Using emerging subsequence in classifying protein structural class

Authors:
Khalid E. K. Saeed;Heon Gyu Lee;Wun-Jae Kim;Eun-Jong Cha;Keun Ho Ryu
Affiliations:
Database/Bioinformatics Laboratory, Chungbuk National University, Cheongju, Korea;Postal Technology Research Center, Electronics & Telecommunication Research Institute, Deleon, Korea;Department of Urology, Chungbuk National University Hospital, Cheongju, Korea;Department of Biomedical Engineering, School of Medicine, Chungbuk National University, Cheongju, Korea;Database/Bioinformatics Laboratory, Chungbuk National University, Cheongju, Korea
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1
Year:
2009

Citing 6
Cited 0

Efficient mining of emerging patterns: discovering trends and differences

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining Emerging Substrings

DASFAA '03 Proceedings of the Eighth International Conference on Database Systems for Advanced Applications
Multiclass Classification with Multi-Prototype Support Vector Machines

The Journal of Machine Learning Research
The Improvement of Naïve Bayesian Classifier Based on the Strategy of Fuzzy Feature Selection

ISDA '06 Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications - Volume 01
Improved use of continuous attributes in C4.5

Journal of Artificial Intelligence Research
Predicting protein structural class from closed protein sequences

PAKDD'03 Proceedings of the 7th Pacific-Asia conference on Advances in knowledge discovery and data mining

Quantified Score

Hi-index	0.01

Visualization

Abstract

Knowledge about protein's structure can help in understanding its function and has many applications in computer-aided drug design and protein engineering. In this paper we introduce a new methodology for predicting protein structural class using Emerging Subsequences (ES). In a sequence database, an emerging subsequence of data class is a subsequence which occurs more frequently in that class rather than other classes. They can capture significant contrast between data classes. Our idea is to discover all the ES from protein sequence database and use as representatives for this data. Our experimental results using CATH database shows good result when evaluating the accuracy of the proposed method.