Travers Ching 1 , Daniel S. Himmelstein 2 , Brett K. Beaulieu-Jones 3 , Alexandr A. Kalinin 4 , Brian T. Do 5 , Gregory P. Way 2 , Enrico Ferrero 6 , Paul-Michael Agapow 7 , Michael Zietz 2 , Michael M. Hoffman 8 , 9 , 10 , Wei Xie 11 , Gail L. Rosen 12 , Benjamin J. Lengerich 13 , Johnny Israeli 14 , Jack Lanchantin 17 , Stephen Woloszynek 12 , Anne E. Carpenter 18 , Avanti Shrikumar 15 , Jinbo Xu 19 , Evan M. Cofer 20 , 21 , Christopher A. Lavender 22 , Srinivas C. Turaga 23 , Amr M. Alexandari 15 , Zhiyong Lu 24 , David J. Harris 25 , Dave DeCaprio 26 , Yanjun Qi 17 , Anshul Kundaje 15 , 16 , Yifan Peng 24 , Laura K. Wiley 27 , Marwin H. S. Segler 28 , Simina M. Boca 29 , S. Joshua Swamidass 30 , Austin Huang 31 , Anthony Gitter 32 , 33 , Casey S. Greene 2
4 April 2018
Journal of the Royal Society Interface
deep learning, genomics, precision medicine, machine learning
Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes and treatment of patients—and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.
Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.