Algorithms for Promoter Prediction in DNA Sequences

Abstract

Nowadays, the prediction of promoters has attracted many researchers’ attention. Unfortunately, most previous prediction algorithms did not provide high enough sensitivity and specificity. The goal of this paper is to develop an efficient prediction algorithm that can increase the detection power (power = 1 - false negative). We present two methods that use the computer power to calculate all possible patterns which are the possible features of promoters. The first method we present FTSS (Fixed Transcriptional Start Site) uses the known TSS positions of promoter sequences to train the score file that helps us in promoter prediction. The other method is NTSS (Nonfixed TSS). The TSS positions of promoter sequences used in NTSS are assumed to be unknown, and NTSS will not take the absolute positions of TSSs into consideration. By the experimental results, our prediction has higher correct rate than other previous methods.