Back

An AI-driven approach for nanobody affinity maturation

Yang, X.; Guo, Z.; Zhao, Q.

2025-11-12 immunology
10.1101/2025.11.11.687768 bioRxiv
Show abstract

B7-H3 (CD276), an immunoregulatory checkpoint molecule overexpressed in numerous cancers, is a promising therapeutic target. Nanobodies possess unique advantages for targeting B7-H3, such as small size, high stability, and the ability to bind cryptic epitopes. However, the rational affinity maturation of these nanobodies is challenging, especially in the absence of detailed structural data on antigen-antibody interactions. Here, we present a computational strategy that leverages artificial intelligence (AI) and molecular modeling, including homology modeling, molecular docking, and free-energy calculations--to systematically predict affinity-enhancing mutations for humanized anti-B7-H3 nanobodies. This AI-driven framework provides a powerful and cost-effective pipeline for accelerating the development of high-affinity nanobody therapeutics prior to experimental validation.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.