Prediction of human microRNA hairpins using only positive sample learning

Abstract

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 nucleo- tides (nt) long and derived from 60-90 nt RNA hairpin structures, called miRNA hairpins. A lar- ger number of sequence segments in the human genome have been computationally identified with such 60-90 nt hairpins, however the major- ity of them are not miRNA hairpins. Most exist- ing computational methods for predicting miRNA hairpins are based on a two-class classi- fier to distinguish between miRNA hairpins and other sequence segments with hairpin struc- tures. The difficulty of these methods is how to select hairpins as negative examples of miRNA hairpins in the training dataset, since only a few miRNA hairpins are available. Therefore, these classifiers 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 hair- pins among the hairpin structures. Different from existing methods for predicting miRNA hairpins, the one-class SVM classifier is trained only on the information of the miRNA class. We also il- lustrate some examples of predicting miRNA hairpins in human chromosomes 10, 15, and 21, where our method overcomes the above disad- vantages of existing two-class methods.