Merging artificial intelligence and computational systems biology has the potential to address complex systems with a holistic view. This integration allows us to build robust regression models to predict enzyme inhibition using data obtained from docking simulations. This work adopts a hands-on approach to generate regression models to predict the inhibition of cyclin-dependent kinase 2. This protein is an anticancer drug target, and we have data for crystallographic structures and inhibition of this enzyme. We employed the Extremely Randomized Trees method implemented in the program SAnDReS 2.0 to predict CDK2 inhibition. Our regression models employ docking results obtained using protein-ligand docking programs Molegro Virtual Docker and AutoDock Vina 1.2. Our Extra Trees regression models showed superior performance compared with other machine learning techniques. All CDK2 datasets and a Jupyter Notebook with SKReg4Model discussed in this work are available at GitHub: https://github.com/azevedolab/docking#readme . We made the source code of the program SAnDReS 2.0 available at https://github.com/azevedolab/sandres .