Summary
Developability properties of antibodies, such as thermostability, can be predicted with higher accuracy using features derived from MD simulations compared to those obtained from either static structures or language model embeddings (1). (2) found that developability predictions made from trajectories starting from either experimental structures or predicted structures tended to correlate with each other better than predictions made from just the experimental structures or predicted structures.
Figures
Ref (2)
See also
- Antibody developability predictions from computational models are sensitive to the structure prediction method
- Abs modeled using MD are better for featurization than those modeled using homology modeling
1.
Rollins ZA, Widatalla T, Cheng AC, Metwally E. AbMelt: Learning antibody thermostability from molecular dynamics. Biophysical Journal. 2024;123(17):2921–33. Available from: https://doi.org/10.1016/j.bpj.2024.06.003
2.
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