Neural Classification of E.coli Promoters Using Selected DNA Profiles

Abstract

Previous research into the neural classification of E.coli promoters has focused on the use of raw DNA sequences and alignment methods. In this paper, we use sequence dependent structural profiles of DNA to train neural networks for promoter recognition. In addition to this, we evaluate the impact of different types of non-promoters used in training and testing on the classification accuracy. 872 E.coli promoters were used in addition to three types of non-promoters, random sequences with the same base frequency as the promoter sequences, genes selected from E.coli and random sequences with the same base frequencies as the gene non-promoters. Raw DNA sequences were then converted to stacking energy and GC-trinucleotide profiles. We found the promoter classification accuracy using structural profiles was comparable to other methods. However, our approach has the advantage of not requiring finding the -35 and -10 hexamers and alignment of the DNA. Overall, using non-promoters from coding regions and random sequences with the same base frequency as the gene non-promoter resulted in the best classification accuracy.