Metabonomics classifies pathways affected by bioactive compounds. Artificial neural network classification of NMR spectra of plant extracts

Ott, Karl‐Heinz; Aranı́bar, Nelly; Singh, Bijay; Stockton, Gerald W.

doi:10.1016/s0031-9422(02)00717-3

Cited by 162 publications

(95 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method has recently demonstrated enormous potentials in many fields such as plant genotype discrimination [2][3], toxicological mechanisms, disease processes, and drug discovery [4][5][6][7][8][9][10]. One such recent application of this method included the rapid and noninvasive diagnosis of coronary heart disease [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Discrimination of Type 2 diabetic patients from healthy controls by using metabonomics method based on their serum fatty acid profiles

Yang

Hong

et al. 2004

Journal of Chromatography B

109

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Discrimination of Type 2 diabetic patients from healthy controls by using metabonomics method based on their serum fatty acid profiles

Yang

Hong

et al. 2004

Journal of Chromatography B

109

View full text Add to dashboard Cite

“…[81], albeit now discredited in general [82]; a more common view is that the site of a pharmaceutical intervention or genetic lesion can be inferred by using modern machine learning or pattern recognition techniques to look at the pattern of metabolic changes that ensue [42,[83][84][85][86], calibrating as appropriate with molecules for which the answer is known [87] and validating using samples not involved in the formation of the predictive model.…”

Section: Mode Of Action Studiesmentioning

confidence: 99%

Systems biology, metabolic modelling and metabolomics in drug discovery and development

Kell

2006

Drug Discovery Today

265

163

View full text Add to dashboard Cite

Unlike signalling pathways, metabolic networks are subject to strict stoichiometric constraints. Metabolomics amplifies changes in the proteome, and represents more closely the phenotype of an organism. Recent advances enable the production (and computer-readable encoding as SBML) of metabolic network models reconstructed from genome sequences, as well as experimental measurements of much of the metabolome. There is increasing convergence between the number of human metabolites estimated via genomics ( 3000) and the number measured experimentally. It is thus both timely, and now possible, to bring these two approaches together as an integrated (if distributed) whole to help understand the genesis of metabolic biomarkers, the progress of disease, and the modes of action, efficacy, off-target effects and toxicity of pharmaceutical drugs. Systems biology and metabolic modelling in the 21st CenturyAlthough there are many individual definitions, most commentators (including this one [1,2]) take it that systems biology involves an iterative interplay between more or less high-throughput and high-content 'wet' experiments, technology development, theory and computational modelling, and that it is the involvement of computational modelling, in particular, in the process that sets systems biology apart from the more traditional and more reductionist molecular biology. Metabolomics illustrates this amply. There is also the view that the perceived decrease in the effectiveness of the target-based drug discovery process [3][4][5], including the still-high levels of attrition [6], means that we must move towards understanding organisms at something more akin to a whole-system level [7][8][9][10][11].The question then arises as to what part of a system one might first beneficially model? Although there has, unsurprisingly, been considerable interest in modelling the major signalling pathways (e.g. Refs [12,13]), there are several reasons why it is timely to turn our attention to the level of small molecule metabolism, which is the focus of this review. Metabolism is more discriminatingIt has long been known, and proven through the formalism of metabolic control analysis [7,10,[14][15][16], that whereas small changes in the concentrations of enzymes (and the transcripts that encode them) have only small effects on the fluxes through metabolic pathways, they have substantial effects on the concentrations of metabolic intermediates. Because the metabolome (nominally the concentrations of 'all' the metabolites measured in a system of interest [17]) is downstream of the proteome, it is thereby 'amplified' both in theory [18] and in practice [19,20] and represents a more sensitive level of organisation than do the macromolecular 'omes for understanding a complex biological system, and the changes in it that might be occasioned by disease or pharmaceutical intervention [21,22]. Metabolic reconstruction is now mature and timelyAn attractive feature for the purposes of modelling is that metabolism, in contrast to signalling pathways, ...

show abstract

“…This has limited their application in the metabolic profiling arena in recent years, since model interpretation is of prime importance in applications such as biomarker screening and chemical structure elucidation. ANNs have found metabolic profiling applications in diverse areas such as classification of tumours (Howells et al, 1992) pre-clinical toxicity prediction (Anthony et al, 1995), and determination of herbicide mode of action in plants (Ott et al, 2003). In all cases, the network weights could not be interpreted directly and other methods had to be used to determine the biochemical reasons for classification.…”

Section: Mathematical Formulationmentioning

confidence: 99%

Statistical Techniques in Metabolic Profiling

Ebbels¹,

Stephens²

2007

Handbook of Statistical Genetics

View full text Add to dashboard Cite

Metabonomics classifies pathways affected by bioactive compounds. Artificial neural network classification of NMR spectra of plant extracts

Cited by 162 publications

References 28 publications

Discrimination of Type 2 diabetic patients from healthy controls by using metabonomics method based on their serum fatty acid profiles

Discrimination of Type 2 diabetic patients from healthy controls by using metabonomics method based on their serum fatty acid profiles

Systems biology, metabolic modelling and metabolomics in drug discovery and development

Statistical Techniques in Metabolic Profiling

Contact Info

Product

Resources

About