Molegro Virtual Docker (MVD) provides a rich graphical interface for docking simulations and related machine learning methods. The Protein Data Bank is the source of structural data for docking simulations with MVD. This chapter focuses on cyclin-dependent kinase 7 (CDK7), a protein target for anticancer drugs. The MVD has a partner program for machine learning modeling named Molegro Data Modeller (MDM). MDM utilizes energy terms, scoring functions, and ligand descriptors as features. Jupyter Notebooks merge binding and structural data with MVD-MDM. An integrated workflow shows how to run different tasks necessary for docking simulations and building regression models to predict binding affinity. A targeted regression model to calculate the binding affinity against CDK7 showed superior predictive performance compared to a classical scoring function from the MVD (Rerank score). This workflow can handle any protein target for which structural and binding data are available. All CDK7 datasets and Jupyter Notebooks discussed in this work are available at GitHub: https://github.com/azevedolab/docking#readme .