Text-mining approach to evaluate terms for ontology development

Authors:
Lam C. Tsoi;Ravi Patel;Wenle Zhao;W. Jim Zheng
Affiliations:
Bioinformatics Graduate Program, Department of Biostatistics, Bioinformatics & Epidemiology, Medical University of South Carolina, 135 Cannon Street, Suite 303, Charleston, SC 29424, USA;Department of Biostatistics, Bioinformatics & Epidemiology, Medical University of South Carolina, Charleston, SC, 29464, USA;Department of Biostatistics, Bioinformatics & Epidemiology, Medical University of South Carolina, Charleston, SC, 29464, USA;Department of Biostatistics, Bioinformatics & Epidemiology, Medical University of South Carolina, Charleston, SC, 29464, USA
Venue:
Journal of Biomedical Informatics
Year:
2009

Citing 8
Cited 3

Principled disambiguation: discriminating adjective senses with modified nouns

Computational Linguistics
A fast string searching algorithm

Communications of the ACM
FatiGO: a web tool for finding significant associations of Gene Ontology terms with groups of genes

Bioinformatics
GO: :TermFinder---open source software for accessing Gene Ontology information and finding significantly enriched Gene Ontology terms associated with a list of genes

Bioinformatics
Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites

Computational Linguistics
Enrichment or depletion of a GO category within a class of genes: which test?

Bioinformatics
Brief communication: Retrieving definitional content for ontology development

Computational Biology and Chemistry
Text2Onto: a framework for ontology learning and data-driven change discovery

NLDB'05 Proceedings of the 10th international conference on Natural Language Processing and Information Systems

Guest Editorial: Current issues in biomedical text mining and natural language processing

Journal of Biomedical Informatics
A clustering study of a 7000 EU document inventory using MDS and SOM

Expert Systems with Applications: An International Journal
Extracting significant Website Key Objects: A Semantic Web mining approach

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Developing ontologies to account for the complexity of biological systems requires the time intensive collaboration of many participants with expertise in various fields. While each participant may contribute to construct a list of terms for ontology development, no objective methods have been developed to evaluate how relevant each of these terms is to the intended domain. We have developed a computational method based on a hypergeometric enrichment test to evaluate the relevance of such terms to the intended domain. The proposed method uses the PubMed literature database to evaluate whether each potential term for ontology development is overrepresented in the abstracts that discuss the particular domain. This evaluation provides an objective approach to assess terms and prioritize them for ontology development.