Published November 16, 2025
| Version Version 1.0
Dataset
Open
Pretrained DeepLabCut model and analysis scripts for adult zebrafish behavioral tracking
Authors/Creators
-
1.
Baylor College of Medicine
Description
This repository contains the pretrained DeepLabCut (DLC) model, example data, and analysis script associated with the STAR Protocol:
"Protocol for quantitative analysis of adult zebrafish swimming behavior using DeepLabCut"
The pretrained model enables users to analyze adult zebrafish swimming videos without performing any model training, making this workflow accessible to researchers with no machine-learning experience. Included in this deposit are:
- the trained DLC model (snapshot, config, and pose_cfg files)
- an example raw video, an example DLC-labeled video, and the corresponding CSV output
- a Python analysis script for generating behavioral metrics (distance traveled, zone occupancy, and heatmaps)
- a README file describing how to load the model in DeepLabCut and how to use the analysis script
This dataset supports the reproducibility of the protocol and enables immediate use of the model for quantitative zebrafish behavioral analysis.
Files
model.zip
Additional details
Related works
- Is supplement to
- Journal article: STAR Protocol (in preparation) (Other)
References
- Mathis, A., Mamidanna, P., Cury, K.M., Abe, T., Murthy, V.N., Mathis, M.W., & Bethge, M. (2018). DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9), 1281–1289.
- Nath, T., Mathis, A., Chen, A.C., Patel, A., Bethge, M., & Mathis, M.W. (2019). Using DeepLabCut for 3D markerless pose estimation across species and behaviors. Nature Protocols, 14, 2152–2176.
- Lauer, J., Zhou, M., Ye, S., Menegas, W., Nath, T., Rahman, M.M., et al. (2022). Multi-animal pose estimation and tracking with DeepLabCut. Nature Methods, 19, 496–504.