Summary
Antibody protein language models are more effective at reproducing developability predictions from sequence than those from structure (1). Additionally, they continue to improve with more data compared to linear regression using other uncorrelated developability predictions.
Figures
Ref (1)
1.
Bashour H, Smorodina E, Pariset M, Zhong J, Akbar R, Chernigovskaya M, et al. Biophysical cartography of the native and human-engineered antibody landscapes quantifies the plasticity of antibody developability. Communications Biology. 2024;7(1). Available from: https://doi.org/10.1038/s42003-024-06561-3