Regularized MANOVA (rMANOVA) in untargeted metabolomics

Engel, Jasper; Blanchet, Lionel; Bloemen, Bart; Heuvel, Lambertus P. van den; Engelke, Udo; Wevers, Ron A.; Buydens, L.M.C.

doi:10.1016/j.aca.2015.06.042

Cited by 64 publications

(50 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test whether any of the individual significant VOCs and the discriminatory profiles were statistically influenced by external factors (i.e. gender, smoking habit, disease location and use of medication), we used the Mann–Whitney U test and Kruskal–Wallis test with a Benjamini–Hochberg post hoc correction for multiple testing for testing the individual VOCs, and regularised multivariate analysis of variance (rMANOVA) for testing the VOCs profile . Major differences in dietary intake during periods of active and quiescent disease could have impact on exhaled VOCs, for example by changing the faecal microbiota composition and activity.…”

Section: Methodsmentioning

confidence: 99%

The potential of volatile organic compounds for the detection of active disease in patients with ulcerative colitis

Smolinska

Bodelier

Dallinga

et al. 2017

Aliment Pharmacol Ther

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

The potential of volatile organic compounds for the detection of active disease in patients with ulcerative colitis

Smolinska

Bodelier

Dallinga

et al. 2017

Aliment Pharmacol Ther

View full text Add to dashboard Cite

show abstract

“…More specifically, linear eigenvalue shrinkage was used to improve upon the sample estimate of the within‐group scatter matrix W . The method was referred to as rMANOVA . As mentioned above, the linear eigenvalue shrinker is a special case of a ridge‐type estimator (Equation ) using a multiple of the identity matrix as target.…”

Section: Ridge‐type Estimatorsmentioning

confidence: 99%

“…Therefore, rMANOVA can also be interpreted from a bias‐variance trade‐off point of view as it seeks to balance using matrix W (equal to [up to a constant] S ) and the target matrix T that specifies a simple within‐group scatter structure using Equation . Other targets, besides the identity matrix, can also be used in rMANOVA such as diag ( W ) or a sparse matrix …”

Section: Ridge‐type Estimatorsmentioning

confidence: 99%

An overview of large‐dimensional covariance and precision matrix estimators with applications in chemometrics

Engel

Buydens

Blanchet

2017

Journal of Chemometrics

View full text Add to dashboard Cite

The covariance matrix (or its inverse, the precision matrix) is central to many chemometric techniques. Traditional sample estimators perform poorly for high-dimensional data such as metabolomics data. Because of this, many traditional inference techniques break down or produce unreliable results. In this paper, we selectively review several modern estimators of the covariance and precision matrix that improve upon the traditional sample estimator. We focus on 3 general techniques: eigenvalue-shrinkage estimation, ridge-type estimation, and structured estimation. These methods rely on different assumptions regarding the structure of the covariance or precision matrix. Various examples, in particular using metabolomics data, are used to compare these techniques and to demonstrate that in concert with, eg, principal component analysis, multivariate analysis of variance, and Gaussian graphical models, better results are obtained. KEYWORDSeigenvalue shrinkage, metabolomics, ridge-type estimation, sparse covariance matrix, sparse precision matrix

show abstract

“…Over the years, several strategies to eliminate the phenomenon of aggregation and adhesion, such as the addition of poly (ethylene oxide) to buffer solution or inner capillary surface modification were proposed [5,6]. The new approach is the modification of functional groups on the microbial surface by divalent metal ions resulting in controlled aggregation of cells [7].…”

Section: Abstractsmentioning

confidence: 99%

“…The analysis of the resulting highly structured data should then allow for all sources of biological variation to be considered. For this purpose, several approaches like analysis of variance-simultaneous component analysis, ASCA [5], regularised multivariate analysis of variance, rMANOVA [6], non-parametric MANOVA [7] and their extensions [8,9] have been proposed in the literature.…”

Section: Stanimirovamentioning

confidence: 99%

Metabolomics Circle 2017 — Abstracts

Journal¹

2017

Medical Research Journal

View full text Add to dashboard Cite

The implementation of scientific knowledge, as a part of applied science, should be aimed at developing practical applications for many fields of natural world (e.g. medicine, pharmacy, cosmetology, food industry etc.). Consequently, in the case of separation techniques the evaluation of separation medium comprises an essential part of analytical methods improvement. Significant efforts have been made over the last few years to achieve stationary phases imitated natural matter (e.g. biological membrane) as well as endogenous compounds (e.g. amino acids).Specificity of chemically bonded ligands in the case of new materials enables receiving a so-called dedicated stationary phases. Moreover, structural similarity of the immobilized ligands with the desired group of analytes determine the high specificity and selectivity of prepared stationary phases. Therefore, the investigations in accordance with the "3S" assumption -similarity, selectivity, and specificity -allow the development of a new generation of separation materials.The chemical immobilization of amino acids and peptides -one of the most essential compounds in life science allow the preparation of materials that exhibit unique interactions with amino acids and peptides as a analytes and beyond. The amino acids-and peptides-silica stationary phases show high selectivity for other groups of biologically significant compounds, i.e. carbohydrates, nucleosides, flavonoids, optical active compounds. Furthermore, stationary phases prepared in compliance with "3S" assumption exhibit wide range of applicability in separation techniques (RP HPLC, HILIC, IC). This approach also includes the preparation of stationary phases containing in the structure specific functional groups characteristics for biological membrane. The development of this type of materials enables the modeling of the transport of substances through the biomembrane, e.g. blood/brain barrier. On the other side, stationary phases imitating membrane lipids provide unique selectivity according to lipids separation, especially phospholipids.As a consequence, the natural biological systems provide a significant center of inspiration for development of chromatographic methods. Based on the principles that governed natural world, it is possible to obtain desired similarity, selectivity, and specificity that determine the resolution of separation methods. The metabolomic data collected using high performance liquid chromatography coupled with mass spectrometry (LC-MS/MS or LC/TOF-MS)can provide signal intensities for a large number of compounds (peaks) present in set of samples (i.e. control and experimental). However, such large metabolomic data sets are usually difficult to interpret, due to the small sample sizes; search for effects (e.g. differences between control and experimental group) that are small; and considering a large number of hypotheses without paying enough attention to the problem of multiple comparisons. It might lead and often leads to conclusions (e.g. biomarker identification) that a...

show abstract

Regularized MANOVA (rMANOVA) in untargeted metabolomics

Cited by 64 publications

References 33 publications

The potential of volatile organic compounds for the detection of active disease in patients with ulcerative colitis

The potential of volatile organic compounds for the detection of active disease in patients with ulcerative colitis

An overview of large‐dimensional covariance and precision matrix estimators with applications in chemometrics

Metabolomics Circle 2017 — Abstracts

Contact Info

Product

Resources

About