Antibody Attributes that Predict the Neutralization and Effector Function of Polyclonal Responses to SARS-CoV-2

Area of Science:

• Immunology
• Machine Learning
• Virology

Background:

• Antibodies are crucial for protection against SARS-CoV-2, but the specific features of the humoral response driving immunity remain unclear.
• Understanding these features is vital for developing effective vaccines and antibody-based therapies against SARS-CoV-2 and future viral threats.

Approach:

• This study utilized machine learning to correlate polyclonal antibody characteristics from natural SARS-CoV-2 infection with various effector functions and neutralization potency.
• Biophysical antibody profiles were used to build predictive models for antibody-mediated phagocytosis, cytotoxicity, complement deposition, and neutralization.
• The models were validated on independent cohorts to ensure accuracy and generalizability.

Key Points:

• Machine learning models accurately predicted key antibody effector functions, including neutralization, based on biophysical antibody profiles.
• SARS-CoV-2-specific IgM was identified as a significant predictor of neutralization activity, with its importance experimentally confirmed.
• The study successfully generated predictive models linking antibody response profiles to antiviral activities.

Conclusions:

• The validated predictive models offer insights into the mechanisms of antibody action against SARS-CoV-2.
• These findings highlight desirable attributes of the humoral response that should be recapitulated in vaccine design and antibody interventions.
• This work advances our understanding of protective humoral immunity and guides the development of next-generation immunotherapies.