CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations

Xinhang Liu, Yan Zeng, Yifan Qin, Hao Li, Jiakai Zhang, Lan Xu, Jingyi Yu

Keywords: Neural Representation, Cryo-EM reconstruction, Structural Biology

TL;DR: We propose CryoFormer, a new approach for continuous heterogeneous cryo-EM reconstruction using a real domain neural representation.

Abstract: Cryo-electron microscopy (cryo-EM) allows for the high-resolution reconstruction of 3D structures of proteins and other biomolecules. Successful reconstruction of both shape and movement greatly helps understand the fundamental processes of life. However, it is still challenging to reconstruct the continuous motions of 3D structures from hundreds of thousands of noisy and randomly oriented 2D cryo-EM images. While recent advancements using Fourier domain coordinate-based neural networks show compelling results in modeling continuous 3D conformations, these methods often struggle to capture local flexible regions accurately. We propose CryoFormer, a new approach for continuous heterogeneous cryo-EM reconstruction. Our approach constructs an implicit feature volume directly in the real domain as the 3D representation. We also design a query-based deformation transformer decoder to effectively predict the density. Our approach is capable of refining pre-computed pose estimations and locating flexible regions. In experiments, our method outperforms current approaches on three public datasets (1 synthetic and 2 experimental) and a new synthetic dataset of PEDV spike protein. The code and new synthetic dataset will be released for better reproducibility of our results.

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 483