The Impact of Docking Pose Generation Error on the Prediction of Binding Affinity

Docking is a computational technique that predicts the preferred conformation and binding affinity of a ligand molecule as bound to a protein pocket. It is often employed to identify a molecule that binds tightly to the target, so that a small concentration of the molecule is sufficient to modulate its biochemical function. The use of non-parametric machine learning, a data-driven approach that circumvents the need of modeling assumptions, has recently been shown to introduce a large improvement in the accuracy of docking scoring. However, the impact of pose generation error on binding affinity prediction is still to be investigated. Here we show that the impact of pose generation is generally limited to a small decline in the accuracy of scoring. These machine-learning scoring functions retained the highest performance on PDBbind v2007 core set in this common scenario where one has to predict the binding affinity of docked poses instead of that of co-crystallized poses (e.g. drug lead optimization). Nevertheless, we observed that these functions do not perform so well at predicting the near-native pose of a ligand. This suggests that having different scoring functions for different problems is a better approach than using the same scoring function for all problems.