: Quantification of user-defined animal behaviors using learning-based holistic assessment.

Journal: Cell reports methods
Published Date:

Abstract

Quantifying animal behavior is important for biological research. Identifying behaviors is the prerequisite of quantifying them. Current computational tools for behavioral quantification typically use high-level properties such as body poses to identify the behaviors, which constrains the information available for a holistic assessment. Here we report , an open-source computational tool for quantifying animal behaviors without this constraint. In , we introduce "pattern image" to represent the animal's motion pattern, in addition to "animation" that shows all spatiotemporal details of a behavior. These two pieces of information are assessed holistically by customizable deep neural networks for accurate behavior identifications. The quantitative measurements of each behavior are then calculated. is applicable for experiments involving multiple animals, requires little programming knowledge to use, and provides visualizations of behavioral datasets. We demonstrate its efficacy in capturing subtle behavioral changes in diverse animal species.

Authors

  • Yujia Hu
    Life Sciences Institute and Department of Cell and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, USA.
  • Carrie R Ferrario
    Department of Pharmacology and Psychology Department (Biopsychology), University of Michigan, Ann Arbor, MI 48109, USA.
  • Alexander D Maitland
    Department of Pharmacology and Psychology Department (Biopsychology), University of Michigan, Ann Arbor, MI 48109, USA.
  • Rita B Ionides
    Department of Pharmacology and Psychology Department (Biopsychology), University of Michigan, Ann Arbor, MI 48109, USA.
  • Anjesh Ghimire
    Department of Psychiatry, University of Michigan, Ann Arbor, MI 48109, USA.
  • Brendon Watson
    Department of Psychiatry, University of Michigan, Ann Arbor, MI 48109, USA.
  • Kenichi Iwasaki
    Life Sciences Institute and Department of Cell and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, USA.
  • Hope White
    Life Sciences Institute and Department of Cell and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, USA.
  • Yitao Xi
    Life Sciences Institute and Department of Cell and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, USA.
  • Jie Zhou
    Departments of Ultrasound, Jiading District Central Hospital Affiliated Shanghai University of Medicine &Health Sciences, Shanghai, China.
  • Bing Ye
    Life Sciences Institute and Department of Cell and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, USA.