Abstract

BEDOYA, Óscar  and  BUSTAMANTE, Santiago. CNN-PROMOTER, NEW CONSENSUS PROMOTER PREDICTION PROGRAM BASED ON NEURAL NETWORKS. Rev.EIA.Esc.Ing.Antioq [online]. 2011, n.15, pp.153-164. ISSN 1794-1237.

A new promoter prediction program called CNN-Promoter is presented. CNN-Promoter allows DNA sequences to be submitted and predicts them as promoter or non-promoter. Several methods have been developed to predict the promoter regions of genomes in eukaryotic organisms including algorithms based on Markov's models, decision trees, and statistical methods. Although there are plenty of programs proposed, there is still a need to improve the sensitivity and specificity values. In this paper, a new program is proposed; it is based on the consensus strategy of using experts to make a better prediction. The consensus strategy is developed by using neural networks. During the training process, the sensitivity and specificity were 100 % and during the test process the model reaches a sensitivity of 74.5 % and a specificity of 82.7 %.

Keywords : Promoter prediction; neural networks; consensus strategy.

        · abstract in Spanish | Portuguese     · text in English     · English ( pdf )