Aligning large biomedical ontologies for semantic interoperability using graph partitioning

Abstract

Ontologies formal specifications of domain knowledge play an imperative role in the semantic web and are developed by several domain experts in the biomedical field. Ontology alignment or mapping is the process of identifying correspondences among the concepts in the ontology to facilitate data integration between heterogeneous data sources. In particular, the proposed ontology mapping system addresses two pivotal issues: 1) to facilitate the automated alignment process by incorporating random forests (RF), an ensemble learning system that is stable for outliers; 2) to improve the execution time by partitioning the ontologies using cluster-walktrap methodology and identify the correspondence between the concepts in parallel. The performance of the system is pragmatically evaluated on benchmark datasets in the anatomy and large biomedical ontology tracks of the OAEI 2013 and 2014. With the aid of the proposed system, quantifiable improvement is noticed to an extent of 4.4% in average precision, recall and F-measure.