Prediction of microRNA Hairpins using One-Class Support Vector Machines

MicroRNAs(miRNAs) are small molecular non- coding RNAs that have important roles in the post-transcriptional mechanism of animals and plants. They are commonly 21-25 nucleotides (nt) long and derived from 60-90 nt RNA hairpin structures, called miRNA hairpins. A larger amount of sequence segments in the human genome have been computationally identified with such a 60-90 nt hairpin, however a majority of them are not miRNA hairpins. Most computational methods so far for predicting miRNA hairpins were based on a two-class classifier to distinguish between miRNA hairpins and the sequence segments with a hairpin structures. The difficulty of these methods is how to select hairpins as the negative examples of miRNA hairpins in the classifier-training datasets since only few miRNA hairpins are available. Therefore, their classifier may be mis-trained due to some false negative examples of the training dataset. In this paper, we introduce a one-class support vector machine (SVM) method to predict miRNA hairpins from the hairpin structures. Different from existing methods for predicting miRNA hairpins, the one-class SVM model is trained only on the information of the miRNA class. We also illustrated some examples of predicting miRNA hairpins in human chromosomes 10, 15, and 21 where our method overcomes the above disadvantage of existing two- class methods.