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

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

作者机构：State Key Laboratory of Quality Research in Chinese MedicineInstitute of Chinese Medical SciencesUniversity of MacaoMacao 999078China State Key Laboratory of Genetic EngineeringSchool of Life SciencesZhongshan HospitalFudan UniversityShanghai 200438China 

出 版 物：《Acta Pharmaceutica Sinica B》 (药学学报（英文版）)

年 卷 期：2022年第12卷第6期

页      面：2950-2962页

核心收录：

学科分类：1007[医学-药学(可授医学、理学学位)] 1001[医学-基础医学(可授医学、理学学位)] 100102[医学-免疫学] 10[医学] 

基　　金：financially supported by the University of Macao Research Grants (MYRG2020-00113-ICMS China) 

主　　题：Lipid nanoparticle Ionizable lipid mRNA Vaccine Formulation prediction Machine learning LightGBM Molecular modeling 

摘      要：Lipid nanoparticle(LNP) is commonly used to deliver mRNA ***,LNP optimization primarily relies on screening ionizable lipids by traditional experiments which consumes intensive cost and *** study attempts to apply computational methods to accelerate the LNP development for mRNA ***,325 data samples of mRNA vaccine LNP formulations with IgG titer were *** machine learning algorithm,lightGBM,was used to build a prediction model with good performance(R^(2)0.87).More importantly,the critical substructures of ionizable lipids in LNPs were identified by the algorithm,which well agreed with published *** 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 *** dynamic modeling further investigated the molecular mechanism of LNPs used in the *** result showed that the lipid molecules aggregated to form LNPs,and mRNA molecules twined around the *** summary,the machine learning predictive model for LNP-based mRNA vaccines was first developed,validated by experiments,and further integrated with molecular *** prediction model can be used for virtual screening of LNP formulations in the future.