Summary
Conformational changes have been modeled using AlphaFold2 by inversion and driving specific collective variables (1). A related approach using ESMFold attempted to sample conformational transition paths using language model embeddings as the target (2).
1.
Xie T, Song Z, Huang J. Conditioned Protein Structure Prediction. PRX Life. 2024;2(4). Available from: https://doi.org/10.1103/prxlife.2.043001
2.
del Alamo D, Jeliazkov JR, Truan D, Karpiak JD. Conformational sampling and interpolation using language-based protein folding neural networks. openRxiv; 2023. Available from: https://doi.org/10.1101/2023.12.16.571997