Metadata-Version: 2.4
Name: stFormer
Version: 0.1.3a0
Summary: A flexible framework for transformer-based analysis of spatial transcriptomics data.
Author-email: Qian Zhu <qzhu@bcm.edu>, Ivy Strope <ivystrope@gmail.com>, William Bowie <William.Bowie@bcm.edu>
Maintainer-email: Qian Zhu <qzhu@bcm.edu>
License-Expression: MIT
Project-URL: Homepage, https://github.com/Istrope/stFormer
Project-URL: Issues, https://github.com/Istrope/stFormer/issues
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 3 - Alpha
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# stFormer

A flexible framework for transformer-based analysis of spatial transcriptomics data. stFormer provides tools for data tokenization, pretraining, embedding extraction, in silico perturbation, and downstream classification.

- Keep up to date on [Github](https://github.com/istrope/stFormer)
- Browse model files on [Hugging-Face](https://huggingface.co/Istrope/stFormer)

# Install
```bash
pip install --upgrade stformer
```
> **Prerequisites:** Python3.8+, OpenMPI (for deepspeed only)

# Features
- Data Tokenization
- Pretraining
- Token/Sequence Classification
- In Silico Perturbation
- Network Dynamic Predictions

## Contributing

Contributions are welcome! Please open issues at our [Github](https://github.com/istrope/stFormer) or submit pull requests for bug fixes and new features.

## Models
Pretrained models and datasets are available through our [hugging-face](https://huggingface.co/Istrope/stFormer) model card 

## License

This project is licensed under the MIT License. See [LICENSE](https://github.com/istrope/stFormer/blob/main/LICENSE) for details.
