Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

Wei Wang; Shuo Feng; Zhuyifan Ye; Hanlu Gao; Jinzhong Lin; Defang Ouyang

doi:10.1016/j.apsb.2021.11.021

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

doi: 10.1016/j.apsb.2021.11.021

a. State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macau 999078, China;
b. State Key Laboratory of Genetic Engineering, School of Life Sciences, Zhongshan Hospital, Fudan University, Shanghai 200438, China

基金项目:

This work was financially supported by the University of Macau Research Grants (MYRG2020-00113-ICMS, China). This work was performed in part at the High-Performance Computing Cluster (HPCC) which is supported by Information and Communication Technology Office (ICTO) of the University of Macau.

详细信息

通讯作者:
Jinzhong Lin,E-mail:linjinzhong@fudan.edu.cn

Defang Ouyang,E-mail:defangouyang@umac.mo

中图分类号: https://www.sciencedirect.com/science/article/pii/S2211383521004597/pdf?md5=4e362569eaf2873c30e4b71d48ddb6d8&pid=1-s2.0-S2211383521004597-main.pdf
计量
- 文章访问数: 91
- HTML全文浏览量: 45
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2021-09-10
- 修回日期: 2021-10-03
- 录用日期: 2021-10-28
- 网络出版日期: 2023-03-17

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

a. State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macau 999078, China;
b. State Key Laboratory of Genetic Engineering, School of Life Sciences, Zhongshan Hospital, Fudan University, Shanghai 200438, China

Funds:

摘要

摘要: Lipid nanoparticle (LNP) is commonly used to deliver mRNA vaccines. Currently, LNP optimization primarily relies on screening ionizable lipids by traditional experiments which consumes intensive cost and time. Current study attempts to apply computational methods to accelerate the LNP development for mRNA vaccines. Firstly, 325 data samples of mRNA vaccine LNP formulations with IgG titer were collected. The machine learning algorithm, lightGBM, was used to build a prediction model with good performance (R² > 0.87). More importantly, the critical substructures of ionizable lipids in LNPs were identified by the algorithm, which well agreed with published results. The animal experimental results showed that LNP using DLin-MC3-DMA (MC3) as ionizable lipid with an N/P ratio at 6:1 induced higher efficiency in mice than LNP with SM-102, which was consistent with the model prediction. Molecular dynamic modeling further investigated the molecular mechanism of LNPs used in the experiment. The result showed that the lipid molecules aggregated to form LNPs, and mRNA molecules twined around the LNPs. In summary, the machine learning predictive model for LNP-based mRNA vaccines was first developed, validated by experiments, and further integrated with molecular modeling. The prediction model can be used for virtual screening of LNP formulations in the future.
- Lipid nanoparticle /
- Ionizable lipid /
- mRNA /
- Vaccine /
- Formulation prediction /
- Machine learning /
- LightGBM /
- Molecular modeling
Abstract: Lipid nanoparticle (LNP) is commonly used to deliver mRNA vaccines. Currently, LNP optimization primarily relies on screening ionizable lipids by traditional experiments which consumes intensive cost and time. Current study attempts to apply computational methods to accelerate the LNP development for mRNA vaccines. Firstly, 325 data samples of mRNA vaccine LNP formulations with IgG titer were collected. The machine learning algorithm, lightGBM, was used to build a prediction model with good performance (R² > 0.87). More importantly, the critical substructures of ionizable lipids in LNPs were identified by the algorithm, which well agreed with published results. The animal experimental results showed that LNP using DLin-MC3-DMA (MC3) as ionizable lipid with an N/P ratio at 6:1 induced higher efficiency in mice than LNP with SM-102, which was consistent with the model prediction. Molecular dynamic modeling further investigated the molecular mechanism of LNPs used in the experiment. The result showed that the lipid molecules aggregated to form LNPs, and mRNA molecules twined around the LNPs. In summary, the machine learning predictive model for LNP-based mRNA vaccines was first developed, validated by experiments, and further integrated with molecular modeling. The prediction model can be used for virtual screening of LNP formulations in the future.
- Lipid nanoparticle /
- Ionizable lipid /
- mRNA /
- Vaccine /
- Formulation prediction /
- Machine learning /
- LightGBM /
- Molecular modeling

HTML全文

参考文献(75)

[1]	Pruβ BM. Current state of the first COVID-19 vaccines. Vaccines 2021;9:30
[2]	Mahase E. COVID-19:UK approves Pfizer and BioNTech vaccine with rollout due to start next week. BMJ 2020;371:m4714
[3]	Tanne JH. COVID-19:Pfizer-BioNTech vaccine is rolled out in US. BMJ 2020;371:m4836
[4]	Polack FP, Thomas SJ, Kitchin N, Absalon J, Gurtman A, Lockhart S, et al. Safety and efficacy of the BNT162b2 mRNA COVID-19 vaccine. N Engl J Med 2020;383:2603-2615
[5]	Baden LR, Sahly HME, Essink B, Kotloff K, Frey S, Novak R, et al. Efficacy and safety of the mRNA-1273 SARS-CoV-2 vaccine. N Engl J Med 2021;384:403-416
[6]	Sahin U, Kariko K, Tureci O. mRNA-based therapeutics-developing a new class of drugs. Nat Rev Drug Discov 2014;13:759-780
[7]	Pardi N, Hogan MJ, Porter FW, Weissman D. mRNA vaccines-a new era in vaccinology. Nat Rev Drug Discov 2018;17:261-279
[8]	Hou X, Zaks T, Langer R, Dong Y. Lipid nanoparticles for mRNA delivery. Nat Rev Mater 2021;10:1-17
[9]	Chaudhary N, Weissman D, Whitehead KA. mRNA vaccines for infectious diseases:principles, delivery and clinical translation. Nat Rev Drug Discov 2021;20:817-838
[10]	Magini D, Giovani C, Mangiavacchi S, Maccari S, Cecchi R, Ulmer JB, et al. Self-amplifying mRNA vaccines expressing multiple conserved influenza antigens confer protection against homologous and heterosubtypic viral challenge. PLoS One 2016;11:e0161193
[11]	Samsa MM, Dupuy LC, Beard CW, Six CM, Schmaljohn CS, Mason PW, et al. Self-amplifying RNA vaccines for venezuelan equine encephalitis virus induce robust protective immunogenicity in mice. Mol Ther 2019;27:850-865
[12]	Zeng C, Hou X, Yan J, Zhang C, Li W, Zhao W, et al. Leveraging mRNA sequences and nanoparticles to deliver SARS-CoV-2 antigens in vivo. Adv Mater 2020;32:e2004452
[13]	Orlandini von Niessen AG, Poleganov MA, Rechner C, Plaschke A, Kranz LM, Fesser S, et al. Improving mRNA-based therapeutic gene delivery by expression-augmenting 3' UTRs identified by cellular library screening. Mol Ther 2019;27:824-836
[14]	Kariko K, Buckstein M, Ni H, Weissman D. Suppression of RNA recognition by toll-like receptors:the impact of nucleoside modification and the evolutionary origin of RNA. Immunity 2005;23:165-175
[15]	Kariko K, Muramatsu H, Welsh FA, Ludwig J, Kato H, Akira S, et al. Incorporation of pseudouridine into mRNA yields superior nonimmunogenic vector with increased translational capacity and biological stability. Mol Ther 2008;16:1833-1840
[16]	Cannarozzi G, Schraudolph NN, Faty M, von Rohr P, Friberg MT, Roth AC, et al. A role for codon order in translation dynamics. Cell 2010;141:355-367
[17]	Chin JX, Chung BK-S, Lee D-Y. Codon Optimization OnLine (COOL):a web-based multi-objective optimization platform for synthetic gene design. Bioinformatics 2014;30:2210-2212
[18]	Freyn AW, da Silva JR, Rosado VC, Bliss CM, Pine M, Mui BL, et al. A multi-targeting, nucleoside-modified mRNA influenza virus vaccine provides broad protection in mice. Mol Ther 2020;28:1569-1584
[19]	Awasthi S, Hook LM, Pardi N, Wang F, Myles A, Cancro MP, et al. Nucleoside-modified mRNA encoding HSV-2 glycoproteins C, D, and E prevents clinical and subclinical genital herpes. Sci Immunol 2019;4:eaaw7083
[20]	Lindgren G, Ols S, Liang F, Thompson EA, Lin A, Hellgren F, et al. Induction of robust B cell responses after influenza mRNA vaccination is accompanied by circulating hemagglutinin-specific ICOS+PD-1+CXCR3+T follicular helper cells. Front Immunol 2017;8:1539
[21]	Eygeris Y, Patel S, Jozic A, Sahay G, Sahay G. Deconvoluting lipid nanoparticle structure for messenger RNA delivery. Nano Lett 2020;20:4543-4549
[22]	Leung AKK, Tam YYC, Chen S, Hafez IM, Cullis PR. Microfluidic mixing:a general method for encapsulating macromolecules in lipid nanoparticle systems. J Phys Chem B 2015;119:8698-8706
[23]	Maurer N, Wong KF, Stark H, Louie L, McIntosh D, Wong T, et al. Spontaneous entrapment of polynucleotides upon electrostatic interaction with ethanol-destabilized cationic liposomes. Biophys J 2001;80:2310-2326
[24]	Gindy ME, Feuston B, Glass A, Arrington L, Haas RM, Schariter J, et al. Stabilization of Ostwald ripening in low molecular weight amino lipid nanoparticles for systemic delivery of siRNA therapeutics. Mol Pharm2014;11:4143-4153
[25]	Sabnis S, Kumarasinghe ES, Salerno T, Mihai C, Ketova T, Senn JJ, et al. A novel amino lipid series for mRNA delivery:improved endosomal escape and sustained pharmacology and safety in non-human primates. Mol Ther 2018;26:1509-1519
[26]	Belliveau NM, Huft J, Lin PJ, Chen S, Leung AK, Leaver TJ, et al. Microfluidic synthesis of highly potent limit-size lipid nanoparticles for in vivo delivery of siRNA. Mol Ther Nucleic Acids 2012;1:e37
[27]	Chen S, Tam YYC, Lin PJC, Sung MMH, Tam YK, Cullis PR. Influence of particle size on the in vivo potency of lipid nanoparticle formulations of siRNA. J Control Release 2016;235:236-244
[28]	Jayaraman M, Ansell SM, Mui BL, Tam YK, Chen J, Du X, et al. Maximizing the potency of siRNA lipid nanoparticles for hepatic gene silencing in vivo. Angew Chem Int Ed Engl 2012;51:8529-8533
[29]	Semple SC, Akinc A, Chen J, Sandhu AP, Mui BL, Cho CK, et al. Rational design of cationic lipids for siRNA delivery. Nat Biotechnol 2010;28:172-176
[30]	Hassett KJ, Benenato KE, Jacquinet E, Lee A, Woods A, Yuzhakov O, et al. Optimization of lipid nanoparticles for intramuscular administration of mRNA vaccines. Mol Ther Nucleic Acids 2019;15:1-11
[31]	Whitehead KA, Dorkin JR, Vegas AJ, Chang PH, Veiseh O, Matthews J, et al. Degradable lipid nanoparticles with predictable in vivo siRNA delivery activity. Nat Commun2014;5:4277
[32]	Kauffman KJ, Dorkin JR, Yang JH, Heartlein MW, DeRosa F, Mir FF, et al. Optimization of lipid nanoparticle formulations for mRNA delivery in vivo with fractional factorial and definitive screening designs. Nano Lett 2015;15:7300-7306
[33]	Jordan MI, Mitchell TM. Machine learning:trends, perspectives, and prospects. Science 2015;349:255-260
[34]	LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436-444
[35]	Schuhmacher A, Gatto A, Hinder M, Kuss M, Gassmann O. The upside of being a digital pharma player. Drug Discov Today 2020;25:1569-1574
[36]	He Y, Ye Z, Liu X, Wei Z, Qiu F, Li H-F, et al. Can machine learning predict drug nanocrystals? J Control Release 2020;322:274-285
[37]	Gao H, Wang W, Dong J, Ye Z, Ouyang D. An integrated computational methodology with data-driven machine learning, molecular modeling and PBPK modeling to accelerate solid dispersion formulation design. Eur J Pharm Biopharm 2021;158:336-346
[38]	Zhao Q, Ye Z, Su Y, Ouyang D. Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques. Acta Pharma Sin B 2019;9:1241-1252
[39]	Gao H, Jia H, Dong J, Yang X, Li H, Ouyang D. Integrated in silico formulation design of self-emulsifying drug delivery systems. Acta Pharm Sin B 2021;11:3585-94
[40]	Bunker A, Rog T. Mechanistic understanding from molecular dynamics simulation in pharmaceutical research 1:drug delivery. Front Mol Biosci 2020;7:604770
[41]	Ouyang D, Smith SC. Introduction to computational pharmaceutics. Computational Pharmaceutics, Hoboken, John Wiley & Sons, Ltd.; 2015, p. 1-5
[42]	Ouyang D, Zhang H, Parekh HS, Smith SC. Structure and dynamics of multiple cationic vectors-siRNA complexation by all-atomic molecular dynamics simulations. J Phys Chem B 2010;114:9231-9237
[43]	Richner JM, Himansu S, Dowd KA, Butler SL, Salazar V, Fox JM, et al. Modified mRNA vaccines protect against Zika virus infection. Cell 2017;168:1114-1125
[44]	A Feldman R, Fuhr R, Smolenov I, Ribeiro A, Panther L, Watson M, et al. mRNA vaccines against H10N8 and H7N9 influenza viruses of pandemic potential are immunogenic and well tolerated in healthy adults in phase 1 randomized clinical trials. Vaccine 2019;37:3326-3334
[45]	18-05482-0
[46]	Pardi N, Hogan MJ, Naradikian MS, Parkhouse K, Cain DW, Jones L, et al. Nucleoside-modified mRNA vaccines induce potent T follicular helper and germinal center B cell responses. J Exp Med2018;215:1571-1588
[47]	Jackson LA, Anderson EJ, Rouphael NG, Roberts PC, Makhene M, Coler RN, et al. An mRNA vaccine against SARS-CoV-2-Preliminary report. N Engl J Med2020;383:1920-1931
[48]	Lederer K, Castano D, Gomez Atria D, Oguin I TH, Wang S, Manzoni TB, et al. SARS-CoV-2 mRNA vaccines foster potent antigen-specific germinal center responses associated with neutralizing antibody generation. Immunity 2020;53:1281-95.e5
[49]	Aliprantis AO, Shaw CA, Griffin P, Farinola N, Railkar RA, Cao X, et al. A phase 1, randomized, placebo-controlled study to evaluate the safety and immunogenicity of an mRNA-based RSV prefusion F protein vaccine in healthy younger and older adults. Hum Vaccin Immunother 2021;17:1248-1261
[50]	Espeseth AS, Cejas PJ, Citron MP, Wang D, DiStefano DJ, Callahan C, et al. Modified mRNA/lipid nanoparticle-based vaccines expressing respiratory syncytial virus F protein variants are immunogenic and protective in rodent models of RSV infection. NPJ Vaccines 2020;5:16
[51]	Maier MA, Jayaraman M, Matsuda S, Liu J, Barros S, Querbes W, et al. Biodegradable lipids enabling rapidly eliminated lipid nanoparticles for systemic delivery of RNAi therapeutics. Molr Ther 2013;21:1570-1578
[52]	Corbett KS, Flynn B, Foulds KE, Francica JR, Boyoglu-Barnum S, Werner AP, et al. Evaluation of the mRNA-1273 vaccine against SARS-CoV-2 in nonhuman primates. N Engl J Med 2020;383:1544-1555
[53]	Bahl K, Senn JJ, Yuzhakov O, Bulychev A, Brito LA, Hassett KJ, et al. Preclinical and clinical demonstration of immunogenicity by mRNA vaccines against H10N8 and H7N9 influenza viruses. Mol Therapy 2017;25:1316-1327
[54]	Rogers D, Hahn M. Extended-connectivity fingerprints. J Chem Inf Model 2010;50:742-754
[55]	Landrum G. RDKit:a software suite for cheminformatics, computational chemistry, and predictive modeling. 2013. Available form:https://docplayer.net/11897218-Rdkit-a-software-suite-for-cheminformatics-computational-chemistry-and-predictive-modeling.html
[56]	Abhimanyu T, Ambika Prasad M, Bishnupriya P, Kumari S, Babita M. Detection of disease-specific parent cells via distinct population of nano-vesicles by machine learning. Curr Pharm Des 2020;26:3985-3996
[57]	Bishnupriya P, Babita M, Abhimanyu T. An integrated-OFFT model for the prediction of protein secondary structure class. Curr Comput Aided Drug Des 2019;15:45-54
[58]	Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM:a highly efficient gradient boosting decision tree. In:Guyon I, Fergus R, Wallach H, Wallach H, Guyon I, Vishwanathan SVN et al., editors. Advances in Neural Information Processing Systems. San Diego:; Neural information processing systems foundation, Inc.; 2017. p. 3147-3155
[59]	Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res 2012;13:281-305
[60]	Liu P, Wysocki J, Souma T, Ye M, Ramirez V, Zhou B, et al. Novel ACE2-Fc chimeric fusion provides long-lasting hypertension control and organ protection in mouse models of systemic renin angiotensin system activation. Kidney Int 2018;94:114-125
[61]	MacKerell AD, Bashford D, Bellott M, Dunbrack RL, Evanseck JD, Field MJ, et al. All-atom empirical potential for molecular modeling and dynamics studies of proteins. J Phys Chem B 1998;102:3586-3616
[62]	Wang W, Ye Z, Gao H, Ouyang D. Computational pharmaceutics-a new paradigm of drug delivery. J Control Release 2021;338:119-136
[63]	Wang J, Wang W, Kollman PA, Case DA. Antechamber:an accessory software package for molecular mechanical calculations. J Am Chem Soc 2001;222:U403
[64]	Liu J, Li D, Liu X. A simple and accurate algorithm for path integral molecular dynamics with the Langevin thermostat. J Chem Phys2016;145:024103
[65]	Berendsen HJ, van Postma J, van Gunsteren WF, DiNola A, Haak JR. Molecular dynamics with coupling to an external bath. J Chem Phys 1984;81:3684-3690
[66]	Akinc A, Goldberg M, Qin J, Dorkin JR, Gamba-Vitalo C, Maier M, et al. Development of lipidoid-siRNA formulations for systemic delivery to the liver. Mol Ther 2009;17:872-879
[67]	Verbeke R, Lentacker I, De Smedt SC, Dewitte H. The dawn of mRNA vaccines:the COVID-19 case. J Control Release 2021;333:511-520
[68]	Chen S, Tam YYC, Lin PJC, Leung AKK, Tam YK, Cullis PR. Development of lipid nanoparticle formulations of siRNA for hepatocyte gene silencing following subcutaneous administration. J ControlRelease 2014;196:106-112
[69]	Huebner S, Battersby BJ, Grimm R, Cevc G. Lipid-DNA complex formation:reorganization and rupture of lipid vesicles in the presence of DNA as observed by cryoelectron microscopy. Biophys J 1999;76:3158-3166
[70]	Rissanou AN, Ouranidis A, Karatasos K. Complexation of single stranded RNA with an ionizable lipid:an all-atom molecular dynamics simulation study. Soft Matter 2020;16:6993-7005
[71]	Rozmanov D, Baoukina S, Peter-Tieleman D. Density based visualization for molecular simulation. Faraday Discuss 2014;169:225-243
[72]	Leung AKK, Hafez IM, Baoukina S, Belliveau NM, Zhigaltsev IV, Afshinmanesh E, et al. Lipid nanoparticles containing siRNA synthesized by microfluidic mixing exhibit an electron-dense nanostructured core. J Phys Chem C Nanomater Interfaces 2012;116:18440-18450
[73]	Arteta MY, Kjellman T, Bartesaghi S, Wallin S, Wu X, Kvist AJ, et al. Successful reprogramming of cellular protein production through mRNA delivered by functionalized lipid nanoparticles. Proc Natl Acad Sci USA 2018;115:E3351-E3360
[74]	Viger-Gravel J, Schantz A, Pinon AC, Rossini AJ, Schantz S, Emsley L. Structure of lipid nanoparticles containing siRNA or mRNA by dynamic nuclear polarization-enhanced NMR spectroscopy. J Phys Chem B 2018;122:2073-2081
[75]	Jia W, Wang H, Chen M, Lu D, Lin L, Car R, et al. Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. In:Cuicchi C, Qualters I, Kramer W, chairs. SC20:International Conference for High Performance Computing, Networking, Storage and Analysis. Piscataway:IEEE press; 2020. Article 5, p. 1-14

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 91
HTML全文浏览量: 45
PDF下载量: 0
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

doi: 10.1016/j.apsb.2021.11.021

通讯作者:
Jinzhong Lin,E-mail:linjinzhong@fudan.edu.cn

Defang Ouyang,E-mail:defangouyang@umac.mo

计量

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

计量

目录

留言板

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

doi: 10.1016/j.apsb.2021.11.021

通讯作者: Jinzhong Lin,E-mail:linjinzhong@fudan.edu.cn Defang Ouyang,E-mail:defangouyang@umac.mo

计量

出版历程

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

计量

出版历程

目录

通讯作者:
Jinzhong Lin,E-mail:linjinzhong@fudan.edu.cn

Defang Ouyang,E-mail:defangouyang@umac.mo