Yet Another SVM for MiRNA Recognition: yasMiR

We designed a new SVM for microRNA identification, whose novelty is two-folded: firstly many of its features incorporate the base-pairing probabilities provided by McCaskill’s algorithm, and secondly the classification performance is improved by using a certain similarity (“profile”based) measure between the training and test microRNAs and a set of carefully chosen (“pivot”) RNA sequences. Comparisons with some of the best existing SVMs for microRNA identification prove that our SVM obtains truly competitive results. Topical keywords: bioinformatics, molecular sequence classification, tools and methods for computational biology. Contact author: Liviu Ciortuz ([email protected]). Availability: The source code of our system and the datasets we used can be found at the address www.info.uaic.ro/∼ciortuz/yasmir.