Interaction-Based Aggregation of mRNA and miRNA Expression Profiles to Differentiate Myelodysplastic Syndrome

  • Jiří KlémaEmail author
  • Jan Zahálka
  • Michael Anděl
  • Zdeněk Krejčík
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 511)


In this work we integrate conventional mRNA expression profiles with miRNA expressions using the knowledge of their validated or predicted interactions in order to improve class prediction in genetically determined diseases. The raw mRNA and miRNA expression features become enriched or replaced by new aggregated features that model the mRNA-miRNA interaction. The proposed subtractive integration method is directly motivated by the inhibition/degradation models of gene expression regulation. The method aggregates mRNA and miRNA expressions by subtracting a proportion of miRNA expression values from their respective target mRNAs. Further, its modification based on singular value decomposition that enables different subtractive weights for different miRNAs is introduced. Both the methods are used to model the outcome or development of myelodysplastic syndrome, a blood cell production disease often progressing to leukemia. The reached results demonstrate that the integration improves classification performance when dealing with mRNA and miRNA features of comparable significance. The proposed methods are available as a part of the web tool miXGENE.


Gene expression Machine learning microRNA Classification Prior knowledge Myelodysplastic syndrome 



This research was supported by the grants NT14539 and NT1 4377 of the Ministry of Health of the Czech Republic.


  1. 1.
    Anděl, M., Kléma, J., Krejčík, Z.: Integrating mRNA and miRNA expressions with interaction knowledge to predict myelodysplastic syndrome. In: Information Technologies - Applications and Theory, Workshop on Bioinformatics in Genomics and Proteomics, ITAT 2013, pp. 48–55 (2013)Google Scholar
  2. 2.
    Brewster, J.L., Beason, K.B., Eckdahl, T.T., et al.: The microarray revolution: perspectives from educators. Biochem. Mol. Biol. Educ. 32(4), 217–227 (2004)CrossRefGoogle Scholar
  3. 3.
    Croce, C.M.: Causes and consequences of microRNA dysregulation in cancer. Nat. Rev. Genet. 10(10), 704–714 (2009)CrossRefGoogle Scholar
  4. 4.
    Merkerova, M.D., Krejcik, Z., Votavova, H., et al.: Distinctive microRNA expression profiles in CD34+ bone marrow cells from patients with myelodysplastic syndrome. Eur. J. Hum. Genet. 19(3), 313–319 (2011)CrossRefGoogle Scholar
  5. 5.
    Dweep, H., Sticht, C., Pandey, P., et al.: miRWalk - database: prediction of possible miRNA binding sites by “walking” the genes of three genomes. J. Biomed. Inform. 44(5), 839–847 (2011)CrossRefGoogle Scholar
  6. 6.
    Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1, 211–8 (1936)zbMATHCrossRefGoogle Scholar
  7. 7.
    Fabian, M.R., Sonenberg, N.: The mechanics of miRNA-mediated gene silencing: a look under the hood of miRISC. Nat. Struct. Mol. Biol. 19(6), 586–593 (2012)CrossRefGoogle Scholar
  8. 8.
    Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002)zbMATHCrossRefGoogle Scholar
  9. 9.
    Holec, M., Gologuzov, V., Kléma, J.: miXGENE tool for learning from heterogeneous gene expression data using prior knowledge. In: Proceedings of the 27th IEEE International Symposium on Computer-Based Medical Systems 2014 (2014) (to appear)Google Scholar
  10. 10.
    Huang, G.T., Athanassiou, C., Benos, P.V.: mirConnX: condition-specific mRNA-microRNA network integrator. Nucleic Acids Res. 39, W416–W423 (2011). Web Server issueCrossRefGoogle Scholar
  11. 11.
    Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398. Springer, Heidelberg (1998) Google Scholar
  12. 12.
    Kim, D., Shin, H., Song, Y.S., et al.: Synergistic effect of different levels of genomic data for cancer clinical outcome prediction. J. Biomed. Inform. 45(6), 1191–1198 (2012)CrossRefGoogle Scholar
  13. 13.
    Kozomara, A., Griffiths-Jones, S.: miRBase: integrating microRNA annotation and deep-sequencing data. Nucleic Acids Res. 39, 152–157 (2011). Database-IssueCrossRefGoogle Scholar
  14. 14.
    Krek, A., Grün, D., Poy, M.N., et al.: Combinatorial microRNA target predictions. Nat. Genet. 37(5), 495–500 (2005)CrossRefGoogle Scholar
  15. 15.
    Lanza, G., Ferracin, M., Gafà, R., et al.: mRNA/microRNA gene expression profile in microsatellite unstable colorectal cancer. Mol. Cancer 6, 54 (2007)CrossRefGoogle Scholar
  16. 16.
    Lee, R.C., Feinbaum, R.L., Ambros, V.: The C. elegans heterochronic gene lin-4 encodes small RNAs with antisense complementarity to lin-14. Cell 75(5), 843–854 (1993)CrossRefGoogle Scholar
  17. 17.
    Lewis, B.P., Shih, I.H.H., et al.: Prediction of mammalian microRNA targets. Cell 115(7), 787–798 (2003)CrossRefGoogle Scholar
  18. 18.
    Li, W., Zhang, S.H., et al.: Identifying multi-layer gene regulatory modules from multi-dimensional genomic data. Bioinformatics 28(19), 2458–66 (2012)CrossRefGoogle Scholar
  19. 19.
    Morin, R., Bainbridge, M., Fejes, A., et al.: Profiling the HeLa S3 transcriptome using randomly primed cDNA and massively parallel short-read sequencing. BioTechniques 45(1), 81–94 (2008)CrossRefGoogle Scholar
  20. 20.
    Peng, X., Li, Y., Walters, K.A., et al.: Computational identification of hepatitis C virus associated microRNA-mRNA regulatory modules in human livers. BMC Genomics 10(1), 373 (2009)CrossRefGoogle Scholar
  21. 21.
    Pollack, J.R., Sørlie, T., Perou, C.M., et al.: Microarray analysis reveals a major direct role of DNA copy number alteration in the transcriptional program of human breast tumors. Proc. Natl. Acad. Sci. USA 99(20), 12963–12968 (2002)CrossRefGoogle Scholar
  22. 22.
    Rhyasen, G.W., Starczynowski, D.T.: Deregulation of microRNAs in myelodysplastic syndrome. Leukemia 26(1), 13–22 (2012)CrossRefGoogle Scholar
  23. 23.
    Sayed, D., Abdellatif, M.: MicroRNAs in development and disease. Physiol. Rev. 91(3), 827–887 (2011)CrossRefGoogle Scholar
  24. 24.
    Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. J. Mol. Biol. 147(1), 195–197 (1981)CrossRefGoogle Scholar
  25. 25.
    Stranger, B.E., Forrest, M.S., Dunning, M., et al.: Relative impact of nucleotide and copy number variation on gene expression phenotypes. Science 315(5813), 848–853 (2007)CrossRefGoogle Scholar
  26. 26.
    Tan Gana, N.H., Victoriano, A.F., Okamoto, T.: Evaluation of online miRNA resources for biomedical applications. Genes Cells 17(1), 11–27 (2012)CrossRefGoogle Scholar
  27. 27.
    Tran, D.H., Satou, K., Ho, T.B.: Finding microRNA regulatory modules in human genome using rule induction. BMC Bioinform. 9(12), S5 (2008)CrossRefGoogle Scholar
  28. 28.
    Vašíková, A., Běličková, M., Budinská, E., et al.: A distinct expression of various gene subsets in cd34+ cells from patients with early and advanced myelodysplastic syndrome. Leuk. Res. 34(12), 1566–1572 (2010)CrossRefGoogle Scholar
  29. 29.
    Wang, X., Naqa, I.M.E.: Prediction of both conserved and nonconserved microRNA targets in animals. Bioinformatics 24(3), 325–332 (2008)CrossRefGoogle Scholar
  30. 30.
    Witten, D.M., Tibshirani, R.J.: Extensions of sparse canonical correlation analysis with applications to genomic data. Stat. Appl. Genet. Mol. Biol. 8(1), 28 (2009)MathSciNetGoogle Scholar
  31. 31.
    Zhang, S.H., Li, Q., et al.: A novel computational framework for simultaneous integration of multiple types of genomic data to identify microRNA-gene regulatory modules. Bioinformatics 27(13), 401–409 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Jiří Kléma
    • 1
    Email author
  • Jan Zahálka
    • 1
  • Michael Anděl
    • 1
  • Zdeněk Krejčík
    • 2
  1. 1.Department of Computer Science and EngineeringCzech Technical UniversityPragueCzech Republic
  2. 2.Department of Molecular GeneticsInstitute of Hematology and Blood TransfusionPragueCzech Republic

Personalised recommendations