---
license: mit
tags:
- biology
---

[Barlow Twins](https://proceedings.mlr.press/v139/zbontar21a/zbontar21a.pdf) model pre-trained on the scTab dataset (~20M cells, ~19k genes). Training details can be found in our paper below. To use the model directly, the same genes must be used in the same order as in the `var.parquet` file.

If you find our work useful, please cite the following paper:

[**Delineating the Effective Use of Self-Supervised Learning in Single-Cell Genomics**](https://doi.org/10.1101/2024.02.16.580624)