Metadata-Version: 2.1
Name: regdiffusion
Version: 0.0.1
Summary: Gene Regulatory Networks Inference using diffusion model
Author-email: Hao Zhu <haozhu233@gmail.com>, Donna Slonim <donna.slonim@tufts.edu>
Maintainer-email: Hao Zhu <haozhu233@gmail.com>
Description-Content-Type: text/markdown
Classifier: License :: OSI Approved :: Apache Software License
Requires-Dist: numpy>=1.16.5
Requires-Dist: pandas>=1.1.1
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: scanpy
Requires-Dist: scikit-learn
Project-URL: Home, https://github.com/TuftsBCB/RegDiffusion

# RegDiffusion: Probabilistic Diffusion-Based Neural Inference of Gene Regulatory Networks

Welcome to the official repository for RegDiffusion, an innovative and high-performance approach for inferring Gene Regulatory Networks (GRNs) from single-cell RNA sequencing data. RegDiffusion leverages the principles of Denoising Diffusion Probabilistic Models to predict regulatory interactions with lifted performance and efficiency.

The details of RegDiffusion is described in the following paper. 

```
From Noise to Knowledge: Probabilistic Diffusion-Based Neural Inference of Gene Regulatory Networks
Hao Zhu, Donna K. Slonim
bioRxiv 2023.11.05.565675; doi: https://doi.org/10.1101/2023.11.05.565675
```

## Installation

## Getting Started

## Citation
