Predicting Antibody-Antigen Mutation ΔΔG via Side-Specific Protein Language Models and Paired Geometric Graph Learning.

Abstract excerpt

Mutation-induced changes in binding free energy (ΔΔG) at antibody-antigen interfaces are important for antibody optimization, mutational scanning, and viral immune escape assessment. However, computational prediction remains challenging because antibodies and antigens have distinct sequence backgrounds, mutation effects are often localized at interfaces, and related complexes may remain across training and...

Topics

• Mutation
• Thermodynamics
• Models, Molecular
• Antigens
• Antibodies
• SARS-CoV-2