Daniel Pasaila, Irina Mohorianu, Andrei Sucila, Stefan Pantiru, Liviu Ciortuz

We designed a new SVM for microRNA identification,whose novelty is two-folded: firstly many of its features incorporatethe base-pairing probabilities provided by McCaskill’s algorithm, and secondly the classification performanceis improved by using a certain similarity (“profile”-based) measure between the training and test microRNAsand a set of carefully chosen (“pivot”) RNA sequences.Comparisons with some of the best existing SVMs for microRNAidentification prove that our SVM obtains trulycompetitive results.

Full Document (PDF)

Bibtex

@TechReport{phd_thesis,
    author = "Mihaela Brut",
    title = "{Ontology-Based Modeling and Recommendation Techniques for Adaptive Hypermedia Systems}",
    institution = "``Al.I.Cuza'' University of Ia{c s}i, Faculty of Computer Science",
    year = "2010",
    number = "TR 10-01",
    url = "https://publications.info.uaic.ro/technical-reports/archive/tr10-01-2010-yet-another-svm-for-mirna-recognition-yasmir/"
}