Latent Space Diffusion Models of Cryo-EM Structures
Preprint
Abstract
Cryo-electron microscopy (cryo-EM) is unique among tools in structural biology in its ability to image large, dynamic protein complexes. Key to this ability is image processing algorithms for heterogeneous cryo-EM reconstruction, including recent deep learning-based approaches. The state-of-the-art method cryoDRGN uses a Variational Autoencoder (VAE) framework to learn a continuous distribution of protein structures from single particle cryo-EM imaging data. While cryoDRGN can model complex structural motions, the Gaussian prior distribution of the VAE fails to match the aggregate approximate posterior, which prevents generative sampling of structures especially for multi-modal distributions (e.g. compositional heterogeneity). Here, we train a diffusion model as an expressive, learnable prior in the cryoDRGN framework. Our approach learns a high-quality generative model over molecular conformations directly from cryo-EM imaging data. We show the ability to sample from the model on two synthetic and two real datasets, where samples accurately follow the data distribution unlike samples from the VAE prior distribution. We also demonstrate how the diffusion model prior can be leveraged for fast latent space traversal and interpolation between states of interest. By learning an accurate model of the data distribution, our method unlocks tools in generative modeling, sampling, and distribution analysis for heterogeneous cryo-EM ensembles.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Statistical Mechanics: Theory and Molecular Simulation2023
- Deep generative modeling for volume reconstruction in cryo-electron microscopyJournal of Structural Biology, 2022
- Image Super-Resolution Via Iterative RefinementIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- 3D Flexible Refinement: Structure and Motion of Flexible Proteins from Cryo-EMMicroscopy and Microanalysis, 2022
- Diffusion Autoencoders: Toward a Meaningful and Decodable Representation2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networksNature Methods, 2021
- Structure, Function, and Antigenicity of the SARS-CoV-2 Spike GlycoproteinCell, 2020
- Modular Assembly of the Bacterial Large Ribosomal SubunitCell, 2016
- A family of embedded Runge-Kutta formulaeJournal of Computational and Applied Mathematics, 1980