Summary
ddG predictions calculated from AlphaFold2 structures using variant effect prediction methods are equally accurate as those derived from experimental structures (1).
See also
- High-accuracy computational models might not always be effective for ligand docking
- Training inverse folding and diffusion models exclusively on predicted protein structures worsens performance due to how locally perfect they are
1.
Diaz DJ, Gong C, Ouyang-Zhang J, Loy JM, Wells J, Yang D, et al. Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations. Nature Communications. 2024;15(1):6170. Available from: https://doi.org/10.1038/s41467-024-49780-2