CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification

BMC Bioinformatics

Riccardo Rizzo¹  Domenico Amato²  Giosue’ Lo Bosco³ 

[1] CNR-ICAR, National Research Council of Italy, Via Ugo La Malfa, 153, 90146, Palermo, Italy;Dipartimento di Matematica e Informatica, Università degli studi di Palermo, Via Archirafi, 34, 90123, Palermo, Italy;Dipartimento di Matematica e Informatica, Università degli studi di Palermo, Via Archirafi, 34, 90123, Palermo, Italy;Dipartimento di Scienze per l’Innovazione tecnologica, Istituto Euro-Mediterraneo di Scienza e Tecnologia, Via Michele Miraglia, 20, 9039, Palermo, Italy;

关键词: Nucleosome classification;    Epigenetic;    Deep learning networks;    Recurrent neural networks;   

DOI  :  10.1186/s12859-020-03627-x

来源: Springer

【 摘 要 】

BackgroundNucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data.ResultsIn this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel levels are devoted to catching both non periodic and periodic DNA string features. A dense layer is devoted to their combination to give a final classification.ConclusionsResults computed on public data sets of different organisms show that CORENup is a state of the art methodology for nucleosome positioning identification based on a Deep Neural Network architecture. The comparisons have been carried out using two groups of datasets, currently adopted by the best performing methods, and CORENup has shown top performance both in terms of classification metrics and elapsed computation time.

【 授权许可】

CC BY