Abstract
Automated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming is a prototypical stereotyped behavior that is often used as an endophenotype in psychiatric genetics. Here, we used mouse grooming behavior as an example and developed a general purpose neural network architecture capable of dynamic action detection at human observer-level performance and operating across dozens of mouse strains with high visual diversity. We provide insights into the amount of human annotated training data that are needed to achieve such performance. We surveyed grooming behavior in the open field in 2457 mice across 62 strains, determined its heritable components, conducted GWAS to outline its genetic architecture, and performed PheWAS to link human psychiatric traits through shared underlying genetics. Our general machine learning solution that automatically classifies complex behaviors in large datasets will facilitate systematic studies of behavioral mechanisms.
Highlights
Behavior, the primary output of the nervous system, is complex, hierarchical, dynamic, and high dimensional (Gomez-Marin et al, 2014)
Our neural network achieved 93.7% accuracy and 91.9% true positive rate (TPR) with a 5% false positive rate (FPR) (Figure 3A,B, pink line)
We identified 46 frames to be the optimal window for a rolling average (Figure 3—figure supplement 3B), which results in a final accuracy of 93.7% (ROC area under the curve (AUC) of 0.984)
Summary
The primary output of the nervous system, is complex, hierarchical, dynamic, and high dimensional (Gomez-Marin et al, 2014). Precise approaches to dissect neuronal function require analysis of behavior at high temporal and spatial resolution Achieving this is a time-consuming task and its automation remains a challenging problem in behavioral neuroscience. In the field of computer vision, modern neural network approaches have presented new solutions to visual tasks that perform just as well as humans (Ching et al, 2018; Angermueller et al, 2016) Application of these tools to biologically relevant problems could alleviate the costs of behavioral experiments and enhance reproducibility. Despite these enticing advantages, few aspects of behavioral biology research leverages neural network approaches. Behavior recognition within dynamic environments is an open challenge in the machine learning community and translatability of proposed solutions to behavioral neuroscience remains unaddressed
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
