- Physical Review Journals
All JournalsPhysics Magazine

PRX Life

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Cryo-EM Images are Intrinsically Low Dimensional

Luke Evans1,*, Octavian-Vlad Murad2,*, Lars Dingeldein3, Pilar Cossio1,4, Roberto Covino5,3, and Marina Meila2

  • *These authors contributed equally to this work.
PDF

PRX Life 3, 033025 – Published 22 September, 2025

DOI: https://doi.org/10.1103/txrb-fw3z

Abstract

Simulation-based inference provides a powerful framework for cryoelectron microscopy, employing neural networks in methods like CryoSBI to infer biomolecular conformations via learned latent representations. This latent space represents a rich opportunity, encoding valuable information about the physical system and the inference process. Harnessing this potential hinges on understanding the underlying geometric structure of these representations. We investigate this structure by applying manifold learning techniques to CryoSBI representations of a simulated benchmark dataset and both simulated and experimental images of hemagglutinin. We reveal that these high-dimensional data inherently populate low-dimensional, smooth manifolds, with simulated data effectively covering the experimental counterpart. By characterizing the manifold's geometry using Diffusion Maps and identifying its principal axes of variation via coordinate interpretation methods, we establish a direct link between the latent structure and key physical parameters. Discovering this intrinsic low-dimensionality and interpretable geometric organization not only validates the CryoSBI approach but also enables us to learn more from the data structure and provides opportunities for improving future inference strategies by exploiting this revealed manifold geometry.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (52)

  1. E. Nogales and S. H. W. Scheres, Cryo-EM: A unique tool for the visualization of macromolecular complexity, Mol. Cell 58, 677 (2015).
  2. A. Dashti, P. Schwander, R. Langlois, R. Fung, W. Li, A. Hosseinizadeh, H. Y. Liao, J. Pallesen, G. Sharma, V. A. Stupina, A. E. Simon, J. D. Dinman, J. Frank, and A. Ourmazd, Trajectories of the ribosome as a Brownian nanomachine, Proc. Natl. Acad. Sci. USA 111, 17492 (2014).
  3. E. D. Zhong, T. Bepler, B. Berger, and J. H. Davis, CryoDRGN: Reconstruction of heterogeneous cryo-EM structures using neural networks, Nat. Meth. 18, 176 (2021).
  4. M. Chen and S. J. Ludtke, Deep learning-based mixed-dimensional Gaussian mixture model for characterizing variability in cryo-EM, Nat. Meth. 18, 930 (2021).
  5. A. Punjani and D. J. Fleet, 3DFlex: determining structure and motion of flexible proteins from cryo-EM, Nat. Methods 20, 860 (2023).
  6. C. Donnat, A. Levy, F. Poitevin, E. D. Zhong, and N. Miolane, Deep generative modeling for volume reconstruction in cryo-electron microscopy, J. Struct. Biol. 214, 107920 (2022).
  7. W. S. Tang, E. D. Zhong, S. M. Hanson, E. H. Thiede, and P. Cossio, Conformational heterogeneity, and probability distributions from single-particle cryo-electron microscopy, Curr. Opin. Struct. Biol. 81, 102626 (2023).
  8. R. R. Lederman and B. Toader, On manifold learning in Plato's cave: Remarks on manifold learning and physical phenomena, in Proceedings of the 2023 International Conference on Sampling Theory, and Applications (SampTA) (IEEE, Los Alamitos, CA, 2023), pp. 1–7.
  9. D. A. Klindt, A. Hyvärinen, A. Levy, N. Miolane, and F. Poitevin, Towards interpretable Cryo-EM: Disentangling latent spaces of molecular conformations, Front. Molec. Biosci. 11, 1393564 (2024).
  10. B. Shi, K. Zhang, D. J. Fleet, R. A. McLeod, R. J. Dwayne Miller, and J. Y. Howe, Deep generative priors for biomolecular 3D heterogeneous reconstruction from cryo-EM projections, J. Struct. Biol. 216, 108073 (2024).
  11. M. Jeon, R. Raghu, M. Astore, G. Woollard, R. Feathers, A. Kaz, S. M. Hanson, P. Cossio, and E. D. Zhong, CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM, Adv. Neural Inf. Proc. Syst. 37, 89468 (2024).
  12. M. P. Rout and A. Sali, Principles for integrative structural biology studies, Cell 177, 1384 (2019).
  13. K. P. Murphy, Probabilistic Machine Learning: An Introduction (MIT Press, Cambridge, MA, 2022).
  14. L. Dingeldein, D. Silva-Sánchez, L. Evans, E. D'Imprima, N. Grigorieff, R. Covino, and P. Cossio, Amortized template matching of molecular conformations from cryoelectron microscopy images using simulation-based inference, Proc. Natl. Acad. Sci. USA 122, e2420158122 (2025).
  15. K. Cranmer, J. Brehmer, and G. Louppe, The frontier of simulation-based inference, Proc. Natl. Acad. Sci. USA 117, 30055 (2020).
  16. G. Papamakarios and I. Murray, Fast ɛ-free inference of simulation models with Bayesian conditional density estimation, Adv. Neural Inf. Proc. Syst. 29 (2016).
  17. R. R. Coifman, S. Lafon, A. B. Lee, M. Maggioni, B. Nadler, F. Warner, and S. W. Zucker, Geometric diffusions as a tool for harmonic analysis, and structure definition of data: Diffusion maps, Proc. Natl. Acad. Sci. USA 102, 7426 (2005).
  18. Y.-C. Chen and M. Meila, Selecting the independent coordinates of manifolds with large aspect ratios, Adv. Neural Inf. Proc. Syst. 32 (2019).
  19. S. J. Koelle, H. Zhang, O.-V. Murad, and M. Meila, Consistency of dictionary-based manifold learning, in International Conference on Artificial Intelligence, and Statistics (PMLR, Cambridge, MA, 2024), pp. 4348–4356.
  20. M. Meilă and H. Zhang, Manifold learning: What, how, and why, Annu. Rev. Stat. Appl. 11, 393 (2024).
  21. G. M. da Silva, J. Y. Cui, D. C. Dalgarno, G. P. Lisi, and B. M. Rubenstein, High-throughput prediction of protein conformational distributions with subsampled AlphaFold2, Nat. Commun. 15, 2464 (2024).
  22. J.-M. Lueckmann, J. Boelts, D. Greenberg, P. Goncalves, and J. Macke, Benchmarking simulation-based inference, in International Conference on Artificial Intelligence, and Statistics (PMLR, 2021), pp. 343–351.
  23. A. Zammit-Mangion, M. Sainsbury-Dale, and R. Huser, Neural methods for amortised parameter inference, arXiv:2404.12484.
  24. M. Schmitt, P.-C. Bürkner, U. Köthe, and S. T. Radev, Detecting model misspecification in amortized Bayesian inference with neural networks: An extended investigation, arXiv:2406.03154.
  25. Y. Z. Tan and J. L. Rubinstein, Through-grid wicking enables high-speed cryoem specimen preparation, Acta Cryst. D 76, 1092 (2020).
  26. P. Grassberger and I. Procaccia, Measuring the strangeness of strange attractors, Physica D 9, 189 (1983).
  27. G. Chen, A. V. Little, and M. Maggioni, Multi-Resolution Geometric Analysis for Data in High Dimensions (Birkhäuser, Boston, 2013), pp. 259–285.
  28. P. Assouad, Plongements lipschitziens dans rn, Bull. Soc. Math. France 111, 429 (1983).
  29. E. Levina and P. Bickel, Maximum likelihood estimation of intrinsic dimension, in Advances in Neural Information Processing Systems, edited by L. Saul, Y. Weiss, and L. Bottou (MIT Press, Cambridge, MA, 2004), Vol. 17.
  30. J. McQueen, M. Meila, and D. Perrault-Joncas, Nearly isometric embedding by relaxation, Adv. Neural Inf. Proc. Syst. 29 (2016).
  31. B. W. Silverman, Density Estimation for Statistics, and Data Analysis (Routledge, Milton Park, UK, 2018).
  32. D. Joncas, M. Meila, and J. McQueen, Improved graph Laplacian via geometric self-consistency, Advances in Neural Information Processing Systems, edited by I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates, Inc., 2017), Vol. 30.
  33. D. Perraul-Joncas and M. Meila, Non-linear dimensionality reduction: Riemannian metric estimation, and the problem of geometric discovery, arXiv:1305.7255.
  34. L. Evans, “cryo-em images are intrinsically low dimensional”: Latent data from SBI, Zenodo (2025), https://zenodo.org/records/15733579.
  35. See Supplemental Material at http://link.aps.org/supplemental/10.1103/txrb-fw3z for additional figures referenced in the text.
  36. E. Seitz, F. Acosta-Reyes, P. Schwander, and J. Frank, Simulation of cryo-EM ensembles from atomic models of molecules exhibiting continuous conformations, bioRxiv 864116 (2019).
  37. J. Giraldo-Barreto, S. Ortiz, E. H. Thiede, K. Palacio-Rodriguez, B. Carpenter, A. H. Barnett, and P. Cossio, A Bayesian approach to extracting free-energy profiles from cryo-electron microscopy experiments, Sci. Rep. 11, 13657 (2021).
  38. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision, and Pattern Recognition (IEEE, Los Alamitos, CA, 2016), pp. 770–778.
  39. C. Durkan, A. Bekasov, I. Murray, and G. Papamakarios, Neural spline flows arXiv:1906.04032.
  40. G. Wright, J. Andén, V. Bansal, J. Xia, C. Langfield, J. Carmichael, K. Sowattanangkul, R. Brook, Y. Shi, A. Heimowitz, G. Pragier, I. Sason, A. Moscovich, Y. Shkolnisky, and A. Singer, ComputationalCryoEM/ASPIRE-Python: v0.12.0 (v0.12.0), Zenodo (2023), https://doi.org/10.5281/zenodo.8321443.
  41. A. J. Hanson, Visualizing Quaternions (Morgan Kaufmann Publishers Inc., San Francisco, CA, 2006).
  42. S. Talts, M. Betancourt, D. Simpson, A. Vehtari, and A. Gelman, Validating Bayesian inference algorithms with simulation-based calibration, arXiv:1804.06788.
  43. D. Huang, A. Bharti, A. Souza, L. Acerbi, and S. Kaski, Learning robust statistics for simulation-based inference under model misspecification, arXiv:2305.15871.
  44. B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, Estimating the support of a high-dimensional distribution, Neural Comput. 13, 1443 (2001).
  45. F. T. Liu, K. M. Ting, and Z.-H. Zhou, Isolation forest, in Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (IEEE, Los Alamitos, CA, 2008), pp. 413–422.
  46. C. I. Lang, F.-K. Sun, B. Lawler, J. Dillon, A. A. Dujaili, J. Ruth, P. Cardillo, P. Alfred, A. Bowers, A. Mckiernan, and D. S. Boning, One class process anomaly detection using kernel density estimation methods, IEEE Trans. Semicond. Manufact. 35, 457 (2022).
  47. C. D. Scott and R. D. Nowak, Learning minimum volume sets, J. Mach. Learn. Res. 7, 665 (2006).
  48. M. Zhao and V. Saligrama, Anomaly detection with score functions based on nearest neighbor graphs, in Advances in Neural Information Processing Systems, edited by Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, and A. Culotta (Curran Associates, Red Hook, NY, 2009), Vol. 22.
  49. M. Belkin and P. Niyogi, Laplacian eigenmaps, and spectral techniques for embedding, and clustering, in Advances in Neural Information Processing Systems, edited by T. Dietterich, S. Becker, and Z. Ghahramani (MIT Press, Cambridge, MA, 2001), Vol. 14.
  50. D. O. Loftsgaarden and C. P. Quesenberry, A nonparametric estimate of a multivariate density function, Ann. Math. Statist. 36, 1049 (1965).
  51. G. Boente and R. Fraiman, Consistency of a nonparametric estimate of a density function for dependent variables, J. Multivar. Anal. 25, 90 (1988).
  52. F. Camastra, and A. Staiano, Intrinsic dimension estimation: Advances, and open problems, Inf. Sci. 328, 26 (2016).

Outline

Information

PRX Life 3, 033025– Published 22 September, 2025
  • Received 16 April 2025
  • Accepted 13 August 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation