Home / Cite

Cite CUBE and credits

CUBE is research software. If you use it, please cite it and the methods it builds on.

How to cite CUBE

A preprint describing CUBE is in preparation. Until it appears, please cite the software:

Valiathan P. CUBE: Comprehensive Unsupervised Behavioral Explorer, version 5. Developed in the laboratory of Patrik Ernfors, Karolinska Institutet. Software, https://github.com/param-valiathan/CUBE

This site documents CUBE v5. Please also state the version or commit you used. This page will be updated with the preprint reference and a DOI when they are available.

Developer and laboratory

CUBE was developed in the laboratory of Patrik Ernfors, Division of Molecular Neurobiology, Department of Medical Biochemistry and Biophysics, Karolinska Institutet (research group website).

Methods and software CUBE builds on

If you use CUBE, please also cite the work it rests on:

  • B-SOiD: Hsu AI, Yttri EA. B-SOiD, an open-source unsupervised algorithm for identification and fast prediction of behaviors. Nature Communications 12:5188 (2021).
  • DeepLabCut: Mathis A, et al. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience 21:1281-1289 (2018).
  • UMAP: McInnes L, Healy J, Melville J. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:1802.03426 (2018).
  • HDBSCAN: McInnes L, Healy J, Astels S. hdbscan: Hierarchical density based clustering. Journal of Open Source Software 2(11):205 (2017).
  • Anipose (3D mode): Karashchuk P, et al. Anipose: a toolkit for robust markerless 3D pose estimation. Cell Reports 36:109730 (2021).

Example data

Open field and elevated plus maze videos, tracking and labels shown on this site come from the public dataset of Sturman O, von Ziegler L, Schläppi C, et al. Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions. Neuropsychopharmacology 45:1942-1952 (2020), doi:10.1038/s41386-020-0776-y.

Licence and use

The source code is available on GitHub. Until the preprint is released, it is provided under the CUBE Pre-publication Source-Available Licence: you may read the code and run unmodified copies for personal, non-commercial evaluation and academic research, with attribution. Redistribution, modification for distribution, derivative software and commercial use need the author's prior written permission. The licence is intended to be replaced by an open-source licence when the preprint appears.

Contact

For questions, bug reports and ideas, open an issue on GitHub or connect on LinkedIn.