VAM! AI Reading Group - Paper: AI (VAEs) for Drug Discovery

​Link: https://arxiv.org/abs/1610.02415

Paper: Automatic chemical design using a data-driven continuous representation of molecules

​Paper Summary:

​How can AI actually help us design better drugs?

​In this session, we’ll use one of the foundational papers in AI-driven drug design, “Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules” by Rafael Gómez-Bombarelli and colleagues, to explore that question in depth.

​The core idea is powerful: instead of treating drug discovery as a slow, brute-force search through massive chemical space, this paper shows how variational autoencoders (VAEs) can learn a continuous latent representation of molecules. That means molecules can be encoded into a learned space, properties can be predicted from that space, and entirely new molecular candidates can be generated and optimized computationally.

​Why does this matter? Traditional drug discovery is expensive, slow, and constrained by the sheer size of chemical space. AI offers a new way to navigate that complexity by turning molecule design into a search and optimization problem. This paper is one of the clearest early examples of that shift, and it still shapes how people think about generative models in drug discovery today.

​This session is for people who want to go beyond surface-level AI hype and understand the technical logic underneath. We’ll break down how the model works, why representing molecules is hard, what VAEs are doing in this context, and where the limitations of this approach begin to show. From there, we’ll use the paper as a lens into the broader question of what it would actually take for AI to meaningfully improve how new medicines are designed.

​Presenter: Pranav Menon

​​Pranav is an Adjunct Professor at UBC Engineering and the Program Director at TKS, where trains young people how to build with emerging technologies (AI, Brain Computer Interfaces, Genetics etc) to solve important problems.

​Recommended Action Item:

• ​Go through the paper and try to have one question and/or comment about the paper before coming to the reading group.

​Want to present?

• ​Please reach out to Issam Laradji

​To learn more about our events and community, see our website: https://vanaimeetup.com/

​Timeline:
🕠 6:00 PM – Arrival & Networking.

​🗣️ 6:10 PM ~ 7:30 – Paper Presentation & Discussions

​About the Founder of VAM

​Issam Laradji is a Research Scientist at ServiceNow and an Adjunct Professor at University of British Columbia. He holds a PhD in Computer Science and a PhD from the University of British Columbia, and his research interests include natural language processing, computer vision, and large-scale optimization.

​Looking forward to discussing the latest AI Papers!

​About Northeastern University

​Founded in 1898, Northeastern is a global research university and the recognized leader in experiential lifelong learning. With 13 campuses across the U.S., U.K., and Canada, over 320,000 alumni, and more than 3,800 partners worldwide, the global university network serves as a platform for scaling ideas, talent, and solutions. Located in the heart of downtown, the Vancouver campus offers a wide range of master’s-level tech degrees, including pathway programs that allow students with non-STEM backgrounds to pursue a graduate degree in tech.