pith. sign in

arxiv: 2211.14169 · v1 · pith:RNXRXYEZnew · submitted 2022-11-25 · 🧬 q-bio.QM · stat.ML

Latent Space Diffusion Models of Cryo-EM Structures

classification 🧬 q-bio.QM stat.ML
keywords cryo-emdistributionmodeldatapriorabilitycryodrgndiffusion
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. On the Limits of Latent Reuse in Diffusion Models

    stat.ML 2026-05 unverdicted novelty 5.0

    Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.