Dr. Minjun Chen is a senior scientist at Division of Bioinformatics and Biostatistics, the US FDA’s National Center for Toxicological Research (NCTR). His major research interests encompass to develop the state-of-the-art computational technologies for the study of drug-induced liver injury and liver disease. He developed the “rule-of-two” and DILIscore models and applied these models to evaluate drug-induced liver injury (DILI) risk of over 50 NDA and IND submissions for supporting the FDA reviewers’ regulatory decision. He also developed the DILIrank database, which has been widely used by the community to support the development of DILI predictive models and biomarkers. He is one of the founders and the chair of the FDA Liver Toxicity Working Group (LTWG) and serves as the vice president of the computational toxicological special section (CTSS) of Society of Toxicology. Dr. Chen has published over 100 peer-reviewed papers and book chapters and is the major editor of a book titled “Drug-Induced
Liver Toxicity” published by Humana Press, Springer in 2018.

OpenTox 2022 Virtual Conference

Quantitative Structure-Activity Relationship (QSAR) Model for Predicting a Drug’s Potential to Cause Liver Injury in Human 

Drug-induced liver injury (DILI) is one of the leading causes of the termination of drug development programs. Consequently, identifying the risk of DILI in humans for drug candidates during the early stages of the development process would greatly reduce the drug attrition rate in the pharmaceutical industry but would require the implementation of new research and development strategies. In this regard, several in silico models have been proposed as alternative means in prioritizing drug candidates. Because the accuracy and utility of a predictive model rests largely on how to annotate the potential of a drug to cause DILI in a reliable and consistent way, the Food and Drug Administration–approved drug labeling was given prominence. Out of 387 drugs annotated, 197 drugs were used to develop a quantitative structure-activity relationship (QSAR) model and the model was subsequently challenged by the left of drugs serving as an external validation set with an overall prediction accuracy of 68.9%. The performance of the model was further assessed by the use of 2 additional independent validation sets. The presented QSAR model, used together with other models developed in our group, could be useful in drug discovery to assess drug candidates for their DILI potential in humans.