CryoNet.Discovery identifies protein structures from cryo-EM density maps across resolutions through cross-modal recognition
Abstract
Cryo-electron microscopy (cryo-EM) is increasingly used not only for structure determination but as a discovery tool for investigating heterogeneous and previously uncharacterized molecular assemblies. Realizing this potential hinges on identifying structures within experimental density maps-a task that grows harder as resolution declines. We developed CryoNet.Discovery, a deep-learning framework that aligns density maps and atomic structures in latent space, recasting structure identification through cross-modal retrieval. On CATH and SCOPe domain benchmarks, it achieved Top-1 accuracies of 85.7% and 84.4%, respectively, at low resolutions (6–10 Å), outperforming ModelAngelo, cryoID, and DomainFit across a wide resolution range, with the largest gains at low resolutions. Extending from domain- to single-chain identification, it scaled to 12,114 protein chains from 1,488 EMDB maps, recovering the correct fold for 89.3% of queries and revealing structurally conserved yet sequence-divergent relationships missed by sequence-based search. CryoNet.Discovery thus provides a scalable foundation for interpreting unresolved cryo-EM maps and advancing cryo-EM as an engine for structural discovery.
References
Nogales, E. & Scheres, S. H. Cryo-EM: a unique tool for the visualization of macromolecular complexity. Mol. Cell 58, 677–689 (2015).
Cheng, Y. Single-particle cryo-EM at crystallographic resolution. Cell 161, 450–457 (2015).
Kuhlbrandt, W. The resolution revolution. Science 343, 1443–1444 (2014).
Bai, X.-C., McMullan, G. & Scheres, S. H. How cryo-EM is revolutionizing structural biology. Trends Biochem. Sci. 40, 49–57 (2015).
Li, X. et al. Electron counting and beam-induced motion correction enable near-atomic-resolution single-particle cryo-EM. Nat. Methods 10, 584–590 (2013).
Pfab, J., Phan, N. M. & Si, D. DeepTracer for fast de novo cryo-EM protein structure modeling and special studies on CoV-related complexes. Proc. Natl Acad. Sci. USA 118, e2017525118 (2021).
Jamali, K. et al. Automated model building and protein identification in cryo-EM maps. Nature 628, 450–457 (2024).
Su, B., Huang, K., Peng, Z., Amunts, A. & Yang, J. CryoAtom improves model building for cryo-EM. Nat. Struct. Mol. Biol. 33, 351–361 (2026).
Xu, Y. & Dang, S. Recent technical advances in sample preparation for single-particle cryo-EM. Front. Mol. Biosci. 9, 892459 (2022).
Doerr, A. Cryo-electron tomography. Nat. Methods 14, 34–34 (2017).
Nogales, E. & Mahamid, J. Bridging structural and cell biology with cryo-electron microscopy. Nature 628, 47–56 (2024).
Asano, S., Engel, B. D. & Baumeister, W. In situ cryo-electron tomography: a post-reductionist approach to structural biology. J. Mol. Biol. 428, 332–343 (2016).
Young, L. N. & Villa, E. Bringing structure to cell biology with cryo-electron tomography. Annu. Rev. Biophys. 52, 573–595 (2023).
Wang, T. et al. CryoSeek: A strategy for bioentity discovery using cryoelectron microscopy. Proc. Natl Acad. Sci. USA 121, e2417046121 (2024).
Wang, T. et al. CryoSeek II: Cryo-EM analysis of glycofibrils from freshwater reveals well-structured glycans coating linear tetrapeptide repeats. Proc. Natl Acad. Sci. USA 122, e2423943122 (2025).
Ho, C.-M. et al. Bottom-up structural proteomics: cryoEM of protein complexes enriched from the cellular milieu. Nat. Methods 17, 79–85 (2020).
Gao, J. et al. DomainFit: Identification of protein domains in cryo-EM maps at intermediate resolution using AlphaFold2-predicted models. Structure 32, 1248–1259.e5 (2024).
Taigman, Y., Yang, M., Ranzato, M. A. & Wolf, L. Deepface: Closing the gap to human-level performance in face verification. Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1701–1708 (2014).
Schroff, F., Kalenichenko, D. & Philbin, J. Facenet: A unified embedding for face recognition and clustering. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 815–823 (2015).
Orengo, C. A. et al. CATH-a hierarchic classification of protein domain structures. Structure 5, 1093–1109 (1997).
Greene, L. H. et al. The CATH domain structure database: new protocols and classification levels give a more comprehensive resource for exploring evolution. Nucleic Acids Res. 35, D291–D297 (2007).
Fox, N. K., Brenner, S. E. & Chandonia, J.-M. SCOPe: Structural Classification of Proteins-extended, integrating SCOP and ASTRAL data and classification of new structures. Nucleic Acids Res. 42, D304–D309 (2014).
Lawson, C. L. et al. EMDataBank unified data resource for 3DEM. Nucleic Acids Res. 44, D396–D403 (2016).
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, 234–241 (2015).
He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 770–778 (2016).
Zhang, K. et al. Practical blind image denoising via Swin-Conv-UNet and data synthesis. Mach. Intell. Res. 20, 822–836 (2023).
Ji, S., Xu, W., Yang, M. & Yu, K. 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221–231 (2012).
Lin, M., Chen, Q. & Yan, S. Network in network. arXiv, arXiv:1312.4400 (2013).
Ba, J. L., Kiros, J. R. & Hinton, G. E. Layer normalization. arXiv, arXiv:1607.06450 (2016).
Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017).
Douze, M. et al. The Faiss Library. IEEE Trans. Big Data 12, 346–361 (2025).
Berman, H. M. et al. The Protein Data Bank. Nucleic Acids Res. 28, 235–242 (2000).
Afonine, P. V. et al. New tools for the analysis and validation of cryo-EM maps and atomic models. Acta Crystallogr. D Struct. Biol. 74, 814–840 (2018).
Pettersen, E. F. et al. UCSF ChimeraX: Structure visualization for researchers, educators, and developers. Protein Sci. 30, 70–82 (2021).
Taheri-Ledari, M., Zandieh, A., Shariatpanahi, S. P. & Eslahchi, C. Assignment of structural domains in proteins using diffusion kernels on graphs. BMC Bioinformatics 23, 369 (2022).
Steinegger, M. & Soding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017).
Steinegger, M. & Soding, J. Clustering huge protein sequence sets in linear time. Nat. Commun. 9, 2542 (2018).
Shi, Y. A glimpse of structural biology through X-ray crystallography. Cell 159, 995–1014 (2014).
Liu, X. et al. Self-supervised learning: Generative or contrastive. IEEE Trans. Knowl. Data Eng. 35, 857–876 (2021).
Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).
Radford, A. et al. Learning transferable visual models from natural language supervision. Proc. 38th Int. Conf. Mach. Learn., 8748–8763 (2021).
Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. Proc. 36th Int. Conf. Mach. Learn., 6105–6114 (2019).
Tsipras, D., Santurkar, S., Engstrom, L., Ilyas, A. & Madry, A. From imagenet to image classification: Contextualizing progress on benchmarks. Proc. 37th Int. Conf. Mach. Learn., 9625–9635 (2020).
Iudin, A., Korir, P. K., Salavert-Torres, J., Kleywegt, G. J. & Patwardhan, A. EMPIAR: a public archive for raw electron microscopy image data. Nat. Methods 13, 387–388 (2016).
Iudin, A. et al. EMPIAR: the electron microscopy public image archive. Nucleic Acids Res. 51, D1503–D1511 (2023).
Punjani, A., Rubinstein, J. L., Fleet, D. J. & Brubaker, M. A. cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination. Nat. Methods 14, 290–296 (2017).
Manning, C. D. Introduction to Information Retrieval. Cambridge Univ. Press (2008).
Cheng, Y., Grigorieff, N., Penczek, P. A. & Walz, T. A primer to single-particle cryo-electron microscopy. Cell 161, 438–449 (2015).
Briggs, J. A. Structural biology in situ-the potential of subtomogram averaging. Curr. Opin. Struct. Biol. 23, 261–267 (2013).
Wan, W. & Briggs, J. A. Cryo-electron tomography and subtomogram averaging. Methods Enzymol. 579, 329–367 (2016).
Weaver, J. et al. GroEL actively stimulates folding of the endogenous substrate protein PepQ. Nat. Commun. 8, 15934 (2017).
Braig, K. et al. The crystal structure of the bacterial chaperonln GroEL at 2.8 A. Nature 371, 578–586 (1994).
Meena, S. R. & Saxena, A. K. Crystal structure of apo-GroEL structure. PDB-4HEL (2013). https://doi.org/4hel
Ni, T. et al. Structure of native HIV-1 cores and their interactions with IP6 and CypA. Sci. Adv. 7, eabj5715 (2021).
Dos Santos, N. F. et al. Lenacapavir allosterically remodels the HIV-1 capsid. bioRxiv, 2026.01.05.697065 (2026).
Rice, P., Longden, I. & Bleasby, A. EMBOSS: the European molecular biology open software suite. Trends Genet. 16, 276–277 (2000).
Zhang, C., Shine, M., Pyle, A. M. & Zhang, Y. US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes. Nat. Methods 19, 1109–1115 (2022).
Zhang, C., Freddolino, L. & Zhang, Y. A graphic and command line protocol for quick and accurate comparisons of protein and nucleic acid structures with US-align. Nat. Protoc. 21, 517–541 (2026).
Xu, J. & Zhang, Y. How significant is a protein structure similarity with TM-score=0.5? Bioinformatics 26, 889–895 (2010).
Orengo, C. A., Jones, D. T. & Thornton, J. M. Protein superfamilies and domain superfolds. Nature 372, 631–634 (1994).
Holm, L. & Sander, C. Mapping the protein universe. Science 273, 595–602 (1996).
Li, F. et al. Structural atlas of Pakpunavirus P7-1 reveals determinants of virion stability and genome ejection. Commun. Biol. 9, 913 (2026).
Subramanian, S., Kerns, H. R., Braverman, S. G. & Doore, S. M. The structure of Shigella virus Sf14 reveals the presence of two decoration proteins and two long tail fibers. Commun. Biol. 8, 222 (2025).
Hay, I. M. et al. Structural basis for a phosphoinositide-driven mTORC2-AKT positive feedback loop. bioRxiv, 2026.01.08.698367 (2026).
Llacer, J. L. et al. Conformational differences between open and closed states of the eukaryotic translation initiation complex. Mol. Cell 59, 399–412 (2015).
Harris, J. A. et al. Selective G protein signaling driven by substance P-neurokinin receptor dynamics. Nat. Chem. Biol. 18, 109–115 (2022).
Liao, M., Cao, E., Julius, D. & Cheng, Y. Structure of the TRPV1 ion channel determined by electron cryo-microscopy. Nature 504, 107–112 (2013).
Metrics
DOI:
Submission ID:
Downloads
Posted
How to Cite
Download Citation
Declaration of Competing Interests
The authors declare no competing interests to disclose.
Copyright
The copyright holder for this preprint is the author/funder.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.