Molegro Virtual Docker (MVD) is one of the most used docking programs to address protein-ligand interactions. It integrates different search algorithms and scoring functions, creating 16 combinations of these approaches. This flexibility allowed its application to a wide range of protein targets with successful prediction of inhibition based on docking results. MVD calculates binding affinity using MolDock and Plants scores, with outputs showing the energy terms employed in these scoring functions. We may use these docking results to build machine learning models to predict the inhibition of specific protein targets. In this chapter, we describe the integration of MVD and Scikit-Learn (Ridge regression method) and its application to predict the inhibition of cyclin-dependent kinase 2 (CDK2). This combination of techniques makes it possible to explore the concept of scoring function space and build an adequate computational model to predict binding affinity with superior predictive performance compared with a classical scoring function.