Reconstructing continuous distributions of 3D protein structure from cryo-EM images
Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structure of proteins and other macromolecular complexes at near-atomic resolution. In single particle cryo-EM, the central problem is to reconstruct the three-dimensional structure of a macromolecule from $10^{4-7}$ n...
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Online Access: | https://hdl.handle.net/1721.1/137001 |
_version_ | 1811085273611632640 |
---|---|
author | Zhong, Ellen D Bepler, Tristan Davis, Joseph H Berger, Bonnie |
author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhong, Ellen D Bepler, Tristan Davis, Joseph H Berger, Bonnie |
author_sort | Zhong, Ellen D |
collection | MIT |
description | Cryo-electron microscopy (cryo-EM) is a powerful technique for determining
the structure of proteins and other macromolecular complexes at near-atomic
resolution. In single particle cryo-EM, the central problem is to reconstruct
the three-dimensional structure of a macromolecule from $10^{4-7}$ noisy and
randomly oriented two-dimensional projections. However, the imaged protein
complexes may exhibit structural variability, which complicates reconstruction
and is typically addressed using discrete clustering approaches that fail to
capture the full range of protein dynamics. Here, we introduce a novel method
for cryo-EM reconstruction that extends naturally to modeling continuous
generative factors of structural heterogeneity. This method encodes structures
in Fourier space using coordinate-based deep neural networks, and trains these
networks from unlabeled 2D cryo-EM images by combining exact inference over
image orientation with variational inference for structural heterogeneity. We
demonstrate that the proposed method, termed cryoDRGN, can perform ab initio
reconstruction of 3D protein complexes from simulated and real 2D cryo-EM image
data. To our knowledge, cryoDRGN is the first neural network-based approach for
cryo-EM reconstruction and the first end-to-end method for directly
reconstructing continuous ensembles of protein structures from cryo-EM images. |
first_indexed | 2024-09-23T13:06:20Z |
format | Article |
id | mit-1721.1/137001 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T13:06:20Z |
publishDate | 2021 |
record_format | dspace |
spelling | mit-1721.1/1370012023-02-03T21:07:00Z Reconstructing continuous distributions of 3D protein structure from cryo-EM images Zhong, Ellen D Bepler, Tristan Davis, Joseph H Berger, Bonnie Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Biology Massachusetts Institute of Technology. Department of Mathematics Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structure of proteins and other macromolecular complexes at near-atomic resolution. In single particle cryo-EM, the central problem is to reconstruct the three-dimensional structure of a macromolecule from $10^{4-7}$ noisy and randomly oriented two-dimensional projections. However, the imaged protein complexes may exhibit structural variability, which complicates reconstruction and is typically addressed using discrete clustering approaches that fail to capture the full range of protein dynamics. Here, we introduce a novel method for cryo-EM reconstruction that extends naturally to modeling continuous generative factors of structural heterogeneity. This method encodes structures in Fourier space using coordinate-based deep neural networks, and trains these networks from unlabeled 2D cryo-EM images by combining exact inference over image orientation with variational inference for structural heterogeneity. We demonstrate that the proposed method, termed cryoDRGN, can perform ab initio reconstruction of 3D protein complexes from simulated and real 2D cryo-EM image data. To our knowledge, cryoDRGN is the first neural network-based approach for cryo-EM reconstruction and the first end-to-end method for directly reconstructing continuous ensembles of protein structures from cryo-EM images. 2021-11-01T17:39:54Z 2021-11-01T17:39:54Z 2020 2021-07-15T18:03:49Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137001 Zhong, Ellen D, Bepler, Tristan, Davis, Joseph H and Berger, Bonnie. 2020. "Reconstructing continuous distributions of 3D protein structure from cryo-EM images." International Conference on Learning Representations (ICLR), 2020. en https://openreview.net/group?id=ICLR.cc/2020/Conference International Conference on Learning Representations (ICLR), 2020 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf arXiv |
spellingShingle | Zhong, Ellen D Bepler, Tristan Davis, Joseph H Berger, Bonnie Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title | Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title_full | Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title_fullStr | Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title_full_unstemmed | Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title_short | Reconstructing continuous distributions of 3D protein structure from cryo-EM images |
title_sort | reconstructing continuous distributions of 3d protein structure from cryo em images |
url | https://hdl.handle.net/1721.1/137001 |
work_keys_str_mv | AT zhongellend reconstructingcontinuousdistributionsof3dproteinstructurefromcryoemimages AT beplertristan reconstructingcontinuousdistributionsof3dproteinstructurefromcryoemimages AT davisjosephh reconstructingcontinuousdistributionsof3dproteinstructurefromcryoemimages AT bergerbonnie reconstructingcontinuousdistributionsof3dproteinstructurefromcryoemimages |