AI Research Catalyst Fund Awardees Virtual Seminar Series

“A Machine Learning Approach to Drug Hit Optimization”

by Dr. Chenglong Li
Professor in Department of Pharmacy/Medicinal Chemistry

Wednesday, October 13, 2021

ABSTRACT:

It is estimated that the process of bringing a single new drug to market can take up to 10 years, and cost billion dollars. The discovery process starts with the identification of a hit compound, a new molecule with promising activity against some disease target, usually by screening a large chemical database with experimental and computational techniques. This is then followed by the hit optimization phase, in which researchers attempt modifications of the initial structure to maximize the activity and minimize possible side effects. At this stage, besides activity, many properties need to be optimized at the same time such as absorption, distribution, and toxicity, making it a very complex and difficult task. It normally takes multiple cycles of design, synthesis, and experimental testing, resulting in the most expensive and laborious stage in drug discovery. Still, many drug candidates still fail approval due to unanticipated effects, and the whole process needs to be restarted. We are developing a new system that will harness the power of Artificial Intelligence to speed up this phase. Using AI, the computers will learn to suggest new molecules while optimizing many variables at the same time, generating new drug suggestions which already incorporate the desired traits. This system will greatly reduce the number of optimization cycles needed to reach a new candidate with greater chances for regulatory approval. It should help make the drug discovery process more efficient, significantly reducing the time and cost for a new drug to reach the market.

Bio: 

Chenglong Li is a professor of medicinal chemistry, biochemistry and biophysics. His main research focus is molecular recognition and closely related drug design and discovery. He combines AI-based deep learning, molecular simulation and experimental approaches to gain insights on specific molecular interactions and molecular design.

Wednesday, October 13, 2021
12:00PM – 1:00PM
Via Zoom

RSVP below. Instructions to attend talk via Zoom will be emailed to you.