Wei-Chun Chou,

Dr. Wei-Chun Chou is a Research Assistant Professor at the Department of Environmental and Global Health and a member of the Center for Environmental and Human Toxicology. He received his Ph.D. in Biomedical Engineering and Environmental Sciences from the National Tsing Hua University in Taiwan. before joining the University of Florida, Dr. Chou was a postdoctoral fellow at the National Institute of Environmental Health Sciences (NIEHS) in Taiwan and the Institute of Computational Comparative Medicine at Kansas State University.

Dr. Chou’s doctoral training was in bioinformatics focusing on developing the machine learning model to discover the genetic fingerprinting deriving the progression of human endometrial cancer. Dr. Chou’s current research program studied the development of Physiologically based pharmacokinetic (PBPK) modeling and applied the model to multiple fields including chemical risk assessment, food safety and nanomedicine delivery. His research has been recognized by the Society of Toxicology (SOT) and received several awards including Andersen-Clewell Trainee Award of the Biological Modeling Specialty Section (BMSS), Best Paper Award of BMSS and Outstanding Postdoctoral Award of Nanoscience and Advanced Materials Specialty Section (NAMSS). In addition, much of his study has been published in high-impact journals on Environmental Health/Sciences including Environmental Health Perspectives, Environmental Science and Technology and Environment International.

Dr. Chou’s current study was to integrate the Bayesian approach and Markov chain Monte Carlo (MCMC) methods to develop a multiple-species generic PBPK model and comprehensive dose-response model in PFAS to address the uncertainty of interspecies extrapolation of PFAS, thereby improving the current risk assessment for PFAS. In addition, Dr. Chou is to advance the risk assessment methodology based the AI-assisted computational approaches and support decision-making in Environmental Health.

Dr. Chou’s study leverages expertise in bioinformatics, risk assessment, and computational toxicology to address key risk assessment issues without resorting to animal testing. These goals are accomplished through the development of physiologically based pharmacokinetic (PBPK) modeling with special emphasis on simulating the exposure dose in potentially sensitive populations such as infants and children. Together with high-throughput screening (HTS) datasets (e.g., Tox21 and ToxCast), these cell-based models provide information to quantitatively describe the mechanism and dose-dependent chemical perturbation of biological pathways. Currently, his research interest includes investigating the association between nanoparticles’ physicochemical properties and tissue distribution, utilizing machine learning, deep learning and AI approach.

0000-0003-3355-6921

• Computational methods for Big Data
• Machine learning and applications
• Precision Public Health