Exploring Scoring Function Space. Developing Computational Models for Drug Discovery

Abstract

Background: The idea of scoring function space established a systems-level approach toaddress the development of models to predict binding affinity faced by those interested in drugdiscovery.Objective: Our goal here is to review the concept of scoring function space and how to explore it todevelop machine learning models to address protein-ligand binding affinity.Method: We searched the articles available in PubMed about the scoring function space. We alsoutilized crystallographic structures found in the protein data bank (PDB). We used datasets available atthe PDBbind, BindingDB, and Binding MOAD to illustrate how to integrate structural and binding data.Results: The application of systems-level approaches to address receptor-drug interactions allows us tohave a holistic view of the process of drug discovery. The scoring function space added flexibility tothe process since it makes it possible to see the drug discovery as a relationship involving mathematicalspaces.Conclusion: The application of the concept of scoring function space gave us an integrated view ofdrug discovery methods. This concept is useful to support the application of methods used for drugdiscovery, where we see the process as a computational search of the chemical space using itsrelationships with the protein and scoring function spaces as a guide to finding new models to expressreceptor-drug binding affinity.