首页> 外文会议>2008高等智能国际会议(2008 International Conference on Advanced Intelligence)论文集 >A MST based Uncertain-Partitioning Clustering Algorithm for Gene Expression Data
【24h】

A MST based Uncertain-Partitioning Clustering Algorithm for Gene Expression Data

机译:基于MST的基因表达数据不确定分区聚类算法

获取原文

摘要

The emerging microarray technology allows scientists simultaneous monitoring of the expression levels of a large number of genes over different time points. Clustering is an important tool for analyzing such microarray data, typical properties of which are its inherent uncertainty, noise and imprecision. In this paper, we propose a MST-based Uncertain-Partitioning (MUP) clustering algorithm, which is a fusion of partition-based clustering and hierarchical clustering in nature. The algorithm identifies iteratively a set of potential inconsistent edges at a time using sliding window approach. By minimizing an objective function of cluster quality, we determine the real inconsistent edges from the potential inconsistent edges, then cut them to form sub clusters. The results of experiments on two real gene expression data sets verify the effectiveness and efficiency of proposed method.
机译:新兴的微阵列技术使科学家可以同时监控不同时间点上大量基因的表达水平。聚类是分析此类微阵列数据的重要工具,其典型特性是其固有的不确定性,噪声和不精确性。在本文中,我们提出了一种基于MST的不确定分区(MUP)聚类算法,该算法本质上是基于分区的聚类和分层聚类的融合。该算法使用滑动窗口方法一次一次地识别出一组潜在的不一致边缘。通过最小化群集质量的目标函数,我们从潜在的不一致边缘中确定了实际不一致的边缘,然后将其裁剪以形成子群集。在两个真实基因表达数据集上的实验结果证明了该方法的有效性和效率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号