We consider the problem of antibody sequence design given 3D structural information. Building on previous work, we propose a fine-tuned inverse folding model that is specifically optimised for antibody structures and outperforms generic protein models on sequence recovery and structure robustness when applied on antibodies, with notable improvement on the hypervariable CDR-H3 loop. We study the canonical conformations of complementarity-determining regions and find improved encoding of these loops into known clusters. Finally, we consider the applications of our model to drug discovery and binder design and evaluate the quality of proposed sequences using physics-based methods.
@article{arxiv.2310.19513,
title = {Inverse folding for antibody sequence design using deep learning},
author = {Frédéric A. Dreyer and Daniel Cutting and Constantin Schneider and Henry Kenlay and Charlotte M. Deane},
journal= {arXiv preprint arXiv:2310.19513},
year = {2023}
}
Comments
2023 ICML Workshop on Computational Biology, model weights available at https://zenodo.org/record/8164693