We developed a new methodology SegMine for semantic analysis of microarray data by exploiting general biological knowledge, and a new workflow environment Orange4WS which supports web service integration. The SegMine methodology consists of two main steps. First, a semantic subgroup discovery algorithm is used to construct semantically annotated rules that identify enriched gene sets. Then, link discovery service BioMine is used for the creation and visualization of new biological hypotheses. The utility of SegMine, implemented as a set of workflows in Orange4WS, is demonstrated in two microarray data analysis applications.
COBISS.SI-ID: 25208871