MintFlow (Microenvironment-induced and INtrinsic Transcriptomic FLOWs) is a package to generate disentangled microenvironment-induced and intrinsic gene expression vectors from spatial transcriptomics data. It interoperates with the scverse ecosystem to enable seamless analysis workflows of spatial transcriptomics data.

Installation

Install MintFlow via pip:

pip install mintflow

For more detailed instructions, visit our documentation.

It's highly recommended to setup wandb when training your own MintFlow models.

To do so:

• Go to wandb and create an account.
• Create a project called "MintFlow".

Resources

• An installation guide, tutorials and API documentation is available in the documentation.
• Please use issues to submit bug reports.
• If you would like to contribute, check out the contributing guide.
• If you find MintFlow useful for your research, please consider citing the MintFlow manuscript.

Reference

@article{Akbarnejad2025,
  author    = {Akbarnejad, A. et al.},
  title     = {Mapping and reprogramming microenvironment-induced cell states in human disease using generative AI},
  journal   = {bioRxiv},
  year      = {2025},
  doi       = {10.1101/2025.06.24.661094},
  url       = {https://doi.org/10.1101/2025.06.24.661094}
}