Dr. Shulin Zhuang received the bachelor degree in chemistry from Qufu Normal University in China in 2001.  He obtained his Doctor degree in Department of Chemistry at Zhejiang University, China in 2007. He investigated the molecular interactions between enzymes and various ligands using molecular dynamics (MD) simulations. Dr. Zhuang performed postdoctoral research at Department of Chemistry of University of British Columbia, Canada from 2007 to 2010, where he investigated mechanical unfolding response of proteins using MD simulations and atomic force microscopy (AFM).  In June 2010, He joined the faculty of Institute of Environmental Health at Zhejiang University. From 2019 till now, he is a professor in Zhejiang University and devotes to the study on the association of human health risks of new pollutants using molecular modeling and machine learning. He have identified many chemicals with endocrine disrupting effects and elucidated the underlying molecular mechanisms. In his lab, the researchers have developed some machine learning based prediction model to screen endocrine disrupting chemicals. Now he is the vice chairman of the Professional Committee of Computational Toxicology of the Chinese Toxicology Society in China and is the chief editor of the textbook "Environmental Data Analysis".

OpenTox Virtual Conference 2023

Toxic studies of endocrine disrupting chemicals by machine learning and molecular modeling

High-throughput screening of endocrine disrupting chemicals (EDCs) is of significant to the health risk assessment of various chemicals.  We have constructed prediction models using machine learning and graph neural network GCN to identify Persistent, Bioaccumulation, Toxic (PBT) substances or Persistent, Mobile, Toxic (PMT) substances. Among these screened chemicals, we evaluated the endocrine disruption of many chemicals. Based on the prediction model, relevant online prediction server was built and the high-throughput prediction software was also developed. To elucidate the underlying mechanisms of EDCs, we investigated the molecular initiating events (MIEs) using molecular modeling and cell-based assays. The key events after chemical exposure were identified and the adverse outcome pathways (AOP) were proposed.