Journal
BRIEFINGS IN BIOINFORMATICS
Volume 23, Issue 4, Pages -Publisher
OXFORD UNIV PRESS
DOI: 10.1093/bib/bbac266
Keywords
metabolite; disease; metabolite-disease associations; graph attention network; graph convolutional network
Funding
- National Natural Science Foundation of China [11805091]
- Foundation of Education Department of Liaoning Province [LJKZ0280]
Ask authors/readers for more resources
Metabolism is the process of replacing old substances with new substances in organisms, which is important for maintaining human life, body growth, and reproduction. Researchers have found that the concentrations of certain metabolites in patients are different from those in healthy individuals. Traditional biological experiments are time-consuming and costly, so there is an urgent need for a new computational method to identify the relationships between metabolites and diseases. In this study, a new deep learning algorithm called GCNAT is proposed to predict potential associations between disease-related metabolites. The algorithm achieves better results than existing predictive methods and can be a useful tool for biomedical research in the future.
Metabolism is the process by which an organism continuously replaces old substances with new substances. It plays an important role in maintaining human life, body growth and reproduction. More and more researchers have shown that the concentrations of some metabolites in patients are different from those in healthy people. Traditional biological experiments can test some hypotheses and verify their relationships but usually take a considerable amount of time and money. Therefore, it is urgent to develop a new computational method to identify the relationships between metabolites and diseases. In this work, we present a new deep learning algorithm named as graph convolutional network with graph attention network (GCNAT) to predict the potential associations of disease-related metabolites. First, we construct a heterogeneous network based on known metabolite-disease associations, metabolite-metabolite similarities and disease-disease similarities. Metabolite and disease features are encoded and learned through the graph convolutional neural network. Then, a graph attention layer is used to combine the embeddings of multiple convolutional layers, and the corresponding attention coefficients are calculated to assign different weights to the embeddings of each layer. Further, the prediction result is obtained by decoding and scoring the final synthetic embeddings. Finally, GCNAT achieves a reliable area under the receiver operating characteristic curve of 0.95 and the precision-recall curve of 0.405, which are better than the results of existing five state-of-the-art predictive methods in 5-fold cross-validation, and the case studies show that the metabolite-disease correlations predicted by our method can be successfully demonstrated by relevant experiments. We hope that GCNAT could be a useful biomedical research tool for predicting potential metabolite-disease associations in the future.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available