BioSPRINT: classification of intron and exon sequences using the SPRINT algorithm

An important problem for computer scientists as well as geneticists involves classifying particular items into common groups. This paper focuses on classifying sequences of DNA as either an intron or an exon. Insights from this classification can reduce the time needed for laboratory work to distinguish between introns and exons. Using a classification tree based on the SPRINT algorithm, sequences from the Drosophila melanogaster and the Caenorhabditis elegans genomes were used for training and testing. A large test sample error rate of 15% was shown for the Drosophila melanogaster, whereas the Caenorhabditis elegans was only 1.6%.