Flow models with applications to cell and molecular biology

Par

Alexander Tong

Université de Montréal

vendredi 16 février 2024, 10:30-11:30 EST, Salle 6214

Pavillon André-Aisenstadt, Université de Montréal, 2920 Chemin de la Tour

Abstract: Generative flow models learn a (possibly stochastic) mapping between source and target distributions. Common paradigms include diffusion models, score matching models, and continuous normalizing flows. In this talk I will first present methods for improved training of flow models using flow matching objectives using ideas from optimal transport. I will then show how these improved methods can be applied to the tasks of (1) modelling cell dynamics, which allow us to better understand disease programs – leading to a new potential therapeutic pathway for triple-negative breast cancer and (2) generative protein design, with applications to biologic drug discovery.

Bio: Alex Tong is a postdoctoral researcher at Université de Montréal and Mila, where he works with Yoshua Bengio at the intersection of generative machine learning and biology with focuses on applications to cell and molecular biology. This work is part of a joint effort with Fabian Theis through the Helmholtz International Lab. He is also cofounder of Dreamfold, a Mila startup which builds generative models for protein design. Alex earned his Ph.D. from the Computer Science Department at Yale University in 2021, under the guidance of Smita Krishnaswamy where he studied optimal transport, graph signal processing, and generative modeling of cell dynamics and perturbations. His research interests span generative modeling, causal discovery, sampling, and optimal transport.