MindRank-Biotech / PharmKG

PharmKG

The code for the paper: PharmKG -- A Dedicated Knowledge Graph Benchmark for Biomedical Data Mining

The code was partly built based on Pykeen and KG-reeval. Thanks a lot for their code sharing!

Copyright

The initial development was made by Aladdin Healthcare Technologies Ltd., Sun Yat-sen University and Mind Rank AI. All Rights Reserved.

Overview

PharmKG is a multi-relational, attributed biomedical knowledge graph, comsed of more than 500 thousands individual interconnectons between genes, drugs and diseases, with 29 relation types over a vocabulary of ~8000 disambiguated entites.

PharmKG Dataset

Raw dataset of PharmKG was hosted on zenodo. And in the experiments we used the cleaned PharmKG-8K dataset. The detailed information can be found in PharmKG_original.zip

Dataset summary

Dataset	Train	Test	Valid	Entities	Triplets
PharmKG-8k	400788	49536	50036	7601	500958
PharmKG-Raw	-	-	-	188296	1093236

Entities distribution

Type	DrugBank	TTD	OMIM	PharmGKB	GNBR	PharmKG
Chemical	1208	1347	-	615	1442	1497
Disease	-	399	987	419	1001	1346
Gene	1166	741	2320	1674	4716	4758

Performance on PharmKG

Category	Model		Hits@N
		MRR	N=1	N=3	N=10	N=100
Distance-Based	TransE	0.091	0.034	0.092	0.198	0.524
	TransR	0.075	0.030	0.071	0.155	0.510
Semantic Matching	RESCAL	0.064	0.023	0.057	0.122	0.413
	ComplEx	0.107	0.046	0.110	0.225	0.552
	Distmult	0.063	0.024	0.058	0.133	0.461
Neural Network	ConvE	0.086	0.038	0.087	0.169	0.425
	ConvKB	0.106	0.052	0.107	0.209	0.548
	RGCN	0.067	0.027	0.062	0.139	0.236
Proposed	HRGAT –w/o	0.138	0.068	0.148	0.275	0.586
	HRGAT	0.154	0.075	0.172	0.315	0.649

Manual

Installation

Under the "PharmKG-D/model/pykeen/pykeen" directory, type python setup.py install --user to compile the pykeen package.

Data Preprocessing

Run code python PharmKG-D/data/preprocess.py

The data for the preprocess.py can be found here

The embedding data can be found here

Competitive Models

Model in Pykeen

TransE, TransR, DistMult, ComplEx, RESCAL

Training

Run code python PharmKG-D/model/pykeen/train.py --model <model_name> --save_path <path> under the root directory of this repository. <model_name> is name of the model you are going to train. <path> is the path to a json file containing the output results.

Neural network-based Model

ConvE, ConvKB, HRGAT

Training

Model training can be started by running the following scripts:

ConvE:

sh PharmKG-D/model/ConvE/run.sh

ConvKB:

sh PharmKG-D/model/ConvKB/run.sh

HRGAT:

sh PharmKG-D/model/HRGAT/run.sh