My research develops advanced mathematical frameworks—commutative algebra, topological data analysis, spectral data analysis, and differential geometry—into practical tools for AI-driven molecular science. These methods span from foundational mathematical theory to applied problems in drug design, protein engineering, materials discovery, and viral evolution, alongside a continuing line of work in complex analysis and operator theory. Representative publications are linked under each theme below; the full list with abstracts and citation metrics is on the Publications page.
Mathematical Foundation of Data Science
Commutative Algebra, Topological data analysis, Spectral data analysis, Geometric data analysis
Illustration of the workflow for predicting deep mutational scanning (DMS) of SARS-CoV-2 S protein RBD-ACE2 complexes using topological deep learning.
[Paper, Poster]
Virus evolution, Cross-species transmission, Deep mutational scanning [Poster]