Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches

Ravi Maharjan; Ki Hyun Kim; Kyeong Lee; Hyo-Kyung Han; Seong Hoon Jeong

doi:10.1016/j.jpha.2024.100996

Volume 14 Issue 11

Nov. 2024

Turn off MathJax

Article Contents

Article Navigation > Journal of Pharmaceutical Analysis > 2024 > 14(11): 100996

Ravi Maharjan, Ki Hyun Kim, Kyeong Lee, Hyo-Kyung Han, Seong Hoon Jeong. Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches[J]. Journal of Pharmaceutical Analysis, 2024, 14(11): 100996. doi: 10.1016/j.jpha.2024.100996

Citation:

Ravi Maharjan, Ki Hyun Kim, Kyeong Lee, Hyo-Kyung Han, Seong Hoon Jeong. Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches[J]. Journal of Pharmaceutical Analysis, 2024, 14(11): 100996. doi: 10.1016/j.jpha.2024.100996

Citation:

Ravi Maharjan, Ki Hyun Kim, Kyeong Lee, Hyo-Kyung Han, Seong Hoon Jeong. Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches[J]. Journal of Pharmaceutical Analysis, 2024, 14(11): 100996. doi: 10.1016/j.jpha.2024.100996

PDF( 4480 KB)

Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches

doi: 10.1016/j.jpha.2024.100996

a. BK21 FOUR Team and Integrated Research Institute for Drug Development, College of Pharmacy, Dongguk University, Gyeonggi, 10326, Republic of Korea;
b. College of Pharmacy, Mokpo National University, Jeonnam, 58554, Republic of Korea

Funds:

This work was partially supported by the Advance Production of Vaccine Raw Materials (Grant Nos.: 20022404 and 20018168) funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea). This work was also partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (Grant No.: NRF-2018R1A5A2023127) and Dongguk University Research Fund of 2023 (Grant No.: S-2023-G0001-00099).

Received Date: Jan. 03, 2024
Accepted Date: May 03, 2024
Rev Recd Date: Apr. 21, 2024
Publish Date: May 08, 2024

Abstract

Abstract

To enhance the efficiency of vaccine manufacturing, this study focuses on optimizing the microfluidic conditions and lipid mix ratios of messenger RNA-lipid nanoparticles (mRNA-LNP). Different mRNA-LNP formulations (n = 24) were developed using an I-optimal design, where machine learning tools (XGBoost/Bayesian optimization and self-validated ensemble (SVEM)) were used to optimize the process and predict lipid mix ratio. The investigation included material attributes, their respective ratios, and process attributes. The critical responses like particle size (PS), polydispersity index (PDI), Zeta potential, pKa, heat trend cycle, encapsulation efficiency (EE), recovery ratio, and encapsulated mRNA were evaluated. Overall prediction of SVEM (>97%) was comparably better than that of XGBoost/Bayesian optimization (>94%). Moreover, in actual experimental outcomes, SVEM prediction is close to the actual data as confirmed by the experimental PS (94–96 nm) is close to the predicted one (95–97 nm). The other parameters including PDI and EE were also close to the actual experimental data.
- Vaccine manufacturing,
- Microfluidic device,
- XGBoost,
- Bayesian optimization,
- Self-validated ensemble model

FullText(HTML)

References(54)

References

[1]	J. Pang, M.X. Wang, I.Y.H. Ang, et al., Potential rapid diagnostics, vaccine and therapeutics for 2019 novel coronavirus (2019-nCoV): A systematic review, J. Clin. Med. 9 (2020), 623.
[2]	S.C. Semple, R. Leone, C.J. Barbosa, et al., Lipid nanoparticle delivery systems to enable mRNA-based therapeutics, Pharmaceutics 14 (2022), 398.
[3]	L. Miao, Y. Zhang, L. Huang, mRNA vaccine for cancer immunotherapy, Mol. Cancer 20 (2021), 41.
[4]	Q. Xiong, G.Y. Lee, J. Ding, et al., Biomedical applications of mRNA nanomedicine, Nano Res. 11 (2018) 5281-5309.
[5]	G. Prakash, A. Shokr, N. Willemen, et al., Microfluidic fabrication of lipid nanoparticles for the delivery of nucleic acids, Adv. Drug Deliv. Rev. 184 (2022), 114197.
[6]	K. Osouli-Bostanabad, S. Puliga, D.R. Serrano, et al., Microfluidic manufacture of lipid-based nanomedicines, Pharmaceutics 14 (2022), 1940.
[7]	A. Algarni, E.H. Pilkington, E.J.A. Suys, et al., In vivo delivery of plasmid DNA by lipid nanoparticles: The influence of ionizable cationic lipids on organ-selective gene expression, Biomater. Sci. 10 (2022) 2940-2952.
[8]	M. Kawaguchi, M. Noda, A. Ono, et al., Effect of cholesterol content of lipid composition in mRNA-LNPs on the protein expression in the injected site and liver after local administration in mice, J. Pharm. Sci. 112 (2023) 1401-1410.
[9]	E. Oude Blenke, E. Ornskov, C. Schoneich, et al., The storage and In-use stability of mRNA vaccines and therapeutics: Not A cold case, J. Pharm. Sci. 112 (2023) 386-403.
[10]	H. Helgers, A. Schmidt, L.J. Lohmann, et al., Towards autonomous operation by advanced process control-Process analytical technology for continuous biologics antibody manufacturing, Processes 9 (2021), 172.
[11]	S. Daniel, Z. Kis, C. Kontoravdi, et al., Quality by Design for enabling RNA platform production processes, Trends Biotechnol. 40 (2022) 1213-1228.
[12]	H.H. Ly, S. Daniel, S.K.V. Soriano, et al., Optimization of lipid nanoparticles for saRNA expression and cellular activation using a design-of-experiment approach, Mol. Pharm. 19 (2022) 1892-1905.
[13]	K. Nag, M.E.H. Sarker, S. Kumar, et al., DoE-derived continuous and robust process for manufacturing of pharmaceutical-grade wide-range LNPs for RNA-vaccine/drug delivery, Sci. Rep. 12 (2022), 9394.
[14]	Y. Suzuki, T. Miyazaki, H. Muto, et al., Design and lyophilization of lipid nanoparticles for mRNA vaccine and its robust immune response in mice and nonhuman Primates, Mol. Ther. Nucleic Acids 30 (2022) 226-240.
[15]	S. Chen, X. Huang, Y. Xue, et al., Nanotechnology-based mRNA vaccines, Nat. Rev. Methods Primers 3 (2023), 63.
[16]	Z. Ghaemmaghamian, R. Zarghami, G. Walker, et al., Stabilizing vaccines via drying: Quality by design considerations, Adv. Drug Deliv. Rev. 187 (2022), 114313.
[17]	A. Ortiz-Perez, D. van Tilborg, R. van der Meel, et al., Machine learning-guided high throughput nanoparticle design, Digit. Discov. 3 (2024) 1280-1291.
[18]	A.W. Freyn, C. Atyeo, P.L. Earl, et al., A monkeypox mRNA-lipid nanoparticle vaccine targeting virus binding, entry, and transmission drives protection against lethal orthopoxviral challenge, bioRxiv. 2022. DOI: 10.1101/2022.12.17.520886.
[19]	A.T. Karl, S. Essex, J. Wisnowski, et al., A workflow for lipid nanoparticle (LNP) formulation optimization using designed mixture-process experiments and self-validated ensemble models (SVEM), J. Vis. Exp. 198 (2023).
[20]	A. Schmidt, H. Helgers, F.L. Vetter, et al., Process automation and control strategy by quality-by-design in total continuous mRNA manufacturing platforms, Processes 10 (2022), 1783.
[21]	K.J. Kauffman, J.R. Dorkin, J.H. Yang, et al., Optimization of lipid nanoparticle formulations for mRNA delivery in vivo with fractional factorial and definitive screening designs, Nano Lett. 15 (2015) 7300-7306.
[22]	T. Lemkus, P. Ramsey, C. Gotwalt, et al., Self-validated ensemble models for design of experiments, arXiv. https://doi.org/10.48550/arXiv.2103.09303.
[23]	M. Zhao, R. Wang, K. Yang, et al., Nucleic acid nanoassembly-enhanced RNA therapeutics and diagnosis, Acta Pharm. Sin. B 13 (2023) 916-941.
[24]	E. Yeung, P. Ramsey, Optimization of a conventional glycosylation analytical method using machine learning and experimental design, BioProcessing Journal 20 (2021).
[25]	W. Wang, S. Feng, Z. Ye, et al., Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm, Acta Pharm. Sin. B 12 (2022) 2950-2962.
[26]	R. Maharjan, S. Hada, J.E. Lee, et al., Comparative study of lipid nanoparticle-based mRNA vaccine bioprocess with machine learning and combinatorial artificial neural network-design of experiment approach, Int. J. Pharm. 640 (2023), 123012.
[27]	Y. Xu, S. Ma, H. Cui, et al., AGILE platform: A deep learning-powered approach to accelerate LNP development for mRNA delivery, bioRxiv. 2023. https://doi.org/10.1101/2023.06.01.543345.
[28]	Y. Qin, A.A. Walters, N. Rouatbi, et al., Evaluation of a DoE based approach for comprehensive modelling of the effect of lipid nanoparticle composition on nucleic acid delivery, Biomaterials 299 (2023), 122158.
[29]	A. Ouranidis, C. Davidopoulou, R.K. Tashi, et al., Pharma 4.0 continuous mRNA drug products manufacturing, Pharmaceutics 13 (2021), 1371.
[30]	R. Maharjan, S.H. Jeong, Application of different models to evaluate the key factors of fluidized bed layering granulation and their influence on granule characteristics, Powder Technol. 408 (2022), 117737.
[31]	L. Schoenmaker, D. Witzigmann, J.A. Kulkarni, et al., mRNA-lipid nanoparticle COVID-19 vaccines: Structure and stability, Int. J. Pharm. 601 (2021), 120586.
[32]	M.M. Tosi, A.P. Ramos, B.S. Esposto, et al., Chapter Six Dynamic light scattering (DLS) of nanoencapsulated food ingredients. S.M. Jafari, Characterization of Nanoencapsulated Food Ingredients, Vol. 4, Academic Press, 2020, New York, pp. 191-211.
[33]	M.J. Carrasco, S. Alishetty, M.G. Alameh, et al., Ionization and structural properties of mRNA lipid nanoparticles influence expression in intramuscular and intravascular administration, Commun. Biol. 4 (2021), 956.
[34]	M.I. Henderson, Y. Eygeris, A. Jozic, et al., Leveraging biological buffers for efficient messenger RNA delivery via lipid nanoparticles, Mol. Pharm. 19 (2022) 4275-4285.
[35]	Y. Fan, C.W. Yen, H.C. Lin, et al., Automated high-throughput preparation and characterization of oligonucleotide-loaded lipid nanoparticles, Int. J. Pharm. 599 (2021), 120392.
[36]	A. Hasanzadeh, M.R. Hamblin, J. Kiani, et al., Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines? Nano Today 47 (2022), 101665.
[37]	D.Y. Ding, Y. Zhang, Y. Jia, et al., Machine learning-guided lipid nanoparticle design for mRNA delivery, arXiv. 2023. https://doi.org/10.48550/arXiv.2308.01402.
[38]	S.A. Damiati, D. Rossi, H.N. Joensson, et al., Artificial intelligence application for rapid fabrication of size-tunable PLGA microparticles in microfluidics, Sci. Rep. 10 (2020), 19517.
[39]	P. Hersh, SVEM in JMP 17. https://community.jmp.com/t5/Elevated-Thinking/SVEM-in-JMP-17/ba-p/538553. (Accessed 3 May 2024).
[40]	P. Kay, P. Hersh, Re-Thinking the Design and Analysis of Experiments? (2021-EU-30MP-776). https://community.jmp.com/t5/Discovery-Summit-Europe-2021/Re-Thinking-the-Design-and-Analysis-of-Experiments-2021-EU-30MP/ta-p/349240. (Accessed 25 December 2023).
[41]	P. Ramsey, W. Levin, T. Lemkus, et al., SVEM: A Paradigm Shift in Design and Analysis of Experiments (2021-EU-45MP-779). https://community.jmp.com/t5/Discovery-Summit-Europe-2021/SVEM-A-Paradigm-Shift-in-Design-and-Analysis-of-Experiments-2021/ta-p/349244. (Accessed 30 November 2023).
[42]	K. Okuda, Y. Sato, K. Iwakawa, et al., On the size-regulation of RNA-loaded lipid nanoparticles synthesized by microfluidic device, J. Control. Release 348 (2022) 648-659.
[43]	X. Hou, T. Zaks, R. Langer, et al., Lipid nanoparticles for mRNA delivery, Nat. Rev. Mater. 6 (2021) 1078-1094.
[44]	A. Lamoot, J. Lammens, E. De Lombaerde, et al., Successful batch and continuous lyophilization of mRNA LNP formulations depend on cryoprotectants and ionizable lipids, Biomater. Sci. 11 (2023) 4327-4334.
[45]	C. Malburet, L. Leclercq, J.F. Cotte, et al., Size and charge characterization of lipid nanoparticles for mRNA vaccines, Anal. Chem. 94 (2022) 4677-4685.
[46]	A. Ji, M. Xu, Y. Pan, et al., Lipid microparticles show similar efficacy with lipid nanoparticles in delivering mRNA and preventing cancer, Pharm. Res. 40 (2023) 265-279.
[47]	R.A. Meyer, S.Y. Neshat, J. Green, et al., Targeting strategies for mRNA delivery, Mater. Today Adv., 14 (2022), 100240.
[48]	Y. Fan, Z. Shi, S. Ma, et al., Spectroscopy-based local modeling method for high-throughput quantification of nucleic acid loading in lipid nanoparticles, Anal. Chem. 94 (2022) 9081-9090.
[49]	X.G. Chen, M. Grauzinyte, A.W. van der Vaart, et al., Applying pattern recognition as a robust approach for silicone oil droplet identification in flow-microscopy images of protein formulations, J. Pharm. Sci. 110 (2021) 1643-1651.
[50]	J. Yang, F. Meng, S. Huang, et al., Process capability analysis for manufacturing processes based on the truncated data from supplier products, Int. J. Prod. Res. 58 (2020) 6235-6251.
[51]	D. Gong, E. Ben-Akiva, A. Singh, et al., Machine learning guided structure function predictions enable in silico nanoparticle screening for polymeric gene delivery, Acta Biomater. 154 (2022) 349-358.
[52]	Y. Lin, Y. Wang, J. Ding, et al., Reactivation of the tumor suppressor PTEN by mRNA nanoparticles enhances antitumor immunity in preclinical models, Sci. Transl. Med. 13 (2021), eaba9772.
[53]	M.A. Islam, J. Rice, E. Reesor, et al., Adjuvant-pulsed mRNA vaccine nanoparticle for immunoprophylactic and therapeutic tumor suppression in mice, Biomaterials 266 (2021), 120431.
[54]	B. Yarahmadi, S.M. Hashemianzadeh, S.M. Milani Hosseini, Machine-learning-based predictions of imprinting quality using ensemble and non-linear regression algorithms, Sci. Rep. 13 (2023), 12111.