Metadata-Version: 2.1
Name: CytoBulk
Version: 0.1.13
Summary: Integrating transcriptional data to decipher the tumor microenvironment with the graph frequency domain model
Home-page: https://github.com/kristaxying/CytoBulk
Author: Xueying WANG
Author-email: your_email@example.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anndata>=0.10.0
Requires-Dist: cellpose>=3.0.10
Requires-Dist: imageio
Requires-Dist: matplotlib
Requires-Dist: numpy>=1.23.0
Requires-Dist: openslide-python
Requires-Dist: ortools==9.3.10497
Requires-Dist: pandas>=2.2.0
Requires-Dist: Pillow
Requires-Dist: POT==0.9.5
Requires-Dist: rpy2>=3.5.0
Requires-Dist: scanpy
Requires-Dist: scikit-learn
Requires-Dist: scipy
Requires-Dist: seaborn
Requires-Dist: torch>2.1.0
Requires-Dist: torchvision
Requires-Dist: tqdm
Requires-Dist: requests
Requires-Dist: openslide-python
Requires-Dist: openslide-bin
Requires-Dist: scikit-image
Requires-Dist: igraph
Requires-Dist: leidenalg

# Overview
CytoBulk aims to Integrate transcriptional and image data to depict the tumor microenvironment accurately with the graph frequency domain model


# Documentation

To install and use CytoBulk, please visit https://kristaxying.github.io/CytoBulk/

# System requirements

We have tested the package on the following systems:
- Linux: Ubuntu 20 (GPU 3080)
- Windows: Windows 11 Enterprise (CPU)

# Installation Guide

Follow the steps below to install and set up **CytoBulk**.

---

## Setting Up the Environment for Python and R
The CytoBulk package is developed based on the pytorch framework and can be implemented on both GPU and CPU. We recommend running the package on GPU. Please ensure that pytorch and CUDNN are installed correctly.
### Option 1: Set Python and R Together
```
conda config --append channels conda-forge
conda create --name cytobulk python=3.10 r-base=4.4
conda activate cytobulk
pip install cytobulk
```
This approach is suitable for users who want all dependencies managed within the same Conda environment. However, it might **not work reliably on Windows** due to potential issues with R configuration in Conda.
### Option 2: Set Only Python and Specify R Path Separately

```
conda create --name cytobulk python=3.10
conda activate cytobulk
pip install cytobulk

```
Then, before running the main program, you need to specify the path to your locally installed R. This can be done using Python by setting the R_HOME environment variable. Add the following lines at the beginning of your Python script:
```
import os
# Set the R installation path (adjust the path based on your R installation)
os.environ['R_HOME'] = r_path
```
## Install required R packages

 To run **CytoBulk**, make sure all the following **prerequisites** are installed.


**R 4.4.0 or higher and the following packages** 

- Giotto (1.1.2) <https://giottosuite.readthedocs.io/en/master/gettingstarted.html>
- scran (1.32.0) <https://bioconductor.org/packages/release/bioc/html/scran.html>
- sva (3.52.0) <https://www.bioconductor.org/packages/release/bioc/html/sva.html>


# Run demo
Please visit Examples section at https://kristaxying.github.io/CytoBulk/.



### Maintainer
WANG Xueying xywang85-c@my.cityu.edu.hk

