Evaluating the contributions of GO term properties to semantic similarity measurement
by Jan Sladek; Young-Rae Cho
International Journal of Data Mining and Bioinformatics (IJDMB), Vol. 18, No. 3, 2017

Abstract: Recent systematic approaches for semantic analysis and annotations in bio-ontology databases have advanced understanding of molecular functions in a genomic scale. Over the last decade, various semantic similarity measures have been proposed to quantify functional similarity between genes using Gene Ontology (GO) and its annotations. However, major challenges in these applications are the increasing complexity of ontology structures and the inconsistency of annotation data. In this study, we explore term properties in GO, such as term specificity and the term balancing effect, and evaluate the contributions of these properties to semantic similarity measurement. Our experiment is designed to predict positive protein-protein interactions (PPIs) by semantic similarities to which these term properties are applied. The experimental results show prediction accuracy improved when GO terms are weighted by term specificity. The experimental results also show balancing terms with respect to their specificity are significant factor in measuring semantic similarity between proteins.

Online publication date: Fri, 06-Oct-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Data Mining and Bioinformatics (IJDMB):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com