Summary
Structural tokens improve zero-shot variant effect prediction in ESM3, but only when using the experimental structure of the WT (1). The use of computational models obtained using Rosetta or short MD simulations substantially lowers the Spearman correlation, despite the resulting embeddings being almost identical.
Figures
Figures from (1)
1.
Loux T, Wang D, Shakhnovich EI. More Structure, Less Accuracy: ESM3’s Binding Prediction Paradox. openRxiv; 2024. Available from: https://doi.org/10.1101/2024.12.09.627585