Büşra Savaş

The paper evaluates if AlphaFold distograms can predict binding-induced hinge motions in proteins, showing they capture flexibility not seen in predicted structures.

The paper applies enhanced AlphaFold2 sampling and data-driven docking to predict antibody-peptide and antibody-MHC I complexes, achieving medium-quality predictions for some targets.

The paper benchmarks six structure-based binding affinity predictors on Spike-ACE2 mutations, finding FoldX performs best with R = -0.51 and 64% accuracy in binary classification.