Math Modeling Seminar: Applications of Topological Data Analysis and Machine Learning Models in Predictive Biology and Drug Discovery

Math Modeling Seminar
Applications of Topological Data Analysis and Machine Learning Models in Predictive Biology and Drug Discovery

Zoom Link here

Dr. Rui Wang
Assistant Professor, School of Mathematics and Statistics
Rochester Institute of Technology

Abstract:
Topological Data Analysis (TDA) provides a powerful tool to extract robust, multiscale, and shape-based insights from complex and high-dimensional datasets. In recent years, the integration of TDA with machine learning has opened new opportunities for modeling biomolecular systems, understanding disease mechanisms, and accelerating drug discovery. This talk will start with two TDA methods I developed, Persistent Spectral Graphs (PSG) and Persistent Path Laplacians (PPL), to extract homotopic shape evolution and directed information from biological datasets that are not accessible to traditional TDA methods. I will then present how PSG-based representations are constructed as input features and integrated into AI pipelines to enable biologically meaningful predictions in public health research, such as forecasting infectivity-strengthening and antibody-escape mutations in SARS-CoV-2, designing potential anti-cocaine addiction drug leads, developing high-likelihood RNA motifs, and enhancing the accuracy of peptide-protein docking.

Speaker Bio:
Rui Wang is currently an Assistant Professor in the School of Mathematics and Statistics, College of Science, at Rochester Institute of Technology. Prior to joining RIT, she was an Independent Postdoctoral Fellow at the Simons Center for Computational Physical Chemistry (SCCPC) at New York University and a Visiting Assistant Professor in the Department of Mathematics at Michigan State University. She hold a Bachelor’s Degree in Mathematics and Applied Mathematics from Xi’an Jiaotong University and a Ph.D. in Applied Mathematics from Michigan State University.

Intended Audience:
Beginners, undergraduates, graduates. Those with interest in the topic.