English

CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks

Computer Vision and Pattern Recognition 2026-03-23 v2

Abstract

Cryo-electron microscopy (cryo-EM) is an indispensable technique for determining the 3D structures of dynamic biomolecular complexes. While typically applied to image a single molecular species, cryo-EM has the potential for structure determination of many targets simultaneously in a high-throughput fashion. However, existing methods typically focus on modeling conformational heterogeneity within a single or a few structures and are not designed to resolve compositional heterogeneity arising from mixtures of many distinct molecular species. To address this challenge, we propose CryoHype, a transformer-based hypernetwork for cryo-EM reconstruction that dynamically adjusts the weights of an implicit neural representation. Using CryoHype, we achieve state-of-the-art results on a challenging benchmark dataset containing 100 structures. We further demonstrate that CryoHype scales to the reconstruction of 1,000 distinct structures from unlabeled cryo-EM images in the fixed-pose setting.

Keywords

Cite

@article{arxiv.2512.06332,
  title  = {CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks},
  author = {Jeffrey Gu and Minkyu Jeon and Ambri Ma and Serena Yeung-Levy and Ellen D. Zhong},
  journal= {arXiv preprint arXiv:2512.06332},
  year   = {2026}
}

Comments

CVPR 2026

R2 v1 2026-07-01T08:12:50.201Z