Keypoint-MoSeq: parsing behavior by linking point tracking to pose dynamics
Authors:
- Caleb WeinrebCWCaleb Weinreb
- Jonah PearlJPJonah Pearl
- Sherry LinSLSherry Lin
- Mohammed Abdal Monium OsmanMOMohammed Abdal Monium Osman
- Red HoffmanRHRed Hoffman
- Sofia MakowskaSMSofia Makowska
- Winthrop F. GillisWGWinthrop F. Gillis
- Maya JayMJMaya Jay
- Shaokai YeSYShaokai Ye
Preprint
Abstract
Keypoint tracking algorithms have revolutionized the analysis of animal behavior, enabling investigators to flexibly quantify behavioral dynamics from conventional video recordings obtained in a wide variety of settings. However, it remains unclear how to parse continuous keypoint data into the modules out of which behavior is organized. This challenge is particularly acute because keypoint data is susceptible to high frequency jitter that clustering algorithms can mistake for transitions between behavioral modules. Here we present keypoint-MoSeq, a machine learning-based platform for identifying behavioral modules (“syllables”) from keypoint data without human supervision. Keypoint-MoSeq uses a generative model to distinguish keypoint noise from behavior, enabling it to effectively identify syllables whose boundaries correspond to natural sub-second discontinuities inherent to mouse behavior. Keypoint-MoSeq outperforms commonly used alternative clustering methods at identifying these transitions, at capturing correlations between neural activity and behavior, and at classifying either solitary or social behaviors in accordance with human annotations. Keypoint-MoSeq therefore renders behavioral syllables and grammar accessible to the many researchers who use standard video to capture animal behavior.Keywords
This publication has 38 references indexed in Scilit:
- Structure of the Zebrafish Locomotor Repertoire Revealed with Unsupervised Behavioral ClusteringCurrent Biology, 2018
- Systematic exploration of unsupervised methods for mapping behaviorPhysical Biology, 2017
- Predictability and hierarchy in Drosophila behaviorProceedings of the National Academy of Sciences, 2016
- Mapping Sub-Second Structure in Mouse BehaviorNeuron, 2015
- Dopamine Is Required for the Neural Representation and Control of Movement VigorCell, 2015
- Mapping the stereotyped behaviour of freely moving fruit fliesJournal of The Royal Society Interface, 2014
- Toward a Science of Computational EthologyNeuron, 2014
- Mapping the structure of drosophilid behaviorbioRxiv, 2014
- The functional organization of behaviourAnimal Behaviour, 1976
- On state estimation in switching environmentsIEEE Transactions on Automatic Control, 1970