Opportunities and obstacles for deep learning in biology and medicine

Abstract

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.

Affiliations

[1 ]Molecular Biosciences and Bioengineering Graduate Program, University of Hawaii at Manoa , Honolulu, HI, USA

[2 ]Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA

[3 ]Genomics and Computational Biology Graduate Group, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA

[4 ]Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI, USA

[5 ]Harvard Medical School , Boston, MA, USA

[6 ]Computational Biology and Stats, Target Sciences , GlaxoSmithKline, Stevenage, UK

[7 ]Data Science Institute, Imperial College London , London, UK

[8 ]Princess Margaret Cancer Centre , Toronto, Ontario, Canada

[9 ]Department of Medical Biophysics , University of Toronto, Toronto, Ontario, Canada

[10 ]Department of Computer Science , University of Toronto, Toronto, Ontario, Canada

[11 ]Electrical Engineering and Computer Science, Vanderbilt University , Nashville, TN, USA

[12 ]Ecological and Evolutionary Signal-processing and Informatics Laboratory, Department of Electrical and Computer Engineering, Drexel University , Philadelphia, PA, USA

[13 ]Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA, USA

[14 ]Biophysics Program, Stanford University , Stanford, CA, USA

[15 ]Department of Computer Science, Stanford University , Stanford, CA, USA

[16 ]Department of Genetics, Stanford University , Stanford, CA, USA

[17 ]Department of Computer Science, University of Virginia , Charlottesville, VA, USA

[18 ]Imaging Platform, Broad Institute of Harvard and MIT , Cambridge, MA, USA

[19 ]Toyota Technological Institute at Chicago , Chicago, IL, USA

[20 ]Department of Computer Science, Trinity University , San Antonio, TX, USA

[21 ]Lewis-Sigler Institute for Integrative Genomics, Princeton University , Princeton, NJ, USA

[22 ]Integrative Bioinformatics, National Institute of Environmental Health Sciences, National Institutes of Health , Research Triangle Park, NC, USA

[23 ]Howard Hughes Medical Institute , Janelia Research Campus, Ashburn, VA, USA

[24 ]National Center for Biotechnology Information and National Library of Medicine, National Institutes of Health , Bethesda, MD, USA

[25 ]Department of Wildlife Ecology and Conservation, University of Florida , Gainesville, FL, USA

[26 ]ClosedLoop.ai , Austin, TX, USA

[27 ]Division of Biomedical Informatics and Personalized Medicine, University of Colorado School of Medicine , Aurora, CO, USA

[28 ]Institute of Organic Chemistry, Westfälische Wilhelms-Universität Münster , Münster, Germany

[29 ]Innovation Center for Biomedical Informatics, Georgetown University Medical Center , Washington, DC, USA

[30 ]Department of Pathology and Immunology, Washington University in Saint Louis , St Louis, MO, USA

[31 ]Department of Medicine, Brown University , Providence, RI, USA

[32 ]Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison , Madison, WI, USA

[33 ]Morgridge Institute for Research , Madison, WI, USA

Author notes

e-mail: gitter@ 123456biostat.wisc.edu

e-mail: greenescientist@ 123456gmail.com

[†]

Author order was determined with a randomized algorithm.

Journal

Journal ID (nlm-ta): J R Soc Interface

Journal ID (iso-abbrev): J R Soc Interface

Journal ID (publisher-id): RSIF

Journal ID (hwp): royinterface

Title: Journal of the Royal Society Interface

Publisher: The Royal Society

ISSN (Print): 1742-5689

ISSN (Electronic): 1742-5662

Publication date (Print): April 2018

Publication date (Electronic): 4 April 2018

Publication date PMC-release 4 April 2018

Volume: 15

Issue: 141

PubMed ID: 29618526

PMC ID: 5938574

DOI: 10.1098/rsif.2017.0387

Publisher ID: rsif20170387

Copyright statement: © 2018 The Authors.

License:

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.

Product

Funding

Funded by: Gordon and Betty Moore Foundation, http://dx.doi.org/10.13039/100000936;

Award ID: GBMF 4552

Award ID: GBMF 4563

Funded by: National Institutes of Health, http://dx.doi.org/10.13039/100000002;

Award ID: DP2GM123485

Award ID: P30CA051008

Award ID: R01AI116794

Award ID: R01GM089652

Award ID: R01GM089753

Award ID: R01LM012222

Award ID: R01LM012482

Award ID: R21CA220398

Award ID: T32GM007753

Award ID: T32HG000046

Award ID: U54AI117924

Funded by: Roy and Diana Vagelos Scholars Program in the Molecular Life Sciences;

Funded by: U.S. National Library of Medicine, http://dx.doi.org/10.13039/100000092;

Award ID: Intramural Research Program

Funded by: National Science Foundation, http://dx.doi.org/10.13039/501100008982;

Award ID: 1245632

Award ID: 1531594

Award ID: 1564955

Funded by: Natural Sciences and Engineering Research Council of Canada, http://dx.doi.org/10.13039/501100000038;

Award ID: RGPIN-2015-3948

Funded by: NSF;

Award ID: 1245632

Award ID: 1531594

Award ID: 1564955

Funded by: Howard Hughes Medical Institute, http://dx.doi.org/10.13039/100000011;

Categories

Subject: 1004

Subject: 22

Subject: 44

Subject: Review Articles

Subject: Headline Review

Custom metadata

cover-date April, 2018