Dynamic Profiling and Prediction of Antibody Response to Booster Inactivated Vaccines by Microsample-driven Biosensor and Machine Learning

Abstract

Knowledge on the antibody response to inactivated vaccines in third dose is crucial because it is one of the primary global vaccination programs. This study integrated microsampling with optical biosensors to profile neutralizing antibodies (NAbs) in fifteen vaccinated healthy donors, followed by application of machine learning to predict antibody response at given timepoints. Over a nine-month duration, microsampling and venipuncture were conducted at seven individual timepoints. A refined iteration of fiber optic-biolayer interferometry (FO-BLI) biosensor was designed, enabling rapid multiplexed biosensing of NAbs towards both wild-type and Omicron variants in minutes. Findings revealed a strong correlation (Pearson r of 0.919, specificity of 100%) between wild-type NAbs levels in microsamples and sera. Following the third dose, Sera NAbs levels for wide-type increased by 2.9-fold after seven days and 3.3-fold within a month, subsequently waning and becoming undetectable in three months. Considerable but incomplete escape of the latest omicron subvariants from booster vaccine elicited NAbs was confirmed, although a higher number of binding antibodies (BAbs) was identified by another rapid FO-BLI biosensor in minutes. Significantly, FO-BLI highly correlated with a pseudovirus neutralization assay in identifying neutralizing capacities (Pearson r of 0.983). Additionally, machine learning demonstrated exceptional accuracy in predicting antibody levels with an error of <5% for both NAbs and BAbs across multiple timepoints. Microsample-driven biosensing enables individuals to access their results within hours after self-collection, while precise models could guide personalized vaccination strategies. The technology's innate adaptability positions its potential for effective translation in diseases prevention and vaccines development.