Enhancing Cryo-EM Maps with 3D Deep Generative Networks for Assisting Protein Structure Modeling

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2023 Aug 7

PMID 37549063

Authors

Sai Raghavendra Maddhuri Venkata Subramaniya

Genki Terashi

Daisuke Kihara

Affiliations

Soon will be listed here.

Abstract

Motivation: The tertiary structures of an increasing number of biological macromolecules have been determined using cryo-electron microscopy (cryo-EM). However, there are still many cases where the resolution is not high enough to model the molecular structures with standard computational tools. If the resolution obtained is near the empirical borderline (3-4.5 Å), improvement in the map quality facilitates structure modeling.

Results: We report EM-GAN, a novel approach that modifies an input cryo-EM map to assist protein structure modeling. The method uses a 3D generative adversarial network (GAN) that has been trained on high- and low-resolution density maps to learn the density patterns, and modifies the input map to enhance its suitability for modeling. The method was tested extensively on a dataset of 65 EM maps in the resolution range of 3-6 Å and showed substantial improvements in structure modeling using popular protein structure modeling tools.

Availability And Implementation: https://github.com/kiharalab/EM-GAN, Google Colab: https://tinyurl.com/3ccxpttx.

Citing Articles

AI-based methods for biomolecular structure modeling for Cryo-EM.

Farheen F, Terashi G, Zhu H, Kihara D Curr Opin Struct Biol. 2025; 90:102989.

PMID: 39864242 PMC: 11793015. DOI: 10.1016/j.sbi.2025.102989.

Protein Secondary Structure and DNA/RNA Detection for Cryo-EM and Cryo-ET Using Emap2sec and Emap2sec.

Baghirov J, Zhu H, Wang X, Kihara D Methods Mol Biol. 2024; 2867:105-120.

PMID: 39576577 DOI: 10.1007/978-1-0716-4196-5_6.

Super-resolution microscopy to study membrane nanodomains and transport mechanisms in the plasma membrane.

Zulueta Diaz Y, Arnspang E Front Mol Biosci. 2024; 11:1455153.

PMID: 39290992 PMC: 11405310. DOI: 10.3389/fmolb.2024.1455153.

The small CRL4 ubiquitin ligase component DDA1 regulates transcription-coupled repair dynamics.

Llerena Schiffmacher D, Lee S, Kliza K, Theil A, Akita M, Helfricht A Nat Commun. 2024; 15(1):6374.

PMID: 39075067 PMC: 11286758. DOI: 10.1038/s41467-024-50584-7.

Machine learning approaches to cryoEM density modification differentially affect biomacromolecule and ligand density quality.

Berkeley R, Cook B, Herzik Jr M Front Mol Biosci. 2024; 11:1404885.

PMID: 38698773 PMC: 11063317. DOI: 10.3389/fmolb.2024.1404885.

References

Terashi G, Kihara D . De novo main-chain modeling for EM maps using MAINMAST. Nat Commun. 2018; 9(1):1618. PMC: 5915429. DOI: 10.1038/s41467-018-04053-7. View

Rotkiewicz P, Skolnick J . Fast procedure for reconstruction of full-atom protein models from reduced representations. J Comput Chem. 2008; 29(9):1460-5. PMC: 2692024. DOI: 10.1002/jcc.20906. View

Pettersen E, Goddard T, Huang C, Couch G, Greenblatt D, Meng E . UCSF Chimera--a visualization system for exploratory research and analysis. J Comput Chem. 2004; 25(13):1605-12. DOI: 10.1002/jcc.20084. View

Terwilliger T, Adams P, Afonine P, Sobolev O . A fully automatic method yielding initial models from high-resolution cryo-electron microscopy maps. Nat Methods. 2018; 15(11):905-908. PMC: 6214191. DOI: 10.1038/s41592-018-0173-1. View

Tickle I . Statistical quality indicators for electron-density maps. Acta Crystallogr D Biol Crystallogr. 2012; 68(Pt 4):454-67. PMC: 3322605. DOI: 10.1107/S0907444911035918. View

Wang R, Kudryashev M, Li X, Egelman E, Basler M, Cheng Y . De novo protein structure determination from near-atomic-resolution cryo-EM maps. Nat Methods. 2015; 12(4):335-8. PMC: 4435692. DOI: 10.1038/nmeth.3287. View

Terashi G, Kihara D . De novo main-chain modeling with MAINMAST in 2015/2016 EM Model Challenge. J Struct Biol. 2018; 204(2):351-359. PMC: 6179447. DOI: 10.1016/j.jsb.2018.07.013. View

Ramirez-Aportela E, Vilas J, Glukhova A, Melero R, Conesa P, Martinez M . Automatic local resolution-based sharpening of cryo-EM maps. Bioinformatics. 2019; 36(3):765-772. PMC: 9883678. DOI: 10.1093/bioinformatics/btz671. View

Terwilliger T, Ludtke S, Read R, Adams P, Afonine P . Improvement of cryo-EM maps by density modification. Nat Methods. 2020; 17(9):923-927. PMC: 7484085. DOI: 10.1038/s41592-020-0914-9. View

10.

Luo Z, Campos-Acevedo A, Lv L, Wang Q, Ma J . Sparseness and Smoothness Regularized Imaging for improving the resolution of Cryo-EM single-particle reconstruction. Proc Natl Acad Sci U S A. 2021; 118(2). PMC: 7812788. DOI: 10.1073/pnas.2013756118. View

11.

Jakobi A, Wilmanns M, Sachse C . Model-based local density sharpening of cryo-EM maps. Elife. 2017; 6. PMC: 5679758. DOI: 10.7554/eLife.27131. View

12.

Pfab J, Phan N, Si D . DeepTracer for fast de novo cryo-EM protein structure modeling and special studies on CoV-related complexes. Proc Natl Acad Sci U S A. 2020; 118(2). PMC: 7812826. DOI: 10.1073/pnas.2017525118. View

13.

Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X . Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Trans Med Imaging. 2018; 37(6):1348-1357. PMC: 6021013. DOI: 10.1109/TMI.2018.2827462. View

14.

Bepler T, Kelley K, Noble A, Berger B . Topaz-Denoise: general deep denoising models for cryoEM and cryoET. Nat Commun. 2020; 11(1):5208. PMC: 7567117. DOI: 10.1038/s41467-020-18952-1. View

15.

Rosenthal P, Henderson R . Optimal determination of particle orientation, absolute hand, and contrast loss in single-particle electron cryomicroscopy. J Mol Biol. 2003; 333(4):721-45. DOI: 10.1016/j.jmb.2003.07.013. View

16.

Sanchez-Garcia R, Gomez-Blanco J, Cuervo A, Carazo J, Sorzano C, Vargas J . DeepEMhancer: a deep learning solution for cryo-EM volume post-processing. Commun Biol. 2021; 4(1):874. PMC: 8282847. DOI: 10.1038/s42003-021-02399-1. View

17.

Zhong E, Bepler T, Berger B, Davis J . CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks. Nat Methods. 2021; 18(2):176-185. PMC: 8183613. DOI: 10.1038/s41592-020-01049-4. View

18.

Ouyang W, Aristov A, Lelek M, Hao X, Zimmer C . Deep learning massively accelerates super-resolution localization microscopy. Nat Biotechnol. 2018; 36(5):460-468. DOI: 10.1038/nbt.4106. View

19.

Chen M, Baldwin P, Ludtke S, Baker M . De Novo modeling in cryo-EM density maps with Pathwalking. J Struct Biol. 2016; 196(3):289-298. PMC: 5118137. DOI: 10.1016/j.jsb.2016.06.004. View

20.

Baker M, Rees I, Ludtke S, Chiu W, Baker M . Constructing and validating initial Cα models from subnanometer resolution density maps with pathwalking. Structure. 2012; 20(3):450-63. PMC: 3307788. DOI: 10.1016/j.str.2012.01.008. View