Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Wissensmanagement in der Bioinformatik

Systematic Feature Evaluation for Gene Name Recognition

Systematic Feature Evaluation for Gene Name Recognition

Jörg Hakenberg1*, Steffen Bickel2, Conrad Plake1, Ulf Brefeld2, Hagen Zahn2, Lukas Faulstich1, Ulf Leser1, and Tobias Scheffer2

1 Humboldt-Universität zu Berlin, Department of Computer Science, Knowledge Management in Bioinformatics
2 Humboldt-Universität zu Berlin, Department of Computer Science, Knowledge Management Group
* Corresponding author. Current affiliation: Knowledge Management in Bioinformatics, Dept. Computer Science, Humboldt-Universität zu Berlin, Rudower Chaussee 25, 12489 Berlin, Germany. Phone: +49.30.2093.3903, eMail: hakenberg(a)informatik.hu-berlin.de


Abstract

In task 1A of the BioCreAtIvE evaluation, systems had to be devised that recognize words and phrases forming gene or protein names in natural language sentences. We approach this problem by building a word classification system based on a sliding window approach with a Support Vector Machine, combined with a pattern-based post-processing for the recognition of phrases. The performance of such a system crucially depends on the type of features chosen for consideration by the classification method, such as pre- or postfixes, character n-grams, patterns of capitalization, or classification of preceding or following words. We present a systematic approach to evaluate the performance of different feature sets based on recursive feature elimination, RFE. Based on a systematic reduction of the number of features used by the system, we can quantify the impact of different feature sets on the results of the word classification problem. This helps us to identify descriptive features, to learn about the structure of the problem, and to design systems that are faster and easier to understand. We observe that the SVM is robust to redundant features. RFE improves the performance by 0.7%, compared to using the complete set of attributes. Moreover, a performance that is only 2.3% below this maximum can be obtained using fewer than 5% of the features.


Published in
BMC Bioinformatics, 6(Suppl 1):S9, 2005
[BMC Bioinformatics] [Full text]