BayesSuites: An Open Web Framework for Visualization of Massive Bayesian Networks
Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:593-596, 2020.
BayesSuites is the first web framework for learning, visualizing, and interpreting Bayesian networks that can scale to tens of thousands of nodes while providing fast and friendly user experience. BayesSuites solves the problems of scalability, extensibility and interpretability that massive networks bring by separating backend calculations from the frontend interface and using specialized learning algorithms for massive networks. We demonstrate the tool by learning and visualizing a genome-wide gene regulatory network from human brain data with 20,708 nodes.