Development and use of machine learning algorithms in vaccine target selection.

Area of Science:

• Immunology
• Computational Biology
• Vaccine Design

Background:

• Rational vaccine design increasingly relies on computational methods.
• Identifying effective vaccine targets, such as B and T cell epitopes, is crucial.

Purpose of the Study:

• To explore the application of Machine Learning (ML) in computational vaccine design.
• To highlight ML's role in identifying epitopes and correlates of protection.
• To discuss the potential of interpretable ML for immunogen discovery and understanding immune responses.

Main Methods:

• Review of Machine Learning models used in vaccine target identification.
• Discussion of data types and prediction tasks relevant to ML in vaccinology.
• Exploration of interpretable ML for elucidating molecular mechanisms.

Main Results:

• ML models can guide the identification of B and T cell epitopes.
• Interpretable ML offers potential for improved immunogen discovery.
• Understanding molecular processes underlying immune responses is facilitated by ML.

Conclusions:

• Machine Learning is a valuable tool for rational vaccine design.
• Interpretable ML can advance scientific discovery in vaccinology.
• Bridging the gap to translational application requires addressing data and methodological challenges.