Display options
Cite
Granik N, Weiss LE, Nehme E, et al. Single-Particle Diffusion Characterization by Deep Learning. Biophys J. 2019;117(2):185-192doi: 10.1016/j.bpj.2019.06.015.
Granik, N., Weiss, L. E., Nehme, E., Levin, M., Chein, M., Perlson, E., Roichman, Y., & Shechtman, Y. (2019). Single-Particle Diffusion Characterization by Deep Learning. Biophysical journal, 117(2), 185-192. https://doi.org/10.1016/j.bpj.2019.06.015
Granik, Naor, et al. "Single-Particle Diffusion Characterization by Deep Learning." Biophysical journal vol. 117,2 (2019): 185-192. doi: https://doi.org/10.1016/j.bpj.2019.06.015
Granik N, Weiss LE, Nehme E, Levin M, Chein M, Perlson E, Roichman Y, Shechtman Y. Single-Particle Diffusion Characterization by Deep Learning. Biophys J. 2019 Jul 23;117(2):185-192. doi: 10.1016/j.bpj.2019.06.015. Epub 2019 Jun 22. PMID: 31280841; PMCID: PMC6701009.
Copy Download .nbib Format: NLM
Share it on

Biophys J. 2019 Jul 23;117(2):185-192. doi: 10.1016/j.bpj.2019.06.015. Epub 2019 Jun 22.

Single-Particle Diffusion Characterization by Deep Learning.

Biophysical journal

Naor Granik, Lucien E Weiss, Elias Nehme, Maayan Levin, Michael Chein, Eran Perlson, Yael Roichman, Yoav Shechtman

Affiliations

  1. Department of Biomedical Engineering; Lorry I. Lokey Interdisciplinary Center for Life Sciences and Engineering.
  2. Department of Biomedical Engineering; Lorry I. Lokey Interdisciplinary Center for Life Sciences and Engineering; Department of Electrical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  3. Raymond & Beverly Sackler School of Chemistry.
  4. Department of Physiology and Pharmacology, Sackler Faculty of Medicine; Sagol School of Neuroscience.
  5. Raymond & Beverly Sackler School of Chemistry; Raymond & Beverly Sackler School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel. Electronic address: [email protected].
  6. Department of Biomedical Engineering; Lorry I. Lokey Interdisciplinary Center for Life Sciences and Engineering. Electronic address: [email protected].

PMID: 31280841 PMCID: PMC6701009 DOI: 10.1016/j.bpj.2019.06.015

Abstract

Diffusion plays a crucial role in many biological processes including signaling, cellular organization, transport mechanisms, and more. Direct observation of molecular movement by single-particle-tracking experiments has contributed to a growing body of evidence that many cellular systems do not exhibit classical Brownian motion but rather anomalous diffusion. Despite this evidence, characterization of the physical process underlying anomalous diffusion remains a challenging problem for several reasons. First, different physical processes can exist simultaneously in a system. Second, commonly used tools for distinguishing between these processes are based on asymptotic behavior, which is experimentally inaccessible in most cases. Finally, an accurate analysis of the diffusion model requires the calculation of many observables because different transport modes can result in the same diffusion power-law α, which is typically obtained from the mean-square displacements (MSDs). The outstanding challenge in the field is to develop a method to extract an accurate assessment of the diffusion process using many short trajectories with a simple scheme that is applicable at the nonexpert level. Here, we use deep learning to infer the underlying process resulting in anomalous diffusion. We implement a neural network to classify single-particle trajectories by diffusion type: Brownian motion, fractional Brownian motion and continuous time random walk. Further, we demonstrate the applicability of our network architecture for estimating the Hurst exponent for fractional Brownian motion and the diffusion coefficient for Brownian motion on both simulated and experimental data. These networks achieve greater accuracy than time-averaged MSD analysis on simulated trajectories while only requiring as few as 25 steps. When tested on experimental data, both net and ensemble MSD analysis converge to similar values; however, the net needs only half the number of trajectories required for ensemble MSD to achieve the same confidence interval. Finally, we extract diffusion parameters from multiple extremely short trajectories (10 steps) using our approach.

Copyright © 2019 Biophysical Society. Published by Elsevier Inc. All rights reserved.

References

  1. Phys Rev Lett. 2004 Apr 30;92(17):178101 - PubMed
  2. J Struct Biol. 2005 Aug;151(2):182-95 - PubMed
  3. Phys Rev Lett. 2006 Mar 10;96(9):098102 - PubMed
  4. Phys Rev E Stat Nonlin Soft Matter Phys. 2008 Feb;77(2 Pt 1):021122 - PubMed
  5. Proc Natl Acad Sci U S A. 2009 Sep 8;106(36):15160-4 - PubMed
  6. Phys Rev Lett. 2009 Oct 30;103(18):180602 - PubMed
  7. Biophys J. 2010 Apr 7;98(7):1364-72 - PubMed
  8. Proc Natl Acad Sci U S A. 2011 Apr 19;108(16):6438-43 - PubMed
  9. Curr Protein Pept Sci. 2011 Dec;12(8):699-713 - PubMed
  10. Nat Methods. 2012 Jun 28;9(7):676-82 - PubMed
  11. Phys Rev E Stat Nonlin Soft Matter Phys. 2012 Jun;85(6 Pt 1):061916 - PubMed
  12. Nat Methods. 2013 Mar;10(3):265-9 - PubMed
  13. Proc Natl Acad Sci U S A. 2013 Mar 26;110(13):4911-6 - PubMed
  14. J Chem Phys. 2013 Sep 28;139(12):121916 - PubMed
  15. Soft Matter. 2014 Nov 7;10(41):8324-9 - PubMed
  16. Phys Chem Chem Phys. 2014 Nov 28;16(44):24128-64 - PubMed
  17. Phys Rev E Stat Nonlin Soft Matter Phys. 2014 Feb;89(2):022708 - PubMed
  18. Phys Rev E Stat Nonlin Soft Matter Phys. 2014 May;89(5):052705 - PubMed
  19. PLoS One. 2015 Feb 13;10(2):e0117722 - PubMed
  20. Sci Rep. 2015 Jun 11;5:11306 - PubMed
  21. Rep Prog Phys. 2015 Dec;78(12):124601 - PubMed
  22. Biochim Biophys Acta. 2016 Oct;1858(10):2451-2467 - PubMed
  23. BMC Bioinformatics. 2016 May 04;17(1):197 - PubMed
  24. Phys Chem Chem Phys. 2016 Aug 24;18(34):23840-52 - PubMed
  25. Chem Rev. 2017 Jun 14;117(11):7331-7376 - PubMed
  26. Elife. 2018 Jan 04;7: - PubMed
  27. Nature. 2018 Feb 22;554(7693):555-557 - PubMed
  28. Phys Chem Chem Phys. 2018 Sep 26;20(37):24099-24108 - PubMed
  29. Phys Chem Chem Phys. 2018 Nov 28;20(46):29018-29037 - PubMed
  30. Annu Rev Biochem. 2019 Jun 20;88:635-659 - PubMed
  31. Soft Matter. 2019 Mar 20;15(12):2526-2551 - PubMed
  32. Proc Natl Acad Sci U S A. 2019 Mar 19;116(12):5550-5557 - PubMed
  33. Opt Express. 2019 Mar 4;27(5):6158-6183 - PubMed

MeSH terms

Publication Types