Bootstrapping cluster analysis: Assessing the reliability of conclusions from microarray experiments

Citation
Mk. Kerr et Ga. Churchill, Bootstrapping cluster analysis: Assessing the reliability of conclusions from microarray experiments, P NAS US, 98(16), 2001, pp. 8961-8965
Citations number
17
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Multidisciplinary
Journal title
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
ISSN journal
0027-8424 → ACNP
Volume
98
Issue
16
Year of publication
2001
Pages
8961 - 8965
Database
ISI
SICI code
0027-8424(20010731)98:16<8961:BCAATR>2.0.ZU;2-0
Abstract
We introduce a general technique for making statistical inference from clus tering tools applied to gene expression microarray data. The approach utili zes an analysis of variance model to achieve normalization and estimate dif ferential expression of genes across multiple conditions. Statistical infer ence is based on the application of a randomization technique, bootstrappin g. Bootstrapping has previously been used to obtain confidence intervals fo r estimates of differential expression for individual genes. Here we apply bootstrapping to assess the stability of results from a cluster analysis. W e illustrate the technique with a publicly available data set and draw conc lusions about the reliability of clustering results in light of variation i n the data. The bootstrapping procedure relies on experimental replication. We discuss the implications of replication and good design in microarray e xperiments.