GEDI-2

A high-performance, memory-efficient R package for integrating gene expression data from single-cell RNA sequencing experiments. GEDI 2.0 implements a unified generative model for interpretable latent embedding of multi-sample, multi-condition single-cell data.

See the full Documentation in the wiki page.

Python implementation of GEDI 2 is available at:
https://github.com/csglab/gedi2py

System Requirements

Installation

From CRAN (latest stable version)

The latest stable release is available on CRAN:

install.packages("gedi2")

From GitHub (latest version with minor fixes)

For the most up-to-date version, including minor fixes not yet on CRAN, install directly from GitHub:

# Install devtools if not already installed
install.packages("devtools")

# Install gedi from GitHub
# devtools::install_github("csglab/gedi2")
install.packages("gedi2", repos = c('https://csglab.r-universe.dev', 'https://cloud.r-project.org'))

Citation

If you use GEDI 2.0 in your research, please cite the original paper:

Mikaeili Namini, A., Saberi, A., & Najafabadi, H. S. (2026). Atlas-level single-cell integration and clustering-free differential expression analysis with GEDI 2.0. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag334

Reproducible Code

All reproducible code, scripts, and resources used in this project are available at: https://github.com/csglab/gedi2_manuscript

Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Submit a pull request

Reporting Issues

Report bugs and request features at: https://github.com/csglab/gedi2/issues

License

This project is licensed under the MIT License - see the LICENSE file for details.