Esta es un versión antigua publicada el 2022-11-08. Consulte la versión más reciente.

IMPLEMENTACIÓN DE TÉCNICAS DE RECONOCIMIENTO DE PATRONES (LEAST SQUARE SUPPORT VECTOR MACHINES) EN PROCESOS DE SELECCIÓN DE PARÁMETROS CARACTERÍSTICOS APLICADOS A SISTEMAS METABOLÓMICOS

Autores/as

William Villamizar Rozo
Luis E. Mendoza
Pablo Santafé G.

DOI:

https://doi.org/10.24054/rcta.v1i21.1897

Palabras clave:

Metabolómica, HNMR, LS-SVM, COW

Resumen

En este artículo se presenta una metodologíaque involucra, técnicas de análisis multivariable y una etapa de pre-procesamiento con el fin de determinar metabolitos característicos en un determinado espectro. Este método novedoso permitió determinar
que ciertos metabolitos son modificados por las diferentes concentraciones y además de conocer la funcionalidad de LS-SVM en datos NMR. También se logró validar procesos como: alineamiento de picos, normalización, corrección de línea base y análisis
multienergía, en datos metabolómicos en aceites de oliva y avellana puros y mezclados con alteraciones de 2%, 5%, 10%, 20% y 30%.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Oliver S.G, Winson MK, Kell D.B, et al.

Systematic functional analysis of the yeast

genome.TrendsBiotechnol 1998; 16:373–8.

. Vladimir Shulaev, Metabolomics technology

and bioinformatics. Briefings in

Bioinformatics.2006; Vol. 7. No 2. 128 -139.

. Viant MR, Rosenblum E.S, Tieerdema RS.

NMR-based metabolomics: a powerful

approach for characterizing theeffects of

environmental stressors on organism health.

Environ SciTechnol 2003; 37:4982–9.

. Hong-Seok Son, Ki Myong Kim, Frans Van

Den Berg,Geum-Sook Hwang, Won-Mok

Park, Cherl-Ho Lee, and Young-

ShickHong,J. 1H Nuclear Magnetic

Resonance-Based Metabolomic

Characterization of Wines by Grape

Varieties and Production Areas.Agric. Food

Chem. 2008, 56, 8007–8016

. D. F. Brougham, G. Ivanova, M. Gottschalk,

D.M. Collins, A. J. Eustace, R. O’Connor,

and J. Havel,Artificial Neural Networks for

Classification in Metabolomic Studies

ofWhole Cells Using 1H NuclearMagnetic

Resonance.

. Richard J. Gilbert, Helen E. Johnson, Michæl

K. Winson, Jem J.

Rowland,RoystonGoodacre, Aileen R.

Smith, Michæl A. Hall and Douglas B. Kell.

Genetic Programming as an Analytical Tool

for MetabolomeData;Institute of Biological

Sciences, University of Wales, Aberystwyth,

Ceredigion.

. Z. Ramadan, D. Jacobs, M. Grigorov, S.

Kochhar. Metabolic profiling using principal

component analysis, discriminant partial

least squares, and genetic algorithms.

Elsevier, Talanta 68 (2006) 1683–1691

. Darwin on the origin of species by means of

natural selection. Canadian Naturalist and

Geologist 5:100-120.

. Vapnik, V. (1998b).The support vector

method of function estimation. In J. A. K.

Suykens, & J. Vandewalle, (Eds.), Nonlinear

Modeling: Advanced Black-box Techniques.

Boston: Kluwer Academic Publishers.

. Jan Luts, Fabian Ojeda, Raf Van de

Plasa,Bart De Moora, Sabine Van Huffela,

Johan A.K. Suykensa , A tutorial on support

vector machine-based methods for

classification problems in chemometrics.

Elsevier AnalyticaChimicaActa 665 (2010)

–145

. Raamsdonk LM, Teusink B, Broadhurst D,

et al. A functional genomics strategy that

uses metabolome data to reveal the

phenotype of silent mutations. Nat

Biotechnol 2001;19:45–50.

. Catchpole GS, Beckmann M, Enot DP, et al.

Hierarchical metabolomics demonstrates

substantial compositional similarity between

genetically modified and conventional potato

crops. PNAS 2005;102:14458–62.

. Nicholson JK, Lindon JC, Holmes E.

‘Metabonomics’ understanding the metabolic

responses of living systems

topathophysiological stimuli via multivariate

statistical analysisof biological NMR

spectroscopic data. Xenobiotica 1999;

:1181–9.

. Watkins SM, German J. B. Metabolomics

and biochemical profiling in drug discovery

and development.CurrOpinMolTher

;4:224–8.

. Watkins SM, Reifsnyder PR, Pan HJ, et al.

Lipid metabolome-wide effects of the

PPARgammaagonistrosiglitazone. J Lipid

Res 2002;43:1809–17.

. [16]Jennifer L. Spratlin,NatalieJ. Serkova,

and S. Gail Eckhardt, Clinical Applications

ofMetabolomics in Oncology:

AReview.ClinCancerRes2009;15:431-440.

. Fiehn O, Kopka J, Trethewey RN, et al.

Identification of uncommon plant

metabolites based on calculation ofelemental

compositions using gas chromatography

andquadrupole mass spectrometry. Anal

Chem 2000; 72: 3573–80.

. Georgia Vigli, AngelosPhilippidis,

Apostolos Spyros, and PhotisDais,

Classification of Edible Oils by Employing

P and 1H NMR Spectroscopy in

Combination with Multivariate Statistical

Analysis. A Proposal for the Detection of

Seed Oil Adulteration in Virgin Olive Oils,J.

Agric. Food Chem. 2003, 51, 5715-5722

. Mannina Luisa, Segre Annalaura,High

Resolution Nuclear Magnetic Resonance:

From Chemical Structure to Food

Authenticity,Grasas y Aceites, Vol. 53. Fasc.

(2002), 22-33.

. Niels-Peter Vest Nielsen, Jens Michael

Carstensen, JørnSmedsgaard ,*Aligning of

single and multiple wavelength

chromatographic profiles for chemometric

data analysis using correlation optimized

warping. Journal of Chromatography A, 805

(1998) 17–35.

Descargas

Publicado

2022-11-08

Versiones

Cómo citar

Villamizar Rozo, W., Mendoza, L. E., & Santafé G., P. (2022). IMPLEMENTACIÓN DE TÉCNICAS DE RECONOCIMIENTO DE PATRONES (LEAST SQUARE SUPPORT VECTOR MACHINES) EN PROCESOS DE SELECCIÓN DE PARÁMETROS CARACTERÍSTICOS APLICADOS A SISTEMAS METABOLÓMICOS. REVISTA COLOMBIANA DE TECNOLOGIAS DE AVANZADA (RCTA), 1(21). https://doi.org/10.24054/rcta.v1i21.1897