AI时代中的电子显微学研究：严峻挑战、无穷机遇与壮阔前景
刘 铮*，沈庆涛，隋森芳
（1. 南方科技大学冷冻电镜中心，广东 深圳 518055； 2. 南方科技大学生命科学学院， 广东 深圳 518055； 3. 清华大学生命科学学院，北京 100084）
摘 要 近十年来结构生物学的发展突飞猛进，标志性的突破有两个，一是以冷冻电镜为代表的结构解析技术方向上的突破，二是以Alphafold算法为代表的结构预测模型上的突破。2024年5月Google DeepMind更新了其生物结构预测工具，最新版本的Alphafold3拥有可以预测几乎所有分子类型的蛋白质复合体结构的能力，在药物互作预测方面也实现了很高的准确性。AlphaFold3的发布为结构生物学研究带来巨大的变革，展现了AI技术的巨大潜力，也点燃了大众对生命科学和医学研究的热情与想象。与此同时，电子显微学的研究并未停下脚步，新技术、新方法层出不穷，在解析全新蛋白结构、超大超复杂复合体结构、动态结构、原位结构，以及更大尺度的细胞、组织、器官样品的研究中，电子显微学依旧有着不可替代的优势。当前有观点认为结构预测模型甚至可以替代以X射线晶体学和电子显微学为代表的传统实验科学，通过计算便能完成生物结构解析，这种观点是片面的。事实上，未来的结构生物学研究，必将是一个整合实验科学与AI技术，从单个蛋白或复合体的结构全面拓展到多蛋白复杂体系、细胞内原位、以及超越微观尺度进入到介观和宏观尺度等方面的研究。
关键词 电子显微学；高分辨结构；Alphafold；结构模型预测
中图分类号：Q6；Q71；Q31；Q51； 文献标识码：ADoi:10.3969/j.issn.1000-6281.2025.01.014
Electron microscopy research in the age of AI: Severe challenges, Infinite opportunities, and Magnificent prospects
LIU Zheng*，SHEN Qingtao，SUI Senfang
(1. Cryo-Electron Microscopy Center, Southern University of Science and Technology, Shenzhen Guangdong 518055；2. School of Life Sciences, Southern University of Science and Technology, Shenzhen Guangdong 518055；3. School of Life Science, Tsinghua University, Beijing 100084，China)
Abstract Over the past decade, structural biology has made sigficant achivements, there are two representational breakthroughs: first, in structural determination techniques, represented by cryo-electron microscopy, and second, in structural prediction models, exemplified by the AlphaFold algorithm. In May 2024, Google DeepMind updated its biological structure prediction tool. The latest version, AlphaFold3, possesses the ability to predict the structures of nearly all types of protein complexes and has also achieved high accuracy in predicting drug interactions. The release of AlphaFold3 has brought about transformative changes structural biology, showcasing the immense potential of AI technology and fueling public enthusiasm and imagination for life science and biomedical research. Meanwhile, research in electron microscopy continues to advance with continuous emergence of new technologies and methods, electron microscopy science retains irreplaceable advantages in analyzing novel protein structures, extremely large and complicate complexes, dynamic structures, in-situ structures, and studies of larger scale samples including cells, tissues, and organs. Some propose that structural prediction models could even replace traditional experimental approaches such as X-ray crystallography and electron microscopy, allowing biomolecular structures analysis through computation alone. However, such opinions are biased, future research in structural biology will inevitably integrate experimental science and AI technology, expanding from the structures of individual proteins or complexes to comprehensive studies of multi-protein systems, intracellular in-situ locations, and beyond microscopic to mesoscopic and macroscopic scales.
Keywords electron microscopy science; high-resolution structure; Alphafold; structure prediction
[1] ABBE E. Beiträge zur theorie des mikroskops und der mikroskopischen wahrnehmung [J]. Archiv für Mikroskopische Anatomie, 1873， 9: 413-418.
[2] DE ROSIER D J, KLUG A. Reconstruction of three dimensional structures from electron micrographs [J]. Nature, 1968，217 (5124): 130-134.
[3] NAKANE T, KOTECHA A, SENTE A, et al. Single-particle Cryo-EM at atomic resolution [J]. Nature, 2020，587 (7832): 152-156.
[4] YIP K M, FISCHE N, PAKNIA R E, et al. Atomic-resolution protein structure determination by Cryo-EM [J]. Nature, 2020，587 (7832): 157-161.
[5] STOKSTAD E, PENNISI E, KAISER J, et al. The runners up [J]. Science, 2017，358 (6370): 1522-1527.
[6] Viruses, microscopy and fast radio bursts: 10 remarkable discoveries from 2020 [J]. Nature, 2020，588 (7839): 596-598.
[7] WYLLIE S, BRAND S, THOMAS M, et al. Preclinical candidate for the treatment of visceral leishmaniasis that acts through proteasome inhibition [J]. Proc Natl Acad Sci USA, 2019，116 (19): 9318-9323.
[8] SELA M, WHITE F H, ANFINSEN C B. Reductive cleavage of disulfide bridges in ribonuclease [J]. Science, 1957，125 (3250): 691-692.
[9] KRAUT J. Structural studies with X-rays [J]. Annu Rev Biochem, 1965，34: 247-268.
[10] JUMPER J, EVANS R, PRITZEL A, et al. Highly accurate protein structure prediction with AlphaFold [J]. Nature, 2021，596 (7873): 583-589.
[11] KREITZ J, FRIEDRICH M J, GURU A, et al. Programmable protein delivery with a bacterial contractile injection system [J]. Nature, 2023，616 (7956): 357-364.
[12] LIM Y, TAMAYO-ORREGO L, SCHMID E, et al. In silico protein interaction screening uncovers DONSON's role in replication initiation [J]. Science, 2023，381 (6664): eadi3448.
[13] MOSALAGANTI S, OBARSKA-KOSINSKA A, SIGGEL M, et al. AI-based structure prediction empowers integrative structural analysis of human nuclear pores [J]. Science, 2022，376 (6598): eabm9506.
[14] ABRAMSON J, ADLER J, DUNGER J, et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3 [J]. Nature, 2024， 630 (8016): 493-500.
[15] KYRILIS F L, SEMCHONOK D A, SKALIDIS I, et al. Integrative structure of a 10-megadalton eukaryotic pyruvate dehydrogenase complex from native cell extracts [J]. Cell Rep, 2021，34 (6): 108727.
[16] JIN Z, WAN L, ZHANG Y, et al. Structure of a TOC-TIC supercomplex spanning two chloroplast envelope membranes [J]. Cell, 2022，185 (25): 4788-4800.
[17] LIU H, LI A, ROCHAIX J D, et al. Architecture of chloroplast TOC-TIC translocon supercomplex [J]. Nature, 2023，615 (7951): 349-357.
[18] MA J, YOU X, SUN S, et al. Structural basis of energy transfer in Porphyridium purpureum phycobilisome [J]. Nature, 2020，579 (7797): 146-151.
[19] NOMBURG J, DOHERTY E E, PRICE N, et al. Birth of protein folds and functions in the virome [J]. Nature, 2024，633 (8030): 710-717.
[20] CROWTHER R A, AMOS L A, FINCH J T, et al. Three dimensional reconstructions of spherical viruses by fourier synthesis from electron micrographs [J]. Nature, 1970，226 (5244): 421-425.
[21] ZHANG X, JIN L, FANG Q, et al. 3.3 A Cryo-EM structure of a nonenveloped virus reveals a priming mechanism for cell entry [J]. Cell, 2010，141 (3): 472-482.
[22] WANG N, ZHAO D, WANG J, et al. Architecture of African swine fever virus and implications for viral assembly [J]. Science, 2019，366 (6465): 640-644.
[23] TIAN W, LI D, ZHANG N, et al. O-glycosylation pattern of the SARS-CoV-2 spike protein reveals an "O-Follow-N" rule [J]. Cell Res, 2021，31 (10): 1123-1125.
[24] WANG A, ZHOU F, LIU C, et al. Structure of infective Getah virus at 2.8 Å resolution determined by cryo-electron microscopy [J]. Cell Discov, 2022，8 (1): 12.
[25] CHAKRAVARTY D, SCHAFER J W, CHEN E A, et al. AlphaFold predictions of fold-switched conformations are driven by structure memorization [J]. Nat Commun, 2024，15 (1): 7296.
[26] YAO H, SONG Y, CHEN Y, et al. Molecular Architecture of the SARS-CoV-2 Virus [J]. Cell, 2020，183 (3): 730-738.
[27] MA X, WANG Y, GAO Y, et al. Structural characteristics of the SARS-CoV-2 Omicron lineages BA.1 and BA.2 virions [J]. Signal Transduct Target Ther, 2023，8 (1): 131.
[28] WANG Y, YAN A, SONG D, et al. Biparatopic antibody BA7208/7125 effectively neutralizes SARS-CoV-2 variants including Omicron BA.1-BA.5 [J]. Cell Discov, 2023，9 (1): 3.
[29] YAN R, ZHANG Y, LI Y, et al. Structural basis for the different states of the spike protein of SARS-CoV-2 in complex with ACE2 [J]. Cell Res, 2021， 31 (6): 717-719.
[30] SHEN H, L Z I, JIANG Y, et al. Structural basis for the modulation of voltage-gated sodium channels by animal toxins [J]. Science, 2018，362 (6412): eaau2596.
[31] GAO S, YAO X, CHEN J, et al. Structural basis for human Ca(v)1.2 inhibition by multiple drugs and the neurotoxin calciseptine [J]. Cell, 2023，186 (24): 5363-5374.
[32] HITE R K, TAO X, MACKINNON R. Structural basis for gating the high-conductance Ca(2+)-activated K(+) channel [J]. Nature, 2017，541 (7635): 52-57.
[33] YANG X, LIN C, CHEN X, et al. Structure deformation and curvature sensing of PIEZO1 in lipid membranes [J]. Nature, 2022， 604 (7905): 377-383.
[34] ZHANG S, ZOU S, YIN D, et al. USP14-regulated allostery of the human proteasome by time-resolved Cryo-EM [J]. Nature, 2022， 605 (7910): 567-574.
[35] DANDEY V P, BUDELL W C, WEI H, et al. Time-resolved Cryo-EM using Spotiton [J]. Nat Methods, 2020，17 (9): 897-900.
[36] LUČIČ V, RIGORT A, BAUMEISTER W. Cryo-electron tomography: The challenge of doing structural biology in situ [J]. J Cell Biol, 2013，202 (3): 407-419.
[37] KONING R I, KOSTER A J, SHARP T H. Advances in cryo-electron tomography for biology and medicine [J]. Ann Anat, 2018， 217: 82-96.
[38] TURK, M， BAUMEISTER W. The promise and the challenges of cryo-electron tomography [J]. FEBS Lett, 2020，594 (20): 3243-3261.
[39] XUE L, LENZ S, ZIMMERMANN-KOGADEEVA M, et al. Visualizing translation dynamics at atomic detail inside a bacterial cell [J]. Nature, 2022，610 (7930): 205-211.
[40] CHENG J, LI B, SI L, et al. Determining structures in a native environment using single-particle cryoelectron microscopy images [J]. Innovation (Camb), 2021，2 (4): 100166.
[41] CHENG J, LIU T, YOU X, et al. Determining protein structures in cellular lamella at pseudo-atomic resolution by GisSPA [J]. Nat Commun, 2023，14 (1): 1282.
[42] YOU X, ZHANG X, CHENG J, et al. In situ structure of the red algal phycobilisome-PSII-PSI-LHC megacomplex [J]. Nature, 2023，616 (7955): 199-206.
[43] ZHANG X, XIAO Y, YOU X, et al. In situ structural determination of cyanobacterial phycobilisome-PSII supercomplex by STAgSPA strategy [J]. Nat Commun, 2024，15 (1): 7201.
[44] PEDDIE C J, GENOUD C, KRESHUK A, et al. Volume electron microscopy [J]. Nature Reviews Methods Primers, 2022，2 (1): 51.
[45] EISENSTEIN M. Seven technologies to watch in 2023 [J]. Nature, 2023，613 (7945): 794-797.
[46] SHAPSON-COE A, JANUSZEWSKI M, BERGER D R, et al. A petavoxel fragment of human cerebral cortex reconstructed at nanoscale resolution [J]. Science, 2024，384 (6696): eadk4858.
