Abstract—When we used DNA sequences of Saccharomyces cerevisiae whose nucleosome positioning data have been experimentally determined to train a Support Vector Machine (SVM) to predict the nucleosome formation potential of any given sequence of DNA, we observed that chromatin structure has an impact on the evolution of genomic DNA molecules. We have found, on average, 15% lower predictive accuracy rates in nucleosomal DNA than in linker DNA. This widespread local rates heterogeneity represents an evolutionary footprint of nucleosome positions and reveals that nucleosome organization is a genomic feature conserved over evolutionary timescales.

Index Terms—Evolutionary footprints, nucleosome, predictive accuracy rates, transcriptional start sit (TSS).

The authors are with Yunnan University of Nationalities, China (e-mail: fengjihua@21cn.com, 275939685@qq.com).

 

Cite:Jihua Feng, Jianping Xiao, Ying Lu, and Qiufu Shan, "Prediction of Nucleosome Positioning Based on Support Vector Machine," International Journal of Bioscience, Biochemistry and Bioinformatics vol. 3, no. 5, pp. 449-451, 2013.