Keypoint MoSeq

GitHub

Colab

Paper

Slack

License

Motion Sequencing (MoSeq) is an unsupervised machine learning method for animal behavior analysis. Given behavioral recordings, MoSeq learns a set of stereotyped movement patterns and when they occur over time. This package provides tools for fitting a MoSeq model to keypoint tracking data and analyzing the results.

Setup

• Local installation
  • Install using conda
  • Install using pip
• Google colab

Tutorials

• Project setup
  • Edit the config file
  • Load data
  • Calibration
  • Fit PCA
• Model fitting
  • Setting kappa
  • Initialization
  • Fitting an AR-HMM
  • Fitting the full model
  • Sort syllables by frequency
  • Extract model results
    • [Optional] Save results to csv
  • Apply to new data
• Visualization
  • Trajectory plots
  • Grid movies
  • Syllable Dendrogram
• Statistical Analysis
  • Setup
  • Assign Groups
  • Generate dataframes
    • Optional: Save dataframes to csv
  • Label syllables
  • Compare between groups
    • Transition matrices
    • Syllable Transition Graph

FAQs

• Code usage
• Input data
  • How much data do I need?
  • How many/which keypoints?
  • Multiple animals
  • Keypoints are noisy
  • High proportion of NaNs
  • Should I preprocess keypoints?
  • Head-fixed animals
  • Non-rodents
  • Loading keypoint tracking data
  • Size variation between animals
  • 3D keypoint data
• Modeling
  • Validating model outputs
  • Choosing the target syllable duration
  • Number of model fitting iterations
  • Detecting existing syllables in new data
  • Continue model fitting but with new data
  • Interpreting model outputs
• Visualization
  • Making grid movies for 3D data
  • Why are there only trajectory plots for a subset of syllables?
  • Why are there only grid movies for a subset of syllables?
  • Why do my trajectory plots and grid movies disagree?
• Troubleshooting
  • Dead kernel
  • Out of memory
  • NaNs during fitting
  • Installation errors

Advanced topics

• Exporting pose estimates
• Automatic kappa scan

Developer API

• Model fitting
• Visualization
• Input/Output
• Utilities
• Error Calibration