An algorithm for computing the semantic similarity among terminologies in gene ontology

The computation of semantic similarity of terminologies in gene ontology is an important application of gene ontology. Moreover, it is an important approach for biologists to deal with the semantic heterogeneity of biological data sets. Existing approaches in this field are based on semantic distance or information quantity. The author proposes a comprehensive approach where the similarity is first computed on the terminological level, inducing density-constraining and depth-constraining variables based on the microscopic structure (density and depth of the nodes) of the gene ontology nodes, then based on node properties and inference-based instances, the comprehensive semantic similarity is computed. From the result of comparison with the Resnik method, the ZZL method, Lin method and Combine method, the above proposed method proves to be favorable.