![]() ![]() Sometimes the scoring function has the dual purposes of finding the binding poses (docking) and predicting the protein-ligand binding affinity (scoring), whilst at other times different scoring functions are used for different purposes (scoring, ranking, docking, or screening). The binding mode search is usually guided by a scoring function. Protein-ligand docking is one of the main computational tools employed in the early stages of structure-based drug discovery-where more accurate methods, such as free energy calculations, are too time-consuming-to predict the binding mode and binding affinity of different ligands in a binding site. Structure-based drug discovery exploits knowledge of protein structures to design novel and potent compounds for a specific target. Combined with AutoDock Vina, \(\Delta\)-AEScore has an RMSE of 1.32 p K units and a Pearson’s correlation coefficient of 0.80 on the CASF-2016 benchmark, while retaining the docking and screening power of the underlying classical scoring function. Therefore, we show that the model can be combined with the classical scoring function AutoDock Vina in the context of \(\Delta\)-learning, where corrections to the AutoDock Vina scoring function are learned instead of the protein-ligand binding affinity itself. However, AEScore does not perform as well in docking and virtual screening tasks, for which it has not been explicitly trained. ![]() The AEV-based scoring function, which we term AEScore, is shown to perform as well or better than other state-of-the-art scoring functions on binding affinity prediction, with an RMSE of 1.22 p K units and a Pearson’s correlation coefficient of 0.83 for the CASF-2016 benchmark. Here we explore the use of atomic environment vectors (AEVs) and feed-forward neural networks, the building blocks of several neural network potentials, for the prediction of protein-ligand binding affinity. Scoring functions for the prediction of protein-ligand binding affinity have seen renewed interest in recent years when novel machine learning and deep learning methods started to consistently outperform classical scoring functions. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |