Protein interaction detection in sentences via gaussian processes: a preliminary evaluation

Polajnar, T., Rogers, S. and Girolami, M. (2011) Protein interaction detection in sentences via gaussian processes: a preliminary evaluation. International Journal of Data Mining and Bioinformatics, 5(1), pp. 52-72. (doi:10.1504/IJDMB.2011.038577)

Full text not currently available from Enlighten.


Classification methods are vital for efficient access of knowledge hidden in biomedical publications. Support vector machines (SVMs) are modern non-parametric deterministic classifiers that produce state of the art performances in text mining, and across other disciplines, while reducing the need for feature engineering. In this paper we offer a much needed evaluation of the Gaussian Process (GP) classifier, as a non-parametric probabilistic analogue to SVMs, which has been rarely applied to text classification. To this end, we provide an extensive experimental comparison of the performance and properties of these competing classifiers on the challenging problem of protein interaction detection in biomedical publications. Our results show that GPs can match the performance of SVMs without the need for costly margin parameter tuning, whilst offering the advantage of an extendable probabilistic framework for text classification.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Rogers, Dr Simon and Polajnar, Miss Tamara and Girolami, Prof Mark
Authors: Polajnar, T., Rogers, S., and Girolami, M.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science
Journal Name:International Journal of Data Mining and Bioinformatics

University Staff: Request a correction | Enlighten Editors: Update this record