Stanford CS25: V5 I Multimodal World Models for Drug Discovery, Eshed Margalit of Noetik.ai

May 20, 2025 Where are all the cancer drugs? The past decade has seen astounding progress in machine learning, including the dominance of large transformer-based models in learning from massive datasets. At the same time, the field of cancer biology has enjoyed rapid improvement in the cost, speed, and resolution of once-futuristic measurement tools. These advancements should go hand in hand, yet we still lack models that can tell us which biological targets to drug in which patient subpopulations. In this talk I'll describe one particularly promising approach to this problem: large multimodal world models of patient biology. The two core ingredients to this approach are quite general: 1) collecting a large dataset that spans many scales and modalities, and 2) training multimodal transformers that learn to fuse those data streams in a way that allows nuanced simulations with a "world model". I will give an accessible overview of these components, and share our progress in applying them to cancer immunotherapy. Speaker: Eshed is a neuroscientist and ML researcher working to understand biological systems with AI. He completed his PhD in neuroscience at Stanford, where he constructed self-supervised neural networks that incorporate biologically-inspired constraints to explain the structure, function, and development of primate visual cortex. Eshed is currently an ML scientist at Noetik, an AI-native biotech startup focused on curing cancer. In his work he develops novel transformer model architectures and tasks that learn from a large multi-modal dataset of patient tumor biology, and applies those models to drug discovery. More about the course can be found here: https://web.stanford.edu/class/cs25/ View the entire CS25 Transformers United playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM