Machine Learning Reveals the Critical Interactions for SARS-CoV-2 Spike Protein Binding to ACE2

Anna Pavlova; Zijian Zhang; Atanu Acharya; Diane L. Lynch; Yui Tik Pang; Zhongyu Mou; Jerry M. Parks; Chris Chipot; James C. Gumbart

doi:10.1021/acs.jpclett.1c01494

Machine Learning Reveals the Critical Interactions for SARS-CoV-2 Spike Protein Binding to ACE2

Anna Pavlova, Zijian Zhang, Atanu Acharya, Diane L. Lynch, Yui Tik Pang, Zhongyu Mou, Jerry M. Parks, Chris Chipot, James C. Gumbart

Molecular Biophysics

Research output: Contribution to journal › Article › peer-review

39 Scopus citations

Abstract

SARS-CoV and SARS-CoV-2 bind to the human ACE2 receptor in practically identical conformations, although several residues of the receptor-binding domain (RBD) differ between them. Herein, we have used molecular dynamics (MD) simulations, machine learning (ML), and free-energy perturbation (FEP) calculations to elucidate the differences in binding by the two viruses. Although only subtle differences were observed from the initial MD simulations of the two RBD-ACE2 complexes, ML identified the individual residues with the most distinctive ACE2 interactions, many of which have been highlighted in previous experimental studies. FEP calculations quantified the corresponding differences in binding free energies to ACE2, and examination of MD trajectories provided structural explanations for these differences. Lastly, the energetics of emerging SARS-CoV-2 mutations were studied, showing that the affinity of the RBD for ACE2 is increased by N501Y and E484K mutations but is slightly decreased by K417N.

Original language	English
Pages (from-to)	5494-5502
Number of pages	9
Journal	Journal of Physical Chemistry Letters
Volume	12
Issue number	23
DOIs	https://doi.org/10.1021/acs.jpclett.1c01494
State	Published - Jun 17 2021

Funding

Computational resources were provided through the Extreme Science and Engineering Discovery Environment (XSEDE; TG-MCB130173), which is supported by the National Science Foundation (NSF; ACI-1548562). This work also used the Hive cluster, which is supported by the National Science Foundation under Grant Number 1828187 and is managed by the Partnership for an Advanced Computing Environment (PACE) at the Georgia Institute of Technology. Z.Z. and A.P. acknowledge support from the College of Sciences at the Georgia Institute of Technology. C.C. acknowledges support from the Agence Nationale de la Recherche (grants ProteaseInAction and Contrats Doctoraux en Intelligence Artificielle) and from the Lorraine Université d’Excellence initiative.

Funders	Funder number
College of Sciences
Lorraine Université d’Excellence
National Science Foundation	1828187, ACI-1548562
Georgia Institute of Technology
Agence Nationale de la Recherche

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1021/acs.jpclett.1c01494

Cite this

@article{d9214169e10540508714ce81652d8615,

title = "Machine Learning Reveals the Critical Interactions for SARS-CoV-2 Spike Protein Binding to ACE2",

abstract = "SARS-CoV and SARS-CoV-2 bind to the human ACE2 receptor in practically identical conformations, although several residues of the receptor-binding domain (RBD) differ between them. Herein, we have used molecular dynamics (MD) simulations, machine learning (ML), and free-energy perturbation (FEP) calculations to elucidate the differences in binding by the two viruses. Although only subtle differences were observed from the initial MD simulations of the two RBD-ACE2 complexes, ML identified the individual residues with the most distinctive ACE2 interactions, many of which have been highlighted in previous experimental studies. FEP calculations quantified the corresponding differences in binding free energies to ACE2, and examination of MD trajectories provided structural explanations for these differences. Lastly, the energetics of emerging SARS-CoV-2 mutations were studied, showing that the affinity of the RBD for ACE2 is increased by N501Y and E484K mutations but is slightly decreased by K417N.",

author = "Anna Pavlova and Zijian Zhang and Atanu Acharya and Lynch, {Diane L.} and Pang, {Yui Tik} and Zhongyu Mou and Parks, {Jerry M.} and Chris Chipot and Gumbart, {James C.}",

note = "Publisher Copyright: {\textcopyright} 2021 American Chemical Society.",

year = "2021",

month = jun,

day = "17",

doi = "10.1021/acs.jpclett.1c01494",

language = "English",

volume = "12",

pages = "5494--5502",

journal = "Journal of Physical Chemistry Letters",

issn = "1948-7185",

publisher = "American Chemical Society",

number = "23",

}

TY - JOUR

T1 - Machine Learning Reveals the Critical Interactions for SARS-CoV-2 Spike Protein Binding to ACE2

AU - Pavlova, Anna

AU - Zhang, Zijian

AU - Acharya, Atanu

AU - Lynch, Diane L.

AU - Pang, Yui Tik

AU - Mou, Zhongyu

AU - Parks, Jerry M.

AU - Chipot, Chris

AU - Gumbart, James C.

PY - 2021/6/17

Y1 - 2021/6/17

N2 - SARS-CoV and SARS-CoV-2 bind to the human ACE2 receptor in practically identical conformations, although several residues of the receptor-binding domain (RBD) differ between them. Herein, we have used molecular dynamics (MD) simulations, machine learning (ML), and free-energy perturbation (FEP) calculations to elucidate the differences in binding by the two viruses. Although only subtle differences were observed from the initial MD simulations of the two RBD-ACE2 complexes, ML identified the individual residues with the most distinctive ACE2 interactions, many of which have been highlighted in previous experimental studies. FEP calculations quantified the corresponding differences in binding free energies to ACE2, and examination of MD trajectories provided structural explanations for these differences. Lastly, the energetics of emerging SARS-CoV-2 mutations were studied, showing that the affinity of the RBD for ACE2 is increased by N501Y and E484K mutations but is slightly decreased by K417N.

AB - SARS-CoV and SARS-CoV-2 bind to the human ACE2 receptor in practically identical conformations, although several residues of the receptor-binding domain (RBD) differ between them. Herein, we have used molecular dynamics (MD) simulations, machine learning (ML), and free-energy perturbation (FEP) calculations to elucidate the differences in binding by the two viruses. Although only subtle differences were observed from the initial MD simulations of the two RBD-ACE2 complexes, ML identified the individual residues with the most distinctive ACE2 interactions, many of which have been highlighted in previous experimental studies. FEP calculations quantified the corresponding differences in binding free energies to ACE2, and examination of MD trajectories provided structural explanations for these differences. Lastly, the energetics of emerging SARS-CoV-2 mutations were studied, showing that the affinity of the RBD for ACE2 is increased by N501Y and E484K mutations but is slightly decreased by K417N.

UR - http://www.scopus.com/inward/record.url?scp=85108387143&partnerID=8YFLogxK

U2 - 10.1021/acs.jpclett.1c01494

DO - 10.1021/acs.jpclett.1c01494

M3 - Article

C2 - 34086459

AN - SCOPUS:85108387143

SN - 1948-7185

VL - 12

SP - 5494

EP - 5502

JO - Journal of Physical Chemistry Letters

JF - Journal of Physical Chemistry Letters

IS - 23

ER -

Machine Learning Reveals the Critical Interactions for SARS-CoV-2 Spike Protein Binding to ACE2

Abstract

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this