A generalisable framework to inject distance information into Alphafold-like structure predictors
Mirabello, C.; Wallner, B.; Orekhov, V.; Nystedt, B.; Pearce, N.
Show abstract
Structure prediction methods are now highly successful at predicting three-dimensional structures from sequence. However, it is still often desirable to supplement these methods with additional external priors on pairwise distances in the structures. We present a general method for injecting prior information into AlphaFold-like structure predictors by biasing the pair representation to produce desirable features in the distogram, which are then reflected in the structures. We demonstrate this approach to: sample alternate states by selectively pushing or pulling mobile amino acid pairs; integrate NMR NOESY data with structure pre-diction; and improve the success of protein-protein and protein-ligand complex prediction. We demonstrate that this approach is applicable both to AlphaFold2 and a reproduction of AlphaFold 3 (OpenFold3). resTrain is open source, available to all users on GitHub and as a Colab notebook: https://github.com/clami66/resTrain
Matching journals
The top 6 journals account for 50% of the predicted probability mass.