AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

TL;DR

AbAffinity is a large language model developed to accurately predict antibody binding affinity to SARS-CoV-2, aiding in rapid antibody design for infectious diseases.

Contribution

The paper introduces AbAffinity, a novel large language model specifically trained for predicting antibody-antigen binding affinities.

Findings

Achieves high accuracy in predicting binding affinities.

Outperforms existing models in antibody affinity prediction.

Provides accessible code and model for the research community.

Abstract

Machine learning-based antibody design is emerging as one of the most promising approaches to combat infectious diseases, due to significant advancements in the field of artificial intelligence and an exponential surge in experimental antibody data (in particular related to COVID-19). The ability of an antibody to bind to an antigens (called binding affinity) is one of the the most critical properties in designing neutralizing antibodies. In this study we introduce Ab-Affinity, a new large language model that can accurately predict the binding affinity of antibodies against a target peptide, e.g., the SARS-CoV-2 spike protein. Code and model are available at https://github.com/ucrbioinfo/AbAffinity.