Saved in:
Bibliographic Details
Main Authors: Zhou, Yi, Li, Yilai, Yuan, Jing, Gu, Quanquan
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