CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
This work addresses a bottleneck in cryo-EM and cryo-ET for structural biologists and drug discovery researchers by providing a flexible prior for multiple tasks, though it builds on existing flow matching methods.
The authors tackled the problem of cryo-EM data processing algorithms not fully benefiting from knowledge of biomolecular density maps by developing CryoFM, a flow-based foundation model that learns the distribution of high-quality density maps and generalizes to downstream tasks, achieving state-of-the-art performance on most tasks without fine-tuning.
Cryo-electron microscopy (cryo-EM) is a powerful technique in structural biology and drug discovery, enabling the study of biomolecules at high resolution. Significant advancements by structural biologists using cryo-EM have led to the production of over 38,626 protein density maps at various resolutions1. However, cryo-EM data processing algorithms have yet to fully benefit from our knowledge of biomolecular density maps, with only a few recent models being data-driven but limited to specific tasks. In this study, we present CryoFM, a foundation model designed as a generative model, learning the distribution of high-quality density maps and generalizing effectively to downstream tasks. Built on flow matching, CryoFM is trained to accurately capture the prior distribution of biomolecular density maps. Furthermore, we introduce a flow posterior sampling method that leverages CRYOFM as a flexible prior for several downstream tasks in cryo-EM and cryo-electron tomography (cryo-ET) without the need for fine-tuning, achieving state-of-the-art performance on most tasks and demonstrating its potential as a foundational model for broader applications in these fields.