Skip to main content
Contact Info
Chun-Wei Tung
Institute of Biotechnology and Pharmaceutical Research, National Health Research Institutes, Taiwan

Dr. Tung’s lab focuses on the development of artificial intelligence and database techniques with applications to the prediction of function and toxicity of biological and chemical molecules. Several publicly available web servers have been developed including ChemDIS, SkinSensDB, and SkinSensPred. He published more than 50 scientific papers and served as an editorial board member for several journals including Scientific Reports. Please refer to for more details.

OpenTox 2022 Virtual Conference

Integrating complementary methods for toxicity prediction

While computational methods such as structural alerts and quantitative structure-activity relationships can serve as first-line tools for the identification of chemicals of high toxicity concern, models with binary outputs and unsatisfied accuracy and coverage prevent the use of computational methods for prioritizing chemicals of high toxicity concern. Moreover, since each model represents only partial mechanisms of a complex toxicity endpoint, a single model alone is considered insufficient for toxicity prediction. It is therefore desirable to consider multiple pieces of evidence for toxicity prediction by integrating multiple complementary methods. This talk will cover our recent works on the integration of complementary computational methods for toxicity prediction and applications to the prioritization of chemicals of developmental and reproductive toxicity and carcinogenicity concerns. Methods of structural alerts, quantitative structure-activity relationships, and in silico toxicogenomics models were utilized for chemical prioritization. The proposed weight-of-evidence model is potentially useful for prioritizing chemicals of high toxicity concern and the methodology may be applied to other toxicities as well.