Metadata-Version: 2.2
Name: FGOT
Version: 0.0.9
Summary: FGOT is a tool for uncovering cellular heterogeneity and their associated transcriptional regulatory links.
Home-page: https://github.com/YCH-bioinf/FGOT-master
Author: Yang Chenghui
Author-email: 2022282110116@whu.edu.cn
License: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
Requires-Dist: anndata==0.10.8
Requires-Dist: gudhi==3.9.0
Requires-Dist: hnswlib==0.8.0
Requires-Dist: networkx==3.2.1
Requires-Dist: numpy==1.26.4
Requires-Dist: pandas==2.2.3
Requires-Dist: scanpy==1.10.2
Requires-Dist: scikit_learn==1.5.1
Requires-Dist: scipy==1.12.0
Requires-Dist: torch==2.5.1
Requires-Dist: tqdm==4.66.2
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: summary

# FGOT-master

## Overview

Integrating single-cell or spatial transcriptomic and epigenomic data enables scrutinizing the transcriptional regulatory mechanisms controlling cell fate.  In current methods, multi-omics measurements are projected into a shared latent space, without connecting transcriptomic and epigenomic features, such as target genes and their regulatory elements, and in addition, the cell-type specific regulatory mechanism are often missing. To address both problems, we develop a Feature Guided Optimal Transport (FGOT) method, which allows incorporation prior knowledge of genes and their regulatory elements relationship, to simultaneously uncover cellular heterogeneity and their associated transcriptional regulatory links. Benchmarking on simulation data and validating via histone modification data or 3D genomics data for matched real data show good robustness and accuracy in integration and inference of regulatory links. From both paired and unpaired multi-omics data, it is found that for the same gene different type of cells have different regulatory relationship. Application of FGOT to paired spatial multi-omics data show spatial differences in regulatory links for the same gene. The method allows systematic screening of more specific regulatory elements in diseases at single-cell level.

## Installation
It's recommended to create a separate conda environment for running FGOT:
```
#create an environment called env_FGOT
conda create -n env_FGOT python=3.10

#activate your environment
conda activate env_FGOT
```
We provide two optional strategies to install FGOT.

The first way is to install it locally. First clone the repository.
```
git clone https://github.com/YCH-bioinf/FGOT-master.git
cd FGOT-master
```
Then package the required packages and install them locally.
```
pip install pybind11
python setup.py sdist bdist_wheel
python setup.py install
pip3 install dist/FGOT-0.0.8-py3-none-any.whl  --force-reinstall
```
The second installed way is by `pip`.
```
pip install FGOT
```


## Data
All datasets used in this study are already published and were obtained from public data repositories. Simulated datasets 1 and 2 were two batches of scRNA-seq with batch effects generated by the R package 'Splatter'. The PBMC data was published on https://support.10xgenomics.com/single-cell-multiome-atac-gex/datasets/1.0.0/pbmc_granulocyte_sorted_10k?. The BMMC data was obtained from the GEO repository (accession no. GSE159417). The spatial-ATAC-RNA-seq mouse brain data was from https://cells.ucsc.edu/?ds=brain-spatial-omics.

The details of all datasets used are available in the Methods section. The data used in our experiments have been uploaded and are freely available at https://drive.google.com/drive/folders/1H3GLroILCYSaGjowwJUjaO4JlKcNDdvy.

## Tutorial
For the step-by-step tutorials, we have released them at https://github.com/YCH-bioinf/FGOT-master/tree/main/examples.


## Support
If you have any questions, please feel free to contact us zhanglh@whu.edu.cn.

## Citation

