Permutation-validated principal components analysis of microarray data 英文参考文献.docVIP

/2002/3/4/research/0019.1 Research Permutation-validated principal components analysis of microarray data Jobst Landgrebe*, Wolfgang Wurst*? and Gerhard Welzl? Addresses: *Max Planck Institute of Psychiatry, Molecular Neurogenetics, Kraepelinstrasse 2-10, 80804 Munich, Germany. ?Institute of Mammalian Genetics and ?Institute of Biomathematics and Biometry, GS0-National Research Center for Environment and Health, Ingolst?dter Landstrasse 1, D-85764 Neuherberg, Germany. Correspondence: Gerhard Welzl. E-mail: welzl@gsf.de Published: 22 March 2002 Received: 12 December 2001 Revised: 31 January 2002 Accepted: 15 February 2002 GenomeBiology 2002, 3(4):research0019.1–0019.11 The electronic version of this article is the complete one and can be found online at /2002/3/4/research/0019 ? 2002 Landgrebe et al., licensee BioMed Central Ltd (Print ISSN 1465-6906; Online ISSN 1465-6914) Abstract Background: In microarray data analysis, the comparison of gene-expression profiles with respect to different conditions and the selection of biologically interesting genes are crucial tasks. Multivariate statistical methods have been applied to analyze these large datasets. Less work has been published concerning the assessment of the reliability of gene-selection procedures. Here we describe a method to assess reliability in multivariate microarray data analysis using permutation-validated principal components analysis (PCA). The approach is designed for microarray data with a group structure. Results: We used PCA to detect the major sources of variance underlying the hybridization conditions followed by gene selection based on PCA-derived and permutation-based test statistics. We validated our method by applying it to well characterized yeast cell-cycle data and to two datasets from our laboratory. We could describe the major sources of variance, select informative genes and vi