Machine Learning for the Prediction of Size and Encapsulation Efficiency of mRNA-Loaded Lipid Nanoparticles Following a Postencapsulation Approach

A library of preformed vesicles (PFVs) was produced with varying lipid compositions and process parameters.

• Chip design and lipid composition influenced the size and polydispersity index (PDI) of PFVs.
• Smaller PFVs were generated with chip designs that provided higher mixing efficiency.
• Postencapsulated formulations consistently exhibited larger nanoparticle sizes and lower PDI values than the original PFVs.
• An XGBoost model was developed to predict the size and encapsulation efficiency (EE%) of lipid nanoparticles based on formulation and process variables.
• The model's accuracy improved with the inclusion of additional pseudolabeled data from the PFVs data set.

AI simplified