Skip to content
2000
image of Graph Convolution and Attention-Combined Learning for Multi-Type Prediction of miRNA-Disease Associations

Abstract

Introduction

Associations of abnormally expressed miRNAs with disease development have long been investigated in the biomedical field. The association types are diverse and complex, including circulation type, epigenetic type, target type, and genetic type, as well as various unknown associations and possibly novel association types. However, most current studies focus on the yes/no binary prediction of miRNA–disease associations. Algorithms for multi-type prediction or novel-type discovery of these associations are less developed.

Methods

Graph convolution and attention mechanisms, integrated within a deep learning framework, form the basis of deepMDpred. In the first step, deepMDpred employs the ViennaRNA tool to derive sequence and functional features of miRNAs by calculating base pairs, minimum free energy, and other relevant properties. In the second step, disease features are extracted using a Graph Convolutional Network (GCN) combined with attention learning, enabling the adaptive capture of the importance of different node features. Finally, a nonlinear fully connected layer (NFCL) is applied to generate the embedding vectors for both diseases and miRNAs.

Results

In five-fold cross-validation, the model achieved high predictive performance for multi-type miRNA–disease associations. For task 1, the average AUC across the four predicted types exceeded 85%, with the genetics type achieving an accuracy of 0.919. For tasks 2 and 3, the average AUC exceeded 80%, and for the un-association type, the AUC reached 0.894. Validation using the HMDD v2.0 and HMDD v3.2 databases confirmed the robustness of the model, while additional case studies with the HMDD v3.2 and HMDD v4.0 databases demonstrated its applicability. Furthermore, investigations in breast and liver cancers supported the method’s capability to identify novel miRNA–disease associations.

Discussion

The findings of this study demonstrate the potential of DeepMDpred as a novel and effective approach for predicting multi-type associations between miRNAs and diseases. Validation across multiple databases, along with successful application in case studies on breast and liver cancers, underscores the generalizability and practical utility of this approach. The framework also offers a pathway for identifying novel associations, which may accelerate the discovery of biomarkers and therapeutic targets in complex diseases such as cancer. Nonetheless, certain limitations remain. Although the model achieves strong performance on curated datasets, its robustness in real-world noisy datasets and its applicability to rare diseases require further investigation. Future research should also consider integrating additional data modalities, including epigenetic modifications and clinical phenotypes, to improve predictive accuracy further and broaden the scope of application.

Conclusion

DeepMDpred is an effective method that combines graph convolution and attention learning for the multi-type prediction of miRNA-disease associations. It provides a better ability to identify new association types between diseases and miRNAs, as well as broader applicability to unveil associated miRNAs with new diseases.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cbio/10.2174/0115748936379275250812105519
2025-08-22
2025-10-31

  • From This Site

    /content/journals/cbio/10.2174/0115748936379275250812105519
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Ambros V. microRNAs. Cell 2001 107 7 823 826 10.1016/S0092‑8674(01)00616‑X 11779458
    [Google Scholar]
  2. Bartel D.P. MicroRNAs. Cell 2004 116 2 281 297 10.1016/S0092‑8674(04)00045‑5 14744438
    [Google Scholar]
  3. Bracken C.P. Scott H.S. Goodall G.J. A network-biology perspective of microRNA function and dysfunction in cancer. Nat. Rev. Genet. 2016 17 12 719 732 10.1038/nrg.2016.134 27795564
    [Google Scholar]
  4. Croce C.M. Calin G.A. miRNAs, cancer, and stem cell division. Cell 2005 122 1 6 7 10.1016/j.cell.2005.06.036 16009126
    [Google Scholar]
  5. Dalal S. Ramirez-Gomez J. Sharma B. Devara D. Kumar S. MicroRNAs and synapse turnover in Alzheimer’s disease. Ageing Res. Rev. 2024 99 102377 10.1016/j.arr.2024.102377 38871301
    [Google Scholar]
  6. Pockar S. Globocnik Petrovic M. Peterlin B. Vidovic Valentincic N. MiRNA as biomarker for uveitis: A systematic review of the literature. Gene 2019 696 162 175 10.1016/j.gene.2019.02.004 30763668
    [Google Scholar]
  7. Gjorgjieva T. Chaloemtoem A. Shahin T. Bayaraa O. Dieng M.M. Alshaikh M. Abdalbaqi M. Del Monte J. Begum G. Leonor C. Manikandan V. Drou N. Arshad M. Arnoux M. Kumar N. Jabari A. Abdulle A. ElGhazali G. Ali R. Shaheen S.Y. Abdalla J. Piano F. Gunsalus K.C. Daggag H. Al Nahdi H. Abuzeid H. Idaghdour Y. Systems genetics identifies miRNA-mediated regulation of host response in COVID-19. Hum. Genomics 2023 17 1 49 10.1186/s40246‑023‑00494‑4 37303042
    [Google Scholar]
  8. Zhang L. Lu Q. Chang C. Epigenetics in health and disease. Adv. Exp. Med. Biol. 2020 1253 3 55 10.1007/978‑981‑15‑3449‑2_1 32445090
    [Google Scholar]
  9. Andersen G.B. Tost J. Circulating miRNAs as biomarker in cancer. Recent Results Cancer Res. 2020 215 277 298 10.1007/978‑3‑030‑26439‑0_15 31605235
    [Google Scholar]
  10. Diener C. Keller A. Meese E. The miRNA–target interactions: An underestimated intricacy. Nucleic Acids Res. 2024 52 4 1544 1557 10.1093/nar/gkad1142 38033323
    [Google Scholar]
  11. Wilkening S. Bader A. Quantitative real-time polymerase chain reaction: methodical analysis and mathematical model. J. Biomol. Tech. 2004 15 2 107 111 15190083
    [Google Scholar]
  12. Pall G.S. Hamilton A.J. Improved northern blot method for enhanced detection of small RNA. Nat. Protoc. 2008 3 6 1077 1084 10.1038/nprot.2008.67 18536652
    [Google Scholar]
  13. Nakamura K. Sawada K. Yoshimura A. Kinose Y. Nakatsuka E. Kimura T. Clinical relevance of circulating cell-free microRNAs in ovarian cancer. Mol. Cancer 2016 15 1 48 10.1186/s12943‑016‑0536‑0 27343009
    [Google Scholar]
  14. Liu R. Luo Q. You W. Jin M. MicroRNA-106 attenuates hyperglycemia-induced vascular endothelial cell dysfunction by targeting HMGB1. Gene 2018 677 142 148 10.1016/j.gene.2018.07.063 30055307
    [Google Scholar]
  15. Cui M. Wang H. Yao X. Zhang D. Xie Y. Cui R. Zhang X. Circulating MicroRNAs in cancer: Potential and challenge. Front. Genet. 2019 10 626 10.3389/fgene.2019.00626 31379918
    [Google Scholar]
  16. Cui M. Liu W. Zhang L. Guo F. Liu Y. Chen F. Liu T. Ma R. Wu R. Over-Expression of miR-21 and Lower PTEN Levels in Wilms’ Tumor with Aggressive Behavior. Tohoku J. Exp. Med. 2017 242 1 43 52 10.1620/tjem.242.43 28529243
    [Google Scholar]
  17. Wang H.F. Dong Z.Y. Yan L. Yang S. Xu H.N. Chen S.L. Wang W.R. Yang Q.L. Chen C.J. The N‐terminal polypeptide derived from vMIP‐II exerts its antitumor activity in human breast cancer through CXCR4/miR‐7‐5p/Skp2 pathway. J. Cell. Physiol. 2020 235 12 9474 9486 10.1002/jcp.29755 32372405
    [Google Scholar]
  18. Ha J. SMAP: Similarity-based matrix factorization framework for inferring miRNA-disease association. Knowl. Base. Syst. 2023 263 110295 10.1016/j.knosys.2023.110295
    [Google Scholar]
  19. Xuan P. Han K. Guo M. Guo Y. Li J. Ding J. Liu Y. Dai Q. Li J. Teng Z. Huang Y. Prediction of microRNAs associated with human diseases based on weighted k most similar neighbors. PLoS One 2013 8 8 e70204 10.1371/journal.pone.0070204 24116246
    [Google Scholar]
  20. Chen X. Yan G.Y. Semi-supervised learning for potential human microRNA-disease associations inference. Sci. Rep. 2014 4 1 5501 10.1038/srep05501 24975600
    [Google Scholar]
  21. Xiao Q. Luo J. Liang C. Cai J. Ding P. A graph regularized non-negative matrix factorization method for identifying microRNA-disease associations. Bioinformatics 2018 34 2 239 248 10.1093/bioinformatics/btx545 28968779
    [Google Scholar]
  22. Ma Y. Shi Y. Chen X. Zhang B. Wu H. Gao J. NFMCLDA: Predicting miRNA-based lncRNA-disease associations by network fusion and matrix completion. Comput. Biol. Med. 2024 174 108403 10.1016/j.compbiomed.2024.108403 38582002
    [Google Scholar]
  23. Chen X. Xie D. Zhao Q. You Z.H. MicroRNAs and complex diseases: From experimental results to computational models. Brief. Bioinform. 2019 20 2 515 539 10.1093/bib/bbx130 29045685
    [Google Scholar]
  24. Chen X. Zhu C.C. Yin J. Ensemble of decision tree reveals potential miRNA-disease associations. PLOS Comput. Biol. 2019 15 7 e1007209 10.1371/journal.pcbi.1007209 31329575
    [Google Scholar]
  25. Xuan P. Sun H. Wang X. Zhang T. Pan S. Inferring the disease-associated miRNAs based on network representation learning and convolutional neural networks. Int. J. Mol. Sci. 2019 20 15 3648 10.3390/ijms20153648 31349729
    [Google Scholar]
  26. Zitnik M. Agrawal M. Leskovec J. Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics 2018 34 13 i457 i466 10.1093/bioinformatics/bty294 29949996
    [Google Scholar]
  27. Zhang X.M. Liang L. Liu L. Tang M.J. Graph neural networks and their current applications in bioinformatics. Front. Genet. 2021 12 690049 10.3389/fgene.2021.690049 34394185
    [Google Scholar]
  28. Sun M. Zhao S. Gilvary C. nlmo O. Zhou J. Wang F. Graph convolutional networks for computational drug development and discovery. Brief. Bioinform. 2020 21 3 919 935 10.1093/bib/bbz042 31155636
    [Google Scholar]
  29. Xuan P. Pan S. Zhang T. Liu Y. Sun H. Graph convolutional network and convolutional neural network based method for predicting lncRNA-Disease associations. Cells 2019 8 9 1012 10.3390/cells8091012 31480350
    [Google Scholar]
  30. Ding Y. Tian L.P. Lei X. Liao B. Wu F.X. Variational graph auto-encoders for miRNA-disease association prediction. Methods 2021 192 25 34 10.1016/j.ymeth.2020.08.004 32798654
    [Google Scholar]
  31. Han P. Yang P. Zhao P. Shang S. Liu Y. Zhou J. Gao X. Kalnis P. GCN-MF: Disease-Gene association identification by graph convolutional networks and matrix factorization. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining Anchorage, AK, USA, 2019, pp.705-713 10.1145/3292500.3330912
    [Google Scholar]
  32. Shen C. Luo J. Ouyang W. Ding P. Chen X. IDDkin: network-based influence deep diffusion model for enhancing prediction of kinase inhibitors. Bioinformatics 2021 36 22-23 5481 5491 10.1093/bioinformatics/btaa1058 33367525
    [Google Scholar]
  33. Wang L. You Z.H. Li Y.M. Zheng K. Huang Y.A. GCNCDA: A new method for predicting circRNA-disease associations based on Graph Convolutional Network Algorithm. PLOS Comput. Biol. 2020 16 5 e1007568 10.1371/journal.pcbi.1007568 32433655
    [Google Scholar]
  34. Bahdanau D. Cho K. Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate. 3rd International Conference on Learning Representations, ICLR 2015 San Diego, United States, 2014,
    [Google Scholar]
  35. Zhang Y. Liu C. Liu M. Liu T. Lin H. Huang C.B. Ning L. Attention is all you need: Utilizing attention in AI-enabled drug discovery. Brief. Bioinform. 2023 25 1 bbad467 10.1093/bib/bbad467 38189543
    [Google Scholar]
  36. Tang X. Luo J. Shen C. Lai Z. Multi-view multichannel attention graph convolutional network for miRNA–disease association prediction. Brief. Bioinform. 2021 22 6 bbab174 10.1093/bib/bbab174 33963829
    [Google Scholar]
  37. Li Z. Zhong T. Huang D. You Z.H. Nie R. Hierarchical graph attention network for miRNA-disease association prediction. Mol. Ther. 2022 30 4 1775 1786 10.1016/j.ymthe.2022.01.041 35121109
    [Google Scholar]
  38. Jiao C.N. Zhou F. Liu B.M. Zheng C.H. Liu J.X. Gao Y.L. Multi-kernel graph attention deep autoencoder for MiRNA-disease association prediction. IEEE J. Biomed. Health Inform. 2024 28 2 1110 1121 10.1109/JBHI.2023.3336247 38055359
    [Google Scholar]
  39. Zhang Y. Chu Y. Lin S. Xiong Y. Wei D.Q. ReHoGCNES-MDA: prediction of miRNA-disease associations using homogenous graph convolutional networks based on regular graph with random edge sampler. Brief. Bioinform. 2024 25 2 bbae103 10.1093/bib/bbae103 38517693
    [Google Scholar]
  40. Chen X. Clarence Yan C. Zhang X. Li Z. Deng L. Zhang Y. Dai Q. RBMMMDA: predicting multiple types of disease-microRNA associations. Sci. Rep. 2015 5 1 13877 10.1038/srep13877 26347258
    [Google Scholar]
  41. Zhang X. Yin J. Zhang X. A semi-supervised learning algorithm for predicting four types MiRNA-Disease associations by mutual information in a heterogeneous network. Genes 2018 9 3 139 10.3390/genes9030139 29498680
    [Google Scholar]
  42. Wang R. Li S. Cheng L. Wong M.H. Leung K.S. Predicting associations among drugs, targets and diseases by tensor decomposition for drug repositioning. BMC Bioinformatics 2019 20 S26 Suppl. 26 628 10.1186/s12859‑019‑3283‑6 31839008
    [Google Scholar]
  43. Huang F. Yue X. Xiong Z. Yu Z. Liu S. Zhang W. Tensor decomposition with relational constraints for predicting multiple types of microRNA-disease associations. Brief. Bioinform. 2021 22 3 bbaa140 10.1093/bib/bbaa140 32725161
    [Google Scholar]
  44. Luo J. Liu Y. Liu P. Lai Z. Wu H. Data integration using tensor decomposition for the prediction of miRNA-Disease associations. IEEE J. Biomed. Health Inform. 2022 26 5 2370 2378 10.1109/JBHI.2021.3125573 34748505
    [Google Scholar]
  45. Yan C. Duan G. Li N. Zhang L. Wu F.X. Wang J. PDMDA: predicting deep-level miRNA–disease associations with graph neural networks and sequence features. Bioinformatics 2022 38 8 2226 2234 10.1093/bioinformatics/btac077 35150255
    [Google Scholar]
  46. Lorenz R. Bernhart S.H. Höner zu Siederdissen C. Tafer H. Flamm C. Stadler P.F. Hofacker I.L. ViennaRNA Package 2.0. Algorithms Mol. Biol. 2011 6 1 26 10.1186/1748‑7188‑6‑26 22115189
    [Google Scholar]
  47. Ning Q. Zhao Y. Gao J. Chen C. Li X. Li T. Yin M. AMHMDA: Attention aware multi-view similarity networks and hypergraph learning for miRNA–disease associations identification. Brief. Bioinform. 2023 24 2 bbad094 10.1093/bib/bbad094 36907654
    [Google Scholar]
  48. Li Y. Qiu C. Tu J. Geng B. Yang J. Jiang T. Cui Q. HMDD v2.0: a database for experimentally supported human microRNA and disease associations. Nucleic Acids Res. 2014 42 D1 D1070 D1074 10.1093/nar/gkt1023 24194601
    [Google Scholar]
  49. Huang Z. Shi J. Gao Y. Cui C. Zhang S. Li J. Zhou Y. Cui Q. HMDD v3.0: A database for experimentally supported human microRNA–disease associations. Nucleic Acids Res. 2019 47 D1 D1013 D1017 10.1093/nar/gky1010 30364956
    [Google Scholar]
  50. Cui C. Zhong B. Fan R. Cui Q. HMDD v4.0: A database for experimentally supported human microRNA-disease associations. Nucleic Acids Res. 2024 52 D1 D1327 D1332 10.1093/nar/gkad717 37650649
    [Google Scholar]
  51. Piñero J. Ramírez-Anguita J.M. Saüch-Pitarch J. Ronzano F. Centeno E. Sanz F. Furlong L.I. The DisGeNET knowledge platform for disease genomics: 2019 update. Nucleic Acids Res. 2020 48 D1 D845 D855 31680165
    [Google Scholar]
  52. Wang D. Wang J. Lu M. Song F. Cui Q. Inferring the human microRNA functional similarity and functional network based on microRNA-associated diseases. Bioinformatics 2010 26 13 1644 1650 10.1093/bioinformatics/btq241 20439255
    [Google Scholar]
  53. Kozomara A. Birgaoanu M. Griffiths-Jones S. miRBase: From microRNA sequences to function. Nucleic Acids Res. 2019 47 D1 D155 D162 10.1093/nar/gky1141 30423142
    [Google Scholar]
  54. Lee Y. Ahn C. Han J. Choi H. Kim J. Yim J. Lee J. Provost P. Rådmark O. Kim S. Kim V.N. The nuclear RNase III Drosha initiates microRNA processing. Nature 2003 425 6956 415 419 10.1038/nature01957 14508493
    [Google Scholar]
  55. Trotta E. On the normalization of the minimum free energy of RNAs by sequence length. PLoS One 2014 9 11 e113380 10.1371/journal.pone.0113380 25405875
    [Google Scholar]
  56. Zeng X. Zhang X. Zou Q. Integrative approaches for predicting microRNA function and prioritizing disease-related microRNA using biological interaction networks. Brief. Bioinform. 2016 17 2 193 203 10.1093/bib/bbv033 26059461
    [Google Scholar]
  57. Wang J.Z. Du Z. Payattakool R. Yu P.S. Chen C.F. A new method to measure the semantic similarity of GO terms. Bioinformatics 2007 23 10 1274 1281 10.1093/bioinformatics/btm087 17344234
    [Google Scholar]
  58. Digitale J.C. Martin J.N. Glymour M.M. Tutorial on directed acyclic graphs. J. Clin. Epidemiol. 2022 142 264 267 10.1016/j.jclinepi.2021.08.001 34371103
    [Google Scholar]
  59. Sun J. Zhang Y. Ma C. Coates M. Guo H. Tang R. He X. Multi-graph Convolution Collaborative Filtering. 2019 IEEE International Conference on Data Mining (ICDM) Beijing, China, 08-11 November 2019, pp. 1306-1311 10.1109/ICDM.2019.00165
    [Google Scholar]
  60. Olivier M. Hollstein M. Hainaut P. TP53 mutations in human cancers: Origins, consequences, and clinical use. Cold Spring Harb. Perspect. Biol. 2010 2 1 a001008 10.1101/cshperspect.a001008 20182602
    [Google Scholar]
  61. Connor R. Dearle A. Claydon B. Vadicamo L. Correlations of cross-entropy loss in machine learning. Entropy 2024 26 6 491 10.3390/e26060491 38920500
    [Google Scholar]
  62. Williams A. Walton N. Maryanski A. Bogetic S. Hines W. Sobes V. Stochastic gradient descent for optimization for nuclear systems. Sci. Rep. 2023 13 1 8474 10.1038/s41598‑023‑32112‑7 37230990
    [Google Scholar]
  63. Yu D.L. Yu Z.G. Han G.S. Li J. Anh V. Heterogeneous types of miRNA-disease associations stratified by multi-layer network embedding and prediction. Biomedicines 2021 9 9 1152 10.3390/biomedicines9091152 34572337
    [Google Scholar]
  64. 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 10.1093/bioinformatics/btz965 31904845
    [Google Scholar]
  65. Zhao Y. Chen X. Yin J. Adaptive boosting-based computational model for predicting potential miRNA-disease associations. Bioinformatics 2019 35 22 4730 4738 10.1093/bioinformatics/btz297 31038664
    [Google Scholar]
  66. Zuker M. Stiegler P. Optimal computer folding of large RNA sequences using thermodynamics and auxiliary information. Nucleic Acids Res. 1981 9 1 133 148 10.1093/nar/9.1.133 6163133
    [Google Scholar]
  67. Md Zaki F.A. Mohamad Hanif E.A. Identifying miRNA as biomarker for breast cancer subtyping using association rule. Comput. Biol. Med. 2024 178 108696 10.1016/j.compbiomed.2024.108696 38850957
    [Google Scholar]
  68. Lagendijk M. Saadatmand S. Koppert L.B. Tilanus-Linthorst M.M.A. de Weerd V. Ramírez-Moreno R. Smid M. Sieuwerts A.M. Martens J.W.M. Correction: MicroRNA expression in pre-treatment plasma of patients with benign breast diseases and breast cancer. Oncotarget 2018 9 62 32096 10.18632/oncotarget.25979 30174799
    [Google Scholar]
  69. Li Z. Duan Y. Yan S. Zhang Y. Wu Y. The miR‐302/367 cluster: Aging, inflammation, and cancer. Cell Biochem. Funct. 2023 41 7 752 766 10.1002/cbf.3836 37555645
    [Google Scholar]
  70. El-Ashry A. Albeltagy A. Ramez A. Hendawy S. Influence of Micro-RNA-423 gene variation on risk and characteristics of breast cancer. Asian Pac. J. Cancer Prev. 2022 23 11 3771 3777 10.31557/APJCP.2022.23.11.3771 36444590
    [Google Scholar]
  71. Fründt T. Krause L. Hussey E. Steinbach B. Köhler D. von Felden J. Schulze K. Lohse A.W. Wege H. Schwarzenbach H. Diagnostic and prognostic value of miR-16, miR-146a, miR-192 and miR-221 in exosomes of hepatocellular carcinoma and liver cirrhosis patients. Cancers 2021 13 10 2484 10.3390/cancers13102484 34069692
    [Google Scholar]
  72. Chen W. Ru J. Wu T. Man D. Wu J. Wu L. Sun Y. Yu H. Li M. Zhang G. Zhu X. Tong R. Xiao H. Li Y. Yang B. MiR-652-3p promotes malignancy and metastasis of cancer cells via inhibiting TNRC6A in hepatocellular carcinoma. Biochem. Biophys. Res. Commun. 2023 640 1 11 10.1016/j.bbrc.2022.11.100 36495604
    [Google Scholar]
  73. Chen J. Zhang K. Xu Y. Gao Y. Li C. Wang R. Chen L. The role of microRNA-26a in human cancer progression and clinical application. Tumour Biol. 2016 37 6 7095 7108 10.1007/s13277‑016‑5017‑y 27039398
    [Google Scholar]
  74. Yao Y. Shi L. Zhu X. Four differentially expressed exosomal miRNAs as prognostic biomarkers and therapy targets in endometrial cancer: Bioinformatic analysis. Medicine 2023 102 34 e34998 10.1097/MD.0000000000034998 37653757
    [Google Scholar]
/content/journals/cbio/10.2174/0115748936379275250812105519
Loading
Graph Convolution and Attention-Combined Learning for Multi-Type Prediction of miRNA-Disease Associations
Bentham Science Publishers ; https://doi.org/10.2174/0115748936379275250812105519
/content/journals/cbio/10.2174/0115748936379275250812105519
/content/journals/cbio/10.2174/0115748936379275250812105519
Loading

Data & Media loading...


  • Article Type:     Research Article
Keywords: deep-MDpred ; miRNA-disease association ; graph convolutional network ; attention mechanism ; multi-type prediction

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test