Docking screens aim at scanning large datasets of small molecules to find potential binders to protein targets related to pathologies. The main computational workhorse of this approach is protein-ligand docking. This chapter focuses on an integrated workflow to perform docking screens using Molegro Virtual Docker (MVD). We describe how to proceed with a target structure and integrate all necessary binding affinity data available at BindingDB to build a regression model to predict inhibition of cyclin-dependent kinase 2 (CDK2) using Molegro Data Modeller (MDM), a machine learning tool integrated into MVD. CDK2 is a protein target for anticancer drug development. Our regression model built with MDM shows superior predictive performance compared with classical scoring functions employed in docking programs. This MDM-built model is ready to use for virtual screening purposes. The integration relies on Jupyter Notebooks at Google Colab. All CDK2 datasets and Jupyter Notebooks discussed in this work are available at GitHub: https://github.com/azevedolab/docking#readme .