OnSim: A Similarity Measure for Determining Relatedness Between Ontology Terms

Abstract

Accurately measuring relatedness between ontology terms becomes a building block for determining similarity of ontology-based annotated entities, e.g., genes annotated with the Gene Ontology. However, existing measures that determine similarity between ontology terms mainly rely on taxonomic hierarchies of classes, and may not fully exploit the semantics encoded in the ontology, i.e., object properties and their axioms. This limitation may conduct to ignore the stated or inferred facts where an ontology term participate in the ontology, i.e., the term neighborhood. Thus, high values of similarity can be erroneously assigned to terms that are taxonomically similar, but whose neighborhoods are different. We present OnSim, a measure where semantics encoded in the ontology is considered as a first-class citizen and exploited to determine relatedness of ontology terms. OnSim considers the neighborhoods of two terms, as well as the object properties that are present in the neighborhood facts and the justifications that support the entailment of these facts. We have extended an existing annotation-based similarity measure with OnSim, and empirically studied the impact of producing accurate values of ontology term relatedness. Experiments were run on benchmarks published by the Collaborative Evaluation of Semantic Similarity Measures (CESSM) tool. The observed results suggest that OnSim increases the Pearson’s correlation coefficient of the annotation-based similarity measure with respect to gold standard similarity measures, as well as its effectiveness is improved with respect to state-of-the-art semantic similarity measures.