Deep Learning in Bioinformatics

Seonwoo Min, Byunghan Lee, Sungroh Yoon

Published 2016-03-21Version 1

As we are living in the era of big data, transforming biomedical big data into valuable knowledge has been one of the most important problems in bioinformatics. At the same time, deep learning has advanced rapidly since early 2000s and is recently showing a state-of-the-art performance in various fields. So naturally, applying deep learning in bioinformatics to gain insights from data is under the spotlight of both the academia and the industry. This article reviews some research of deep learning in bioinformatics. To provide a big picture, we categorized the research by both bioinformatics domains - omics, biomedical imaging, biomedical signal processing - and deep learning architectures - deep neural network, convolutional neural network, recurrent neural network, modified neural network - as well as present brief descriptions of each work. Additionally, we introduce a few issues of deep learning in bioinformatics such as problems of class imbalance data and suggest future research directions such as multimodal deep learning. We believe that this paper could provide valuable insights and be a starting point for researchers to apply deep learning in their bioinformatics studies.