Abstract
Batch effects will influence the interpretation of metabolomics data. In order to avoid misleading results, batch effects should be corrected and normalized prior to statistical analysis. Metabolomics studies are usually performed without targeted compounds (e.g., internal standards) and it is a challenging task to validate batch effects correction methods. In addition, statistical properties of metabolomics data are quite different from genomics data (where most of the currently used batch correction methods have originated from). In this study, we firstly analyzed already published metabolomics datasets so as to summarize and discuss their statistical properties. Then, based on available datasets, we developed novel statistical properties-based in silico simulations of metabolomics peaks’ intensity data so as to analyze the influence of batch effects on metabolomic data with the use of currently available batch correction strategies. Overall, 252000 batch corrections on 14000 different in silico simulated datasets and related differential analyses were performed in order to evaluate and validate various batch correction methods. The obtained results indicate that log transformations strongly influence the performance of all investigated batch correction methods. False positive rates increased after application of batch correction methods with almost no improvement on true positive rates among the analyzed batch correction methods. Hence, in metabolomic studies it is recommended to implement preliminary experiments to simulate batch effects from real data in order to select adequate batch correction method, based on a given distribution of peaks intensity. The presented study is reproducible and related R package mzrtsim software can be found online (https://github.com/yufree/mzrtsim).