Current progress and open challenges for applying deep learning across the biosciences

Nicolae Sapoval; Amirali Aghazadeh; Michael G. Nute; Dinler A. Antunes; Advait Balaji; Richard Baraniuk; C. J. Barberan; Ruth Dannenfelser; Chen Dun; Mohammadamin Edrisi; R. A.Leo Elworth; Bryce Kille; Anastasios Kyrillidis; Luay Nakhleh; Cameron R. Wolfe; Zhi Yan; Vicky Yao; Todd J. Treangen

doi:10.1038/s41467-022-29268-7

Current progress and open challenges for applying deep learning across the biosciences

Nicolae Sapoval, Amirali Aghazadeh, Michael G. Nute, Dinler A. Antunes, Advait Balaji, Richard Baraniuk, C. J. Barberan, Ruth Dannenfelser, Chen Dun, Mohammadamin Edrisi, R. A.Leo Elworth, Bryce Kille, Anastasios Kyrillidis, Luay Nakhleh, Cameron R. Wolfe, Zhi Yan, Vicky Yao, Todd J. Treangen

Houston Methodist

Research output: Contribution to journal › Review article › peer-review

188 Scopus citations

Abstract

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.

Original language	English (US)
Article number	1728
Pages (from-to)	1728
Journal	Nature Communications
Volume	13
Issue number	1
DOIs	https://doi.org/10.1038/s41467-022-29268-7
State	Published - Apr 1 2022

Keywords

Computational Biology
Deep Learning
Phylogeny
Proteins
Systems Biology

ASJC Scopus subject areas

General
General Physics and Astronomy
General Chemistry
General Biochemistry, Genetics and Molecular Biology

Access to Document

10.1038/s41467-022-29268-7

Cite this

Sapoval, N., Aghazadeh, A., Nute, M. G., Antunes, D. A., Balaji, A., Baraniuk, R., Barberan, C. J., Dannenfelser, R., Dun, C., Edrisi, M., Elworth, R. A. L., Kille, B., Kyrillidis, A., Nakhleh, L., Wolfe, C. R., Yan, Z., Yao, V., & Treangen, T. J. (2022). Current progress and open challenges for applying deep learning across the biosciences. Nature Communications, 13(1), 1728. Article 1728. https://doi.org/10.1038/s41467-022-29268-7

Sapoval, N, Aghazadeh, A, Nute, MG, Antunes, DA, Balaji, A, Baraniuk, R, Barberan, CJ, Dannenfelser, R, Dun, C, Edrisi, M, Elworth, RAL, Kille, B, Kyrillidis, A, Nakhleh, L, Wolfe, CR, Yan, Z, Yao, V & Treangen, TJ 2022, 'Current progress and open challenges for applying deep learning across the biosciences', Nature Communications, vol. 13, no. 1, 1728, pp. 1728. https://doi.org/10.1038/s41467-022-29268-7

@article{bb8ec83b33c545688fa307460d493d4f,

title = "Current progress and open challenges for applying deep learning across the biosciences",

abstract = "Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.",

keywords = "Computational Biology, Deep Learning, Phylogeny, Proteins, Systems Biology",

author = "Nicolae Sapoval and Amirali Aghazadeh and Nute, {Michael G.} and Antunes, {Dinler A.} and Advait Balaji and Richard Baraniuk and Barberan, {C. J.} and Ruth Dannenfelser and Chen Dun and Mohammadamin Edrisi and Elworth, {R. A.Leo} and Bryce Kille and Anastasios Kyrillidis and Luay Nakhleh and Wolfe, {Cameron R.} and Zhi Yan and Vicky Yao and Treangen, {Todd J.}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = apr,

day = "1",

doi = "10.1038/s41467-022-29268-7",

language = "English (US)",

volume = "13",

pages = "1728",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Current progress and open challenges for applying deep learning across the biosciences

AU - Sapoval, Nicolae

AU - Aghazadeh, Amirali

AU - Nute, Michael G.

AU - Antunes, Dinler A.

AU - Balaji, Advait

AU - Baraniuk, Richard

AU - Barberan, C. J.

AU - Dannenfelser, Ruth

AU - Dun, Chen

AU - Edrisi, Mohammadamin

AU - Elworth, R. A.Leo

AU - Kille, Bryce

AU - Kyrillidis, Anastasios

AU - Nakhleh, Luay

AU - Wolfe, Cameron R.

AU - Yan, Zhi

AU - Yao, Vicky

AU - Treangen, Todd J.

PY - 2022/4/1

Y1 - 2022/4/1

N2 - Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.

AB - Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.

KW - Computational Biology

KW - Deep Learning

KW - Phylogeny

KW - Proteins

KW - Systems Biology

UR - http://www.scopus.com/inward/record.url?scp=85127507526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85127507526&partnerID=8YFLogxK

U2 - 10.1038/s41467-022-29268-7

DO - 10.1038/s41467-022-29268-7

M3 - Review article

C2 - 35365602

AN - SCOPUS:85127507526

SN - 2041-1723

VL - 13

SP - 1728

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 1728

ER -

Current progress and open challenges for applying deep learning across the biosciences

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this