Semantic Graph Mining for e-Science

In this paper, we present a methodology, called Seman-tic Graph Mining, for computer-aided extraction of action-able rules from consolidated semantic graphs of statements. First, generate semantic annotations of a set of heterogeneous knowledge/information resources in terms of domain ontol-ogy. Second, merge a semantic graph by means of semantic integration of the annotated resources. Third, discover and recognize patterns from the graph. Fourth, generate and eval-uate a set of candidate rules, which are organized and indexed for interactive discovery of actionable rules. As initial imple-mentation efforts of the methodology, a generic architecture of specialized knowledge discovery services is proposed, and an application in biomedicine is initiated