Metadata-Version: 2.1
Name: scmidas
Version: 0.0.15
Summary: A torch-based integration method for single-cell multi-omic data.
Author-email: labomics <omicshub@outlook.com>
Project-URL: Homepage, https://github.com/labomics/midas
Project-URL: Issues, https://github.com/labomics/midas/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: toml
Requires-Dist: tqdm
Requires-Dist: numpy
Requires-Dist: torch >1.12
Requires-Dist: matplotlib
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: scanpy
Requires-Dist: louvain
Requires-Dist: rpy2
Requires-Dist: anndata2ri

# MIDAS: a deep generative model for mosaic integration and knowledge transfer of single-cell multimodal data.

![image](./src/midas.png)
MIDAS is a deep generative model designed for mosaic integration, facilitating the integration of RNA, ADT, and ATAC data across batches. 


Read our documentation at https://scmidas.readthedocs.io/en/latest/. We provide **tutorials** in the documentation.


## Installation

```bash
git clone https://github.com/labomics/midas.git
cd midas
conda create -n scmidas python=3.9
conda activate scmidas
pip install scmidas
```

Optional packages:

```bash
pip install ipykernel jupyter
```

## Reproducibility

Refer to https://github.com/labomics/midas/tree/reproducibility.

## Citation

If you use MIDAS in your work, please cite the midas publication as follows:
```
@article{he2024mosaic,
  title={Mosaic integration and knowledge transfer of single-cell multimodal data with MIDAS},
  author={He, Zhen and Hu, Shuofeng and Chen, Yaowen and An, Sijing and Zhou, Jiahao and Liu, Runyan and Shi, Junfeng and Wang, Jing and Dong, Guohua and Shi, Jinhui and others},
  journal={Nature Biotechnology},
  pages={1--12},
  year={2024},
  publisher={Nature Publishing Group US New York}
}
```
