Meta-analysis of untargeted metabolomic data from multiple profiling experiments

Abstract

metaXCMS is a software program for the analysis of liquid chromatography/mass spectrometry-based untargeted metabolomic data. It is designed to identify the differences between metabolic profiles across multiple sample groups (e.g., 'healthy' versus 'active disease' versus 'inactive disease'). Although performing pairwise comparisons alone can provide physiologically relevant data, these experiments often result in hundreds of differences, and comparison with additional biologically meaningful sample groups can allow for substantial data reduction. By performing second-order (meta-) analysis, metaXCMS facilitates the prioritization of interesting metabolite features from large untargeted metabolomic data sets before the rate-limiting step of structural identification. Here we provide a detailed step-by-step protocol for going from raw mass spectrometry data to metaXCMS results, visualized as Venn diagrams and exported Microsoft Excel spreadsheets. There is no upper limit to the number of sample groups or individual samples that can be compared with the software, and data from most commercial mass spectrometers are supported. The speed of the analysis depends on computational resources and data volume, but will generally be less than 1 d for most users. metaXCMS is freely available at http://metlin.scripps.edu/metaxcms/.

Figure 1

Introduction of pairwise and second-order comparison. XCMS performs a pairwise comparison of two sample groups with any number of biological replicates. Data from multiple pairwise comparisons is then used by metaXCMS to perform a second-order comparison in which shared and unique differences are identified.

Figure 2

Data reduction by meta-analysis. Three pairwise comparisons of different pain models to their respective controls resulted in 22,577 detected metabolite features (model A is animals plantar injected with Complete Freund’s Adjuvant, model B is animals treated with noxious heat, and model C is animals intraperitoneally injected with serum from K/BxN mice, for further details see Tautenhahn et al.). Next, features with fold changes less than 1.5 and p-values greater than 0.05 were filtered and the remaining 1,825 features were plotted. A second-order comparison by metaXCMS showed that only 3 of these features were commonly shared, one of which was determined to be histamine.

Figure 3

Visualization of theoretical meta-analysis applied to identify biomarkers of disease severity. The left Venn diagram shows shared and unique metabolite features for mild disease, severe disease, and healthy patients. While features in the areas labeled a, b, and c may serve as biomarkers, areas a and c could provide additional markers specific to mild and severe disease respectively. The right Venn diagram shows a second-order visualization of the same comparison that is representative of metaXCMS output when the parameters are set to plot only metabolite features that are unique to disease (i.e., features that are detected in disease but not in healthy samples). The advantage of the second-order visualization is that it is not limited to representing only metabolites unique to a certain sample group. Rather, metabolites that are up- and down-regulated by even small fold changes can be easily represented according to user-defined thresholds. Given that biomarkers may not be metabolites unique to disease samples but instead metabolites that increase by some quantified fold change, second-order visualizations are generally better suited for metabolomic data since they can be used to show up- and down-regulated features (see Venn diagram in Figure 2). Changing the second-order visualization here to include features with smaller fold changes, for example, would result in the display of more features that might represent useful diagnostic markers.

Figure 4

Overview of the computational workflow. The workflow consists of five stages: acquisition of LC/MS data, conversion of the data to .mzXML files, analysis of the files by XCMS, analysis of XCMS results by metaXCMS, and result browsing and interpretation.

Figure 5

MSConvertGUI.exe, the graphical user interface of the ProteoWizard file converter. The input fields or icons of the software that correspond to specific steps in the protocol are indicated by the step number.

Figure 6

Retention-time correction curves generated by XCMS. Each colored line represents a different sample processed. Note that the retention-time deviation is different for each sample and that it is not linear.

Figure 7

Graphical user interface of metaXCMS. The input fields or icons related to the import of XCMS diffreports are indicated by arrows that are numbered according to the protocol step in which they are described.

Figure 8

Graphical user interface of metaXCMS. Filtering may be performed on the basis of p-value, fold change, and up-/down-regulation. The input fields or icons related to filtering are indicated by arrows that are numbered according to the protocol step in which they are described.

Figure 9

Graphical user interface of metaXCMS. Features that are uniquely or commonly altered among the pairwise comparisons are displayed as Venn diagrams. The icons related to data visualization and export are indicated by arrows that are numbered according to the protocol step in which they are described.

Figure 10

Graphical user interface of metaXCMS. Retention-time correction for all samples compared is displayed and EICs are generated. The icons related to retention-time correction and EIC generation are indicated by arrows that are numbered according to the protocol step in which they are described.