- This event has passed.
CIS Seminar: “Graph representation learning for drug discovery”
March 25 at 3:00 PM - 4:00 PM
The current pandemic highlights an acute need to develop fast therapeutics against health threats. Traditional approaches to drug discovery are expensive and slow to react to pandemics. In this talk, I will discuss how to accelerate drug discovery with deep learning, and demonstrate their success in antibiotic discovery and COVID-19 drug combination design. In computational terms, the major challenge of drug discovery is molecular graph generation and multi-objective optimization. While deep learning has been extensively investigated for graph encoding, graph generation is a harder combinatorial task and remains under-explored. To address these challenges, I will present novel deep generative models that leverage the low treewidth prior of molecular graphs and demonstrate their success in molecular optimization.
Wengong Jin is a Ph.D. candidate in MIT CSAIL advised by Prof. Regina Barzilay and Prof. Tommi Jaakkola. He received a B.Eng degree from Shanghai Jiao Tong University in 2016 and a S.M. degree from MIT in 2018. His research interest is in deep learning, graph structured data, and drug discovery. He was a recipient of the William A. Martin Award for the best S.M. thesis in computer science at MIT. His work was published in machine learning conferences (ICML, NeurIPS, ICLR) and biology journals such as Cell. His work on antibiotic discovery was covered in Nature News, Science Blog, Guardian, BBC News, GovTech, Innovators, Financial Times, CBS Boston, Wbur, and STAT. His algorithms have been deployed in various pharmaceutical companies, including Amgen, AstraZeneca, BASF, Bayer, GSK, Janssen, Novartis, Merck, and Pfizer.