Guowei Wei, Michigan State University.
October 13, 2020. 12:45 – 1:45 pm.
A Virtual Seminar on Blackboard Collaborate.
Artificial intelligence (AI) has fundamentally changed the landscape of science, technology, industry, and social media in the past few years. It holds a great future for the design and discovery of COVID-19 diagnostics, vaccines, and drugs significantly faster and cheaper. However, AI-based developments of COVID-19 diagnostics, vaccines, antibody therapies, and small-molecular drugs encounter obstacles arising from the structural complexity of protein-drug interactions and the high dimensionality of drug candidates’ chemical/biological space. We tackle these challenges mathematically. Our work focuses on reducing the biomolecular complexity and dimensionality in AI. We have introduced evolutionary de Rham-Hodge, multiscale cohomology, and persistent spectral graph to obtain high-level abstractions of protein-drug interactions and thus significantly enhance AI’s ability to predict optimal antibody therapies, repurposed drugs, and new drug candidates for COVID-19. We genotype SARS-CoV-2 genome isolates to understand the SARS-CoV-2 infectivity changes and mitigate mutational threat on the current development of diagnostics, vaccines, antibody therapies, and small-molecular drugs.
Guowei Wei a Foundation Professor of Mathematics, Electrical and Computer Engineering, and Biochemistry and Molecular Biology at Michigan State University. Funded by NSF, NIH, NASA, Michigan Economic Development Corporation, Pfizer and Bristol-Myers Squibb, his current research interests include mathematical molecular bioscience and biophysics, deep learning, drug discovery, and computational geometry and topology. He has advised over a hundred of students, postdocs, and visiting scientists. Professor Wei has served extensively in a wide variety of national and international panels, committees and journal editorships.