scRegulate 0.1.4

Python Toolkit for Transcription Factor Activity Inference and Clustering of scRNA-seq Data

scRegulate

Single-Cell Regulatory-Embedded Variational Inference of Transcription Factor Activity from Gene Expression

Introduction

scRegulate is a powerful tool designed for the inference of transcription factor activity from single cell/nucleus RNA data using advanced generative modeling techniques. It leverages a unified learning framework to optimize the modeling of cellular regulatory networks, providing researchers with accurate insights into transcriptional regulation. With its efficient clustering capabilities, scRegulate facilitates the analysis of complex biological data, making it an essential resource for studies in genomics and molecular biology.

For further information and example tutorials, please check our documentation.

If you have any questions or concerns feel free to open an issue.

Requirements

scRegulate is implemented in the PyTorch framework. Running scRegulate on CUDA is highly recommended if available.

Before installing and running scRegulate, ensure you have the following libraries installed:

• PyTorch (version 2.0 or higher)
• NumPy (version 1.23 or higher)
• Scanpy (version 1.9 or higher)
• Anndata (version 0.8 or higher)

You can install these dependencies using pip:

pip install torch numpy scanpy anndata

Installation

You can install scRegulate via pip for a lightweight installation:

pip install scRegulate

Alternatively, if you want the latest, unreleased version, you can install it directly from the source on GitHub:

pip install git+https://github.com/YDaiLab/scRegulate.git

For users who prefer Conda or Mamba for environment management, you can install scRegulate along with extra dependencies using:

mamba create -n=scRegulate conda-forge::scRegulate

License

The code in scRegulate is licensed under the MIT License, which permits academic and commercial use, modification, and distribution.

Please note that any third-party dependencies bundled with scRegulate may have their own respective licenses.

Citation

scRegulate manuscript is currently under peer review.

If you use scRegulate in your research, please cite:

Mehrdad Zandigohar, Jalees Rehman and Yang Dai (2025). scRegulate: Single-Cell Regulatory-Embedded Variational Inference of Transcription Factor Activity from Gene Expression, Bioinformatics Journal (under review). [DOI link here]

📄 Read the preprint on bioRxiv: 10.1101/2025.04.17.649372