Fold'EM: Direct atomic structure inference from Cryo-EM particles

2026-10-01

AI Summary

This study addresses the substantial sample requirements in cryo-EM density reconstruction and the difficulty of atomic modeling at low resolutions by proposing a test-time computation framework. For the first time, this method directly integrates sequence priors from protein generative models into the particle imaging stage. By combining joint optimization with unsupervised orientation inference algorithms, it bypasses intermediate density reconstruction to infer atomic structures end-to-end directly from particle images. Experimental results demonstrate that the proposed framework accurately recovers atomic models from both small-sample and heterogeneous mixture data, successfully resolving distinct conformational states within mixed particle populations. These findings indicate that the approach significantly reduces the cost and accessibility barriers associated with structural determination.

Abstract

Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cryo-EM computational pipeline first combines many particle images to reconstruct an electrostatic potential (ESP) map and then fits an atomic model to the recovered map. Density reconstruction has high sample complexity, requiring large numbers of particle images and making structure determination high-cost and low-throughput, particularly for heterogeneous samples. Downstream atomic model building, in turn, becomes increasingly difficult as the resolution of the reconstructed map deteriorates. Protein structure prediction models provide strong sequence-derived priors on atomic structure, and experiment-guided approaches can use these priors to recover structures consistent with experimental measurements. Yet, in cryo-EM, such priors are typically integrated only after density reconstruction during atomic model fitting. We introduce Fold'EM, an inference-time framework that combines priors from protein generative models directly with cryo-EM particle images to determine atomic models from a small number of single particle images, bypassing both intermediate density reconstruction and downstream model building against the reconstructed map. Across synthetic and experimental cryo-EM datasets, Fold'EM recovers accurate atomic structures both with known particle orientations and in an ab-initio setting where orientations are inferred jointly with structure. In heterogeneous datasets, Fold'EM further resolves distinct conformational states from mixed particle populations without separately reconstructing a density map and building an atomic model for each state. We believe these results open new avenues for structure determination in the low-sample regime and for characterizing low-population conformational states directly from cryo-EM particles.

Problem

• Cryo-EM
• atomic structure inference
• single-particle reconstruction
• conformational heterogeneity
• low-sample regime

Innovation

• Cryo-EM
• atomic structure inference
• protein generative models
• conformational heterogeneity
• low-sample regime