Prediction of human microRNA hairpins using only positive sample learning

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 number of sequence segments in the human genome have been computationally identified with such 60-90 nt hairpins, however the majority of them are not miRNA hairpins. Most existing computational methods for predicting miRNA hairpins are based on a two-class classifier to distinguish between miRNA hairpins and other sequence segments with hairpin structures. 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 hairpins 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 illustrate some examples of predicting miRNA hairpins in human chromosomes 10, 15, and 21, where our method overcomes the above disadvantages of existing two-class methods.