Computationally predicting binding affinity in protein-ligand complexes: free energy-based simulations and machine learning-based scoring functions

Accurately predicting protein-ligand binding affinities can substantially facilitate the drug discovery process, but it remains as a difficult problem. To tackle the challenge, many computational methods have been proposed. Among these methods, free energy-based simulations and machine learning-based scoring functions can potentially provide accurate predictions. In this paper, we review these two classes of methods, following a number of thermodynamic cycles for the free energy-based simulations and a feature-representation taxonomy for the machine learning-based scoring functions. More recent deep learning-based predictions, where a hierarchy of feature representations are generally extracted, are also reviewed. Strengths and weaknesses of the two classes of methods, coupled with future directions for improvements, are comparatively discussed.

Automated summary

This paper reviews two classes of methods for accurately predicting protein-ligand binding affinities: free energy-based simulations and machine learning-based scoring functions. It follows thermodynamic cycles for the former and a feature-representation taxonomy for the latter. Additionally, recent deep learning-based predictions are also discussed, with comparisons of strengths, weaknesses, and future directions for improvements.