MGRL: Predicting Drug-Disease Associations Based on Multi-Graph Representation Learning

Overview

Journal Front Genet

Date 2021 May 31

PMID 34054920

Citations 6

Authors

Bo-Wei Zhao

Zhu-Hong You

Leon Wong

Ping Zhang

Hao-Yuan Li

Lei Wang

Affiliations

Soon will be listed here.

Abstract

Drug repositioning is an application-based solution based on mining existing drugs to find new targets, quickly discovering new drug-disease associations, and reducing the risk of drug discovery in traditional medicine and biology. Therefore, it is of great significance to design a computational model with high efficiency and accuracy. In this paper, we propose a novel computational method MGRL to predict drug-disease associations based on multi-graph representation learning. More specifically, MGRL first uses the graph convolution network to learn the graph representation of drugs and diseases from their self-attributes. Then, the graph embedding algorithm is used to represent the relationships between drugs and diseases. Finally, the two kinds of graph representation learning features were put into the random forest classifier for training. To the best of our knowledge, this is the first work to construct a multi-graph to extract the characteristics of drugs and diseases to predict drug-disease associations. The experiments show that the MGRL can achieve a higher AUC of 0.8506 based on five-fold cross-validation, which is significantly better than other existing methods. Case study results show the reliability of the proposed method, which is of great significance for practical applications.

Citing Articles

Herb-disease association prediction model based on network consistency projection.

Chen L, Zhang S, Zhou B Sci Rep. 2025; 15(1):3328.

PMID: 39865145 PMC: 11770172. DOI: 10.1038/s41598-025-87521-7.

Label Transfer for Drug Disease Association in Three Meta-Paths.

Dao N, Le M, Dang X Evol Bioinform Online. 2024; 20:11769343241272414.

PMID: 39279816 PMC: 11401013. DOI: 10.1177/11769343241272414.

Exploring potential circRNA biomarkers for cancers based on double-line heterogeneous graph representation learning.

Zhang Y, Wang Z, Wei H, Chen M BMC Med Inform Decis Mak. 2024; 24(1):159.

PMID: 38844961 PMC: 11157868. DOI: 10.1186/s12911-024-02564-6.

RLFDDA: a meta-path based graph representation learning model for drug-disease association prediction.

Zhang M, Zhao B, Su X, He Y, Yang Y, Hu L BMC Bioinformatics. 2022; 23(1):516.

PMID: 36456957 PMC: 9713188. DOI: 10.1186/s12859-022-05069-z.

Prediction of drug-drug interaction events using graph neural networks based feature extraction.

Al-Rabeah M, Lakizadeh A Sci Rep. 2022; 12(1):15590.

PMID: 36114278 PMC: 9481536. DOI: 10.1038/s41598-022-19999-4.

References

Li J, Lu Z . A New Method for Computational Drug Repositioning Using Drug Pairwise Similarity. Proceedings (IEEE Int Conf Bioinformatics Biomed). 2014; 2012:1-4. PMC: 4175719. DOI: 10.1109/BIBM.2012.6392722. View

Jiang H, Huang Y, You Z . SAEROF: an ensemble approach for large-scale drug-disease association prediction by incorporating rotation forest and sparse autoencoder deep neural network. Sci Rep. 2020; 10(1):4972. PMC: 7080766. DOI: 10.1038/s41598-020-61616-9. View

Jarada T, Rokne J, Alhajj R . A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions. J Cheminform. 2021; 12(1):46. PMC: 7374666. DOI: 10.1186/s13321-020-00450-7. View

Law V, Knox C, Djoumbou Y, Jewison T, Guo A, Liu Y . DrugBank 4.0: shedding new light on drug metabolism. Nucleic Acids Res. 2013; 42(Database issue):D1091-7. PMC: 3965102. DOI: 10.1093/nar/gkt1068. View

Yi H, You Z, Huang D, Guo Z, Chan K, Li Y . Learning Representations to Predict Intermolecular Interactions on Large-Scale Heterogeneous Molecular Association Network. iScience. 2020; 23(7):101261. PMC: 7317230. DOI: 10.1016/j.isci.2020.101261. View

Luo H, Li M, Wang S, Liu Q, Li Y, Wang J . Computational drug repositioning using low-rank matrix approximation and randomized algorithms. Bioinformatics. 2018; 34(11):1904-1912. DOI: 10.1093/bioinformatics/bty013. View

Luo H, Wang J, Li M, Luo J, Peng X, Wu F . Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm. Bioinformatics. 2016; 32(17):2664-71. DOI: 10.1093/bioinformatics/btw228. View

Amaratunga D, Cabrera J, Lee Y . Enriched random forests. Bioinformatics. 2008; 24(18):2010-4. DOI: 10.1093/bioinformatics/btn356. View

Chen Z, You Z, Guo Z, Yi H, Luo G, Wang Y . Prediction of Drug-Target Interactions From Multi-Molecular Network Based on Deep Walk Embedding Model. Front Bioeng Biotechnol. 2020; 8:338. PMC: 7283956. DOI: 10.3389/fbioe.2020.00338. View

10.

Yella J, Yaddanapudi S, Wang Y, Jegga A . Changing Trends in Computational Drug Repositioning. Pharmaceuticals (Basel). 2018; 11(2). PMC: 6027196. DOI: 10.3390/ph11020057. View

11.

Yi H, You Z, Guo Z . Construction and Analysis of Molecular Association Network by Combining Behavior Representation and Node Attributes. Front Genet. 2019; 10:1106. PMC: 6854842. DOI: 10.3389/fgene.2019.01106. View

12.

Gottlieb A, Stein G, Ruppin E, Sharan R . PREDICT: a method for inferring novel drug indications with application to personalized medicine. Mol Syst Biol. 2011; 7:496. PMC: 3159979. DOI: 10.1038/msb.2011.26. View

13.

Liang X, Zhang P, Yan L, Fu Y, Peng F, Qu L . LRSSL: predict and interpret drug-disease associations based on data integration using sparse subspace learning. Bioinformatics. 2017; 33(8):1187-1196. DOI: 10.1093/bioinformatics/btw770. View

14.

Xuan P, Cao Y, Zhang T, Wang X, Pan S, Shen T . Drug repositioning through integration of prior knowledge and projections of drugs and diseases. Bioinformatics. 2019; 35(20):4108-4119. DOI: 10.1093/bioinformatics/btz182. View

15.

Yue X, Wang Z, Huang J, Parthasarathy S, Moosavinasab S, Huang Y . Graph embedding on biomedical networks: methods, applications and evaluations. Bioinformatics. 2019; 36(4):1241-1251. PMC: 7703771. DOI: 10.1093/bioinformatics/btz718. View

16.

Zhang P, Wang F, Hu J . Towards drug repositioning: a unified computational framework for integrating multiple aspects of drug similarity and disease similarity. AMIA Annu Symp Proc. 2015; 2014:1258-67. PMC: 4419869. View

17.

Guo Z, You Z, Yi H . Integrative Construction and Analysis of Molecular Association Network in Human Cells by Fusing Node Attribute and Behavior Information. Mol Ther Nucleic Acids. 2020; 19:498-506. PMC: 6951835. DOI: 10.1016/j.omtn.2019.10.046. View

18.

Zickenrott S, Angarica V, Upadhyaya B, del Sol A . Prediction of disease-gene-drug relationships following a differential network analysis. Cell Death Dis. 2016; 7:e2040. PMC: 4816176. DOI: 10.1038/cddis.2015.393. View

19.

Li J, Zhang S, Liu T, Ning C, Zhang Z, Zhou W . Neural inductive matrix completion with graph convolutional networks for miRNA-disease association prediction. Bioinformatics. 2020; 36(8):2538-2546. DOI: 10.1093/bioinformatics/btz965. View

20.

Li J, Zheng S, Chen B, Butte A, Swamidass S, Lu Z . A survey of current trends in computational drug repositioning. Brief Bioinform. 2015; 17(1):2-12. PMC: 4719067. DOI: 10.1093/bib/bbv020. View