Time Series Segmentation for Gene Regulatory Process with Time-Window-Extension Technique

摘要：

Many important Biological processes fall into different successive phases with piecewise time varying structures. To reveal the sequential regulatory relationship between different phases, time series segmentation is the first step toward elucidations of the underlying structure of GRN dynamics. In this paper, we aim to propose a new approach to solve this segmentation problem, called Time-Window-Extension Technique. Combined with clustering techniques, e.g. NMF method, we can produce the biological meaningful segmentation from time series expression profile, or identify the change points of nonstationary time series. Artificial data sets are also adopted to validate its effectiveness.

关键词： time series cluster NMF segmentation correlation matrix

作者: Zhi-Yong Zhang Katsuhisa Horimoto Zengrong Liu

作者单位: Department of Mathematics, Shanghai University, Shanghai 200444, China Institute of systems biology, Nationai Institute of Advanced Industrial Science and Technology, Tokyo, Japan Institute of systems biology, Shanghai University, Shanghai 200444, China

会议类型: 国际会议

会议名称: The Second International Symposium(OSB08)(第二届国际优化及系统生物学学术会议)

会议地点: 云南丽江

会议语种:英文

页码: 198-203

在线出版日期: 2008-10-31（万方平台首次上网日期，不代表论文的发表时间）