KGNN / Git / Diff of /README.md

Models:

Amanda-D/

KGNN

Downloads: 1

Diff of /README.md [c0da92] .. [21b321]

Switch to unified view


# Knowledge Graph Neural Network
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.

<img align="center" src="https://github.com/xzenglab/KGNN/blob/master/Figure1.png?raw=true">
Figure 1 shows the overview of KGNN. It takes the parsed DDI matrix and knowledge graph obtained from preprocessing of dataset as the input. It outputs the interaction value for the drug-drug pair. 

# Requirement
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

# Installation
You can create a virtual environment using [conda](https://github.com/conda/conda).
```bash
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  
```

# Dataset
We just provide the preprocessed KG from KEGG-drug dataset owing to the size limited. And you can directly download the original DrugBank dataset ([V5.1.4](https://www.drugbank.ca/releases/5-1-4)). Note that the construction of KG please refer to [Bio2RDF](https://github.com/bio2rdf/bio2rdf-scripts/wiki) tool in detail.

# Usage
```bash
python run.py
```

# Citation
```bash
@inproceedings{ijcai2020-380,  
  title     = {KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction},  
  author    = {Lin, Xuan and Quan, Zhe and Wang, Zhi-Jie and Ma, Tengfei and Zeng, Xiangxiang},  
  booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}},  
  publisher = {International Joint Conferences on Artificial Intelligence Organization},               
  editor    = {Christian Bessiere},     
  pages     = {2739--2745},    
  year      = {2020},  
  month     = {7},  
  note      = {Main track},  
  doi       = {10.24963/ijcai.2020/380},  
  url       = {https://doi.org/10.24963/ijcai.2020/380},  
}  
```

For any clarification, comments, or suggestions please create an issue or contact [Jacklin](Jack_lin@hnu.edu.cn).

	a/README.md		b/README.md
1	# Knowledge Graph Neural Network	1	# Knowledge Graph Neural Network
2	This is our implementation for the paper	2	This is our implementation for the paper
3	> 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.	3	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.
4		4
5	<img align="center" src="Figure1.png">	5	<img align="center" src="https://github.com/xzenglab/KGNN/blob/master/Figure1.png?raw=true">
6	Figure 1 shows the overview of KGNN. It takes the parsed DDI matrix and knowledge graph obtained from preprocessing of dataset as the input. It outputs the interaction value for the drug-drug pair.	6	Figure 1 shows the overview of KGNN. It takes the parsed DDI matrix and knowledge graph obtained from preprocessing of dataset as the input. It outputs the interaction value for the drug-drug pair.
7		7
8	# Requirement	8	# Requirement
9	To run the code, you need the following dependencies:	9	To run the code, you need the following dependencies:
10	* Python == 3.6.6	10	* Python == 3.6.6
11	* Keras == 2.3.0	11	* Keras == 2.3.0
12	* Tensorflow == 1.13.1	12	* Tensorflow == 1.13.1
13	* scikit-learn == 0.22	13	* scikit-learn == 0.22
14		14
15	# Installation	15	# Installation
16	You can create a virtual environment using [conda](https://github.com/conda/conda).	16	You can create a virtual environment using [conda](https://github.com/conda/conda).
17	```bash	17	```bash
18	conda create -n kgnn python=3.6.6	18	conda create -n kgnn python=3.6.6
19	source activate kgnn	19	source activate kgnn
20	git clone https://github.com/xzenglab/KGNN.git	20	git clone https://github.com/xzenglab/KGNN.git
21	cd KGNN	21	cd KGNN
22	pip install -r requirement.txt	22	pip install -r requirement.txt
23	```	23	```
24		24
25	# Dataset	25	# Dataset
26	We just provide the preprocessed KG from KEGG-drug dataset owing to the size limited. And you can directly download the original DrugBank dataset ([V5.1.4](https://www.drugbank.ca/releases/5-1-4)). Note that the construction of KG please refer to [Bio2RDF](https://github.com/bio2rdf/bio2rdf-scripts/wiki) tool in detail.	26	We just provide the preprocessed KG from KEGG-drug dataset owing to the size limited. And you can directly download the original DrugBank dataset ([V5.1.4](https://www.drugbank.ca/releases/5-1-4)). Note that the construction of KG please refer to [Bio2RDF](https://github.com/bio2rdf/bio2rdf-scripts/wiki) tool in detail.
27		27
28	# Usage	28	# Usage
29	```bash	29	```bash
30	python run.py	30	python run.py
31	```	31	```
32		32
33	# Citation	33	# Citation
34	```bash	34	```bash
35	@inproceedings{ijcai2020-380,	35	@inproceedings{ijcai2020-380,
36	title = {KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction},	36	title = {KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction},
37	author = {Lin, Xuan and Quan, Zhe and Wang, Zhi-Jie and Ma, Tengfei and Zeng, Xiangxiang},	37	author = {Lin, Xuan and Quan, Zhe and Wang, Zhi-Jie and Ma, Tengfei and Zeng, Xiangxiang},
38	booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}},	38	booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}},
39	publisher = {International Joint Conferences on Artificial Intelligence Organization},	39	publisher = {International Joint Conferences on Artificial Intelligence Organization},
40	editor = {Christian Bessiere},	40	editor = {Christian Bessiere},
41	pages = {2739--2745},	41	pages = {2739--2745},
42	year = {2020},	42	year = {2020},
43	month = {7},	43	month = {7},
44	note = {Main track},	44	note = {Main track},
45	doi = {10.24963/ijcai.2020/380},	45	doi = {10.24963/ijcai.2020/380},
46	url = {https://doi.org/10.24963/ijcai.2020/380},	46	url = {https://doi.org/10.24963/ijcai.2020/380},
47	}	47	}
48	```	48	```
49		49
50	For any clarification, comments, or suggestions please create an issue or contact [Jacklin](Jack_lin@hnu.edu.cn).	50	For any clarification, comments, or suggestions please create an issue or contact [Jacklin](Jack_lin@hnu.edu.cn).