On the Computational Prediction of miRNA Promoters
MicroRNAs transcription regulation is an open topic in molecular biology and the identification of the promoters of microRNAs would give us relevant insights on cellular regulatory mechanisms. In the present study, we introduce a new computational methodo
- PDF / 130,728 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 8 Downloads / 201 Views
partment of Computer Engineering and Informatics, University of Patras, Patra, Greece {cmichail,korfiati,likothan}@ceid.upatras.gr 2 InSyBio Ltd., London, UK [email protected] 3 Department of Social Work, Technological Institute of Western Greece, Patra, Greece [email protected]
Abstract. MicroRNAs transcription regulation is an open topic in molecular biology and the identification of the promoters of microRNAs would give us relevant insights on cellular regulatory mechanisms. In the present study, we introduce a new computational methodology for the prediction of microRNA promoters, which is based on the hybrid combination of an adaptive genetic algorithm with a nu-Support Vector Regression (nu-SVR) classifier. This methodology uses genetic algorithms to locate the optimal features set and to optimize the parameters of the nu-SVR classifier. The main advantage of the proposed solution is that it systematically studies and calculates a vast number of features that can be used for promoters prediction including frequency-based properties, regulatory elements and epigenetic features. The proposed method also handles efficiently the issues of over-fitting, feature selection, convergence and class imbalance. Experimental results give accuracy over 87 % in the miRNA promoter prediction. Keywords: miRNA promoters Classification Feature selection Transcription start sites
Computational prediction
1 Introduction One of the current trends in molecular biology is studying the various types of short and long non-coding RNAs (ncRNAs) [1]. MicroRNAs (miRNAs) are the most thoroughly characterized subclass of short RNAs in the recent literature [2]. miRNAs are short (21–23 nt) and single stranded endogenous RNA molecules. They regulate protein coding genes by binding to the 3’ untranslated regions (3’ UTRs) of their target mRNAs. This binding event causes translational repression of the target gene or stimulates rapid degradation of the target transcript [3]. miRNAs are involved in diverse biological processes, including development, differentiation, apoptosis, cell proliferation, and disease [3]. A growing number of studies indicate that miRNAs play © IFIP International Federation for Information Processing 2016 Published by Springer International Publishing Switzerland 2016. All Rights Reserved L. Iliadis and I. Maglogiannis (Eds.): AIAI 2016, IFIP AICT 475, pp. 573–583, 2016. DOI: 10.1007/978-3-319-44944-9_51
574
C. Michail et al.
crucial roles in human disease development, progression, prognosis, diagnosis and evaluation of treatment response [4] and miRNAs have been linked to cancer, neurodegenerative and cardiovascular diseases. Many algorithms are able to predict miRNA genes and their targets, but their transcription regulation is still under investigation [5]. It is generally believed that intragenic (intronic, exonic) miRNAs (located in introns or exons of protein coding genes) are co-transcribed with their host genes [6], but literature has indicated that intragenic miRNA genes may be transcribed by
Data Loading...
