Recognition of Promoters in DNA Sequences Using Weightily Averaged One-dependence Estimators

Abstract

The completion of the human genome project in the last decade has generated a strong demand in computational analysis techniques in order to fully exploit the acquired human genome database. The human genome project generated a perplexing mass of genetic data which necessitates automatic genome annotation. There is a growing interest in the process of gene finding and gene recognition from DNA sequences. In genetics, a promoter is a segment of a DNA that marks the starting point of transcription of a particular gene. Therefore, recognizing promoters is a one step towards gene finding in DNA sequences. Promoters also play a fundamental role in many other vital cellular processes. Aberrant promoters can cause a wide range of diseases including cancers. This paper describes a state-of-the-art machine learning based approach called weightily averaged one-dependence estimators to tackle the problem of recognizing promoters in genetic sequences. To lower the computational complexity and to increase the generalization capability of the system, we employ an entropy-based feature extraction approach to select relevant nucleotides that are directly responsible for promoter recognition. We carried out experiments on a dataset extracted from the biological literature for a proof-of-concept. The proposed system has achieved an accuracy of 97.17% in classifying promoters. The experimental results demonstrate the efficacy of our framework and encourage us to extend the framework to recognize promoter sequences in various species of higher eukaryotes.