The Translational Data Analytics Institute and five peer institutions are co-presenting a Generative AI Coast-to-Coast Discussion Series that brings together speakers to discuss generative AI in research and foster community and collaboration among researchers from multiples disciplines and institutions. Other participating institutions are Johns Hopkins University; Rice University; the International Computer Science Institute; the University of Michigan; and the University of Washington.
Aug. 23 Topic: Generative AI in Biomedical Science
Moderator
Angela Wilkins, Executive Director, Ken Kennedy Institute, Rice University
Speakers
Xia Ning, Professor, Biomedical Informatics, Computer Science and Engineering, Translational Data Analytics Institute, The Ohio State University - "Generative AI for Drug Discovery"
Abstract: Artificial Intelligence (AI) for drug discovery has been going far beyond predictive analysis over existing drug candidates. The recent, cutting-edge generative AI enables tremendous opportunities to generate new drug structures and peptide sequences that may not exist but exhibit better properties than any existing ones. This talk will demonstrate three studies on generative AI to 1) generate new small-molecule drug candidates, 2) identify synthetic paths for any (generated) small molecules and 3) generate new binding peptide sequences for MHC Class I proteins. Dr.Ning will present work using auto-encoder-based deep learning, graph neural networks, and deep reinforcement learning for the three studies. Overall, it will show how generative AI can help drug discovery that cannot be achieved using conventional methods.
Speaker 2: TBD
Photo illustration by Volodymyr Hryshchenko on Unsplash
