• Corpus ID: 254018301

Latent Space Diffusion Models of Cryo-EM Structures

  title={Latent Space Diffusion Models of Cryo-EM Structures},
  author={Karsten Kreis and Tim Dockhorn and Zihao Li and Ellen D. Zhong},
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… 
1 Citations

Figures and Tables from this paper

Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Action

An introduction of the key concepts and theoretical foundations of three cornerstone diffusion modeling frameworks (denoising diffusion probabilistic models, noise-conditioned scoring networks, and stochastic differential equations), followed by a comprehensive description of diffusion models employed in the different domains of bioinformatics.



CryoDRGN: Reconstruction of heterogeneous cryo-EM structures using neural networks

CryoDRGN, an algorithm that leverages the representation power of deep neural networks to directly reconstruct continuous distributions of 3D density maps and map per-particle heterogeneity of single-particles cryo-EM datasets, is presented.

Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy

CryoDRGN2: Ab initio neural reconstruction of 3D protein structures from real cryo-EM images

Protein structure determination from cryo-EM data requires reconstructing a 3D volume (or distribution of volumes) from many noisy and randomly oriented 2D projection images. While the standard

Computational Methods for Single-Particle Electron Cryomicroscopy.

Computational methods for structure determination by single-particle cryo-EM and their guiding principles from statistical inference, machine learning, and signal processing that also play a significant role in many other data science applications are discussed.

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

VAEBM is proposed, a symbiotic composition of a VAE and an EBM that offers the best of both worlds and outperforms state-of-the-art VAEs and EBMs in generative quality on several benchmark image datasets by a large margin.

cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination

It is shown that stochastic gradient descent (SGD) and branch-and-bound maximum likelihood optimization algorithms permit the major steps in cryo-EM structure determination to be performed in hours or minutes on an inexpensive desktop computer.

A Score-based Geometric Model for Molecular Dynamics Simulations

A novel model called ScoreMD, which perturbs the molecular structure with a conditional noise depending on atomic accelerations and employs conformations at previous timeframes as the prior distribution for sampling, and incorporates the directions and velocities of atomic motions via 3D spherical Fourier-Bessel representations.

3D Flexible Refinement: Structure and Motion of Flexible Proteins from Cryo-EM

The ability to obtain insight into motion in macromolecules, as well as the ability to resolve features that are usually lost in cryo-EM of flexible specimens, will provide new insight and allow new avenues of investigation into biomolecular structure and function.

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation

This paper proposes a novel generative model named GEODIFF for molecular conformation prediction that treats each atom as a particle and learns to directly reverse the diffusion process (i.e., transforming from a noise distribution to stable conformations) as a Markov chain.

D2C: Diffusion-Denoising Models for Few-shot Conditional Generation

Diffusion-Decoding models with Contrastive representations (D2C), a paradigm for training unconditional variational autoencoders (VAEs) for few-shot conditional image generation and contrastive self-supervised learning to improve representation quality is described.