liuchuwei / pglcn

PGLCN

Biological informed graph neural network for tumor mutation burden prediction and immunotherapy-related pathway analysis in gastric cancer

Table of Contents

1. Getting Started
   • Prerequisites
   • Installation
2. Usage
3. References
4. License
5. Contact

Getting Started

Prerequisites

• check environments.yml for list of needed packages

Installation

1. Clone the repo

   git clone https://github.com/liuchuwei/PGLCN.git

2. Create conda environment

   conda env create -f environment.yml

3. Based on your use, you may need to download one or more of the following
   a. Data files
   b. Log files
   c. NoteBook

Usage

1. Activate the created conda environment

   source activate PGLCN

2. Train model: you can train a new model or use --project args to reproduct the model mentioned in: "Biological informed graph neural network for tumor mutation burden prediction and immunotherapy-related pathway analysis in gastric cancer"

   python pglcn.py train --project pretrain_stad

3. Explain model

   python pglcn.py explain --project stad_pglcn

License

Distributed under the GPL-2.0 License License. See LICENSE for more information.

Contact

[email protected]

References

Biological informed graph neural network for tumor mutation burden prediction and immunotherapy-related pathway analysis in gastric cancer, Computational and Structural Biotechnology Journal, Volume 21, 2023, Pages 4540-4551, ISSN 2001-0370, https://doi.org/10.1016/j.csbj.2023.09.021.