Comparative study of lipid nanoparticle-based mRNA vaccine bioprocess with machine learning and combinatorial artificial neural network-design of experiment approach

To develop a combinatorial artificial-neural-network design-of-experiment (ANN-DOE) model, the effect of ionizable lipid, an ionizable lipid-to-cholesterol ratio, N/P ratio, flow rate ratio (FRR), and total flow rate (TFR) on the outcome responses of mRNA-LNP vaccine were evaluated using a definitive screening design (DSD) and machine learning (ML) algorithms. Particle size (PS), PDI, zeta potential (ZP), and encapsulation efficiency (EE) of mRNA-LNP were optimized within a defined constraint (PS 40-100 nm, PDI <= 0.30, ZP >=(+/-)0.30 mV, EE >= 70 %), fed to ML algorithms (XGBoost, bootstrap forest, support vector machines, k-nearest neighbors, generalized regression-Lasso, ANN) and prediction was compared to ANN-DOE model. Increased FRR decreased the PS and increased ZP, while increased TFR increased PDI and ZP. Similarly, DOTAP and DOTMA produced higher ZP and EE. Particularly, a cationic ionizable lipid with an N/P ratio >= 6 provided a higher EE. ANN showed better predictive ability (R2 = 0.7269-0.9946), while XGBoost demonstrated better RASE (0.2833-2.9817). The ANN -DOE model outperformed both optimized ML models by R2 = 1.21 % and RASE = 43.51 % (PS prediction), R2 = 0.23 % and RASE = 3.47 % (PDI prediction), R2 = 5.73 % and RASE = 27.95 % (ZP prediction), and R2 = 0.87 % and RASE = 36.95 % (EE prediction), respectively, which demonstrated that ANN-DOE model was superior in predicting the bioprocess compared to independent models.

Automated summary

A combinatorial artificial-neural-network design-of-experiment (ANN-DOE) model was developed to evaluate the effects of various factors on the outcome responses of mRNA-LNP vaccine. The ANN-DOE model outperformed optimized ML models in predicting the bioprocess of the vaccine. Increased flow rate ratio (FRR) decreased particle size and increased zeta potential (ZP), while increased total flow rate (TFR) increased PDI and ZP. The ANN-DOE model demonstrated better predictive ability and accuracy compared to independent ML models.