Metadata-Version: 2.4
Name: scdynomics
Version: 0.0.1
Summary: Optimized, pretrainable, multiomics-capable transformer for single-cell omics
Author-email: JackSSk <gyu17@alumni.jh.edu>, Simon Mages <g.yu@lmu.de>
Maintainer: Jan Watter, JackSSk, Simon Mages
License-Expression: MIT
Project-URL: Source, https://github.com/KlughammerLab/scDynOmics
Project-URL: Documentation, https://klughammerlab.github.io/scDynOmics/html/index.html
Classifier: Programming Language :: Python :: 3
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: hdf5plugin>=4.3.0
Requires-Dist: h5py>=3.10.0
Requires-Dist: intervaltree>=3.1.0
Requires-Dist: scanpy>=1.9.6
Requires-Dist: anndata>=0.10.3
Requires-Dist: torch>=2.6.0
Requires-Dist: pytorch_lightning>=2.2.0
Requires-Dist: torchmetrics>=1.6.1
Requires-Dist: captum>=0.8.0
Requires-Dist: pandas>=2.2.0
Requires-Dist: numpy>=1.26.4
Requires-Dist: scipy>=1.11.4
Requires-Dist: scib>=1.1.5
Dynamic: license-file

# scDynOmics

[![anndata-0.10.3](https://img.shields.io/badge/anndata-0.10.3-teal)](https://github.com/scverse/anndata)
[![gget-0.28.4](https://img.shields.io/badge/gget-0.28.4-black)](https://github.com/pachterlab/gget)
[![numpy-1.26.4](https://img.shields.io/badge/numpy-1.26.4-green)](https://github.com/numpy/numpy)
[![pandas-2.2.0](https://img.shields.io/badge/pandas-2.2.0-blue)](https://github.com/pandas-dev/pandas)
[![torch-2.2.0](https://img.shields.io/badge/torch-2.2.0-yellow)](https://github.com/pytorch/pytorch)
[![pytorch_lightning-2.2.0](https://img.shields.io/badge/pytorch_lightning-2.2.0-violet)](https://github.com/Lightning-AI/pytorch-lightning)
[![scanpy-1.9.6](https://img.shields.io/badge/scanpy-1.9.6-pink)](https://github.com/scverse/scanpy)
[![scipy-1.11.4](https://img.shields.io/badge/scipy-1.11.4-lightblue)](https://github.com/scipy/scipy)

**scDynOmics** is an optimized, pretrainable transformer model designed for representation learning from multimodal single-cell data.
Motivated by gene regulatory networks, the framework utilizes a Linformer-style attention mechanism to efficiently scale to coding-genome-wide multimodal inputs. 


## Install

```bash
git clone https://github.com/KlughammerLab/scDynOmics.git
cd scDynOmics
pip install .
```

## Test

*Note: At least one GPU is recommended for testing and operation.*

You can run the built-in test script to verify the installation and core pipeline.
From the repository root, run:

```bash
python scripts/test.py --data_dir ./data --log_dir ./logs/test/
```


## Tutorial

The documentation and tutorial notebooks are available at [here](https://klughammerlab.github.io/scDynOmics/html/index.html).


## Reference

If you use scDynOmics in your research, please consider citing our preprint:
> [**scDynOmics: An Optimized Transformer Model for Representation Learning from Single-Cell Multiomics**](https://www.biorxiv.org/content/10.64898/2026.02.28.708160v1)  
> Gang Yu, Timothy J.S. Ramnarine, Johanna Klughammer, Simon W. Mages. bioRxiv 2026.

```bibtex
@misc{yu2026scdynomics,
  title={scDynOmics: An Optimized Transformer Model for Representation Learning from Single-Cell Multiomics},
  author={Yu, Gang and Ramnarine, Timothy J. S. and Klughammer, Johanna and Mages, Simon W.},
  year={2026},
  publisher={bioRxiv},
  url={https://doi.org/10.64898/2026.02.28.708160},
  doi={10.64898/2026.02.28.708160}
}
```
