| |
ML-NYC Mixer
|
| With Romain Lopez (Prof. CS, NYU). |
| Flatiron Institute, 162 5th Ave |
|
Feb 11 (Wed) , 2026 @ 04:00 PM
| |
FREE |
|
|
|
|
|
|
|
|
| |
/-73.99071503,40.74046326,13,0,0/550x200?access_token=pk.eyJ1IjoiZ2FyeXNndWlkZSIsImEiOiJjamtobmRiYmgwb3gwM3F1a2o2Mmd0YWw3In0.DinA62CR3-OKtf3axa5O7Q)
|
| |
| DETAILS |
|
Learning from Millions of Cells with Deep Generative Models
The ML in NYC Speaker Series + Happy Hour is excited to host Professor Romain Lopez of NYU as our February speaker! His talk will take place Wednesday, February 11 at 4pm at the Flatiron Institute. As always, there will be a reception afterward for all attendees.
Title: Learning from Millions of Cells with Deep Generative Models
Abstract: Biology is emerging as a highly sought-after application for the deployment of AI tools, & interest has only accelerated since the impact of AlphaFold on protein folding. This talk is specifically focused on deep generative models & their applications to the field of cellular & molecular biology. I will explain how profiling of RNA at scale enables the systematic mapping of cellular states in both healthy & disease contexts, & how ML plays a central role in denoising & interpreting the underlying data. I will discuss a few key challenges including (1) processing data at scale to discover new biology from large-scale collaborative efforts to map all cell types in the human body, (2) mapping variation in cellular states across modalities, & (3) modeling data from large-scale perturbation studies (e.g., for drug discovery applications).
Bio: Romain Lopez is an Assistant Professor of Computer Science & Biology at New York University. He received his MSc in Applied Mathematics from cole polytechnique & his PhD in Electrical Engineering & Computer Sciences from UC Berkeley, advised by Professors Michael I. Jordan & Nir Yosef. He was a Postdoctoral Fellow at Genentech & Stanford University, hosted by Professors Aviv Regev & Jonathan Pritchard. He has received Best Paper honors at leading AI & computational biology venues as well as a STAT Wunderkind Award (2024), recognizing North America's most promising early-career scientists. His research develops probabilistic & causal machine learning methods to uncover the mechanisms that govern cellular behavior & disease, including the scVI framework & the scvi-tools ecosystem for deep generative modeling of single-cell omics data.
|
|
|
|
|
|
|
|
