Abstract—In recent years, the number of articles that describe protein structure and function is increasing. Since the articles are written using polysemic and complex terminologies, however, such naive retrieval methods as full text search often fail to find appropriate articles. We propose a new method in which the structural and functional concepts of proteins are considered using Gene Ontology (GO) and other databases. In our proposed method, articles of interest are submitted as queries to solve the problem caused by the ambiguity of the terminologies, and then articles similar to the query article are retrieved. In addition, giving another article as an additional query article clarifies the user intention and improves retrieval accuracy. The effectiveness of our proposed method was confirmed by evaluating its accuracy through retrieval experiments, especially for retrieving new articles.

Index Terms—Article retrieval, ontology, similarity between articles, user intention.

The authors are with the Graduate School of System Informatics, Kobe University, Kobe, Japan (e-mail: t-aso@cs25.scitec.kobe-u.ac.jp, ohkawa@kobe-u.ac.jp).

 

Cite:T. Aso and T. Ohkawa, "Method of Retrieving Articles on Protein Structure Analysis from User Intention," International Journal of Bioscience, Biochemistry and Bioinformatics vol. 3, no. 3, pp. 182-186, 2013.