Protein-ligand binding affinity prediction: Is 3D binding pose needed?

Abstract Accurate protein-ligand binding affinity prediction is crucial in drug discovery. Existing methods are predominately docking-free, without explicitly considering atom-level interaction between proteins and ligands in scenarios where crystallized protein-ligand binding conformations are unavailable. Now, with breakthroughs in deep learning AI-based protein folding and binding conformation prediction, can we improve binding affinity prediction? This study introduces a framework, Folding-Docking-Affinity (FDA), which folds proteins, determines protein-ligand binding conformations and predicts binding affinities from three-dimensional protein-ligand binding structures. Our experiments demonstrate that the FDA outperforms state-of-the-art docking-free models in the DAVIS dataset, showcasing the potential of explicit modeling of three-dimensional binding conformations for enhancing binding affinity prediction accuracy.