Search

DNA sequences are the basic data type that is processed to perform a generic study of biological data analysis. One key component of the biological analysis is represented by sequence classification, a methodology that is widely used to analyze sequential data of different nature. However, its application to DNA sequences requires a proper representation of such sequences, which is still an open research problem. Machine Learning (ML) methodologies have given a fundamental contribution to the solution of the problem. Among them, recently, also Deep Neural Network (DNN) models have shown strongly encouraging results. In this chapter, we deal with specific classification problems related to two biological scenarios: (A) metagenomics and (B) chromatin organization. The investigations have been carried out by considering DNA sequences as input data for the classification methodologies. In particular, we study and test the efficacy of (1) different DNA sequence representations and (2) several Deep Learning (DL) architectures that process sequences for the solution of the related supervised classification problems. Although developed for specific classification tasks, we think that such architectures could be served as a suggestion for developing other DNN models that process the same kind of input.

Background Nucleosomes 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. Results In 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. Conclusions Results 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.

Nucleosomes are the fundamental repeating unit of chromatin. A nucleosome is an 8 histone proteins complex, in which approximately 147–150 pairs of DNA bases bind. Several biological studies have clearly stated that the regulation of cell type-specific gene activities are influenced by nucleosome positioning. Bioinformatic studies have improved those results showing proof of sequence specificity in nucleosomes’ DNA fragment. In this work, we present a recurrent neural network that uses nucleosome sequence features representation for their classification. In particular, we implement an architecture which stacks convolutional and long short-term memory layers, with the main purpose to avoid the features extraction and selection steps. We have computed classifications using eight datasets of three different organisms with a growing genome complexity, from yeast to human. We have also studied the capability of the model trained on the highest complex species in recognizing nucleosomes of the other organisms.