Improved Prediction of Stabilizing Mutations in Proteins by Incorporation of Mutational Effects on Ligand Binding

While many computational methods accurately predict destabilizing mutations, identifying stabilizing mutations has remained a challenge, because of their relative rarity. We tested ΔΔG ⁰ predictions from computational predictors such as Rosetta, ThermoMPNN, RaSP, and DeepDDG, using 82 mutants of the bacterial toxin CcdB as a test case. On this dataset, the best computational predictor is ThermoMPNN, which identifies stabilizing mutations with a precision of 68%. However, the average increase in T _m for these predicted mutations was only 1°C for CcdB, and predictions were poorer for a more challenging target, influenza neuraminidase. Using data from multiple previously described yeast surface display libraries and in vitro thermal stability measurements, we trained logistic regression models to identify stabilizing mutations with a precision of 90% and an average increase in T _m of 3°C for CcdB. When such libraries contain a population of mutants with significantly enhanced binding relative to the corresponding wild type, there is no benefit in using computational predictors. It is then possible to predict stabilizing mutations without any training, simply by examining the distribution of mutational binding scores. This avoids laborious steps of in vitro expression, purification, and stability characterization. When this is not the case, combining data from computational predictors with high-throughput experimental binding data enhances the prediction of stabilizing mutations. However, this requires training on stability data measured in vitro with known stabilized mutants. It is thus feasible to predict stabilizing mutations rapidly and accurately for any system of interest that can be subjected to a binding selection or screen.