AI in Drug Design: Part I – Molecular Drug Discovery

26 March 2024 | 6:00 PM - 7:00 PM CET | 12:00 PM - 1:00 PM ET | Online Webinar
AI in Drug Design: Part I – Molecular Drug Discovery

As part of Advancing Drug Discovery: A Webinar Series of the National Academies of Sciences, Engineering and Medicine, a two part series on AI in Drug Design will be featured. The 60-minute session will consist a presentation from Dr. Marinka, Assistant Professor at Harvard in the Department of Biomedical Informatics, on molecular drug discovery and a Q+A session.

The first part of this workshop introduces how AI is advancing molecular drug discovery. Large language models and generative AI are profoundly transforming drug design. The discussion includes self-supervised learning, which utilizes extensive unlabelled datasets, and geometric deep learning, which leverages the geometry and structure of biochemical data. These approaches give rise to generative models that help design useful molecules by generating molecular structures that maximize binding affinity with biological targets, serve as optimal binders, and have specific biochemical properties. For drugs to be effective, they must act on biological targets in relevant biological contexts. The session describes PINNACLE, a graph neural network that identifies optimal cellular contexts for drug action. PINNACLE models perform an array of tasks, including enhancing 3D structural protein representations critical in immune-oncology, predicting the effects of drugs across cell-type contexts, and nominating therapeutic targets in a cell-type specific manner.

Registration and information about AI in Drug Design: Part II – Clinical Drug Development on April 23.


Speaker bio

Marinka Zitnik is an Assistant Professor at Harvard in the Department of Biomedical Informatics with additional appointments at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, Broad Institute of MIT and Harvard, and Harvard Data Science. Zitnik investigates the foundations of AI that contribute to the scientific understanding of medicine and therapeutic design, eventually enabling AI to learn on its own and acquire knowledge autonomously. Her research won several best paper and research awards, including Kavli Fellowship of the National Academy of Sciences, awards from International Society for Computational Biology, International Conference in Machine Learning, Bayer Early Excellence in Science, Amazon Faculty Research, Google Faculty Research, Roche Alliance with Distinguished Scientists, and Sanofi iDEA-iTECH Award. She founded Therapeutics Data Commons, a global open-science AI foundation to advance therapeutic science and is the faculty lead of the AI4Science initiative.



Ana Ferreras –

Photo by National Cancer Institute on Unsplash

Skip to content