Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
This work addresses the challenge of accurate structure prediction for immune proteins like antibodies and T-cell receptors, which is crucial for accelerating therapeutic development, though it appears incremental by building on existing protein structure prediction methods.
The paper tackles the problem of predicting structures for antigen-recognizing immune proteins by introducing Ibex, a model that explicitly distinguishes between bound and unbound conformations, achieving state-of-the-art accuracy with superior out-of-distribution performance compared to existing tools.
We introduce Ibex, a pan-immunoglobulin structure prediction model that achieves state-of-the-art accuracy in modeling the variable domains of antibodies, nanobodies, and T-cell receptors. Unlike previous approaches, Ibex explicitly distinguishes between bound and unbound protein conformations by training on labeled apo and holo structural pairs, enabling accurate prediction of both states at inference time. Using a comprehensive private dataset of high-resolution antibody structures, we demonstrate superior out-of-distribution performance compared to existing specialized and general protein structure prediction tools. Ibex combines the accuracy of cutting-edge models with significantly reduced computational requirements, providing a robust foundation for accelerating large molecule design and therapeutic development.