clustering gene expression patterns（聚类的基因表达模式）.pdfVIP

Clustering Gene Expression Patterns y z Amir BenDor Ron Shamir Zohar Yakhini July Abstract Recent advances in biotechnology allow researchers to measure expression levels for thousands of genes simultaneously across dierent conditions and over time Analysis of data pro duced by such exp eriments oers p otential insight into gene function and regulatory mechanisms A key step in the analysis of gene expression data is the detection of groups of genes that manifest similar expression patterns The corresp onding algorithmic problem is to cluster multicondition gene expression patterns In this pap er we describ e a novel clustering algorithm that was develop ed for analysis of gene ex pression data We dene an appropriate sto chastic error mo del on the input and prove that under the conditions of the mo del the algorithm recovers the cluster structure with high probability The running time of the algorithm on an ngene dataset is O n 2 logn c We also present a practical heuristic based on the same algorithmic ideas The heuristic was implemented and its p erformance is demonstrated on simulated data and on real gene expression data with very promising results Intro duction In any living cell that undergo es a biological pro cess dierent subsets of its genes are expressed in dierent stages of the pro cess The particular genes expressed at a given stage and their relative abundance are crucial to the cells prop er function Measuring gene expression levels in dierent developmental stages dierent b o dy tissues dierent clinical conditions and dierent organisms