2022Levy CryoFire

From 3DEM-Methods
Jump to navigation Jump to search

Citation

Levy, Axel / Wetzstein, Gordon / Martel, Julien N. P. / Poitevin, Frederic / Zhong, Ellen Amortized Inference for Heterogeneous Reconstruction in Cryo-EM 2022. Proc. Advances in Neural Information Processing Systems, Vol. 35, p. 13038-13049

Abstract

Cryo-electron microscopy (cryo-EM) is an imaging modality that provides unique insights into the dynamics of proteins and other building blocks of life. The algorithmic challenge of jointly estimating the poses, 3D structure, and conformational heterogeneity of a biomolecule from millions of noisy and randomly oriented 2D projections in a computationally efficient manner, however, remains unsolved. Our method, cryoFIRE, performs ab initio heterogeneous reconstruction with unknown poses in an amortized framework, thereby avoiding the computationally expensive step of pose search while enabling the analysis of conformational heterogeneity. Poses and conformation are jointly estimated by an encoder while a physics-based decoder aggregates the images into an implicit neural representation of the conformational space. We show that our method can provide one order of magnitude speedup on datasets containing millions of images without any loss of accuracy. We validate that the joint estimation of poses and conformations can be amortized over the size of the dataset. For the first time, we prove that an amortized method can extract interpretable dynamic information from experimental datasets.

Keywords

Links

https://proceedings.neurips.cc/paper_files/paper/2022/file/54b8b4e0b4ba4aad112e84f32e3b5dbb-Paper-Conference.pdf

Related software

Related methods

Comments