Biophysical Priors Enhance Protein–Protein Binding ΔΔG Prediction

Predicting mutational effects on protein–protein binding affinity ($\Delta\Delta G$) remains a challenging task: current models often generalize poorly due to limited and biased training data. In this talk,  Ww will show that SKEMPI2, the dominant training and evaluation dataset in this field, is affected by a subtle and pervasive data leakage due to sequential and structural redundancy, leading to inflated estimates of performance across models.  We introduce ProtBFF (\underline{Prot}ein \underline{B}iophysical \underline{F}eature \underline{F}ramework), a lightweight, encoder-agnostic module that injects five key biophysical features (interface, burial, dihedral, SASA, lDDT) into residue latent representations via cross-embedding attention. ProtBFF consistently improves predictive power and, with ProSST, achieves state-of-the-art performance on clustered SKEMPI2 and other datasets, rivaling far more specialized models. These results point to a simple, general recipe for protein property prediction: integrate biophysical priors with machine learning.