A DEEP LEARNING NEURAL NETWORK FOR NUCLEOSOME IDENTIFICATION

The basic unit of eukaryotic chromatin is the nucleosome, consisting of about 150bp of DNA wrapped around a protein core made of histone proteins. Nucleosomes position is modulated in vivo to regulate fundamental nuclear processes. Several studies have shown that nucleosome positioning plays an important role in gene regulation and that distinct DNA sequence features have been identified to be associated with nucleo- some positioning. Starting from this suggestion, the identification of nucleosomes on a genomic scale has been successfully performed by DNA sequence features representation and classical supervised classification methods such as Support Vector Machines, Logistic regression and so on. Taking in consideration the successful application of the deep neural networks on several challenging classification problems, in this paper we want to investigate on their potentiality in solving the aforementioned task.