Supervised Machine Learning Methods Applied to Predict Ligand-Binding Affinity

Background: Calculation of ligand-binding affinity is an open problem in computational medicinal chemistry. The ability to computationally predict affinities has a beneficial impact in the early stages of drug development, since it allows a mathematical model to assess protein-ligand interactions. Due to the availability of structural and binding information, machine learning methods have been applied to generate scoring functions with good predictive power. Objective: Our goal here is to review recent developments in the application of machine learning methods to predict ligand-binding affinity. Method: We focus our review on the application of computational methods to predict binding affinity for protein targets. In addition, we also describe the major available databases for experimental binding constants and protein structures. Furthermore, we explain the most successful methods to evaluate the predictive power of scoring functions. Results: Association of structural information with ligand-binding affinity makes it possible to generate scoring functions targeted to a specific biological system. Through regression analysis, this data can be used as a base to generate mathematical models to predict ligand-binding affinities, such as inhibition constant, dissociation constant and binding energy. Conclusion: Experimental biophysical techniques were able to determine the structures of over 120,000 macromolecules. Considering also the evolution of binding affinity information, we may say that we have a promising scenario for development of scoring functions, making use of machine learning techniques. Recent developments in this area indicate that building scoring functions targeted to the biological systems of interest shows superior predictive performance, when compared with other approaches.