Paired Spectral Content Measure for Gene and Exon Prediction in Eukaryotes

Abstract

In this paper, we report on a new discrete Fourier transform (DFT) based method for gene and exon prediction in eukaryotes. The proposed paired spectral content (PSC) measure is compared with the well-known DFT based spectral content and spectral rotation measures, using the GENSCAN test set. False positive vs. sensitivity, receiver operating characteristic (ROC) curve and exonic nucleotides detected as false positive results all show that the newly proposed PSC outperforms existing methods, with 50% less DFT processing.