LEMRG: Decision Rule Generation Algorithm for Mining MicroRNA Expression Data

  • Łukasz PiątekEmail author
  • Jerzy W. Grzymała-Busse
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 1028)


Recently, research on mining microRNA (or miRNA) expression data has received a lot of attention, mainly because of its role in gene regulation. However, such type of data – usually saved in the form of microarrays – are very specific, because they contain only a small number of cases (often less than 100) compared with large number of attributes (equal to several hundreds or even tens of thousand). The small number of cases available during the learning process can cause instability of the newly created classifiers. Secondly, the huge number of attributes imposes the necessity of selecting only a few dominant attributes strongly correlated with the decision. Thus, an application of fundamental machine learning approaches of mining microarray data and its further classification is problematic or even could just fail.

Thus, the main goal of our research is to develop the generalized algorithm of mining microarray data (including miRNA data sets), mainly to improve stability and, consequently, accuracy of classification for the newly created learning classifiers. The main concept of the novel approach is based on iteratively inducing many subsequent decision rule sets – called decision rule generations – instead of inducing only a single decision rule set, as it is done routinely. The decision rules have been chosen as the baseline classifiers of the newly developed LEMRG (Learning from Examples Module based on Rule Generations) algorithm mainly because the decision rule-based knowledge representation is easier for humans to comprehend, rather than other learning models. In our research we used a miRNA expression level learning data set describing 11 types of human cancers, while the testing data set contained poorly differentiated cases of only four types of cancers. As expected, our new classifiers – saved in the form of so-called cumulative decision rule sets – had better stability and accuracy of classification than single decision rule sets induced in the traditional manner. Furthermore, the LEMRG was compared with other machine learning models. It was proven that only 3 out of all 16 tested classifiers enabled so effective classification as our newly developed approach. Thus, using our cumulative set of decision rules, all cases of cancer from two selected concepts – colon and ovary – were correctly classified. Furthermore, we showed the role of these selected miRNAs as the potential biomarkers for diagnosis of tumors.

A preliminary result of our research on decision rule generations was initially presented at the first International Conference of Digital Medicine and Medical 3D Printing (17-19.06.2016, Nanjing, China).


MicroRNA MiRNA Decision rule generations Cumulative decision rule sets Data mining Induction of decision rules LEM2 MLEM2 GTS AQ LEMRG 



The research work of Łukasz Piątek on this chapter has been supported by ANDREA (A ctive N anocoated DR y-electrode for E eg A pplication) EU-funded FP7-PEOPLE Marie Curie I ndustry- A cademia P artnerships and P athways (IAPP) project.


  1. 1.
    Lu J, Getz G, Miska EA, Alvarez-Saavedra E, Lamb J, Peck D, Sweet-Cordero A, Ebet BL, Mak RH, Ferrando AA, Downing JR, Jacks T, Horvitz HR, Golub TR (2005) MicroRNA expression profiles classify human cancers. Nature 435:834–838CrossRefPubMedGoogle Scholar
  2. 2.
    Grzymała-Busse JW, Piątek, Ł (n.d.) LEMRG – decision rule generation algorithm for mining microRNA expression data. The preliminary research. In: Proc. of the 1st international conference of digital medicine & medical 3D printing, 17-19.06.2016, Nanjing, ChinaGoogle Scholar
  3. 3.
    Chee M, Yang R, Hubbell E, Berno A, Huang XC, Stern D, Winkler J, Lockhart DJ, Morris MS, Fodor PA (1996) Assessing genetic information with high-density dna arrays. Science 274:610–614CrossRefPubMedGoogle Scholar
  4. 4.
    Golub TR, Slonim DK, Tamayo P, Huard C, Gaasenbeek M, Mesirov JP, Coller H, Loh ML, Downing JR, Caligiuri MA, Bloomfield CD, Lander ES (1999) Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286:531–537CrossRefPubMedGoogle Scholar
  5. 5.
    Bontempi G (2007) A blocking strategy to improve gene selection for classification of gene expression data. IEEE/ACM Trans Comput biol Bioinforma 4:293–300CrossRefGoogle Scholar
  6. 6.
    Lazar C, Taminau J, Maganck S, Steenhoff D, Coletta A, Molter C, de Schaetzen V, Duque R, Bersini H, Nowé A (2012) A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE/ACM Trans Comput Biol Bioinforma 9:1106–1119CrossRefGoogle Scholar
  7. 7.
    Huang J, Fang H, Fan X (2010) Decision forest for classification gene expression data. Comput Biol Med 40:698–707CrossRefPubMedGoogle Scholar
  8. 8.
    Stiglic G, Rodriguez JJ, Kokol P (2010) Finding optimal classifiers for small feature sets in genomic and proteomics. Pattern Recognit Bioinforma Adv Neural Control Elsevier Neurocomputing 73:2346–2352Google Scholar
  9. 9.
    Chen AH, Tsau Y-W, Lin C-H (2010) Novel methods to identify biologically relevant genes for leukemia and prostate cancer from gene expression profiles. BMC Genomics 11:274. doi: 10.1186/1471-2164-11-274
  10. 10.
    Nanni L, Lumini A (2011) Wavelet selection for disease classification by DNA microarray data. Expert Syst Appl 38:990–995CrossRefGoogle Scholar
  11. 11.
    Chen AH, Lin C-H (2011) A novel support vector sampling technique to improve classification accuracy and to identify key genes of leukemia and prostate cancer. Expert Syst Appl 38:3209–3219CrossRefGoogle Scholar
  12. 12.
    Huerta EB, Duval B, Hao J (2010) A hybrid LDA and genetic algorithm for gene selection and classification of microarray data. Neurocomputing 73:2375–2383CrossRefGoogle Scholar
  13. 13.
    Ghorai S, Mukherjee A, Sengupta S, Dutta PK (2011) Cancer classification from gene expression data by NPPC ensemble. IEEE/ACM Trans Comput Biol Bioinform 8:659–671CrossRefPubMedGoogle Scholar
  14. 14.
    Ambros V (2004) The function of animal microRNAs. Nature 431:350–355CrossRefPubMedGoogle Scholar
  15. 15.
    Sanger Institute.
  16. 16.
    Kim VN, Nam JW (2006) Genomics on MicroRNA. Trends Genet 22:165–173CrossRefPubMedGoogle Scholar
  17. 17.
    Harfe BD (2005) MicroRNAs in vertebrate development. Curr Opin Genet Dev 15:410–415CrossRefPubMedGoogle Scholar
  18. 18.
    Bartel DP (2004) MicroRNA: genomic, biogenesis, mechanism, and function. Cell 116:281–297CrossRefPubMedGoogle Scholar
  19. 19.
    McManus MT (2003) MicroRNAs and cancer. Semin Cancer Biol 13:253–258CrossRefPubMedGoogle Scholar
  20. 20.
    Brown D, Shingara J, Keiger K, Shelton J, Lew K, Cannon B, Banks S, Wowk S, Byrom M, Cheng A, Wang X, Labourier E (2005) Cancer-related miRNAs uncovered by the mirVana miRNA microarray platform. Ambion Technotes Newsl 12:8–11Google Scholar
  21. 21.
    Tran DH, Ho TB, Pham TH, Satou K (2011) MicroRNA expression profiles for classification and analysis of tumor samples, special section on knowledge discovery, data mining and creativity support systems. IEICE Trans Inf Syst 94:416–422CrossRefGoogle Scholar
  22. 22.
    Ibrahim R, Yousri NA, Ismail MA, El-Makky NM MiRNA and gene expression based cancer classification using self-learning and co-training approaches. In: Proc. of the IEEE international conference on bioinformatics and biomedicine (BIBM 2013), 18-21.12.2013, Shanghai, China, p. 495–498Google Scholar
  23. 23.
    Lowery AJ, Miller N, Devaney A, McNeill RE, Davoren PA, Lemetre C, Benes V, Schmidt S, Blake J, Ball G, Kerin MJ (2009) MicroRNA signatures predict oestrogen receptor, progesterone receptor and MER2/neu receptor status in breast cancer. Breast Cancer Res 11:R27. doi: 10.1186/bcr2257 CrossRefPubMedPubMedCentralGoogle Scholar
  24. 24.
    Fang J, Grzymała-Busse JW (2006) Mining of microRNA expression data – a rough set approach. In: Proc. of the 1st international conference on rough sets and knowledge technology (RSKT 2006). Springer, Berlin, p. 758–765Google Scholar
  25. 25.
    Breiman L (1996) Bagging predictors. Mach Learn 24:123–140Google Scholar
  26. 26.
    Schapire RE (1990) The strength of weak learnability. Mach Learn 5:197–227Google Scholar
  27. 27.
    Freund Y (1995) An adaptive version of the boost by majority algorithm. Inf Comput 121:256–285CrossRefGoogle Scholar
  28. 28.
    Freund Y, Schapire RE Experiments with a new boosting algorithm. Proc. of the 13th international conference on machine learning (ICML 1996), 3-6.07.1997, Bari, Italy, pp 148–156Google Scholar
  29. 29.
    Freund Y, Schapire RE (1999) A short introduction to boosting. J Jpn Soc Artif Intell 14:771–780Google Scholar
  30. 30.
    Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 29:832–844Google Scholar
  31. 31.
    Ho TK (1995) Random decision forests. In: Proceedings of the 3rd international conference on document analysis and recognition, 14–16.08.1995, Montreal, QC, Canada, pp 278–282Google Scholar
  32. 32.
    Wang CW New ensemble machine learning method for classification and prediction on gene expression data. In: Proc. of the 28th IEEE EMBS annual international conference, 30.08-3.09.2006, New York, USA, p. 3478–3481Google Scholar
  33. 33.
    Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11:341–356CrossRefGoogle Scholar
  34. 34.
    Grzymała-Busse JW (1992) LERS – a system for learning from examples based on rough sets. In: Słowiński R (ed) Intelligent decision support. Handbook of applications and advanced of rough set theory. Kluwer Academic Publishers, Dordrecht, pp 3–18Google Scholar
  35. 35.
    Grzymała-Busse JW MLEM2 Discretization during rule induction. In: Proc. of the international conference on intelligent information processing and WEB mining systems, IIPWM 2003, Springer-Verlag, 02-05.06.2003, Zakopane (Poland), p. 499–50Google Scholar
  36. 36.
    Paja W (2008) Budowa optymalnych modeli uczenia na podstawie wtórnych źródeł wiedzy, PhD Thesis. AGH University of Science and Technology, Kraków (in Polish)Google Scholar
  37. 37.
    Grzymała-Busse JW (2005) Rule induction. In: Maimon O, Rokach L (eds) Chapter (13) in data mining and knowledge discovery handbook. Springer, New York, pp 277–294CrossRefGoogle Scholar
  38. 38.
    Grzymała-Busse JW (2004) C3.4 discretization of numerical attributes. In: Klösgen W, Żytkow J (eds) Handbook on data mining and knowledge discovery. Oxford University Press, Oxford, pp 218–225Google Scholar
  39. 39.
    Grzymała-Busse JW (2004) Rough set approach to incomplete data. In: Prof. of the international conference on artificial inteligence and soft computing (ICAISC 2004), Zakopane, Poland, Lecture Notes in Artificial Intelligence, 3070, Springer-Verlag, p. 50–55Google Scholar
  40. 40.
    Pawlak Z, Grzymała-Busse JW, Słowiński R, Ziarko W (1995) Rough sets. Commun ACM 38:89–95CrossRefGoogle Scholar
  41. 41.
    Żytkow JM (2002) Types and forms of knowledge: rules. In: Klösgen W, Żytkow JM (eds) Handbook of data mining and knowledge discovery. Oxford Press, Oxford, pp 51–54Google Scholar
  42. 42.
    Quinlan JR (1996) Bagging, boosting, and C4.5. In: Proc. of the 13th national conference on artificial intelligence, AAAI Press/MIT Press, Cambridge, MA, USA, pp 725–730Google Scholar
  43. 43.
    Quinlan JR (1993) C4.5, programs for empirical learning. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
  44. 44.
    Mitchell TM (1997) Machine learning. McGraw-Hill, Inc, New YorkGoogle Scholar
  45. 45.
    Stefanowski J (1998) Rough set based rule induction techniques for classification problems. In: Proceeding of 6th European congress on intelligent techniques and soft computing, 7-10.09.1998, Aachen (Germany), 1 pp 109–113Google Scholar
  46. 46.
    An A (2003.,No.4–5) Learning classification rules from data. Int J Comput Math Appl 45:737–748CrossRefGoogle Scholar
  47. 47.
    Grzymała-Busse JW (2006) Rough set strategies to data with missing attribute values. In: Lin TY, Ohsuga S, Liau CJ, Hu X (eds) Foundations and novel approaches in data mining, studies in computational intelligence, vol 9. Springer-Verlag, Heidelberg, pp 197–212Google Scholar
  48. 48.
    University of California, Irvine.
  49. 49.
    Michalski RS, Mozetic I, Hong J, Lavrac N The multi-purpose incremental system AQ15 and its testing application to three medical domains. Proc. of the AAAI’86, Philadelphia, USA, 1986, p. 1041–1045Google Scholar
  50. 50.
    Grzymała-Busse JW (1997) A new version of the rule induction system LERS. Fundam Informaticae 31:27–39Google Scholar
  51. 51.
    Hippe ZS (1997) Uczenie maszynowe – obiecującą strategią przetwarzania informacji w biznesie? Informatyka 4:27–31; 5:29–33 (in Polish)Google Scholar
  52. 52.
    Weiss S, Kulikowski CA (1991) Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems, Chapter How to Estimate the True Performance of a Learning System. Morgan Kaufmann Publishers, San Mateo, pp 17–49Google Scholar
  53. 53.
    Sharma TC, Jain M (2013) WEKA approach for comparative study of classification algorithms. Int J Adv Res Comput Commun Eng 2(4):1925–1931Google Scholar
  54. 54.
  55. 55.
    Pellatt DF, Stevens JR, Wolff RK, Mullany LE, Herrick JS, Samowitz W, Slattery ML (2016) Expression profiles of miRNA subsets distinguish human colorectal carnicoma and normal colonic mucosa. Clin Transl Gastroenterol 7(3), e152. doi: 10.1038/ctg.2016.11
  56. 56.
    Han C, Yu Z, Duan Z, Kan Q (2014) Role of microRNA-1 in human cancer and its therapeutic potentials. Biomed Res Int 2014., Article ID 428371:11Google Scholar
  57. 57.
    Hou N, Han J, Li J, Liu Y, Qin Y, Ni L, Song T, Huang C (2014) MicroRNA profiling in human colon cancer cells during 5-fluorouracil-induced autophagy. PLoS One 9(12), e114779,
  58. 58.
    Wang B, Shen Z, Gao Z, Zhao G, Wang C, Yang Y, Zhang J, Yan Y, Shen C, Jiang K, Te Y, Wang S (2015) MiR-194, commonly repressed in colorectal cancer, suppresses tumor growth by regulating the MAP 4K4/c-Jun/MDM2 signaling pathway. Cell Cycle 14(7):1046–1058. doi: 10.1080/15384101.2015.1007767 CrossRefPubMedPubMedCentralGoogle Scholar
  59. 59.
    Migliore C, Martin V, Leoni VP, Restivo A, Atzori L, Petrelli A, Isella C, Zorcolo L, Sarotto I, Casula G, Comoglio PM, Columbano A, Giordano S (2012) MiR-1 downregulation cooperates with MACC1 in promoting MET overexpression in human colon cancer. Clin Cancer Res 18:737–747CrossRefPubMedGoogle Scholar
  60. 60.
    Tang W, Jiang Y, Mu X, Xu L, Cheng W, Wang X (2014) MiR-135a functions as a tumor suppressor in epithelial ovarian cancer and regulates HOXA10 expression. Cell Signal:1420–1426. doi: 10.1016/j.cellsig.2014.03.002
  61. 61.
    Gao YC, Wu J (2015) MicroRNA-200c and microRNA-141 as potential diagnostic and prognostic biomarkers for ovarian cancer. Tumour Biol 36:4843–4850CrossRefPubMedGoogle Scholar
  62. 62.
    Miles GD, Seiler M, Rodriguez L, Rajagopal G, Bhanot G (2012) Identifying microRNA/mRNA dysregulations in ovarian cancer. BioMed Cent Res Notes. doi: 10.1186/1756-0500-5-164
  63. 63.
    Wyman SK, Parkin RK, Mitchell PS, Fritz BR, O’Briant K, Godwin AK, Urban N, Drescher CW, Knudsen BS, Tewari M (2009) Repertoire of microRNAs in epithelial ovarian cancer as determined by next generation sequencing of small RNA cDNA libraries. Public Libr Sci One. doi: 10.1371/journal.pone.0005311
  64. 64.
    Yekta S, Shih IH, Bartel DP (2004) MicroRNA-directed cleavage of HOXB8 mRNA. Science 304:594–596CrossRefPubMedGoogle Scholar
  65. 65.
    Eis PS, Tam W, Sun L, Chadburn A, Li Z, Gomez MF, Lund E, Dahlberg JE (2005) Accumulation of miR-155 and BIC RNA in human B cell lymphomas. Proc Natl Acad Sci USA 102:3627–3632CrossRefPubMedPubMedCentralGoogle Scholar
  66. 66.
    Wang LMJ, Ren AM, Wu HF, Tan RY, Tu RQ (2014) A ten-microRNA signature identified from a genome-wide microRNA expression profiling in human epithelial ovarian cancer. Public Libr Sci One.

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.Institute für Biomedizinische Technik und InformatikTechnische Universität IlmenauIlmenauGermany
  2. 2.Department of Expert Systems and Artificial IntelligenceUniversity of Information Technology and ManagementRzeszówPoland
  3. 3.Department of Electrical Engineering and Computer ScienceUniversity of KansasLawrenceUSA

Personalised recommendations