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

Abstract
Data availability
Article and author information
Metrics

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

(2021) fDKLC_Neuron_ID_C.elegans
Open Science Foundation, DOI 10.17605/OSF.IO/T7DZU.

http://dx.doi.org/10.17605/OSF.IO/T7DZU

The following previously published data sets were used

(2017) Tracking Neurons in a Moving and Deforming Brain Dataset
IEEE DataPorts DOI:10.21227/H2901H.

https://dx.doi.org/10.21227/H2901H

Article and author information

Author details

Xinwei Yu

Department of Physics, Princeton University, Princeton, United States

Competing interests
The authors declare that no competing interests exist.
Matthew S Creamer

Princeton Neuroscience Institute, Princeton University, Princeton, United States

Competing interests
The authors declare that no competing interests exist.
Francesco Randi

Department of Physics, Princeton University, Princeton, United States

Competing interests
The authors declare that no competing interests exist.
Anuj Kumar Sharma Ph.D.

Department of Physics, Princeton University, Princeton, United States

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0001-5061-9731
Scott W Linderman

Department of Statistics, Stanford University, Stanford, United States

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0002-3878-9073
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.

"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.

Copyright

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.