New Methods for Splice Site Recognition

Abstract

Splice sites are locations in DNA which separate protein-coding regions (exons) from noncoding regions (introns). Accurate splice site detectors thus form important components of computational gene finders. We pose splice site recognition as a classification problem with the classifier learnt from a labeled data set consisting of only local information around the potential splice site. Note that finding the correct position of splice sites without using global information is a rather hard task. We analyze the genomes of the nematode Caenorhabditis elegans and of humans using specially designed support vector kernels. One of the kernels is adapted from our previous work on detecting translation initiation sites in vertebrates and another uses an extension to the well-known Fisher-kernel. We find excellent performance on both data sets.

We thank for valuable discussions with A. Zien, K. Karplus and T. Furey. G.R. would like to thank UC Santa Cruz for warm hospitality. This work was partially funded by DFG under contract JA 379/9-2, JA 379/7-2, MU 987/1-1, and NSF grant CCR-9821087. This work was supported by an award under the Merit Allocation Scheme on the National Facility of the Australian Partnerschip for Advanced Computing.

To our knowledge, on the splice site recognition problem, only the work of [13] explicitly documented the care it exercised in the design of the experiments.