Abstract

Intracellular transport is predominantly heterogeneous in both time and space, exhibiting varying non-Brownian behavior. Characterization of this movement through averaging methods over an ensemble of trajectories or over the course of a single trajectory often fails to capture this heterogeneity. Here, we developed a deep learning feedforward neural network trained on fractional Brownian motion, providing a novel, accurate and efficient method for resolving heterogeneous behavior of intracellular transport in space and time. The neural network requires significantly fewer data points compared to established methods. This enables robust estimation of Hurst exponents for very short time series data, making possible direct, dynamic segmentation and analysis of experimental tracks of rapidly moving cellular structures such as endosomes and lysosomes. By using this analysis, fractional Brownian motion with a stochastic Hurst exponent was used to interpret, for the first time, anomalous intracellular dynamics, revealing unexpected differences in behavior between closely related endocytic organelles.

Data availability

Supporting files are on GitHub and Zenodo.

The following data sets were generated
    1. Daniel Han
    (2019) hurst-exp
    Github, dadanhan/hurst-exp.git.

Article and author information

Author details

  1. Daniel Han

    Department of Mathematics, School of Biological Sciences, Department of Physics and Astronomy, University of Manchester, Manchester, United Kingdom
    For correspondence
    daniel.han@manchester.ac.uk
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-9088-1651
  2. Nickolay Korabel

    Mathematics, University of Manchester, Manchester, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  3. Runze Chen

    Department of Computer Science, University of Manchester, Manchester, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  4. Mark Johnston

    School of Biological Sciences, University of Manchester, Manchester, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  5. Anna Gavrilova

    Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  6. Victoria J Allan

    Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
    For correspondence
    viki.allan@manchester.ac.uk
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-4583-0836
  7. Sergei Fedotov

    Department of Mathematics, University of Manchester, Manchester, United Kingdom
    For correspondence
    sergei.fedotov@manchester.ac.uk
    Competing interests
    The authors declare that no competing interests exist.
  8. Thomas A Waigh

    Physics and Astronomy, University of Manchester, Manchester, United Kingdom
    For correspondence
    t.a.waigh@manchester.ac.uk
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7084-559X

Funding

Wellcome Trust (215189/Z/19/Z)

  • Daniel Han

EPSRC (EP/J019526/1)

  • Nickolay Korabel
  • Victoria J Allan
  • Sergei Fedotov
  • Thomas A Waigh

BBSRC (BB/H017828/1)

  • Victoria J Allan

Wellcome Trust (108867/Z/15/Z)

  • Anna Gavrilova

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Reviewing Editor

  1. Robert H Singer, Albert Einstein College of Medicine, United States

Version history

  1. Received: September 26, 2019
  2. Accepted: March 22, 2020
  3. Accepted Manuscript published: March 24, 2020 (version 1)
  4. Version of Record published: April 8, 2020 (version 2)
  5. Version of Record updated: May 26, 2020 (version 3)

Copyright

© 2020, Han et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 1,822
    views
  • 301
    downloads
  • 39
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Daniel Han
  2. Nickolay Korabel
  3. Runze Chen
  4. Mark Johnston
  5. Anna Gavrilova
  6. Victoria J Allan
  7. Sergei Fedotov
  8. Thomas A Waigh
(2020)
Deciphering anomalous heterogeneous intracellular transport with neural networks
eLife 9:e52224.
https://doi.org/10.7554/eLife.52224

Share this article

https://doi.org/10.7554/eLife.52224

Further reading

    1. Cancer Biology
    2. Cell Biology
    Mengya Zhao, Beiying Dai ... Yijun Chen
    Research Article

    Philadelphia chromosome-positive (Ph+) leukemia is a fatal hematological malignancy. Although standard treatments with tyrosine kinase inhibitors (TKIs) have achieved remarkable success in prolonging patient survival, intolerance, relapse, and TKI resistance remain serious issues for patients with Ph+ leukemia. Here, we report a new leukemogenic process in which RAPSYN and BCR-ABL co-occur in Ph+ leukemia, and RAPSYN mediates the neddylation of BCR-ABL. Consequently, neddylated BCR-ABL enhances the stability by competing its c-CBL-mediated degradation. Furthermore, SRC phosphorylates RAPSYN to activate its NEDD8 E3 ligase activity, promoting BCR-ABL stabilization and disease progression. Moreover, in contrast to in vivo ineffectiveness of PROTAC-based degraders, depletion of RAPSYN expression, or its ligase activity decreased BCR-ABL stability and, in turn, inhibited tumor formation and growth. Collectively, these findings represent an alternative to tyrosine kinase activity for the oncoprotein and leukemogenic cells and generate a rationale of targeting RAPSYN-mediated BCR-ABL neddylation for the treatment of Ph+ leukemia.

    1. Cell Biology
    2. Genetics and Genomics
    Yangzi Zhao, Lijun Ren ... Zhukuan Cheng
    Research Article

    Cohesin is a multi-subunit protein that plays a pivotal role in holding sister chromatids together during cell division. Sister chromatid cohesion 3 (SCC3), constituents of cohesin complex, is highly conserved from yeast to mammals. Since the deletion of individual cohesin subunit always causes lethality, it is difficult to dissect its biological function in both mitosis and meiosis. Here, we obtained scc3 weak mutants using CRISPR-Cas9 system to explore its function during rice mitosis and meiosis. The scc3 weak mutants displayed obvious vegetative defects and complete sterility, underscoring the essential roles of SCC3 in both mitosis and meiosis. SCC3 is localized on chromatin from interphase to prometaphase in mitosis. However, in meiosis, SCC3 acts as an axial element during early prophase I and subsequently situates onto centromeric regions following the disassembly of the synaptonemal complex. The loading of SCC3 onto meiotic chromosomes depends on REC8. scc3 shows severe defects in homologous pairing and synapsis. Consequently, SCC3 functions as an axial element that is essential for maintaining homologous chromosome pairing and synapsis during meiosis.