The use of polymers, both synthetic and natural, is ubiquitous and they are found in virtually any aspect of modern life, including e.g. engineering composites, medical devices, packaging, and electronics. Several topologies can derive from the different types of connectivities and 3D positioning of all the bonds inside polymers, which are the base to predict the polymer macroscopic properties. A particularly complex case are the network/crosslinked polymers which have applications such as hygiene products, tissue engineering scaffolds, and drug delivery devices. They can be obtained using chain-growth synthesis and a large number of side reactions can be encountered, as well as a more complex reactant structure involving a plethora of functional groups. A major example for polymer networks and drug delivery systems are the ones using hydrogels, which showcase a combination of both chemical and physical interactions. Modeling the formation of these systems lead to precise material design, but has the main drawback of a complicated set of chemical reactions that must be characterized, in addition to long simulation time. To tackle these, in this project we propose to (i) expand the capabilities of our stochastic algorithms applied to polymer networks reactions and interactions, (ii) gather information from polymer networks through machine learning as a predictive tool for microscopic properties and (iii) upgrade the 3D visualization toolbox for this system.