Improving Stereochemical Limitations in Protein-Ligand Complex Structure Prediction

Abstract AlphaFold3 has revolutionized biology by enabling the prediction of protein complexes with various biomolecules, including small molecular ligands. However, the ligand structures predicted by the model often contain stereochemical errors. In this study, our comprehensive evaluation of AlphaFold3 and its clone model, Boltz-1, demonstrated significant limitations in ligand stereochemistry of their predicted structures, including chirality, bond, and angle geometries. To address the issue, we developed the restraint-guided inference method that applies stereochemical restraints during the reverse diffusion process. This approach perfectly reproduces the chirality specified in the input chemical structure and improves bond and angle geometries of ligands, while maintaining comparable performance in binding pose prediction. Our method provides a practical solution to the stereochemical errors in predicting protein-ligand complexes, thereby enhancing applications of structure prediction in structural biology and drug discovery.