Predicting human microbe-drug associations based on graph attention network

Published on Feb. 28, 2024Total Views: 354 times Total Downloads: 135 times Download Mobile

Author: SHI Sairu ¹ KONG Shu ²  ZHANG Ji ¹

Affiliation: 1. School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang 471023, Henan Province, China 2. School of Science, Beijing University of Civil Engineering and Architecture, Beijing 102616, China

Keywords: Microbe-drug associations Multiple kernel fusion Graph attention network Heterogeneous network Cross validation

DOI: 10.12173/j.issn.1004-4337.202309229

Reference: Shi SR, Kong S, Zhang J. Predicting human microbe-drug associations based on graph attention network[J]. Journal of Mathematical Medicine, 2024, 37(2): 81-90. DOI: 10.12173/j.issn.1004-4337.202309229[Article in Chinese]  Copied

Abstract
Full-text
References

Abstract

Objective Graph attention network (GAT) was used to predict the potential association between human microbes and drugs.

Methods Three commonly used microbe-drug associations (MDA) datasets including MDAD, aBiofilm and Drug Virus were selected. Based on the rich biological information in the datasets, a heterogeneous network was constructed and a GAT-based framework for predicting MDA called GATMDA was proposed, which was used to predict the association between microbes and drugs.

Results Compared with the existing eight prediction methods, GATMDA had better prediction effect on three datasets through three cross-validation methods. During the performance evaluation of 5-fold cross-validation on three datasets, the area under the curve (AUC) were 0.988 6, 0.994 1, and 0.983 6, respectively, and the area under the precision-recall curve (AUPR) were 0.966 7, 0.986 9 and 0.879 5. The effectiveness of GATMDA in predicting MDA was further validated through case studies.

Conclusion Based on GAT, the GATMDA model can effectively predict MDA through the constructed heterogeneous network.

Full-text

Please download the PDF version to read the full text: download

References

1.Sommer F, Bäckhed F. The gut microbiota--masters of host development and physiology[J]. Nat Rev Microbiol, 2013, 11(4): 227-238. DOI: 10.1038/nrmicro2974.

2.David LA, Maurice CF, Carmody RN, et al. Diet rapidly and reproducibly alters the human gut microbiome[J]. Nature, 2014, 505(7584): 559-563. DOI: 10.1038/nature12820.

3.Davenport ER, Mizrahi-Man O, Michelini K, et al. Seasonal variation in human gut microbiome composition[J]. PloS One, 2014, 9(3): e90731. DOI: 10.1371/journal.pone.0090731.

4.Donia MS, Cimermancic P, Schulze CJ, et al. A systematic analysis of biosynthetic gene clusters in the human microbiome reveals a common family of antibiotics[J]. Cell, 2014, 158(6): 1402-1414. DOI: 10.1016/j.cell.2014.08.032.

5.Williamson R, Hakenbeck R, Tomasz A. In vivo interaction of beta-lactam antibiotics with the penicillin-binding proteins of streptococcus pneumoniae[J]. Antimicrob Agents Chemother, 1980, 18(4): 629-637. DOI: 10.1128/AAC.18.4.629.

6.Kovac J, Kovac D, Slobodnikova L, et al. Enterococcus faecalis and Candida albicans in the dental root canal and periapical infections[J]. Bratisl Lek Listy, 2013, 114(12): 716-720. DOI: 10.4149/bll_2013_151.

7.Szczuka E, Jabłońska L, Kaznowski A. Effect of subinhibitory concentrations of tigecycline and ciprofloxacin on the expression of biofilm-associated genes and biofilm structure of staphylococcus epidermidis[J]. Microbiology (Reading), 2017, 163(5): 712-718. DOI: 10.1099/mic.0.000453.

8.Sharma AK, Jaiswal SK, Chaudhary N, et al. A novel approach for the prediction of species-specific biotransformation of xenobiotic/drug molecules by the human gut microbiota[J]. Sci Rep, 2017, 7(1): 9751. DOI: 10.1038/s41598-017-10203-6.

9.杨煜清. 基于层次贝叶斯模型的微生物关联网络推断方法研究[D]. 北京: 清华大学, 2019. [Yang YQ. Study of methods of microbial association network inference based on hierarchical Bayesian model[D]. Beijing: Tsinghua University, 2019.] DOI: 10.27266/d.cnki.gqhau.2019.000405.

10.Zhu LZ, Duan GH, Yan C, et al. Prediction of microbe-drug associations based on chemical structures and the KATZ measure[J]. Current Bioinformatics, 2021, 16(6): 807-819. DOI: 10.2174/1574893616666210204144721.

11.Long Y, Wu M, Kwoh CK, et al. Predicting human microbe-drug associations via graph convolutional network with conditional random field[J]. Bioinformatics, 2020, 36(19): 4918-4927. DOI: 10.1093/bioinformatics/btaa598.

12.于诗睿, 李爱花, 林紫洛, 等. 基于异构网络的相关数据挖掘任务研究综述[J]. 医学信息学杂志, 2023, 44(4): 28-34. [Yu SR, Li AH, Lin ZL, et al. A review of related data mining tasks based on heterogeneous networks[J]. Journal of Medical Intelligence, 2023, 44(4): 28-34.] DOI: 10.3969/j.issn.1673-6036.2023.04.005.

13.Wang W, Chen H. Predicting miRNA-disease associations based on graph attention networks and dual Laplacian regularized least squares[J]. Brief Bioinform, 2022, 23(5): bbac292. DOI: 10.1093/bib/bbac292.

14.龙亚辉. 基于图机器学习的微生物网络关系预测算法研究[D]. 长沙: 湖南大学, 2022. [Long YH. Graph-based machine learning algorithms for microbe network prediction[D]. Changsha: Hunan University, 2022.] DOI: 10.27135/d.cnki.ghudu.2021.001004.

15.Chen X, Huang YA, You ZH, et al. A novel approach based on KATZ measure to predict associations of human microbiota with non-infectious diseases[J]. Bioinformatics, 2017, 33(5): 733-739. DOI: 10.1093/bioinformatics/btw715.

16.Mei JP, Kwoh CK, Yang P, et al. Drug-target interaction prediction by learning from local information and neighbors[J]. Bioinformatics, 2013, 29(2): 238-245. DOI: 10.1093/bioinformatics/bts670.

17.Cui XH, Qu XL, Li DM, et al. MKGCN: multi-modal knowledge graph convolutional network for music recommender systems[J]. Electronics, 2023, 12(12): 2688. DOI: 10.3390/electronics12122688.

18.Tian Z, Yu Y, Fang H, et al. Predicting microbe-drug associations with structure-enhanced contrastive learning and self-paced negative sampling strategy[J]. Brief Bioinform, 2023, 24(2): bba634. DOI: 10.1093/bib/bbac634.

19.Griffith BP, Brett-Smith H, Kim G, et al. Effect of stavudine on human immunodeficiency virus type 1 virus load as measured by quantitative mononuclear cell culture, plasma RNA, and immune complex-dissociated antigenemia[J]. J Infect Dis, 1996, 173(5): 1252-1255. DOI: 10.1093/infdis/173.5.1252.

20.Mink M, Mosier SM, Janumpalli S, et al. Impact of human immunodeficiency virus type 1 gp41 amino acid substitutions selected during enfuvirtide treatment on gp41 binding and antiviral potency of enfuvirtide in vitro[J]. J Virol, 2005, 79(19): 12447-12454. DOI: 10.1128/JVI.79.19.12447-12454.2005.

21.Aggarwal N, Kitano S, Puah GRY, et al. Microbiome and human health: current understanding, engineering, and enabling technologies[J]. Chem Rev, 2023, 123(1): 31-72. DOI: 10.1021/acs.chemrev.2c00431.

22.Madhukar NS, Khade PK, Huang L, et al. A Bayesian machine learning approach for drug target identification using diverse data types[J]. Nat Commun, 2019, 10(1): 5221. DOI: 10.1038/s41467-019-12928-6.

23.Zhang ZC, Zhang XF, Wu M, et al. A graph regularized generalized matrix factorization model for predicting links in biomedical bipartite networks[J]. Bioinformatics, 2020, 36(11): 3474-3481. DOI: 10.1093/bioinformatics/btaa157.

24.Li Z, Wang X, Li J, et al. Deep attributed network representation learning of complex coupling and interaction[J]. Knowl. Based Syst, 2021, 212: 106618. DOI: 10.1016/j.knosys.2020.106618.

25.Gönen M, Alpaydin E. Multiple kernel learning algorithms[J]. Journal of Machine Learning Research, 2011, 12(64): 2211-2268. DOI: 10.5555/1953048.2021071.