This study formulates antiviral repositioning as a matrix completion problem wherein the antiviral drugs are along the rows and the viruses are along the columns. The input matrix is partially filled, with ones in positions where the antiviral drug has been known to be effective against a virus. The curated metadata for antivirals (chemical structure and pathways) and viruses (genomic structure and symptoms) are encoded into our matrix completion framework as graph Laplacian regularization. We then frame the resulting multiple graph regularized matrix completion (GRMC) problem as deep matrix factorization. This is solved by using a novel optimization method called HyPALM (Hybrid Proximal Alternating Linearized Minimization). Results of our curated RNA drug–virus association data set show that the proposed approach excels over state-of-the-art GRMC techniques. When applied to in silico prediction of antivirals for COVID-19, our approach returns antivirals that are either used for treating patients or are under trials for the same.
Get full access to this article
View all access options for this article.
References
1.
AbboudF., ChouzenouxE., PesquetJ.-C., et al.2014. A hybrid alternating proximal method for blind video restoration, 1811–1815. In Proceedings of the 22nd European Signal Processing Conference (EUSIPCO 2014). Lisboa, Portugal.
2.
AliM.J., HanifM., HaiderM.A., et al.2020. Treatment options for covid-19: A review. Front. Med. 7, 480.
3.
BegM., and AtharF.2020. Anti-HIV and anti-HCV drugs are the putative inhibitors of RNA-dependent-RNA polymerase activity of NSP12 of the SARS COV-2 (COVID-19). Pharm. Pharmacol. Int. J. 8, 163–172.
4.
BeigelJ., TomashekK., DoddL., et al.2020. Remdesivir for the treatment of COVID-19—Final report. N. Engl. J. Med. 383, 993–994.
5.
BolteJ., SabachS., and TeboulleM.2014. Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 459–494.
6.
ChopraA., SalujaM., and VenugopalanA.2014. Effectiveness of chloroquine and inflammatory cytokine response in patients with early persistent musculoskeletal pain and arthritis following chikungunya virus infection. Arthritis Rhumatol. 66, 319–326.
7.
ChouzenouxE., PesquetJ.-C., and RepettiA.2016. A block coordinate variable metric forward-backward algorithm. J. Glob. Optim. 66, 457–485.
8.
CobanogluM.C., LiuC., HuF., et al.2013. Predicting drug-target interactions using probabilistic matrix factorization. J. Chem. Inf. Model. 53, 3399–3409.
9.
DaiY.-F., and ZhaoX.-M.2015. A survey on the computational approaches to identify drug targets in the postgenomic era. Biomed. Res. Int.
10.
DasI., BasantrayI., MamidiP., et al.2014. Heat shock protein 90 positively regulates chikungunya virus replication by stabilizing viral non-structural protein nsp2 during infection. PLoS One, 9, e100531.
11.
De ClercqE., and LiG.2016. Approved antiviral drugs over the past 50 years. Clin. Microbiol. Rev. 29, 695–747.
12.
DingH., TakigawaI., MamitsukaH., et al.2013. Similarity-based machine learning methods for predicting drug–target interactions: A brief review. Brief. Bioinform. 15, 734–747.
13.
DuanY., LiuQ., ZhaoS., et al.2020. The trial of chloroquine in the treatment of corona virus disease 2019 (COVID-19) and its research progress in forensic toxicology. Fa Yi Xue Za Zhi, 36, 157–163.
14.
EastmanR.T., RothJ.S., BrimacombeK.R., et al.2020. Remdesivir: A review of its discovery and development leading to emergency use authorization for treatment of COVID-19. ACS Cent. Sci. 6, 672–683.
15.
ElfikyA.A., MahdyS.M., and ElshemeyW.M.2017. Quantitative structure-activity relationship and molecular docking revealed a potency of anti-hepatitis c virus drugs against human corona viruses. J. Med. Virol. 89, 1040–1047.
16.
EzzatA., ZhaoP., WuM., et al.2017. Drug-target interaction prediction with graph regularized matrix factorization. IEEE/ACM Trans. Comput. Biol. Bioinform. 14, 646–656.
17.
FuL., YeF., FengY., et al.2020. Both boceprevir and gc376 efficaciously inhibit SARS-CoV-2 by targeting its main protease. Nat. Commun. 11, 1–8.
18.
GallegosK.M., DrusanoG.L., D ArgenioD.Z., et al.2016. Chikungunya virus: in vitro response to combination therapy with ribavirin and interferon alfa 2a. J. Infect. Dis. 214, 1192–1197.
19.
HeS., LinB., ChuV., et al.2015. Repurposing of the antihistamine chlorcyclizine and related compounds for treatment of hepatitis c virus infection. Sci. Transl. Med. 7, 282ra49–282ra49.
20.
HuY., JacobJ., ParkerG.J., et al.2020. The challenges of deploying artificial intelligence models in a rapidly evolving pandemic. Nat. Mach. Intell. 2, 298–300.
21.
HungI.F.-N., LungK.-C., TsoE.Y.-K., et al. 2020. Triple combination of interferon beta-1b, lopinavir–ritonavir, and ribavirin in the treatment of patients admitted to hospital with covid-19: An open-label, randomised, phase 2 trial. Lancet, 395, 1695–1704.
22.
JadambaE., and ShinM.2016. A systematic framework for drug repositioning from integrated omics and drug phenotype profiles using pathway-drug network. Biomed. Res. Int. 2016, 7147039.
KalofoliasV., BressonX., BronsteinM., et al.2014. Matrix completion on graphs. arXiv preprint arXiv:1408.1717.
25.
KhaliliJ.S., ZhuH., MakN.S.A., et al. 2020. Novel coronavirus treatment with ribavirin: Groundwork for an evaluation concerning COVID-19. J. Med. Virol.
26.
LeeV.S., ChongW.L., SukumaranS.D., et al.2020. Computational screening and identifying binding interaction of anti-viral and anti-malarial drugs: Toward the potential cure for SARS-CoV-2. Progr. Drug Discov. Biomed. Sci. 3.
27.
LipsitchM., PerlmanS., and WaldorM.K.2020. Testing COVID-19 therapies to prevent progression of mild disease. Lancet Infect. Dis.
28.
LoH.S., HuiK.P., LaiH.-M., et al.2020. Simeprevir suppresses SARS-CoV-2 replication and synergizes with remdesivir. bioRxiv.
29.
Luengo-OrozM., PhamK.H., BullockJ., et al.2020. Artificial intelligence cooperation to support the global response to COVID-19. Nat. Mach. Intell. 1–3.
MongiaA., and MajumdarA.2019. Drug-target interaction prediction using multi-graph regularized deep matrix factorization. bioRxiv, 774539.
33.
MongiaA., and MajumdarA.2020a. Deep matrix completion on graphs: Application in drug target interaction prediction, 1324–1328. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020). IEEE.
34.
MongiaA., and MajumdarA.2020b. Drug-target interaction prediction using multi graph regularized nuclear norm minimization. PLoS One 15, e0226484.
35.
MongiaA., SahaS.K., ChouzenouxE., et al.2021. A computational approach to aid clinicians in selecting anti-viral drugs for covid-19 trials. Sci. Rep. 11, 1–12.
36.
MongiaA., SenguptaD., and MajumdarA.2019. deepmc: Deep matrix completion for imputation of single-cell RNA-seq data. J. Comput. Biol. 27.
37.
O'CarrollI., and ReinA.2016. Viral nucleic acids, 517. In Encyclopedia of Cell Biology.
38.
PickettB.E., SadatE.L., ZhangY., et al.2012. Vipr: An open bioinformatics database and analysis resource for virology research. Nucl. Acids Res. 40(D1):D593–D598.
39.
RazonableR.R.2011. Antiviral drugs for viruses other than human immunodeficiency virus. Mayo Clinic Proc. 86, 1009–1026.
40.
SahooS.K., and VardhanS.2020. Computational evidence on repurposing the anti-influenza drugs baloxavir acid and baloxavir marboxil against COVID-19. arXiv preprint arXiv:2009.01094.
41.
SarpatwariA., KaltenboeckA., and KesselheimA.S.2020. Missed opportunities on emergency remdesivir use. JAMA, 324, 331–332.
42.
SchramowskiP., StammerW., TesoS., et al.2020. Making deep neural networks right for the right scientific reasons by interacting with their explanations. Nat. Mach. Intell. 2, 476–486.
43.
ShahB., ModiP., and SagarS.R.2020. In silico studies on therapeutic agents for covid-19: Drug repurposing approach. Life Sci. 117652.
44.
ShenD., WuG., and SukH.-I.2017. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248.
45.
ShiryaevS. A., MesciP., PintoA., et al.2017. Repurposing of the anti-malaria drug chloroquine for zika virus treatment and prophylaxis. Sci. Rep. 7, 1–9.
46.
SocherR., BengioY., and ManningC.D.2012. Deep learning for NLP (without magic), 5. In Tutorial Abstracts of ACL 2012.
47.
SugayaN., and OhashiY.2010. Long-acting neuraminidase inhibitor laninamivir octanoate (cs-8958) versus oseltamivir as treatment for children with influenza virus infection. Antimicrob. Agents Chemother. 54, 2575–2582.
48.
SultanI., HowardS., and TbakhiA.2020. Drug repositioning suggests a role for the heat shock protein 90 inhibitor geldanamycin in treating COVID-19 infection. PLoS One, 15, e0238907.
49.
SunR., and LuoZ.-Q.2016. Guaranteed matrix completion via non-convex factorization. IEEE Trans. Inf. Theory, 62, 6535–6579.
50.
TrezzaA., IovinelliD., SantucciA., et al.2020. An integrated drug repurposing strategy for the rapid identification of potential SARS-CoV-2 viral inhibitors. Sci. Rep. 10, 1–8.
51.
TrigeorgisG., BousmalisK., ZafeiriouS., et al.2017. A deep matrix factorization method for learning attribute representations. IEEE Trans. Pattern Anal. Mach. Intell. 39, 417–429.
52.
VankadariN.2020. Arbidol: A potential antiviral drug for the treatment of SARS-CoV-2 by blocking the trimerization of viral spike glycoprotein? Int. J. Antimicrob. Agents, 56, 105998.
53.
WangM., TangC., and ChenJ.2018. Drug-target interaction prediction via dual laplacian graph regularized matrix completion. Biomed Res. Int. 2018, 1425608.
54.
WangX., CaoR., ZhangH., et al.2020. The anti-influenza virus drug, arbidol is an efficient inhibitor of SARS-CoV-2 in vitro. Cell Discov. 6, 1–5.
55.
WangY., YinW., and ZengJ.2019. Global convergence of admm in nonconvex nonsmooth optimization. J. Sci. Comput. 78, 29–63.
56.
WintherB., and MygindN.2003. Potential benefits of ibuprofen in the treatment of viral respiratory infections. Inflammopharmacology, 11, 445.
57.
XuP., HuangJ., FanZ., et al.2020. Arbidol/IFN-2b therapy for patients with corona virus disease 2019: A retrospective multicenter cohort study. Microb. Infect. 22, 200–205.
58.
YangC., KeC., YueD., et al.2020. Effectiveness of arbidol for covid-19 prevention in health professionals. Front. Public Health, 8, 249.
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.
