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

MIDAS turns mosaic data into imputed and batch-corrected data to support single-cell multimodal analysis.

Read our paper at Mosaic integration and knowledge transfer of single-cell multimodal data with MIDAS.

Read our documentation at https://scmidas.readthedocs.io/en/latest/.

Installation

conda create -n scmidas python=3.12
conda activate scmidas
conda install scmidas

or:

pip install scmidas

🔥New

• MIDAS supports not only RNA, ADT, and ATAC data but also allows seamless integration of additional modalities with straightforward configuration.
• Leverages PyTorch Lightning for efficient training, including advanced strategies such as distributed data parallel (DDP).
• Integrates with TensorBoard for real-time visualization and tracking of training metrics, such as loss.

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}
}