CryoFIFA: deep curriculum learning for cryo-EM fine and fast ab-initio reconstruction
摘要
Cryo-electron microscopy (Cryo-EM) single particle analysis (SPA) is currently the primary method for determining structures of macromolecular complexes ranging from tens of kilodaltons (kDa) to several megadaltons (MDa). Traditional cryo-EM three-dimensional (3D) reconstruction and refinement methods are based on maximum likelihood approaches. Recently, deep learning-based methods began to emerge in the field of cryo-EM reconstruction. Here, we propose cryoFIFA, a deep curriculum learning-based approach for cryo-EM fine and fast 3D reconstruction. CryoFIFA enables the ab-initio reconstruction of macromolecules ranging from ~150 kDa to over 2 MDa, and significantly enhances reconstructing speed through supporting multi-GPU processing. It also demonstrates superior performance in the reconstruction of near-atomic resolution map for G-protein coupling receptors (GPCR) complex. CryoFIFA provides a framework for exploring new paradigms in deep learning-driven cryo-EM reconstruction, highlighting the potential for future applications of deep learning in cryo-EM analysis.
参考文献
Kühlbrandt, W. The Resolution Revolution. Science 343, 1443-1444 (2014). https://doi.org/doi:10.1126/science.1251652
Cheng, Y., Grigorieff, N., Penczek, Pawel A. & Walz, T. A Primer to Single Particle Cryo-Electron Microscopy. Cell 161, 438-449 (2015). https://doi.org/10.1016/j.cell.2015.03.050
Merk, A. et al. Breaking Cryo-EM Resolution Barriers to Facilitate Drug Discovery. Cell 165, 1698-1707 (2016). https://doi.org/10.1016/j.cell.2016.05.040
Scheres, S. H. W. RELION: Implementation of a Bayesian approach to cryoEM structure determination. Journal of Structural Biology 180, 519-530 (2012). https://doi.org/https://doi.org/10.1016/j.jsb.2012.09.006
Punjani, A., Rubinstein, J. L., Fleet, D. J. & Brubaker, M. A. cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination. Nature Methods 14, 290-296 (2017). https://doi.org/10.1038/nmeth.4169
Tang, G. et al. EMAN2: An extensible image processing suite for electron microscopy. Journal of Structural Biology 157, 38-46 (2007). https://doi.org/https://doi.org/10.1016/j.jsb.2006.05.009
Bell, J. M., Chen, M., Baldwin, P. R. & Ludtke, S. J. High resolution single particle refinement in EMAN2.1. Methods 100, 25-34 (2016). https://doi.org/https://doi.org/10.1016/j.ymeth.2016.02.018
Bepler, T. et al. Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs. Nature Methods 16, 1153-1160 (2019). https://doi.org/10.1038/s41592-019-0575-8
Bepler, T., Kelley, K., Noble, A. J. & Berger, B. Topaz-Denoise: general deep denoising models for cryoEM and cryoET. Nature Communications 11, 5208 (2020). https://doi.org/10.1038/s41467-020-18952-1
Sanchez-Garcia, R. et al. DeepEMhancer: a deep learning solution for cryo EM volume post-processing. Communications Biology 4, 874 (2021). https://doi.org/10.1038/s42003-021-02399-1
Kimanius, D. et al. Data-driven regularization lowers the size barrier of cryoEM structure determination. Nature Methods 21, 1216-1221 (2024). https://doi.org/10.1038/s41592-024-02304-8
Jamali, K. et al. Automated model building and protein identification in cryoEM maps. Nature 628, 450-457 (2024). https://doi.org/10.1038/s41586-02407215-4
Levy, A. et al. in Computer Vision – ECCV 2022. (eds Shai Avidan et al.) 540557 (Springer Nature Switzerland).
Zhong, E. D., Lerer, A., Davis, J. H. & Berger, B. in 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 4046-4055.
Levy, A., Wetzstein, G., Martel, J., Poitevin, F. & Zhong, E. D. Amortized Inference for Heterogeneous Reconstruction in Cryo-EM. Adv Neural Inf Process Syst 35, 13038-13049 (2022).
Barnett, A., Greengard, L., Pataki, A. & Spivak, M. Rapid Solution of the Cryo-EM Reconstruction Problem by Frequency Marching. SIAM Journal on Imaging Sciences 10, 1170-1195 (2017). https://doi.org/10.1137/16M1097171
Han, Y. et al. High-yield monolayer graphene grids for near-atomic resolution cryoelectron microscopy. Proceedings of the National Academy of Sciences 117, 1009-1014 (2020). https://doi.org/10.1073/pnas.1919114117
Zhu, A. et al. Molecular basis for substrate recognition and transport of human GABA transporter GAT1. Nature Structural & Molecular Biology 30, 1012-1022 (2023). https://doi.org/10.1038/s41594-023-00983-z
Wong, W. et al. Cryo-EM structure of the Plasmodium falciparum 80S ribosome bound to the anti-protozoan drug emetine. eLife 3, e03080 (2014). https://doi.org/10.7554/eLife.03080
Plaschka, C., Lin, P.-C. & Nagai, K. Structure of a pre-catalytic spliceosome. Nature 546, 617-621 (2017). https://doi.org/10.1038/nature22799
Ru, H. et al. Molecular Mechanism of V(D)J Recombination from Synaptic RAG1-RAG2 Complex Structures. Cell 163, 1138-1152 (2015). https://doi.org/https://doi.org/10.1016/j.cell.2015.10.055
Liao, M., Cao, E., Julius, D. & Cheng, Y. Structure of the TRPV1 ion channel determined by electron cryo-microscopy. Nature 504, 107-112 (2013). https://doi.org/10.1038/nature12822
Diver, M. M., Cheng, Y. & Julius, D. Structural insights into TRPM8 inhibition and desensitization. Science 365, 1434-1440 (2019). https://doi.org/10.1126/science.aax6672
Huang, J. et al. Structure-guided discovery of protein and glycan components in native mastigonemes. Cell 187, 1733-1744.e1712 (2024). https://doi.org/10.1016/j.cell.2024.02.037
Rasmussen, S. G. F. et al. Crystal structure of the β2 adrenergic receptor–Gs protein complex. Nature 477, 549-555 (2011). https://doi.org/10.1038/nature10361
Yan, C., Wan, R., Bai, R., Huang, G. & Shi, Y. Structure of a yeast step II catalytically activated spliceosome. Science 355, 149-155 (2017). https://doi.org/10.1126/science.aak9979
Iudin, A. et al. EMPIAR: the Electron Microscopy Public Image Archive. Nucleic Acids Research 51, D1503-D1511 (2023). https://doi.org/10.1093/nar/gkac1062
Paszke, A. et al. in Advances in Neural Information Processing Systems 32 (eds H. Wallach et al.) 8024–8035 (Curran Associates, Inc., 2019).
Zhu, J. et al. A minority of final stacks yields superior amplitude in single particle cryo-EM. Nature Communications 14, 7822 (2023). https://doi.org/10.1038/s41467-023-43555-x
He, K., Zhang, X., Ren, S. & Sun, J. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770-778.
Zhou, Y., Barnes, C., Lu, J., Yang, J. & Li, H. in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5738-5746.
Mildenhall, B. et al. in Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 421 (Springer-Verlag, Glasgow, United Kingdom, 2020). 405
Rohou, A. & Grigorieff, N. CTFFIND4: Fast and accurate defocus estimation from electron micrographs. J Struct Biol 192, 216-221 (2015). https://doi.org/10.1016/j.jsb.2015.08.008
Zhang, K. Gctf: Real-time CTF determination and correction. Journal of Structural Biology 193, 1-12 (2016). https://doi.org/https://doi.org/10.1016/j.jsb.2015.11.003
Bengio, Y., Louradour, J., Collobert, R. & Weston, J. in Proceedings of the 26th Annual International Conference on Machine Learning 41–48 (Association for Computing Machinery, Montreal, Quebec, Canada, 2009).
指标
DOI：
Submission ID：
下载次数
已发布
如何引用
下载引用
利益冲突声明
作者声明无任何需要披露的利益冲突。
Copyright
本预印本的版权持有者为作者/资助方。
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.