DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels
- Harvard Medical School, United States
- Boston Children's Hospital, United States
- Massachusetts General Hospital, United States
- Champalimaud Center for the Unknown, Portugal
Abstract
Videos of animal behavior are used to quantify researcher-defined behaviors-of-interest to study neural function, gene mutations, and pharmacological therapies. Behaviors-of-interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors-of-interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram's rapid, automatic, and reproducible labeling of researcher-defined behaviors-of-interest may accelerate and enhance supervised behavior analysis.
Data availability
Code is posted publicly on Github and linked in the paper. Video datasets and human annotations are publicly available and linked in the paper.
Article and author information
Author details
Christopher D Harvey
Funding
National Institutes of Health (R01MH107620)
- Christopher D Harvey
National Science Foundation (GRFP)
- Nivanthika K Wimalasena
Fundacao para a Ciencia ea Tecnologia (PD/BD/105947/2014)
- Tomás Cruz
Harvard Medical School Dean's Innovation Award
- Christopher D Harvey
Harvard Medical School Goldenson Research Award
- Christopher D Harvey
National Institutes of Health (DP1 MH125776)
- Christopher D Harvey
National Institutes of Health (R01NS089521)
- Christopher D Harvey
National Institutes of Health (R01NS108410)
- Christopher D Harvey
National Institutes of Health (F31NS108450)
- James P Bohnslav
National Institutes of Health (R35NS105076)
- Clifford J Woolf
National Institutes of Health (R01AT011447)
- Clifford J Woolf
National Institutes of Health (R00NS101057)
- Lauren L Orefice
National Institutes of Health (K99DE028360)
- David A Yarmolinsky
European Research Council (ERC-Stg-759782)
- M Eugenia Chiappe
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Mackenzie W Mathis, EPFL, Switzerland
Ethics
Animal experimentation: All experimental procedures were approved by the Institutional Animal Care and Use Committees at Boston Children's Hospital (protocol numbers 17-06-3494R and 19-01-3809R) or Massachusetts General Hospital (protocol number 2018N000219) and were performed in compliance with the Guide for the Care and Use of Laboratory Animals.
Version history
- Received: September 23, 2020
- Preprint posted: September 25, 2020 (view preprint)
- Accepted: September 1, 2021
- Accepted Manuscript published: September 2, 2021 (version 1)
- Version of Record published: September 21, 2021 (version 2)
Copyright
© 2021, Bohnslav 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
-
- 12,498
- views
-
- 1,200
- downloads
-
- 95
- 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)
DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels
eLife 10:e63377.
https://doi.org/10.7554/eLife.63377
Further reading
-
- Immunology and Inflammation
- Neuroscience
CD4+CD25+Foxp3+ regulatory T cells (Treg) have been implicated in pain modulation in various inflammatory conditions. However, whether Treg cells hamper pain at steady state and by which mechanism is still unclear. From a meta-analysis of the transcriptomes of murine Treg and conventional T cells (Tconv), we observe that the proenkephalin gene (Penk), encoding the precursor of analgesic opioid peptides, ranks among the top 25 genes most enriched in Treg cells. We then present various evidence suggesting that Penk is regulated in part by members of the Tumor Necrosis Factor Receptor (TNFR) family and the transcription factor Basic leucine zipper transcription faatf-like (BATF). Using mice in which the promoter activity of Penk can be tracked with a fluorescent reporter, we also show that Penk expression is mostly detected in Treg and activated Tconv in non-inflammatory conditions in the colon and skin. Functionally, Treg cells proficient or deficient for Penk suppress equally well the proliferation of effector T cells in vitro and autoimmune colitis in vivo. In contrast, inducible ablation of Penk in Treg leads to heat hyperalgesia in both male and female mice. Overall, our results indicate that Treg might play a key role at modulating basal somatic sensitivity in mice through the production of analgesic opioid peptides.
-
- Neuroscience
Biological synaptic transmission is unreliable, and this unreliability likely degrades neural circuit performance. While there are biophysical mechanisms that can increase reliability, for instance by increasing vesicle release probability, these mechanisms cost energy. We examined four such mechanisms along with the associated scaling of the energetic costs. We then embedded these energetic costs for reliability in artificial neural networks (ANNs) with trainable stochastic synapses, and trained these networks on standard image classification tasks. The resulting networks revealed a tradeoff between circuit performance and the energetic cost of synaptic reliability. Additionally, the optimised networks exhibited two testable predictions consistent with pre-existing experimental data. Specifically, synapses with lower variability tended to have (1) higher input firing rates and (2) lower learning rates. Surprisingly, these predictions also arise when synapse statistics are inferred through Bayesian inference. Indeed, we were able to find a formal, theoretical link between the performance-reliability cost tradeoff and Bayesian inference. This connection suggests two incompatible possibilities: evolution may have chanced upon a scheme for implementing Bayesian inference by optimising energy efficiency, or alternatively, energy-efficient synapses may display signatures of Bayesian inference without actually using Bayes to reason about uncertainty.
