Skip to main content

Advertisement

SpringerLink
Log in

Hessian Regularized \(L_{2,1}\)-Nonnegative Matrix Factorization and Deep Learning for miRNA–Disease Associations Prediction

  • Original research article
  • Published:
Interdisciplinary Sciences: Computational Life Sciences Aims and scope Submit manuscript

Abstract

Since the identification of microRNAs (miRNAs), empirical research has demonstrated their crucial involvement in the functioning of organisms. Investigating miRNAs significantly bolsters efforts related to averting, diagnosing, and treating intricate human maladies. Yet, exploring every conceivable miRNA–disease association consumes significant resources and time within conventional wet experiments. On the computational front, forecasting potential miRNA–disease connections serves as a valuable source of preliminary insights for medical investigators. As a result, we have developed a novel matrix factorization model known as Hessian-regularized \(L_{2,1}\) nonnegative matrix factorization in combination with deep learning for predicting associations between miRNAs and diseases, denoted as \(HRL_{2,1}\)-NMF-DF. In particular, we introduce a novel iterative fusion approach to integrate all similarities. This method effectively diminishes the sparsity of the initial miRNA–disease associations matrix. Additionally, we devise a mixed model framework that utilizes deep learning, matrix decomposition, and singular value decomposition to capture and depict the intricate nonlinear features of miRNA and disease. The prediction performance of the six matrix factorization methods is improved by comparison and analysis, similarity matrix fusion, data preprocessing, and parameter adjustment. The AUC and AUPR obtained by the new matrix factorization model under fivefold cross validation are comparative or better with other matrix factorization models. Finally, we select three diseases including lung tumor, bladder tumor and breast tumor for case analysis, and further extend the matrix factorization model based on deep learning. The results show that the hybrid algorithm combining matrix factorization with deep learning proposed in this paper can predict miRNAs related to different diseases with high accuracy.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data Availability Statement

The datasets of this work can be downloaded from http://www.cuilab.cn/hmdd. The source code used in this work are available upon request.

References

  1. John B, Enright AJ, Aravin A et al (2004) Human microrna targets. Plos Biol 2(11):e363. https://doi.org/10.1371/journal.pbio.0020363

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Chatterjee S, GroHans H (2009) Active turnover modulates mature microrna activity in caenorhabditis elegans. Nature 461(7263):546–549. https://doi.org/10.1038/nature08349

    Article  CAS  PubMed  ADS  Google Scholar 

  3. Bushati N, Cohen SM (2007) Microrna functions. Annu Rev Cell Dev Biol 23:175–205. https://doi.org/10.1146/annurev.cellbio.23.090506.123406

    Article  CAS  PubMed  Google Scholar 

  4. Munsky B, Neuert G, van Oudenaarden A (2012) Using gene expression noise to understand gene regulation. Science 336(6078):183–187. https://doi.org/10.1126/science.1216379

    Article  MathSciNet  CAS  PubMed  PubMed Central  ADS  Google Scholar 

  5. Meira LAA, Máximo VR, Fazenda IL et al (2012) Accelerated motif detection using combinatorial techniques. In: 2012 eighth international conference on signal image technology and internet based systems. IEEE, pp 744–753. https://doi.org/10.1109/SITIS.2012.113

  6. Li Y, Xu J, Chen H et al (2013) Comprehensive analysis of the functional microrna-mrna regulatory network identifies mirna signatures associated with glioma malignant progression. Nucleic Acids Res 41(22):e203. https://doi.org/10.1093/nar/gkt1054

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Li J, Liu Y, Xin X et al (2012) Evidence for positive selection on a number of microrna regulatory interactions during recent human evolution. PLoS Genet 8(3):e1002578. https://doi.org/10.1371/journal.pgen.1002578

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Riba A, Bosia C, Baroudi ME et al (2014) A combination of transcriptional and microrna regulation improves the stability of the relative concentrations of target genes. PLoS Comput Biol 10(2):e1003490. https://doi.org/10.1371/journal.pcbi.1003490

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Esteller M (2011) Non-coding rnas in human diseases. Nat Rev Genet 12(12):861–874. https://doi.org/10.1038/nrg3074

    Article  CAS  PubMed  Google Scholar 

  10. Sun X, Liu ZH, Xie JM (eds) (2005) Basics for bioinformatics. Tsinghua University Press, Beijing. http://opac.nlc.cn/F

  11. Ghosh Z, Chakrabarti J, Mallick B (2007) mirnomics-the bioinformatics of microrna genes. Biochem Biophys Res Commun 363(1):6–11. https://doi.org/10.1016/j.bbrc.2007.08.030

    Article  CAS  PubMed  Google Scholar 

  12. Hou YY, Ying XM, Li WJ (2008) Computational approaches to microrna discovery. Hereditas (Bjing) 30(6):687–696. https://doi.org/10.3724/SP.J.1005.2008.00687

    Article  CAS  Google Scholar 

  13. Baanin N, Stoean R, Zivkovic M et al (2021) Performance of a novel chaotic firefly algorithm with enhanced exploration for tackling global optimization problems: application for dropout regularization. Mathematics 9(21):2705

    Article  Google Scholar 

  14. Jiang Q, Hao Y, Wang G et al (2010) Prioritization of disease micrornas through a human phenome-micrornaome network. BMC Syst Biol 4(1):S2. https://doi.org/10.1186/1752-0509-4-S1-S2

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Chen X, Liu MX, Yan GY (2012) Rwrmda: predicting novel human microrna-disease associations. Mol Biosyst 8(10):2792–2798. https://doi.org/10.1039/c2mb25180a

    Article  CAS  PubMed  Google Scholar 

  16. Chen X, Yan CC, Zhang X et al (2016) Wbsmda: Within and between score for mirna-disease association prediction. Sci Rep 6(1):21106. https://doi.org/10.1038/srep21106

    Article  CAS  PubMed  PubMed Central  ADS  Google Scholar 

  17. Chen X, Yan CC, Zhang X et al (2016) Hgimda: heterogeneous graph inference for mirna-disease association prediction. Oncotarget 7(40):65257–65269. https://doi.org/10.18632/oncotarget.11251

    Article  PubMed  PubMed Central  Google Scholar 

  18. You Z, Huang ZA, Zhu ZX et al (2017) Pbmda: a novel and effective path-based computational model for mirna-disease association prediction. PLoS Comput Biol 13(3):e1005455. https://doi.org/10.1371/journal.pcbi.1005455

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Chen X, Yang JR, Guan NN et al (2018) Grmda: graph regression for mirna-disease association prediction. Front Physiol 9:92. https://doi.org/10.3389/fphys.2018.00092

    Article  PubMed  PubMed Central  ADS  Google Scholar 

  20. Ji C, Wang Y, Ni J et al (2021) Predicting mirna-disease associations based on heterogeneous graph attention networks. Front Genet 12(727):744. https://doi.org/10.3389/fgene.2021.727744

    Article  CAS  Google Scholar 

  21. Xu J, Li CX, Lv JY et al (2011) Prioritizing candidate disease mirnas by topological features in the mirna target-dysregulated network: case study of prostate cancer. Mol Cancer Ther 10(10):1857–1866. https://doi.org/10.1158/1535-7163.MCT-11-0055

    Article  CAS  PubMed  Google Scholar 

  22. Chen X, Huang L (2017) Lrsslmda: Laplacian regularized sparse subspace learning for mirna-disease association prediction. PLoS Comput Biol 13(12):e1005912. https://doi.org/10.1371/journal.pcbi.1005912

    Article  CAS  PubMed  PubMed Central  ADS  Google Scholar 

  23. Chen X, Wang L, Qu J et al (2018) Predicting mirna-disease association based on inductive matrix completion. Bioinformatics 34(24):4256–4265. https://doi.org/10.1093/bioinformatics/bty503

    Article  CAS  PubMed  Google Scholar 

  24. Chen X, Wang CC, Yin J et al (2018) Novel human mirna-disease association inference based on random forest. Mol Ther Nucleic Acids 13:568–79. https://doi.org/10.1016/j.omtn.2018.10.005

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. Zhao Y, Chen X, Yin J (2019) Adaptive boosting-based computational model for predicting potential mirna-disease associations. Bioinformatics 35(22):4730–4738. https://doi.org/10.1093/bioinformatics/btz297

    Article  CAS  PubMed  Google Scholar 

  26. Wang CC, Li TH, Huang L et al (2022) Prediction of potential mirnadisease associations based on stacked autoencoder. Brief Bioinform 23(2):bbac021. https://doi.org/10.1093/bib/bbac021

    Article  CAS  PubMed  Google Scholar 

  27. Liu W, Lin H, Huang L et al (2022) Identification of mirna-disease associations via deep forest ensemble learning based on autoencoder. Brief Bioinform 23(3):bbac104. https://doi.org/10.1093/bib/bbac104

    Article  CAS  PubMed  Google Scholar 

  28. Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev 51:455–500. https://doi.org/10.1137/07070111x

    Article  MathSciNet  ADS  Google Scholar 

  29. Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791. https://doi.org/10.1038/44565

    Article  CAS  PubMed  ADS  Google Scholar 

  30. Xiao Q, Luo J, Liang C et al (2018) A graph regularized non-negative matrix factorization method for identifying microrna-disease associations. Bioinformatics 34(2):239–248. https://doi.org/10.1093/bioinformatics/btx545

    Article  CAS  PubMed  Google Scholar 

  31. Chen X, Wang L, Qu J et al (2018) Predicting mirna-disease association based on inductive matrix completion. Bioinformatics 32(24):4256–4265. https://doi.org/10.1093/bioinformatics/bty503

    Article  CAS  Google Scholar 

  32. 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

    Article  PubMed  PubMed Central  Google Scholar 

  33. Xu J, Cai L, Liao B et al (2019) Identifying potential mirnas-disease associations with probability matrix factorization. Front Genet 10:1234. https://doi.org/10.3389/fgene.2019.01234

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Zhang W, Yue X, Lin W et al (2018) Predicting drug-disease associations by using similarity constrained matrix factorization. BMC Bioinform 19(1):233. https://doi.org/10.1186/s12859-018-2220-4

    Article  CAS  Google Scholar 

  35. Shen Z, Zhang YH, Han K et al (2017) Mirna-disease association prediction with collaborative matrix factorization. Complexity 2017:1–9. https://doi.org/10.1155/2017/2498957

    Article  MathSciNet  Google Scholar 

  36. Zhang Y, Chen M, Cheng X et al (2020) Msfsp: a novel mirna-disease association prediction model by federating multiple-similarities fusion and space projection. Front Genet 11:389. https://doi.org/10.3389/fgene.2020.00389

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Ha J, Park C, Park C et al (2019) Imipmf: inferring mirna-disease interactions using probabilistic matrix factorization. J Biomed Inform 102(103):358. https://doi.org/10.1016/j.jbi.2019.103358

    Article  Google Scholar 

  38. Chen X, Li SX, Yin J et al (2020) Potential mirna-disease association prediction based on kernelized Bayesian matrix factorization. Genomics 112(1):809–819. https://doi.org/10.1016/j.ygeno.2019.05.021

    Article  CAS  PubMed  Google Scholar 

  39. Li L, Gao Z, Wang Y et al (2021) Scmfmda: predicting microrna-disease associations based on similarity constrained matrix factorization. PLoS Comput Biol 17(7):e1009165. https://doi.org/10.1371/journal.pcbi.1009165

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  40. Lin CJ (2007) On the convergence of multiplicative update algorithms for nonnegative matrix factorization. IEEE Trans Neural Netw 18(6):1589–1596. https://doi.org/10.1109/TNN.2007.895831

    Article  Google Scholar 

  41. Devarajan K (2008) Nonnegative matrix factorization: an analytical and interpretive tool in computational biology. PLoS Comput Biol 4(7):e1000029. https://doi.org/10.1371/journal.pcbi.1000029

    Article  CAS  PubMed  PubMed Central  ADS  Google Scholar 

  42. 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

    Article  CAS  PubMed  Google Scholar 

  43. Cheng L, Li J, Ju P et al (2014) Semfunsim: a new method for measuring disease similarity by integrating semantic and gene functional association. PLoS One 9(6):e99415. https://doi.org/10.1371/journal.pone.0099415

    Article  MathSciNet  PubMed  PubMed Central  ADS  Google Scholar 

  44. Yan C, Wang JX, Ni P et al (2019) Dnrlmf-mda:predicting microrna-disease associations based on similarities of micrornas and diseases. IEEE/ACM Trans Comput Biol Bioinform 16(1):233–243. https://doi.org/10.1109/TCBB.2017.2776101

    Article  CAS  PubMed  Google Scholar 

  45. Wei L, Wang JX, Li M et al (2018) Predicting microrna-disease associations based on improved microrna and disease similarities. IEEE/ACM Trans Comput Biol Bioinform 15(6):1774–1782. https://doi.org/10.1109/TCBB.2016.2586190

    Article  Google Scholar 

  46. van Laarhoven T, Nabuurs SB, Marchiori E (2011) Gaussian interaction profile kernels for predicting drug-target interaction. Bioinformatics 27(21):3036–3043. https://doi.org/10.1093/bioinformatics/btr500

    Article  CAS  PubMed  Google Scholar 

  47. Lan W, Li M, Zhao K et al (2017) Ldap: a web server for lncrna-disease association prediction. Bioinformatics 33(3):458–460. https://doi.org/10.1093/bioinformatics/btw639

    Article  CAS  PubMed  Google Scholar 

  48. Kozomara A, Griffiths-Jones S (2013) Mirbase: annotating high confidence micrornas using deep sequencing data. Nucleic Acids Res 42(Database issue):D68–D73. https://doi.org/10.1093/nar/gkt1181

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  49. Needleman SB, Wunsch CD (1970) A general method applicable to search for similarities in amino acid sequence of 2 proteins. J Mol Biol 48(3):443–453. https://doi.org/10.1016/0022-2836(70)90057-4

    Article  CAS  PubMed  Google Scholar 

  50. Xiao Q, Luo J, Liang C et al (2018) A graph regularized non-negative matrix factorization method for identifying microrna-disease associations. Bioinformatics 34(2):239–248. https://doi.org/10.1093/bioinformatics/btx545

    Article  CAS  PubMed  Google Scholar 

  51. Ezzat A, Zhao P, Wu M et al (2017) Drug-target interaction prediction with graph regularized matrix factorization. IEEE/ACM Trans Comput Biol Bioinform 14(3):646–656. https://doi.org/10.1109/TCBB.2016.2530062

    Article  CAS  PubMed  Google Scholar 

  52. Xia LY, Yang ZY, Zhang H et al (2019) Improved prediction of drug-target interactions using self-paced learning with collaborative matrix factorization. J Chem Inf Model 59(7):3340–3351. https://doi.org/10.1021/acs.jcim.9b00408

    Article  CAS  PubMed  Google Scholar 

  53. Wang Y, Yu G, Wang J et al (2020) Weighted matrix factorization on multi-relational data for lncrna-disease association prediction. Methods 173:32–43. https://doi.org/10.1016/j.ymeth.2019.06.015

    Article  CAS  PubMed  Google Scholar 

  54. Jiang Y, Liu B, Yu L et al (2018) Predict mirna-disease association with collaborative filtering. Neuroinformatics 16(3–4):363–372. https://doi.org/10.1007/s12021-018-9386-9

    Article  PubMed  Google Scholar 

  55. Shao B, Liu B, Yan C (2018) Sacmda: mirna-disease association prediction with short acyclic connections in heterogeneous graph. Neuroinformatics 16(3–4):373–382. https://doi.org/10.1007/s12021-018-9373-1

    Article  PubMed  Google Scholar 

  56. Zhang F, Song H, Zeng M et al (2019) Deepfunc: a deep learning framework for accurate prediction of protein functions from protein sequences and interactions. Proteomics 19(12):e1900019. https://doi.org/10.1002/pmic.201900019

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported in part by Natural Science Foundation of Hunan Province of China (Grant no. 2021JJ30684), Key Foundation of Hunan Educational Committee (Grant no. 19A497), Hunan Provincial Key Research Program (Grant no. 2022WK2009).

Author information

Author notes

  1. Qi Gao, Ling-Zhi Peng and Jing Tang contributed equally to this work.

Authors and Affiliations

  1. Department of Mathematics and Computational Science, Xiangtan University, Xiangtan, 411105, China

    Guo-Sheng Han, Qi Gao, Ling-Zhi Peng & Jing Tang

  2. Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering, Xiangtan University, Xiangtan, 411105, China

    Guo-Sheng Han, Qi Gao, Ling-Zhi Peng & Jing Tang

Authors
  1. Guo-Sheng Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qi Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ling-Zhi Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jing Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

GSH directed the research. GSH, JT and QG designed the experiments. JT, QG and LZP ran all the experiments and wrote the paper. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Guo-Sheng Han.

Ethics declarations

Ethics approval

Not applicable.

Consent for publication

Not applicable.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, GS., Gao, Q., Peng, LZ. et al. Hessian Regularized \(L_{2,1}\)-Nonnegative Matrix Factorization and Deep Learning for miRNA–Disease Associations Prediction. Interdiscip Sci Comput Life Sci 16, 176–191 (2024). https://doi.org/10.1007/s12539-023-00594-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12539-023-00594-8

Keywords

Search

Navigation