This project aims at exploring the applicability of the Convolutional Neural Networks (CNN) for solving the Protein-Protein Docking Problem. Starting from fitting the Protein representations to the Convolutional Network’s requirements, the project will aim at building training and validation datasets that will be used by the CNN architecture. Using the datasets generated, different CNN architectures will be considered, trained and evaluated, estimating the feasibility of using these deep learning models to solve the Protein docking problem.