 |
    |
Predicting Human miRNA Target Genes Using a Novel Evolutionary Methodology
Korfiati Aigli1, Kleftogiannis Dimitris2, Theofilatos Konstantinos1, Likothanassis Spiros1, Tsakalidis Athanasios1, and Mavroudi Seferina1
1Department of Computer Engineering and Informatics, University of Patras, Greece
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
2Math. and Computer Sciences and Engineering, King Abdullah Univ. of Science and Technology
[email protected]
Abstract. The discovery of miRNAs had great impacts on traditional biology. Typically, miRNAs have the potential to bind to the 3’untraslated region (UTR) of their mRNA target genes for cleavage or translational repression. The experimental identification of their targets has many drawbacks including cost, time and low specificity and these are the reasons why many computational approaches have been developed so far. However, existing computational approaches do not include any advanced feature selection technique and they are facing problems concerning their classification performance and their interpretability. In the present paper, we propose a novel hybrid methodology which combines genetic algorithms and support vector machines in order to locate the optimal feature subset while achieving high classification performance. The proposed methodology was compared with two of the most promising existing methodologies in the problem of predicting human miRNA targets. Our approach outperforms existing methodologies in terms of classification performances while selecting a much smaller feature subset.
Keywords: miRNAs, miRNA targets, genetic algorithms, evolutionary computation, Support Vector Machines, Machine Learning classification, multiobjective optimization
LNAI 7297, p. 291 ff.
[email protected]
© Springer-Verlag Berlin Heidelberg 2012