Abstract
miRNAs are important regulators for many crucial biological processes. Many recent studies have shown that miRNAs are closely related to various human diseases and can be potential biomarkers or therapeutic targets for some diseases, such as cancers. Therefore, accurately predicting miRNA–disease associations is of great importance for understanding and curing diseases. However, how to efficiently utilize the characteristics of miRNAs and diseases and the information on known miRNA–disease associations for prediction is still not fully explored. In this study, we propose a novel computational method for predicting miRNA–disease associations. The proposed method combines the graph convolutional network and the hypergraph convolutional network. The graph convolutional network is utilized to extract the information from miRNA-similarity data as well as disease-similarity data. Based on the representations of miRNAs and diseases learned by the graph convolutional network, we further use the hypergraph convolutional network to capture the complex high-order interactions in the known miRNA–disease associations. We conduct comprehensive experiments with different datasets and predictive tasks. The results show that the proposed method consistently outperforms several other state-of-the-art methods. We also discuss the influence of hyper-parameters and model structures on the performance of our method. Some case studies also demonstrate that the predictive results of the method can be verified by independent experiments.
Graphical Abstract
Similar content being viewed by others
Data Availability
The code of the proposed method and the datasets are available at https://github.com/LiangXujun/CGHCN.
References
Saliminejad K, Khorram Khorshid HR, Soleymani Fard S et al (2019) An overview of micrornas: biology, functions, therapeutics, and analysis methods. J Cell Physiol 234:5451–5465. https://doi.org/10.1002/jcp.27486
Paul P, Chakraborty A, Sarkar D et al (2018) Interplay between mirnas and human diseases. J Cell Physiol 233:2007–2018. https://doi.org/10.1002/jcp.25854
Zhou S-S, Jin J-P, Wang J-Q et al (2018) mirnas in cardiovascular diseases: potential biomarkers, therapeutic targets and challenges. Acta Pharmacol Sin 39:1073–1084. https://doi.org/10.1038/aps.2018.30
Zhou S-S, Jin J-P, Wang J-Q et al (2014) Micrornas in cancer: biomarkers, functions and therapy. Trends Mol Med 20:460–469. https://doi.org/10.1016/j.molmed.2014.06.005
Zhou S-S, Jin J-P, Wang J-Q et al (2017) Mirna biogenesis and regulation of diseases: an overview. Methods Mol Biol 1509:1–10. https://doi.org/10.1007/978-1-4939-6524-3_1
Huang Z, Shi J, Gao Y et al (2019) Hmdd v3.0: a database for experimentally supported human microrna-disease associations. Nucleic Acids Res 47:1013–1017. https://doi.org/10.1093/nar/gky1010
Zhou S-S, Jin J-P, Wang J-Q et al (2017) A survey on database resources for microrna-disease relationships. Brief Funct Genomics 16:146–151. https://doi.org/10.1093/bfgp/elw015
Mahjoubin-Tehran M, Rezaei S, Jalili A et al (2021) A comprehensive review of online resources for microRNA–diseases associations: the state of the art. Briefings Bioinf 23(1):bbab381. https://doi.org/10.1093/bib/bbab381
Jiang Q, Hao Y, Wang G et al (2010) Prioritization of disease microRNAs through a human phenome-microRNAome network. BMC Syst Biol 4(Suppl 1):S2. https://doi.org/10.1186/1752-0509-4-s1-s2
Jiang Q, Hao Y, Wang G et al (2012) RWRMDA: predicting novel human microRNA–disease associations. Mol BioSyst 8(10):2792. https://doi.org/10.1039/c2mb25180a
Xuan P, Han K, Guo Y et al (2015) Prediction of potential disease-associated microRNAs based on random walk. Bioinformatics 31(11):1805–1815. https://doi.org/10.1093/bioinformatics/btv039
Xuan P, Dong Y, Guo Y et al (2019) An improved random forest-based computational model for predicting novel miRNA-disease associations. BMC Bioinf 20(1):624. https://doi.org/10.1186/s12859-019-3290-7
Jiang L, Ding Y, Tang J et al (2018) MDA-SKF: Similarity kernel fusion for accurately discovering miRNA-disease association. Front Genet 9:618. https://doi.org/10.3389/fgene.2018.00618
Chen X, Yin J, Qu J et al (2018) MDHGI: Matrix decomposition and heterogeneous graph inference for miRNA-disease association prediction. PLoS Comput Biol 14(8):1006418. https://doi.org/10.1371/journal.pcbi.1006418
Chen X, Li T-H, Zhao Y et al (2020) Deep-belief network for predicting potential miRNA-disease associations. Briefings Bioinf 22(3):bbaa186. https://doi.org/10.1093/bib/bbaa186
Xuan P, Dong Y, Guo Y et al (2018) Dual convolutional neural network based method for predicting disease-related miRNAs. Int J Mol Sci 19(12):3732. https://doi.org/10.3390/ijms19123732
Peng W, Che Z, Dai W et al (2022) Predicting miRNA-disease associations from miRNA-gene-disease heterogeneous network with multi-relational graph convolutional network model. IEEE/ACM Trans Comput Biol Bioinform 20(6):3363–3375. https://doi.org/10.1109/TCBB.2022.3187739
Wang C-C, Li T, Huang L et al (2022) Prediction of potential miRNA-disease associations based on stacked autoencoder. Briefings Bioinf 23(2):bbac021. https://doi.org/10.1093/bib/bbac021
Li J, Zhang S, Liu T et al (2020) Neural inductive matrix completion with graph convolutional networks for miRNA-disease association prediction. Bioinformatics 36(8):2538–2546. https://doi.org/10.1093/bioinformatics/btz965
Jin C, Shi Z, Lin K et al (2022) Predicting mirna-disease association based on neural inductive matrix completion with graph autoencoders and self-attention mechanism. Biomolecules 12(1):64. https://doi.org/10.3390/biom12010064
Li Z, Li J, Nie R et al (2021) A graph auto-encoder model for mirna-disease associations prediction. Briefings Bioinf 22(4):bbaa240. https://doi.org/10.1093/bib/bbaa240
Li L, Wang Y-T, Ji C-M et al (2021) GCAEMDA: Predicting miRNA-disease associations via graph convolutional autoencoder. PLoS Comput Biol 17(12):1009655. https://doi.org/10.1371/journal.pcbi.1009655
Ai N, Liang Y, Yuan H-L et al (2022) MHDMF: Prediction of miRNA–disease associations based on deep matrix factorization with multi-source graph convolutional network. Comput Biol Med 149:106069. https://doi.org/10.1016/j.compbiomed.2022.106069
Tang X, Luo J, Shen C et al (2021) Multi-view multichannel attention graph convolutional network for miRNA–disease association prediction. Briefings Bioinf 22(6):bbab174. https://doi.org/10.1093/bib/bbab174
Tang X, Luo J, Shen C et al (2006) Learning with hypergraphs: Clustering, classification, and embedding. In: NIPS. https://doi.org/10.7551/mitpress/7503.003.0205
Huang Z, Shi J, Gao Y et al (1970) A general method applicable to the search for similarities in the amino acid sequence of two proteins. J Mol Biol 48(3):443–453. https://doi.org/10.1016/0022-2836(70)90057-4
Liang X, Li J, Fu Y et al (2018) miRBase: from microRNA sequences to function. Nucleic Acids Res 47(D1):155–162. https://doi.org/10.1093/nar/gky1141
Liang X, Li J, Fu Y et al (2016) rDNAse: R package for generating various numerical representation schemes of DNA sequences. https://cran.r-project.org/web/packages/rDNAse/
Wang D, Wang J, Lu M et al (2010) Inferring the human microrna functional similarity and functional network based on microrna-associated diseases. Bioinformatics 26(13):1644–1650. https://doi.org/10.1093/bioinformatics/btq241
Xuan P, Han K, Guo M et al (2013) Prediction of micrornas associated with human diseases based on weighted k most similar neighbors. PLoS One 8(8):e70204. https://doi.org/10.1371/journal.pone.0070204
Morris C, Ritzert M, Fey M et al (2019) Weisfeiler and leman go neural: Higher-order graph neural networks. arXiv:1810.02244. https://doi.org/10.48550/arXiv.1810.02244
Mei J, Kwoh CK, Yang P et al (2013) Drug-target interaction prediction by learning from local information and neighbors. Bioinformatics 29(2):238–245. https://doi.org/10.1186/s12859-019-3290-7
Ji S, Feng Y, Ji R et al (2020) Dual channel hypergraph collaborative filtering. In: SIGKDD. https://doi.org/10.1093/bioinformatics/bts670
Ruan X, Jiang C, Lin P et al (2023) MSGCL: inferring miRNA–disease associations based on multi-view self-supervised graph structure contrastive learning. Briefings Bioinf 24(2):bbac623. https://doi.org/10.1093/bib/bbac623
Zhang H, Fang J, Sun Y et al (2023) Predicting miRNA-disease associations via node-level attention graph auto-encoder. IEEE/ACM Trans Comput Biol Bioinform 20(2):1308–1318. https://doi.org/10.1109/tcbb.2022.3170843
Ning Q, Zhao Y, Gao J et al (2023) AMHMDA: attention aware multi-view similarity networks and hypergraph learning for miRNA–disease associations identification. Briefings Bioinf 24(2):bbad094. https://doi.org/10.1093/bib/bbad094
Wang Y-T, Wu Q-W, Gao Z et al (2021) MiRNA-disease association prediction via hypergraph learning based on high-dimensionality features. BMC Med Inform Decis Mak 21(Suppl 1):133. https://doi.org/10.1186/s12911-020-01320-w
Wang C-C, Li T, Huang L et al (2015) The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PLoS One 10(3):e0118432. https://doi.org/10.1371/journal.pone.0118432
Wang C-C, Li T, Huang L et al (2017) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. https://doi.org/10.48550/arXiv.1609.02907
Wang C-C, Li T, Huang L et al (2017) Inductive representation learning on large graphs. In: NIPS. https://doi.org/10.48550/arXiv.1706.02216
Velickovic P, Cucurull G, Casanova A et al (2018) Graph attention networks. arXiv:1710.10903. https://doi.org/10.17863/CAM.48429
Wang X, He X, Wang M et al (2019) Neural graph collaborative filtering. In: SIGIR. https://doi.org/10.1145/3331184.3331267
Huang H-Y, Lin Y-C-D, Cui S-D et al (2021) mirtarbase update 2022: an informative resource for experimentally validated mirna–target interactions. Nucleic Acids Res 50:222–230. https://doi.org/10.1093/nar/gkab1079
González JP, Ramírez-Anguita JM, Saüch-Pitarch J et al (2019) The disgenet knowledge platform for disease genomics: 2019 update. Nucleic Acids Res 48:845–855. https://doi.org/10.1093/nar/gkz1021
Jiang J, Liu H-L, Tao L et al (2018) Let-7d inhibits colorectal cancer cell proliferation through the CST1/p65 pathway. Int J Oncol. https://doi.org/10.3892/ijo.2018.4419
Tie Y, Chen C, Yang Y et al (2018) Upregulation of let-7f-5p promotes chemotherapeutic resistance in colorectal cancer by directly repressing several pro-apoptotic proteins. Oncol Lett. https://doi.org/10.3892/ol.2018.8410
He D, Yue Z, Li G et al (2018) Low serum levels of miR-101 are associated with poor prognosis of colorectal cancer patients after curative resection. Med Sci Monit 24:7475–7481. https://doi.org/10.12659/msm.909768
Chen M-B, Yang L, Lu P-H et al (2015) MicroRNA-101 down-regulates sphingosine kinase 1 in colorectal cancer cells. Biochem Biophys Res Commun 463(4):954–960. https://doi.org/10.1016/j.bbrc.2015.06.041
Montgomery RL, Hullinger TG, Semus HM et al (2018) miR-24 inhibited the killing effect of natural killer cells to colorectal cancer cells by downregulating paxillin. Biomed. Pharmacother 101:257–263. https://doi.org/10.1016/j.biopha.2018.02.024
Shidal C, Singh NP, Nagarkatti P et al (2019) Microrna-92 expression in cd133, jakarta.xml.bind.jaxbelement@62ed5800, melanoma stem cells regulates immunosuppression in the tumor microenvironment via integrin-dependent activation of tgfb. Cancer Res 79:3622–3635. https://doi.org/10.1158/0008-5472.CAN-18-2659
Yang C, Xia Z, Zhu L et al (2019) Microrna-139-5p modulates the growth and metastasis of malignant melanoma cells via the pi3k/akt signaling pathway by binding to igf1r. Cell Cycle 18:3513–3524. https://doi.org/10.1080/15384101.2019.1690881
Nguyen T, Kuo C, Nicholl MB et al (2011) Downregulation of microrna-29c is associated with hypermethylation of tumor-related genes and disease outcome in cutaneous melanoma. Epigenetics 6:388–394. https://doi.org/10.4161/epi.6.3.14056
Tittarelli A, Navarrete M, Lizana M et al (2020) Hypoxic melanoma cells deliver micrornas to dendritic cells and cytotoxic t lymphocytes through connexin-43 channels. Int J Mol Sci 21(20):7567. https://doi.org/10.3390/ijms21207567
He Y, Yang Y, Liao Y et al (2020) mir-140-3p inhibits cutaneous melanoma progression by disrupting akt/p70s6k and jnk pathways through abhd2. Mol Ther Oncolytics 17:83–93. https://doi.org/10.1016/j.omto.2020.03.009
Zhang M, Cheng Y-J, Sara JD et al (2017) Circulating microrna-145 is associated with acute myocardial infarction and heart failure. Chin Med J (Engl.) 130: 51–56. https://doi.org/10.4103/0366-6999.196573
Cao RY, Li Q, Miao Y et al (2016) The emerging role of microrna-155 in cardiovascular diseases. Biomed Res Int 2016:9869208. https://doi.org/10.1155/2016/9869208
Sadat-Ebrahimi S-R, Rezabakhsh A, Aslanabadi N et al (2022) Novel diagnostic potential of mir-1 in patients with acute heart failure. PLoS One 17:0275019. https://doi.org/10.1371/journal.pone.0275019
Caravia XM, Fanjul V, Oliver E et al (2018) The microrna-29/pgc1a regulatory axis is critical for metabolic control of cardiac function. PLoS Biol 16:2006247. https://doi.org/10.1371/journal.pbio.2006247
Montgomery RL, Hullinger TG, Semus HM et al (2011) Therapeutic inhibition of mir-208a improves cardiac function and survival during heart failure. Circulation 124:1537–1547. https://doi.org/10.1161/CIRCULATIONAHA.111.030932
Zoph B, Ghiasi G, Lin T et al (2020) Rethinking pre-training and self-training. In: Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (eds) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual. https://doi.org/10.48550/arXiv.2006.06882
Liang X, Li J, Fu Y et al (2022) A novel machine learning model based on sparse structure learning with adaptive graph regularization for predicting drug side effects. J Biomed Inform 132:104131. https://doi.org/10.1016/j.jbi.2022.104131
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors have no competing interests.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liang, X., Guo, M., Jiang, L. et al. Predicting miRNA–Disease Associations by Combining Graph and Hypergraph Convolutional Network. Interdiscip Sci Comput Life Sci (2024). https://doi.org/10.1007/s12539-023-00599-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12539-023-00599-3