DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels

  1. James P Bohnslav
  2. Nivanthika K Wimalasena
  3. Kelsey J Clausing
  4. Yu Y Dai
  5. David A Yarmolinsky
  6. Tomás Cruz
  7. Adam D Kashlan
  8. M Eugenia Chiappe
  9. Lauren L Orefice
  10. Clifford J Woolf
  11. Christopher D Harvey  Is a corresponding author
  1. Harvard Medical School, United States
  2. Boston Children's Hospital, United States
  3. Massachusetts General Hospital, United States
  4. 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.

The following previously published data sets were used

Article and author information

Author details

  1. James P Bohnslav

    Neurobiology, Harvard Medical School, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Nivanthika K Wimalasena

    F.M. Kirby Neurobiology Center, Boston Children's Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  3. Kelsey J Clausing

    Molecular Biology, Massachusetts General Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Yu Y Dai

    Molecular Biology, Massachusetts General Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  5. David A Yarmolinsky

    F.M. Kirby Neurobiology Center, Boston Children's Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  6. Tomás Cruz

    Champalimaud Neuroscience Programme, Champalimaud Center for the Unknown, Lisbon, Portugal
    Competing interests
    The authors declare that no competing interests exist.
  7. Adam D Kashlan

    F.M. Kirby Neurobiology Center, Boston Children's Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  8. M Eugenia Chiappe

    Champalimaud Neuroscience Porgramme, Champalimaud Center for the Unknown, Lisbon, Portugal
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-1761-0457
  9. Lauren L Orefice

    Molecular Biology, Massachusetts General Hospital, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  10. Clifford J Woolf

    Department of Neurobiology, Harvard Medical School, Boston, United States
    Competing interests
    The authors declare that no competing interests exist.
  11. Christopher D Harvey

    Neurobiology, Harvard Medical School, Boston, United States
    For correspondence
    harvey@hms.harvard.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-9850-2268

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.

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.

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

  • 13,042
    views
  • 1,252
    downloads
  • 103
    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. James P Bohnslav
  2. Nivanthika K Wimalasena
  3. Kelsey J Clausing
  4. Yu Y Dai
  5. David A Yarmolinsky
  6. Tomás Cruz
  7. Adam D Kashlan
  8. M Eugenia Chiappe
  9. Lauren L Orefice
  10. Clifford J Woolf
  11. Christopher D Harvey
(2021)
DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels
eLife 10:e63377.
https://doi.org/10.7554/eLife.63377

Share this article

https://doi.org/10.7554/eLife.63377

Further reading

    1. Neuroscience
    Giordano de Guglielmo, Lieselot Carrette ... Olivier George
    Research Article

    Addiction is commonly characterized by escalation of drug intake, compulsive drug seeking, and continued use despite harmful consequences. However, the factors contributing to the transition from moderate drug use to these problematic patterns remain unclear, particularly regarding the role of sex. Many preclinical studies have been limited by small sample sizes, low genetic diversity, and restricted drug access, making it challenging to model significant levels of intoxication or dependence and translate findings to humans. To address these limitations, we characterized addiction-like behaviors in a large sample of >500 outbred heterogeneous stock (HS) rats using an extended cocaine self-administration paradigm (6 hr/daily). We analyzed individual differences in escalation of intake, progressive ratio (PR) responding, continued use despite adverse consequences (contingent foot shocks), and irritability-like behavior during withdrawal. Principal component analysis showed that escalation of intake, progressive ratio responding, and continued use despite adverse consequences loaded onto a single factor that was distinct from irritability-like behaviors. Categorizing rats into resilient, mild, moderate, and severe addiction-like phenotypes showed that females exhibited higher addiction-like behaviors, with a lower proportion of resilient individuals compared to males. These findings suggest that, in genetically diverse rats with extended drug access, escalation of intake, continued use despite adverse consequences, and PR responding are highly correlated measures of a shared underlying construct. Furthermore, our results highlight sex differences in resilience to addiction-like behaviors.

    1. Neuroscience
    Tingting Li, Wenwen Shi ... Yong Q Zhang
    Research Article

    Traumatic brain injury (TBI) caused by external mechanical forces is a major health burden worldwide, but the underlying mechanism in glia remains largely unclear. We report herein that Drosophila adults exhibit a defective blood–brain barrier, elevated innate immune responses, and astrocyte swelling upon consecutive strikes with a high-impact trauma device. RNA sequencing (RNA-seq) analysis of these astrocytes revealed upregulated expression of genes encoding PDGF and VEGF receptor-related (Pvr, a receptor tyrosine kinase), adaptor protein complex 1 (AP-1, a transcription factor complex of the c-Jun N-terminal kinase pathway) composed of Jun-related antigen (Jra) and kayak (kay), and matrix metalloproteinase 1 (Mmp1) following TBI. Interestingly, Pvr is both required and sufficient for AP-1 and Mmp1 upregulation, while knockdown of AP-1 expression in the background of Pvr overexpression in astrocytes rescued Mmp1 upregulation upon TBI, indicating that Pvr acts as the upstream receptor for the downstream AP-1–Mmp1 transduction. Moreover, dynamin-associated endocytosis was found to be an important regulatory step in downregulating Pvr signaling. Our results identify a new Pvr–AP-1–Mmp1 signaling pathway in astrocytes in response to TBI, providing potential targets for developing new therapeutic strategies for TBI.