Summary
AlphaFold2 prefers to model proteins in the holo form for 67% of cases (1).
See also
- AlphaFold2 and RosettaFold sometimes produce different conformations
- pLDDT and PAE in protein folding neural networks are correlated
- AF2 RMSD to ground truth correlated with RMSD between conformations
- pLDDT and PAE inversely correlated with protein dynamics in dynamic naturally occurring proteins, but not de novo proteins
- AlphaFold2 predicts Apo conformations with poorer RMSD than holo conformations
1.
Saldaño T, Escobedo N, Marchetti J, Zea DJ, Mac Donagh J, Velez Rueda AJ, et al. Impact of protein conformational diversity on AlphaFold predictions. Bioinformatics. 2022;38(10):2742–8. Available from: https://doi.org/10.1093/bioinformatics/btac202