Automated behavioural phenotyping of Xenopus laevis tadpoles from 24-well plate video.
TadPose provides a pipeline for extracting posture dynamics and velocity features from multi-well plate recordings of tadpoles, enabling unsupervised behavioural clustering to quantify seizure phenotypes in models of developmental and epileptic encephalopathies (DEE).
- Well detection — Hough circle transform with eigenvector-corrected centres to accurately localise all 24 wells despite lens distortion.
- Video segmentation — Split full-plate recordings into individual per-well videos for downstream pose estimation.
- Pose estimation — Seven anatomical landmarks tracked via DeepLabCut (eyes, tail base, three tail segments, tail tip).
- Feature extraction — Body-centric velocity decomposition (thrust, yaw, slip) and posture dynamics (frame-to-frame landmark displacement in a frons-aligned coordinate system).
- Behavioural clustering — GPU-accelerated k-means via STAG on combined velocity + posture dynamics features, yielding 36 stable behavioural prototypes.
pip install -e .If you use TadPose in your research, please cite:
Matthews, A.R.H., Beck, C., & Geurten, B.R.H. (2026). TadPose: Automated behavioural phenotyping of Xenopus laevis tadpoles from 24-well plate video. [Software]. GitHub. https://github.com/zerotonin/tadpose
MIT — see LICENSE.