BIOINFORMATICS Accurate identification of alternatively spliced exons using support vector machine

Motivation: Alternative splicing is a major component of the regulation acting on mammalian transcriptomes. It is esti-mated that over half of all human genes have more than one splice variant. Previous studies have shown that alterna-tively spliced exons possess several features that distinguish them from constitutively spliced ones. Recently, we have demonstrated that such features can be used to distinguish alternative from constitutive exons. In the current study we use advanced machine learning methods to generate robust alternative exons classifier. Results: We extracted several hundred local sequence featu-res of constitutive as well as alternative exons. Using feature selection methods we find seven attributes that are dominant for the task of classification. Several less informative featu-res help to slightly increase the performance of the classifier. The classifier achieves a true positive rate of 50 % for a false positive rate of 0.5%. This result enables one to reliably iden-tify alternatively spliced exons in exon databases that are believed to be dominated by constitutive exons. Availability: Upon request from the authors. Contact