Statistical validation of megavariate effects in ASCA

A permutation approach is used to validate megavariate effects observed with ASCA. By permuting the class labels of the underlying experimental design, a distribution of no-effect is calculated. If the observed effect is clearly different from this distribution the effect is deemed significantThe permutation approach is studied using simulated data which gave successful results. It was then used on real-life metabolomics data set dealing with bromobenzene-dosed rats. In this metabolomics experiment the dosage and time-interaction effect were validated, both effects are significant. Histological screening of the treated rats' liver agrees with this finding.The suggested procedure gives approximate p-values for testing effects underlying metabolomics data sets. Therefore, performing model validation is possible using the proposed procedure.In life science research many measuring tools emerged in recent years. These tools give a coarse profile of biological classes such a transcripts (transcriptomics), proteins (proteomics) and metabolites (metabolomics). This paper focuses on the field of metabolomics; the comprehensive quantitative and qualitative analysis of all small molecules of cells, body fluids, and tissues. The mix of hypothesis and discovery driven omics-experiments create novel biostatistical challenges noted since combining pattern recognition and body fluid profiling in the early eighties [1]. Interpreting the multivariate metabolomics results means integrating biological knowledge with possible contributing metabolites.Metabolomics data sets comprise hundreds of metabolites measured in typically tenths of samples. Multivariate statistics on data that have fewer samples than metabolites is cumbersome. Usually there is an experimental design underlying the metabolomics data sets. The obvious technique for analyzing such data, Multivariate Analysis of Variance (MANOVA) [2] cannot deal with data that consists of more metabolites than samples.The recent introd