Discovery-Driven Mathematics and Artificial Intelligence for Biosciences and Drug Discovery

Discovery-driven mathematics and artificial intelligence for biosciences and drug discovery Project Summary Artificial intelligence (AI) is one of the most transformative technologies in human history and has profoundly changed the world around us in the past few years. Advancing AI has become a national strategy. Currently, AI is playing a crucial role in every aspect of biosciences. However, there are many challenges that that hinder the further advance of AI in pandemic forecasting, drug discovery, and directed evolution. My team has been addressing these challenges with a unique approach that utilizes advanced mathematics (i.e., algebraic topology, differential geometry, and combinatorial graphs) to empower AI for biosciences, including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) modeling, drug discovery, and AI-assisted directed evolution. Our approach has had proven successes in discovering the mechanisms of SARS-CoV-2 evolution and transmission in the early stage of the pandemic (i.e., May 2020), successful forecasting of two key mutation sites involved in prevailing SARS-CoV-2 variants long before their occurrence, and in D3R Grand Challenges, a worldwide competition series in computer-aided drug design. I plan to further pursue this unique path by focusing on three ambitious directions: 1) Develop a genome-informed mathematical AI paradigm to predict emerging viral variants and their impacts; 2) Develop an automated, human-proteome informed AI platform for drug discovery, and 3) Develop a mathematical AI-assisted paradigm for directed evolution. My research will be carried out in strong partnerships with experimental labs, Pfizer, and Bristol Myers Squibb.