The coronavirus disease 2019 (COVID-19) global pandemic resulted in millions of people becoming infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and close to seven million deaths worldwide. It is essential to further explore and design effective COVID-19 treatment drugs that target the main protease of SARS-CoV-2, a major target for COVID-19 drugs. In this study, machine learning was applied for predicting the SARS-CoV-2 main protease binding of Food and Drug Administration (FDA)-approved drugs to assist in the identification of potential repurposing candidates for COVID-19 treatment. Ligands bound to the SARS-CoV-2 main protease in the Protein Data Bank and compounds experimentally tested in SARS-CoV-2 main protease binding assays in the literature were curated. These chemicals were divided into training (516 chemicals) and testing (360 chemicals) data sets. To identify SARS-CoV-2 main protease binders as potential candidates for repurposing to treat COVID-19, 1188 FDA-approved drugs from the Liver Toxicity Knowledge Base were obtained. A random forest algorithm was used for constructing predictive models based on molecular descriptors calculated using Mold2 software. Model performance was evaluated using 100 iterations of fivefold cross-validations which resulted in 78.8% balanced accuracy. The random forest model that was constructed from the whole training dataset was used to predict SARS-CoV-2 main protease binding on the testing set and the FDA-approved drugs. Model applicability domain and prediction confidence on drugs predicted as the main protease binders discovered 10 FDA-approved drugs as potential candidates for repurposing to treat COVID-19. Our results demonstrate that machine learning is an efficient method for drug repurposing and, thus, may accelerate drug development targeting SARS-CoV-2.
SharmaATiwariSDebMKMartyJL. Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2): a global pandemic and treatment strategies.Int J Antimicrob Agents2020;56:106054
2.
CohenJ. Omicron sparks a vaccine strategy debate.Science2021;374:1544–5
3.
HardenbrookNJZhangP. A structural view of the SARS-CoV-2 virus and its assembly.Curr Opin Virol2022;52:123–34
4.
van de LeemputJHanZ. Understanding individual SARS-CoV-2 proteins for targeted drug development against COVID-19.Mol Cell Biol2021;41:e0018521
5.
LeeMMajorMHongH. Distinct conformations of SARS-CoV-2 omicron spike protein and its interaction with ACE2 and antibody.Int J Mol Sci2023;24:3774
6.
YangHRaoZ. Structural biology of SARS-CoV-2 and implications for therapeutic development.Nat Rev Microbiol2021;19:685–700
7.
GaoKWangRChenJTepeJJHuangFWeiGW. Perspectives on SARS-CoV-2 main protease inhibitors.J Med Chem2021;64:16922–55
8.
LambYN. Nirmatrelvir plus ritonavir: first approval.Drugs2022;82:585–91
9.
MengistHMDilnessaTJinT. Structural basis of potential inhibitors targeting SARS-CoV-2 main protease.Front Chem2021;9:622898
10.
PillaiyarTManickamMNamasivayamVHayashiYJungSH. An overview of severe acute respiratory syndrome-coronavirus (SARS-CoV) 3CL protease inhibitors: peptidomimetics and small molecule chemotherapy.J Med Chem2016;59:6595–628
11.
JinZDuXXuYDengYLiuMZhaoYZhangBLiXZhangLPengCDuanYYuJWangLYangKLiuFJiangRYangXYouTLiuXYangXBaiFLiuHLiuXGuddatLWXuWXiaoGQinCShiZJiangHRaoZYangH. Structure of M(pro) from SARS-CoV-2 and discovery of its inhibitors.Nature2020;582:289–93
12.
La MonicaGBonoALauriaAMartoranaA. Targeting SARS-CoV-2 main protease for treatment of COVID-19: covalent inhibitors structure-activity relationship insights and evolution perspectives.J Med Chem2022;65:12500–34
13.
HuQXiongYZhuGHZhangYNZhangYWHuangPGeGB. The SARS-CoV-2 main protease (Mpro): structure, function, and emerging therapies for COVID-19.MedComm20202022;3:e151
14.
PushpakomSIorioFEyersPAEscottKJHopperSWellsADoigAGuilliamsTLatimerJMcNameeCNorrisASanseauPCavallaDPirmohamedM. Drug repurposing: progress, challenges and recommendations.Nat Rev Drug Discov2019;18:41–58
15.
LuoHMattesWMendrickDLHongH. Molecular docking for identification of potential targets for drug repurposing.Curr Top Med Chem2016;16:3636–45
16.
YeHWeiJTangKLFeuersRHongHX. Drug repositioning through network pharmacology.Current Topics in Medicinal Chemistry2016;16:3646–56
17.
OerlemansRRuiz-MorenoAJCongYDinesh KumarNVelasco-VelazquezMANeochoritisCGSmithJReggioriFGrovesMRDomlingA. Repurposing the HCV NS3-4A protease drug boceprevir as COVID-19 therapeutics.RSC Med Chem2020;12:370–9
18.
PathakNChenYTHsuYCHsuNYKuoCJTsaiHPKangJJHuangCHChangSYChangYHLiangPHYangJM. Uncovering flexible active site conformations of SARS-CoV-2 3CL proteases through protease pharmacophore clusters and COVID-19 drug repurposing.ACS Nano2021;15:857–72
19.
AmbrosioFACostaGRomeoIEspositoFAlkhatibMSalpiniRSvicherVCoronaAMalunePTramontanoECeccherini-SilbersteinFAlcaroSArteseA. Targeting SARS-CoV-2 main protease: a successful story guided by an in silico drug repurposing approach.J Chem Inf Model2023;63:3601–13
20.
PrasadKKumarV. Artificial intelligence-driven drug repurposing and structural biology for SARS-CoV-2.Curr Res Pharmacol Drug Discov2021;2:100042
21.
WilliamsAHZhanCG. Staying ahead of the game: how SARS-CoV-2 has accelerated the application of machine learning in pandemic management.BioDrugs2023;37:649–74
22.
RajputABhamareKTThakurAKumarM. Anti-biofilm: machine learning assisted prediction of IC(50) activity of chemicals against biofilms of microbes causing antimicrobial resistance and implications in drug repurposing.J Mol Biol2023;435:168115
23.
FengHJiangJWeiGW. Machine-learning repurposing of DrugBank compounds for opioid use disorder.Comput Biol Med2023;160:106921
24.
AzevedoPPecanhaBRBFlores-JuniorLAPAlvesTFDiasLRSMuriEMFLimaC. In silico drug repurposing by combining machine learning classification model and molecular dynamics to identify a potential OGT inhibitor.J Biomol Struct Dyn. Epub ahead of print 13 April 2023. DOI: 10.1080/07391102.2023.2199868
25.
HongHTongWXieQFangHPerkinsR. An in silico ensemble method for lead discovery: decision forest.SAR QSAR Environ Res2005;16:339–47
HuangYLiXXuSZhengHZhangLChenJHongHKuskoRLiR. Quantitative structure-activity relationship models for predicting inflammatory potential of metal oxide nanoparticles.Environ Health Perspect2020;128:67010
28.
WangZChenJHongH. Developing QSAR models with defined applicability domains on PPARgamma binding affinity using large data sets and machine learning algorithms.Environ Sci Technol2021;55:6857–66
29.
JiZGuoWWoodELLiuJSakkiahSXuXPattersonTAHongH. Machine learning models for predicting cytotoxicity of nanomaterials.Chem Res Toxicol2022;35:125–39
30.
ChenMZhangJWangYLiuZKellyRZhouGFangHBorlakJTongW. The liver toxicity knowledge base: a systems approach to a complex end point.Clin Pharmacol Ther2013;93:409–12
31.
QiaoJLiYSZengRLiuFLLuoRHHuangCWangYFZhangJQuanBShenCMaoXLiuXSunWYangWNiXWangKXuLDuanZLZouQCZhangHLQuWLongYHLiMHYangRCLiuXYouJZhouYYaoRLiWPLiuJMChenPLiuYLinGFYangXZouJLiLHuYLuGWLiWMWeiYQZhengYTLeiJYangS. SARS-CoV-2 M(pro) inhibitors with antiviral activity in a transgenic mouse model.Science2021;371:1374–8
32.
LuttensAGullbergHAbdurakhmanovEVoDDAkaberiDTalibovVONekhotiaevaNVangeelLDe JongheSJochmansDKrambrichJTasALundgrenBGravenforsYCraigAJAtilawYSandstromAMoodieLWKLundkvistAvan HemertMJNeytsJLennerstrandJKihlbergJSandbergKDanielsonUHCarlssonJ. Ultralarge Virtual screening identifies SARS-CoV-2 main protease inhibitors with broad-spectrum activity against coronaviruses.J Am Chem Soc2022;144:2905–20
33.
ResnickSJIketaniSHongSJZaskALiuHKimSMeloreSNairMSHuangYTayNESRovisTYangHWStockwellBRHoDDChavezA. A simplified cell-based assay to identify coronavirus 3CL protease inhibitors.2020, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7457602/
34.
HongHXieQGeWQianFFangHShiLSuZPerkinsRTongW. Mold(2), molecular descriptors from 2D structures for chemoinformatics and toxicoinformatics.J Chem Inf Model2008;48:1337–44
35.
HongHThakkarSChenMTongW. Development of decision forest models for prediction of drug-induced liver injury in humans using a large set of FDA-approved drugs.Sci Rep2017;7:17311
36.
GoddenJWStahuraFLBajorathJ. Variability of molecular descriptors in compound databases revealed by Shannon entropy calculations.J Chem Inf Comput Sci2000;40:796–800
37.
LiuJGuoWDongFAungstJFitzpatrickSPattersonTAHongH. Machine learning models for rat multigeneration reproductive toxicity prediction.Front Pharmacol2022;13:1018226
38.
BreimanL. Random Forests.Mach Learning2001;45:5–32
39.
HongHRuaDSakkiahSSelvarajCGeWTongW. Consensus modeling for prediction of estrogenic activity of ingredients commonly used in sunscreen products.Int J Environ Res Public Health2016;13:958
40.
WeaverSGleesonMP. The importance of the domain of applicability in QSAR modeling.J Mol Graph Model2008;26:1315–26
41.
KlingspohnWMatheaMTer LaakAHeinrichNBaumannK. Efficiency of different measures for defining the applicability domain of classification models.J Cheminform2017;9:44
42.
KarSRoyKLeszczynskiJ. Applicability domain: a step toward confident predictions and decidability for QSAR modeling.Methods Mol Biol2018;1800:141–69
43.
SimoensSHuysI. R&D costs of new medicines: a landscape analysis.Front Med2021;8:760762
44.
SchlanderMHernandez-VillafuerteKChengCYMestre-FerrandizJBaumannM. How much does it cost to research and develop a new drug? A systematic review and assessment.Pharmacoeconomics2021;39:1243–69
45.
KumarPBhardwajTKumarAGehiBRKapugantiSKGargNNathGGiriR. Reprofiling of approved drugs against SARS-CoV-2 main protease: an in-silico study.J Biomol Struct Dyn2022;40:3170–84
46.
WuCLiuYYangYZhangPZhongWWangYWangQXuYLiMLiXZhengMChenLLiH. Analysis of therapeutic targets for SARS-CoV-2 and discovery of potential drugs by computational methods.Acta Pharm Sin B2020;10:766–88
47.
MaCLXiaZLSaccoMDHuYMTownsendJAMengXZChozaJTanHZJangJGongoraMVZhangXJZhangFSXiangYMartyMTChenYWangJ. Discovery of di- and trihaloacetamides as covalent SARS-CoV-2 main protease inhibitors with high target specificity.J Am Chem Soc2021;143:20697–709
48.
DurojaiyeABClarkeJRDStamatiadesGAWangC. Repurposing cefuroxime for treatment of COVID-19: a scoping review of in silico studies.J Biomol Struct Dyn2021;39:4547–54
49.
HuffSKummethaIRTiwariSKHuanteMBClarkAEWangSBBrayWSmithDCarlinAFEndsleyMRanaTM. Discovery and mechanism of SARS-CoV-2 main protease inhibitors.J Med Chem2022;65:2866–79
50.
ArunKGSharanyaCSAbhithajJFrancisDSadasivanC. Drug repurposing against SARS-CoV-2 using E-pharmacophore based virtual screening, molecular docking and molecular dynamics with main protease as the target.J Biomol Struct Dyn2021;39:4647–58
51.
SaarKLMcCorkindaleWFearonDBobyMBarrHBen-ShmuelAConsortiumCMLondonNvon DelftFChoderaJDLeeAA. Turning high-throughput structural biology into predictive inhibitor design.Proc Natl Acad Sci U S A2023;120:e2214168120
52.
NguyenTHTamNMTuanMVZhanPVuVVQuangDTNgoST. Searching for potential inhibitors of SARS-COV-2 main protease using supervised learning and perturbation calculations.Chem Phys2023;564:111709
53.
JanairoGIBYuDECJanairoJIB. A machine learning regression model for the screening and design of potential SARS-CoV-2 protease inhibitors.Netw Model Anal Health Inform Bioinform2021;10:51
54.
GomesISSantanaCAMarcolinoLSLimaLHFMelo-MinardiRCDiasRSde PaulaSOSilveiraSA. Computational prediction of potential inhibitors for SARS-COV-2 main protease based on machine learning, docking, MM-PBSA calculations, and metadynamics.PLoS ONE2022;17:e0267471
55.
FerdousNRezaMNHossainMUMahmudSNapisSChowdhuryKMohiuddinAKM. Mpropred: a machine learning (ML) driven Web-App for bioactivity prediction of SARS-CoV-2 main protease (Mpro) antagonists.PLoS ONE2023;18:e0287179
56.
MekniNCoronnelloCLangerTRosaMPerriconeU. Support vector machine as a supervised learning for the prioritization of novel potential SARS-CoV-2 main protease inhibitors.Int J Mol Sci2021;22:7714
57.
SamadAAjmalAMahmoodAKhurshidBLiPJanSMRehmanAUHePAbdallaANUmairMHuJWadoodA. Identification of novel inhibitors for SARS-CoV-2 as therapeutic options using machine learning-based virtual screening, molecular docking and MD simulation.Front Mol Biosci2023;10:1060076
58.
VermaAKAggarwalR. Repurposing potential of FDA-approved and investigational drugs for COVID-19 targeting SARS-CoV-2 spike and main protease and validation by machine learning algorithm.Chem Biol Drug Des2021;97:836–53
59.
XuLChenRLiuJPattersonTAHongH. Analyzing 3D structures of the SARS-CoV-2 main protease reveals structural features of ligand binding for COVID-19 drug discovery.Drug Discov Today2023;28:103727
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
