Deciphering anomalous heterogeneous intracellular transport with neural networks

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

Publication 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

  • 1,584
    Page views
  • 253
    Downloads
  • 26
    Citations

Article citation count generated by polling the highest count across the following sources: Crossref, Scopus, PubMed Central.

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

Further reading

    1. Cancer Biology
    2. Cell Biology
    Elena Tomas Bort, Megan Daisy Joseph ... Richard Philip Grose
    Research Article

    Pancreatic ductal adenocarcinoma (PDAC) continues to show no improvement in survival rates. One aspect of PDAC is elevated ATP levels, pointing to the purinergic axis as a potential attractive therapeutic target. Mediated in part by highly druggable extracellular proteins, this axis plays essential roles in fibrosis, inflammation response and immune function. Analysing the main members of the PDAC extracellular purinome using publicly available databases discerned which members may impact patient survival. P2RY2 presents as the purinergic gene with the strongest association with hypoxia, the highest cancer cell-specific expression and the strongest impact on overall survival. Invasion assays using a 3D spheroid model revealed P2Y2 to be critical in facilitating invasion driven by extracellular ATP. Using genetic modification and pharmacological strategies we demonstrate mechanistically that this ATP-driven invasion requires direct protein-protein interactions between P2Y2 and αV integrins. DNA-PAINT super-resolution fluorescence microscopy reveals that P2Y2 regulates the amount and distribution of integrin αV in the plasma membrane. Moreover, receptor-integrin interactions were required for effective downstream signalling, leading to cancer cell invasion. This work elucidates a novel GPCR-integrin interaction in cancer invasion, highlighting its potential for therapeutic targeting.

    1. Cell Biology
    Enric Gutiérrez-Martínez, Susana Benet Garrab ... Maria F Garcia-Parajo
    Research Article

    The immunoglobulin-like lectin receptor CD169 (Siglec-1) mediates the capture of HIV-1 by activated dendritic cells (DC) through binding to sialylated ligands. These interactions result in a more efficient virus capture as compared to resting DCs, although the underlying mechanisms are poorly understood. Using a combination of super-resolution microscopy, single particle tracking and biochemical perturbations we studied the nanoscale organization of Siglec-1 on activated DCs and its impact on viral capture and its trafficking to a single viral-containing compartment. We found that activation of DCs leads to Siglec-1 basal nanoclustering at specific plasma membrane regions where receptor diffusion is constrained by Rho-ROCK activation and formin-dependent actin polymerization. Using liposomes with varying ganglioside concentrations, we further demonstrate that Siglec-1 nanoclustering enhances the receptor avidity to limiting concentrations of gangliosides carrying sialic ligands. Binding to either HIV-1 particles or ganglioside-bearing liposomes lead to enhanced Siglec-1 nanoclustering and global actin rearrangements characterized by a drop in RhoA activity, facilitating the final accumulation of viral particles in a single sac-like compartment. Overall, our work provides new insights on the role of the actin machinery of activated DCs in regulating the formation of basal Siglec-1 nanoclustering, being decisive for the capture and actin-dependent trafficking of HIV-1 into the virus-containing compartment.