This is our implementation for the paper

Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma and Xiangxiang Zeng. KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction. IJCAI' 20 accepted.

To run the code, you need the following dependencies:

• Python == 3.6.6
• Keras == 2.3.0
• Tensorflow == 1.13.1
• scikit-learn == 0.22

You can create a virtual environment using conda.

conda create -n kgnn python=3.6.6  
source activate kgnn  
git clone https://github.com/xzenglab/KGNN.git  
cd KGNN  
pip install -r requirement.txt  

We just provide the preprocessed KG from KEGG dataset owing to the size limited. Please feel free contact us if you need the KG from DrugBank dataset (V5.1.4). The construction of KG please refer to Bio2RDF tool in detail.

python run.py

(To appear)

For any clarification, comments, or suggestions please create an issue or contact Jacklin.