Learning patterns in the dynamics of biological networks

摘要: Our dynamic graph-based relational mining approach has been developed to learn structural patterns in biological networks as they change over time. The analysis of is important not only understand life at the system-level, but also discover novel other data. Most current data approaches overlook features networks, because are focused on static graphs. analyzes a sequence graphs and discovers rules that capture changes occur between pairs sequence. These represent graph rewrite first must go through be isomorphic second graph. Then, our feeds into machine learning system learns general transformation describing types for class networks. discovered graph-rewriting show how time, repeated changes. In this paper, we apply evaluate biosystems We results using coverage prediction metrics, compare literature.