Simple Behavioral Analysis (SimBA) as a platform for explainable machine learning in behavioral neuroscience.

Journal: Nature neuroscience
PMID: 38778146

Abstract

The study of complex behaviors is often challenging when using manual annotation due to the absence of quantifiable behavioral definitions and the subjective nature of behavioral annotation. Integration of supervised machine learning approaches mitigates some of these issues through the inclusion of accessible and explainable model interpretation. To decrease barriers to access, and with an emphasis on accessible model explainability, we developed the open-source Simple Behavioral Analysis (SimBA) platform for behavioral neuroscientists. SimBA introduces several machine learning interpretability tools, including SHapley Additive exPlanation (SHAP) scores, that aid in creating explainable and transparent behavioral classifiers. Here we show how the addition of explainability metrics allows for quantifiable comparisons of aggressive social behavior across research groups and species, reconceptualizing behavior as a sharable reagent and providing an open-source framework. We provide an open-source, graphical user interface (GUI)-driven, well-documented package to facilitate the movement toward improved automation and sharing of behavioral classification tools across laboratories.

Authors

  • Nastacia L Goodwin
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Jia J Choong
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Sophia Hwang
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Kayla Pitts
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Liana Bloom
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Aasiya Islam
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Yizhe Y Zhang
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Eric R Szelenyi
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Xiaoyu Tong
    Department of Radiology, First Affiliated Hospital of Dalian Medical University, Shahekou District, Lianhe Road, Dalian, Liaoning, China (S.W., X.T., Y.F., M.H., Y.L., X.F.).
  • Emily L Newman
    Department of Psychiatry, Harvard Medical School McLean Hospital, Belmont, MA, USA.
  • Klaus Miczek
    Department of Psychology, Tufts University, Medford, MA, USA.
  • Hayden R Wright
    Department of Integrative Physiology and Neuroscience, Washington State University, Pullman, WA, USA.
  • Ryan J McLaughlin
    Graduate Program in Bioinformatics, University of British Columbia, Genome Sciences Centre, 100-570 West 7th Avenue, Vancouver, British Columbia, Canada.
  • Zane C Norville
    Stanford University School of Medicine, Stanford, CA, USA.
  • Neir Eshel
    Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA.
  • Mitra Heshmati
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Simon R O Nilsson
    Department of Biological Structure, University of Washington, Seattle, WA, USA.
  • Sam A Golden
    Department of Biological Structure, University of Washington, Seattle, WA, USA. sagolden@uw.edu.

Keywords

External Resources

Popular Topics
Recent Journals