改进的时序基因表达数据动态聚类算法

Improved dynamic model-based clustering for time-course gene expression data

文[1]采用了一种基于动态模型的聚类算法,将时序基因表达数据作为一组时间序列进行动态的聚类分析,得到了较为理想的聚类结果。对上述算法在数据初始化方面进行了合理改进,并利用贝叶斯理论对数据的联合概率分布进行了重新分析。实验表明,提出的改进算法所得聚类结果明显优于原算法所得结果。

This paper refers to a dynamic model-based clustering algorithm in ,which can analyze a time-course gene expres- sion data as a set of time series dynamlcally,such that better clustering results can be produced.Some reasonable improvements are used in the initialization hereinafter.And the joint probability distribution for the time-course gene expression dataset is also reanalyzed using Bayes theory.Experimented results demonstrate that the results obtained by the improved clustering algorithm are better than those obtained by the dynamic model-based clustering algorithm.