BioML Seminar 10: Stephan Eismann on foundational models for RNA
[IN PERSON EVENT IN BERKELEY — Valley Life Sciences Building, Room 2040]
Join us for the 10th seminar from the BioML group in Machine Learning at Berkeley, sponsored by Pillar VC. We're hosting Stephan Eismann, head of ML at Atomic AI.
Stephan will talk about ATOM-1: A Foundation Model for RNA Structure and Function Built on Chemical Mapping Data
RNA-based medicines and RNA-targeting drugs are emerging as promising new approaches for treating disease. Optimizing these therapeutics by naive experimental screening is a time-consuming and expensive process, while rational design requires an accurate understanding of the structure and function of RNA. To address this design challenge, we developed ATOM-1, the first RNA foundation model trained on chemical mapping data, enabled by data collection strategies purposely developed for machine learning training. Using small probe neural networks on top of ATOM-1 embeddings, we demonstrate that this model has developed rich internal representations of RNA. Trained on limited amounts of additional data, these small networks achieve state-of-the-art accuracy on key RNA prediction tasks, suggesting that this approach can enable the design of therapies across the RNA landscape.
Prior to joining Atomic, Stephan did his PhD in the AI Laboratory at Stanford University where his research focused on the development of novel ML algorithms for problems in structural biology. Originally from Germany, he studied physics in Heidelberg and London before coming to the US.