Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations

Lars Elend; Luise Jacobsen; Tim Cofala; Jonas Prellberg; Thomas Teusch; Oliver Kramer; Ilia A. Solov’Yov

doi:10.3390/molecules27134020

Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations

Lars Elend, Luise Jacobsen, Tim Cofala, Jonas Prellberg, Thomas Teusch, Oliver Kramer^*, Ilia A. Solov’Yov

^*Kontaktforfatter

University of Oldenburg

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

23 Downloads (Pure)

Abstract

Drug design is a time-consuming and cumbersome process due to the vast search space of drug-like molecules and the difficulty of investigating atomic and electronic interactions. The present paper proposes a computational drug design workflow that combines artificial intelligence (AI) methods, i.e., an evolutionary algorithm and artificial neural network model, and molecular dynamics (MD) simulations to design and evaluate potential drug candidates. For the purpose of illustration, the proposed workflow was applied to design drug candidates against the main protease of severe acute respiratory syndrome coronavirus 2. From the ∼140,000 molecules designed using AI methods, MD analysis identified two molecules as potential drug candidates.

Originalsprog	Engelsk
Artikelnummer	4020
Tidsskrift	Molecules
Vol/bind	27
Udgave nummer	13
Antal sider	25
ISSN	1420-3049
DOI	https://doi.org/10.3390/molecules27134020
Status	Udgivet - jul. 2022

Bibliografisk note

Funding Information:
Acknowledgments: Computational resources for the simulations were provided by the CARL Cluster at the Carl-von-Ossietzky University Oldenburg, which is supported by the DFG and the ministry for science and culture of Lower Saxony. The work was supported by the North-German Supercomputing Alliance (HLRN).

Funding Information:
Funding: This research was funded by the Danish Councils for Independent Research, the Volkswagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)).

Funding Information:
This research was funded by the Danish Councils for Independent Research, the Volk-swagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)).

Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Dokumenter og links

10.3390/molecules27134020Licens: CC BY

Open access versionForlagets udgivne version, 13,3 MBLicens: CC BY

Citationsformater

@article{0f7f97db0af14385bb1a50899877fd47,

title = "Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations",

abstract = "Drug design is a time-consuming and cumbersome process due to the vast search space of drug-like molecules and the difficulty of investigating atomic and electronic interactions. The present paper proposes a computational drug design workflow that combines artificial intelligence (AI) methods, i.e., an evolutionary algorithm and artificial neural network model, and molecular dynamics (MD) simulations to design and evaluate potential drug candidates. For the purpose of illustration, the proposed workflow was applied to design drug candidates against the main protease of severe acute respiratory syndrome coronavirus 2. From the ∼140,000 molecules designed using AI methods, MD analysis identified two molecules as potential drug candidates.",

keywords = "artificial intelligence, drug design, evolutionary algorithms, molecular dynamics, neural networks, SARS-CoV-2",

author = "Lars Elend and Luise Jacobsen and Tim Cofala and Jonas Prellberg and Thomas Teusch and Oliver Kramer and Solov{\textquoteright}Yov, {Ilia A.}",

note = "Funding Information: Acknowledgments: Computational resources for the simulations were provided by the CARL Cluster at the Carl-von-Ossietzky University Oldenburg, which is supported by the DFG and the ministry for science and culture of Lower Saxony. The work was supported by the North-German Supercomputing Alliance (HLRN). Funding Information: Funding: This research was funded by the Danish Councils for Independent Research, the Volkswagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)). Funding Information: This research was funded by the Danish Councils for Independent Research, the Volk-swagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)). Publisher Copyright: {\textcopyright} 2022 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2022",

month = jul,

doi = "10.3390/molecules27134020",

language = "English",

volume = "27",

journal = "Molecules",

issn = "1420-3049",

publisher = "MDPI",

number = "13",

}

TY - JOUR

T1 - Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations

AU - Elend, Lars

AU - Jacobsen, Luise

AU - Cofala, Tim

AU - Prellberg, Jonas

AU - Teusch, Thomas

AU - Kramer, Oliver

AU - Solov’Yov, Ilia A.

N1 - Funding Information: Acknowledgments: Computational resources for the simulations were provided by the CARL Cluster at the Carl-von-Ossietzky University Oldenburg, which is supported by the DFG and the ministry for science and culture of Lower Saxony. The work was supported by the North-German Supercomputing Alliance (HLRN). Funding Information: Funding: This research was funded by the Danish Councils for Independent Research, the Volkswagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)). Funding Information: This research was funded by the Danish Councils for Independent Research, the Volk-swagen Foundation (Lichtenberg Professorship to IAS), the DFG, German Research Foundation, (GRK1885—Molecular Basis of Sensory Biology, SFB 1372—Magnetoreception and Navigation in Vertebrates, and GRK 1765/2—Research Training Group SCARE), as well as the ministry for science and culture of Lower Saxony (Simulations meet experiments on the nanoscale: Opening up the quantum world to artificial intelligence (SMART)). Publisher Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2022/7

Y1 - 2022/7

N2 - Drug design is a time-consuming and cumbersome process due to the vast search space of drug-like molecules and the difficulty of investigating atomic and electronic interactions. The present paper proposes a computational drug design workflow that combines artificial intelligence (AI) methods, i.e., an evolutionary algorithm and artificial neural network model, and molecular dynamics (MD) simulations to design and evaluate potential drug candidates. For the purpose of illustration, the proposed workflow was applied to design drug candidates against the main protease of severe acute respiratory syndrome coronavirus 2. From the ∼140,000 molecules designed using AI methods, MD analysis identified two molecules as potential drug candidates.

AB - Drug design is a time-consuming and cumbersome process due to the vast search space of drug-like molecules and the difficulty of investigating atomic and electronic interactions. The present paper proposes a computational drug design workflow that combines artificial intelligence (AI) methods, i.e., an evolutionary algorithm and artificial neural network model, and molecular dynamics (MD) simulations to design and evaluate potential drug candidates. For the purpose of illustration, the proposed workflow was applied to design drug candidates against the main protease of severe acute respiratory syndrome coronavirus 2. From the ∼140,000 molecules designed using AI methods, MD analysis identified two molecules as potential drug candidates.

KW - artificial intelligence

KW - drug design

KW - evolutionary algorithms

KW - molecular dynamics

KW - neural networks

KW - SARS-CoV-2

U2 - 10.3390/molecules27134020

DO - 10.3390/molecules27134020

M3 - Journal article

C2 - 35807268

AN - SCOPUS:85133162184

SN - 1420-3049

VL - 27

JO - Molecules

JF - Molecules

IS - 13

M1 - 4020

ER -

Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations

Abstract

Bibliografisk note

Dokumenter og links

Fingeraftryk

Citationsformater