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

• DOI: 10.1016/j.apsb.2021.11.021
• Publication Date: 2021-12-02T01:53:09Z
• Authors: Wei Wang; Shuo Feng; Zhuyifan Ye; Hanlu Gao; Jinzhong Lin; Defang Ouyang
• Keywords: 0303 health sciences; 03 medical and health sciences; Ionizable lipid; mRNA; Machine learning; Lipid nanoparticle; Formulation prediction; Original Article; Therapeutics. Pharmacology; RM1-950; Vaccine; 3. Good health

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 apply computational methods accelerate the development for Firstly, 325 data samples of vaccine formulations with IgG titer were collected. The machine learning algorithm, lightGBM, was build a prediction model good performance (R2 > 0.87). More importantly, critical substructures in LNPs identified well agreed published results. animal experimental results showed that using DLin-MC3-DMA (MC3) as lipid an N/P ratio at 6:1 induced higher efficiency mice than SM-102, consistent prediction. Molecular dynamic modeling further investigated molecular mechanism experiment. result molecules aggregated form LNPs, twined around LNPs. In summary, predictive LNP-based vaccines first developed, validated experiments, integrated modeling. can be virtual future.