Real-time, low-latency closed-loop feedback using markerless posture tracking

  1. Gary A Kane
  2. Gonçalo Lopes
  3. Jonny L Saunders
  4. Alexander Mathis
  5. Mackenzie W Mathis  Is a corresponding author
  1. Harvard University, United States
  2. NeuroGears, United Kingdom
  3. University of Oregon, United States
  4. EPFL, Switzerland

Abstract

The ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here we provide a new DeepLabCut-Live! package that achieves low-latency real-time pose estimation (within 15 ms, >100 FPS), with an additional forward-prediction module that achieves zero-latency feedback, and a dynamic-cropping mode that allows for higher inference speeds. We also provide three options for using this tool with ease: (1) a stand-alone GUI (called DLC-Live! GUI, and integration into (2) Bonsai and (3) AutoPilot. Lastly, we benchmarked performance on a wide range of systems so that experimentalists can easily decide what hardware is required for their needs.

Data availability

All models, data, test scripts and software is already released and made freely available on GitHub: https://github.com/DeepLabCut/DeepLabCut-live

Article and author information

Author details

  1. Gary A Kane

    The Rowland Institute at Harvard, Harvard University, Cambridge, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7703-5055
  2. Gonçalo Lopes

    NeuroGears, London, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-0731-4945
  3. Jonny L Saunders

    Institute of Neuroscience, Department of Psychology, University of Oregon, Eugene, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Alexander Mathis

    Life Sciences, EPFL, Geneva, Switzerland
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3777-2202
  5. Mackenzie W Mathis

    Brain Mind Institute, EPFL, Genève, Switzerland
    For correspondence
    mackenzie.mathis@epfl.ch
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-7368-4456

Funding

Chan Zuckerberg Initiative (EOSS)

  • Alexander Mathis
  • Mackenzie W Mathis

National Science Foundation (1309047)

  • Jonny L Sanders

The Rowland Institute at Harvard, Harvard University

  • Gary A Kane
  • Alexander Mathis
  • Mackenzie W Mathis

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

Reviewing Editor

  1. Gordon J Berman, Emory University, United States

Ethics

Animal experimentation: All mouse work was carried out under the permission of the IACUC at Harvard University (#17-07-309). Dog videos and feedback was exempt from IACUC approval (with conformation with IACUC).

Version history

  1. Received: August 8, 2020
  2. Accepted: December 6, 2020
  3. Accepted Manuscript published: December 8, 2020 (version 1)
  4. Accepted Manuscript updated: December 9, 2020 (version 2)
  5. Version of Record published: January 4, 2021 (version 3)

Copyright

© 2020, Kane 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

  • 12,966
    views
  • 1,392
    downloads
  • 68
    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. Gary A Kane
  2. Gonçalo Lopes
  3. Jonny L Saunders
  4. Alexander Mathis
  5. Mackenzie W Mathis
(2020)
Real-time, low-latency closed-loop feedback using markerless posture tracking
eLife 9:e61909.
https://doi.org/10.7554/eLife.61909

Share this article

https://doi.org/10.7554/eLife.61909

Further reading

    1. Computational and Systems Biology
    Qianmu Yuan, Chong Tian, Yuedong Yang
    Tools and Resources

    Revealing protein binding sites with other molecules, such as nucleic acids, peptides, or small ligands, sheds light on disease mechanism elucidation and novel drug design. With the explosive growth of proteins in sequence databases, how to accurately and efficiently identify these binding sites from sequences becomes essential. However, current methods mostly rely on expensive multiple sequence alignments or experimental protein structures, limiting their genome-scale applications. Besides, these methods haven’t fully explored the geometry of the protein structures. Here, we propose GPSite, a multi-task network for simultaneously predicting binding residues of DNA, RNA, peptide, protein, ATP, HEM, and metal ions on proteins. GPSite was trained on informative sequence embeddings and predicted structures from protein language models, while comprehensively extracting residual and relational geometric contexts in an end-to-end manner. Experiments demonstrate that GPSite substantially surpasses state-of-the-art sequence-based and structure-based approaches on various benchmark datasets, even when the structures are not well-predicted. The low computational cost of GPSite enables rapid genome-scale binding residue annotations for over 568,000 sequences, providing opportunities to unveil unexplored associations of binding sites with molecular functions, biological processes, and genetic variants. The GPSite webserver and annotation database can be freely accessed at https://bio-web1.nscc-gz.cn/app/GPSite.

    1. Cell Biology
    2. Computational and Systems Biology
    Thomas Grandits, Christoph M Augustin ... Alexander Jung
    Research Article

    Computer models of the human ventricular cardiomyocyte action potential (AP) have reached a level of detail and maturity that has led to an increasing number of applications in the pharmaceutical sector. However, interfacing the models with experimental data can become a significant computational burden. To mitigate the computational burden, the present study introduces a neural network (NN) that emulates the AP for given maximum conductances of selected ion channels, pumps, and exchangers. Its applicability in pharmacological studies was tested on synthetic and experimental data. The NN emulator potentially enables massive speed-ups compared to regular simulations and the forward problem (find drugged AP for pharmacological parameters defined as scaling factors of control maximum conductances) on synthetic data could be solved with average root-mean-square errors (RMSE) of 0.47 mV in normal APs and of 14.5 mV in abnormal APs exhibiting early afterdepolarizations (72.5% of the emulated APs were alining with the abnormality, and the substantial majority of the remaining APs demonstrated pronounced proximity). This demonstrates not only very fast and mostly very accurate AP emulations but also the capability of accounting for discontinuities, a major advantage over existing emulation strategies. Furthermore, the inverse problem (find pharmacological parameters for control and drugged APs through optimization) on synthetic data could be solved with high accuracy shown by a maximum RMSE of 0.22 in the estimated pharmacological parameters. However, notable mismatches were observed between pharmacological parameters estimated from experimental data and distributions obtained from the Comprehensive in vitro Proarrhythmia Assay initiative. This reveals larger inaccuracies which can be attributed particularly to the fact that small tissue preparations were studied while the emulator was trained on single cardiomyocyte data. Overall, our study highlights the potential of NN emulators as powerful tool for an increased efficiency in future quantitative systems pharmacology studies.