Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders.

Researchers

Journal

Modalities

Models

Abstract

Genomics data provide great opportunities for translational research and the clinical practice, e.g., for predicting disease stages. However, the classification of such data is a challenging task due to their high dimensionality, noise and heterogeneity. In recent years, deep learning classifiers generated much interest but due to their complexity, so far, little is known about the utility of this method for genomics. In this paper, we address this problem by studying a computational diagnostics task by classification of breast cancer and inflammatory bowel disease patients based on high-dimensional gene expression data.We provide a comprehensive analysis of the classification performance of deep belief networks (DBN) in dependence on its multiple model parameters and in comparison with support vector machines (SVM). Furthermore, we investigate combined classifiers that integrate deep belief networks with support vector machines. Such a classifier utilizes a DBN as representation learner forming the input for a SVM. Overall, our results provide guidelines for the complex usage of DBN for classifying gene expression data from complex diseases. This article is protected by copyright. All rights reserved.
FEBS Open Bio (2019) © 2019 The Authors. Published by FEBS Press and John Wiley & Sons Ltd.