues

Abstract

Research on theoretical prediction methods for the reaction mechanisms and thyroid hormone disrupting effects of emerging pollutants in human body faces significant challenges. The application of in silico methods utilizing machine learning is increasingly recognized as an effective strategy to address the mechanisms of reactions catalyzed by human cytochrome P450 enzymes (CYPs) and to predict the adverse effects of emerging pollutants. Bisphenol analogues (BPs) represent one of the most important endocrine disruptors, which can cause serious effects on the ecological environment and human health. Herein, density functional theory (DFT) was employed to investigate the reaction mechanisms of O-addition and H-abstraction of 20 BPs by human CYPs. The machine learning integrated quantitative structure-activity relationship (ML-QSAR) were established to predict the energy barriers of three types of reactions. Moreover, binding affinities were calculated between BPs (including their metabolites) and TRβ-LBD to evaluate their thyroid hormone disrupting effects. The binding affinities data of BPs to TRβ-LBD were used as training set to develop a ML-QSAR for efficient prediction of potentially hazardous BPs. A ML-QSAR model with R 2 of 0.869 was established to predict their thyroid hormone disrupting effects. Our study enhances the understanding of the catalytic mechanisms of BPs by CYPs, which can provide reference for the design of environmentally friendly BPs in the future. The predictive model developed for thyroid hormone disrupting effects can aid in identifying the adverse effects of emerging BPs, supporting more effective the management of toxic compounds.