Nuclear Receptor Sequence Visualization and Subfamily Classification
Nuclear receptors (NRs) are one of the most abundant classes of transcriptional regulators in animals (metazoans). However, it is both time-consuming and costly to determining their structural and functional information. In this study, we present a novel method to visualizing the NR sequences and a predictor called NRSP-CA to predict the functional subfamily type, where CA stands for Cellular Automaton, meaning that the CA images (CAI) have been utilized to reveal the pattern features hidden in piles of long and complicated protein sequences. Meanwhile, the geometric moments extracted from the CAI are used to represent the samples of proteins through their pseudo amino acid composition. The classification was achieved on the basis of Fuzzy K nearest neighbor (FKNN) classifier. The overall predictive accuracy about 72％ and 91％ have been achieved through the rigorous jackknife cross-validation and independent test on a nuclear receptor benchmark dataset with low redundancy derived from the NucleaRDB. This indicates that our method can be a useful associated tool for subfamily recognition of NRs.
Cellular automaton image Geometric moment sequence visualization Nuclear receptor Fuzzy K nearest neighbor algorithm
Pu Wang Xuan Xiao
School of Mechanical & Electronic Engineering Jing-De-Zhen Ceramic Institute Jing-De-Zhen, China
国际会议
2010 International Conference on Future Information Technology(2010年未来信息技术国际会议 ICFIT 2010)
长沙
英文
566-570
2010-12-14（万方平台首次上网日期，不代表论文的发表时间）