[초청강연] AI-based protein structure prediction and protein design

AI-based protein structure prediction and protein design

Minkyung Baek

School of Biological Sciences, Seoul National University

Proteins are large biomolecules that play critical roles in essentially all biological processes.
Protein structure prediction is very important as the function of a protein is mainly dependent
on its 3D structure. With the increase in bio big data, data-driven approaches using artificial
intelligence (AI) techniques have made considerable progress in protein structure modeling
and its interaction prediction. The AI-based protein modeling method changed a framework
of protein research and opened a new era in Digital Biology. In this talk, I’ll present an AI-
based protein structure prediction method, RoseTTAFold, and its utilization to study
interactions between proteins and nucleic acids. RoseTTAFold enables rapid generation of
accurate protein tertiary and quaternary structures from sequence information alone, reducing
computational cost of traditional approaches such as template-based modeling and protein-
protein docking. I’ll also introduce AI-based protein design methods based on RoseTTAFold
and describe new opportunities in therapeutics and vaccine development based on artificial
proteins designed by AI.