Classification of nuclear receptor subfamilies with RBF kernel in support vector machine

Authors:
Jun Cai;Yanda Li
Affiliations:
Institute of Bioinformatics, Tsinghua University, Beijing, China;Institute of Bioinformatics, Tsinghua University, Beijing, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Year:
2005

Citing 2
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
No Unbiased Estimator of the Variance of K-Fold Cross-Validation

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nuclear receptors (NRs) are ligand-inducible transcription factors that regulate diverse functions as a superfamily of crucial medical significance. Because of their involvement in many physiological and pathological processes, the development of methods to infer the different NR subfamilies has become an important goal in biomedical research. In this paper we introduce a sequence-based computational approach-Support Vector Machine to classify the 19 subfamilies of NRs. We use 4-tuple residue composition instead of dipeptide composition to encode the NR sequences. The overall predictive accuracy about 96% has been achieved in a five fold cross-validation.