Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.08631 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909414770868224 |
|---|---|
| author | Zhou, Yi Li, Yilai Yuan, Jing Gu, Quanquan |
| author_facet | Zhou, Yi Li, Yilai Yuan, Jing Gu, Quanquan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08631 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CryoFM: A Flow-based Foundation Model for Cryo-EM Densities Zhou, Yi Li, Yilai Yuan, Jing Gu, Quanquan Biomolecules Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning 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. |
| title | CryoFM: A Flow-based Foundation Model for Cryo-EM Densities |
| topic | Biomolecules Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning |
| url | https://arxiv.org/abs/2410.08631 |