Computational and statistical analysis of metabolomics data

Abstract

Metabolomics is the comprehensive study of small molecule metabolites in biological systems. By assaying and analyzing thousands of metabolites in biological samples, it provides a whole picture of metabolic status and biochemical events happening within an organism and has become an increasingly powerful tool in the disease research. In metabolomics, it is common to deal with large amounts of data generated by nuclear magnetic resonance (NMR) and/or mass spectrometry (MS). Moreover, based on different goals and designs of studies, it may be necessary to use a variety of data analysis methods or a combination of them in order to obtain an accurate and comprehensive result. In this review, we intend to provide an overview of computational and statistical methods that are commonly applied to analyze metabolomics data. The review is divided into five sections. The first two sections will introduce the background and the databases and resources available for metabolomics research. The third section will briefly describe the principles of the two main experimental methods that produce metabolomics data: MS and NMR, followed by the fourth section that describes the preprocessing of the data from these two approaches. In the fifth and the most important section, we will review four main types of analysis that can be performed on metabolomics data with examples in metabolomics. These are unsupervised learning methods, supervised learning methods, pathway analysis methods and analysis of time course metabolomics data. We conclude by providing a table summarizing the principles and tools that we discussed in this review.

Normalization and integration of large-scale metabolomics data using support vector regression

“…SVR maintains all of the main features that characterize the maximal margin algorithm in SVM, and has a non-linear kernel function for margin optimization and maximization (Steinwart and Christmann 2008;Brereton and Lloyd 2010;Ren et al 2015). SVM method uses supervised learning models for classification, however, it is usually called as SVR when it is used for regression analysis.…”

“…To get the minimum structure risk function which is fitted data well, so we must minimize 1 2 jjwjj 2 þ C P P i¼1 ðn i þ n à i Þ under the prerequisites that all the data points in training dataset (i.e., peaks in QC sample dataset) are in the defined region. An in-depth theoretical background about SVR can be found in the literature (Steinwart and Christmann 2008;Brereton and Lloyd 2010;Ren et al 2015).…”

“…In this work, we introduce one of the most widely used machine learning methods, support vector regression (SVR), for the purpose of data regression in metabolomics (Brereton and Lloyd 2010;Ren et al 2015). SVR maintains all of the main features that characterize the maximal margin algorithm in the support vector machine (SVM) algorithm (Cortes and Vapnik 1995), and a non-linear kernel function (e.g., radial basis function) is used for margin optimization and maximization (Steinwart and Christmann 2008).…”

“…In SVM, dependent variables are discrete and the goal is to find the hyperplane which can separate observations into different classes. But in SVR, dependent variables are continuous and the hyperplane is used to predict the distribution of observations (Steinwart and Christmann 2008;Brereton and Lloyd 2010;Ren et al 2015). Therefore, SVR normalization can accurately fit non-linear signal drift, is not susceptible to the presence of outliers, and thus has excellent generation capability for prediction when compared with linear and LOESS-based normalizations.…”

High-resolution characterization of the human microbiome

“…Accordingly, in contrast to metatranscriptomics and metaproteomics, the processing and analysis of community-wide metabolomic data can rely on standard approaches for single-organism metabolomics with essentially no modifications. For untargeted mass spectrometry metabolomics, these analyses typically involve normalization and putative identification of metabolites by searching either for matches in a spectral library or for known compounds with matching mass and chromatographic elution profiles 165 . The greater challenge, however, lies in the interpretation of these datasets, and in linking the observed variation in biomolecule abundances with other data on community structure and function.…”