Groupwise semantic similarity measures

This page introduces the collection of groupwise semantic similarity measures which are implemented by the latest HESML version (V1R5). First column sets the corresponding GroupwiseSimilarityMeasureType (enum) code to instance the measure in HESML by calling the function MeasureFactory.getGroupwiseNoParameterMeasure() or MeasureFactory.getGroupwiseBasedOnPairwiseMeasure().

A groupwise semantic similarity measure is used to compute the degree of similarity between two sets of concepts defined into an ontology. This type of measure is commonly used to compare sets of GO terms in genomics, although they could also be used to compare sets of WordNet synsets evoked by two words. Before HESML V1R5 version, all WordNet-based similarity measures have been defined as the highest similarity score between the sets of WordNet synsets (concepts) evoked by two words; however, since HESML V1R5 it is possible to use different groupwise metrics and the BasedOnPairwiseMeasure groupwise similarity measures as detailed in table below. Table below shows the groupwise measures which are currently implemented in the latest version of HESML.

SimilarityMeasureType enum Reference
BasedOnPairwiseMeasure This groupwise measure is defined as the maximum [1, eq. 2], average [2, eq. 1] or Best-Match-Average (BMA) [2, eq. 2] of the pairwise similarity values evaluated with any pairwise semantic similarity measure implemented by HESML.
[1] J.L. Sevilla, V. Segura, A. Podhorski, E. Guruceaga, J.M. Mato, L.A. Martínez-Cruz, F.J. Corrales, A. Rubio, Correlation between gene expression and GO semantic similarity, IEEE/ACM Trans. Comput. Biol. Bioinform. 2 (2005) 330–338. [2] F. Azuaje, H. Wang, O. Bodenreider, Ontology-driven similarity approaches to supporting gene functional assessment, in: Proceedings of the ISMB’2005 SIG Meeting on Bio-Ontologies, academia.edu, 2005: pp. 9–10.
SimGIC C. Pesquita, D. Faria, H. Bastos, A. Falcão, F. Couto, Evaluating GO-based semantic similarity measures, in: Proc. 10th Annual Bio-Ontologies Meeting, 2007: p. 38.
SimUI R. Gentleman, Visualizing and distances using GO, URL http://www.Bioconductor.org/docs/vignettes.html 38 (2005). http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.592.2206&rep=rep1&type=pdf
SimLP R. Gentleman, Visualizing and distances using GO, URL http://www.Bioconductor.org/docs/vignettes.html 38 (2005). http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.592.2206&rep=rep1&type=pdf

Contact Us

UNED - Universidad Nacional de Educación a Distancia - ETSI Informática
Juan del Rosal, 16
28040 Madrid, Spain