Fast deep neural correspondence for tracking and identifying neurons in C. elegans using semi-synthetic training

  1. Xinwei Yu
  2. Matthew S Creamer
  3. Francesco Randi
  4. Anuj Kumar Sharma Ph.D.
  5. Scott W Linderman
  6. Andrew Michael Leifer  Is a corresponding author
  1. Princeton University, United States
  2. Stanford University, United States

Abstract

We present an automated method to track and identify neurons in C. elegans, called 'fast Deep Neural Correspondence' or fDNC, based on the transformer network architecture. The model is trained once on empirically derived semi-synthetic data and then predicts neural correspondence across held-out real animals. The same pre-trained model both tracks neurons across time and identifies corresponding neurons across individuals. Performance is evaluated against hand-annotated datasets, including NeuroPAL [1]. Using only position information, the method achieves 79.1% accuracy at tracking neurons within an individual and 64.1% accuracy at identifying neurons across individuals. Accuracy at identifying neurons across individuals is even higher (78.2%) when the model is applied to a dataset published by another group [2]. Accuracy reaches 74.7% on our dataset when using color information from NeuroPAL. Unlike previous methods, fDNC does not require straightening or transforming the animal into a canonical coordinate system. The method is fast and predicts correspondence in 10ms making it suitable for future real-time applications.

Data availability

All datasets generated as part of this work have been deposited in a public Open Science Foundation repository DOI:10.17605/OSF.IO/T7DZU.

The following data sets were generated
The following previously published data sets were used

Article and author information

Author details

  1. Xinwei Yu

    Department of Physics, Princeton University, Princeton, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Matthew S Creamer

    Princeton Neuroscience Institute, Princeton University, Princeton, United States
    Competing interests
    The authors declare that no competing interests exist.
  3. Francesco Randi

    Department of Physics, Princeton University, Princeton, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Anuj Kumar Sharma Ph.D.

    Department of Physics, Princeton University, Princeton, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-5061-9731
  5. Scott W Linderman

    Department of Statistics, Stanford University, Stanford, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3878-9073
  6. Andrew Michael Leifer

    Department of Physics and Princeton Neuroscience Institute, Princeton University, Princeton, United States
    For correspondence
    leifer@princeton.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-5362-5093

Funding

Simons Foundation (543003)

  • Andrew Michael Leifer

Simons Foundation (697092)

  • Scott W Linderman

National Science Foundation (IOS-184537)

  • Andrew Michael Leifer

National Science Foundation (PHY-1734030)

  • Andrew Michael Leifer

National Institutes of Health (R21NS101629)

  • Andrew Michael Leifer

National Institutes of Health (1R01NS113119)

  • Scott W Linderman

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

Publication history

  1. Received: January 9, 2021
  2. Accepted: July 13, 2021
  3. Accepted Manuscript published: July 14, 2021 (version 1)
  4. Version of Record published: August 16, 2021 (version 2)

Copyright

© 2021, Yu 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

  • 1,368
    Page views
  • 135
    Downloads
  • 2
    Citations

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

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. Xinwei Yu
  2. Matthew S Creamer
  3. Francesco Randi
  4. Anuj Kumar Sharma Ph.D.
  5. Scott W Linderman
  6. Andrew Michael Leifer
(2021)
Fast deep neural correspondence for tracking and identifying neurons in C. elegans using semi-synthetic training
eLife 10:e66410.
https://doi.org/10.7554/eLife.66410

Further reading

    1. Neuroscience
    Camila Vesga-Castro et al.
    Review Article

    Over the last few years, there has been growing interest in measuring the contractile force (CF) of engineered muscle tissues to evaluate their functionality. However, there are still no standards available for selecting the most suitable experimental platform, measuring system, culture protocol, or stimulation patterns. Consequently, the high variability of published data hinders any comparison between different studies. We have identified that cantilever deflection, post deflection, and force transducers are the most commonly used configurations for CF assessment in 2D and 3D models. Additionally, we have discussed the most relevant emerging technologies that would greatly complement CF evaluation with intracellular and localized analysis. This review provides a comprehensive analysis of the most significant advances in CF evaluation and its critical parameters. In order to compare contractile performance across experimental platforms, we have used the specific force (sF, kN/m2), CF normalized to the calculated cross-sectional area (CSA). However, this parameter presents a high variability throughout the different studies, which indicates the need to identify additional parameters and complementary analysis suitable for proper comparison. We propose that future contractility studies in skeletal muscle constructs report detailed information about construct size, contractile area, maturity level, sarcomere length, and, ideally, the tetanus-to-twitch ratio. These studies will hopefully shed light on the relative impact of these variables on muscle force performance of engineered muscle constructs. Prospective advances in muscle tissue engineering, particularly in muscle disease models, will require a joint effort to develop standardized methodologies for assessing CF of engineered muscle tissues.

    1. Genetics and Genomics
    2. Neuroscience
    Junhao Li et al.
    Research Article

    Two epigenetic pathways of transcriptional repression, DNA methylation and Polycomb repressive complex 2 (PRC2) are known to regulate neuronal development and function. However, their respective contributions to brain maturation are unknown. We found that conditional loss of the de novo DNA methyltransferase Dnmt3a in mouse excitatory neurons altered expression of synapse-related genes, stunted synapse maturation, and impaired working memory and social interest. At the genomic level, loss of Dnmt3a abolished postnatal accumulation of CG and non-CG DNA methylation, leaving adult neurons with an unmethylated, fetal-like epigenomic pattern at ~222,000 genomic regions. The PRC2-associated histone modification, H3K27me3, increased at many of these sites. Our data support a dynamic interaction between two fundamental modes of epigenetic repression during postnatal maturation of excitatory neurons, which together confer robustness on neuronal regulation.