Metabolites 2013, 3(1), 155-167; doi:10.3390/metabo3010155

Knowledge Discovery in Spectral Data by Means of Complex Networks

1 Faculdade de Ciências e Tecnologia, Departamento de Engenharia Electrotécnica, Universidade Novade Lisboa, Portugal 2 Centre for Biomedical Technology, Polytechnic University of Madrid Pozuelo de Alarcón, 28223 Madrid, Spain 3 Innaxis Foundation & Research Institute, Jos´e Ortega y Gasset 20, 28006, Madrid, Spain 4 Biophysics and Biological Science Laboratory, Centro Universitario de los Lagos, Universidad de Guadalajara, 47460, Lagos de Moreno, Jalisco, Mexico 5 Biotechnology and Mechatronic Academy Instituto Politécnico Nacional-UPIIG, 36275, Silao de la Victoria, Guanajuato, Mexico 6 Centro de Investigaciones en Óptica, A. C. 20200, Aguascalientes, Mexico 7 Hospital Regional de Alta Especialización del Bajío 37660, León, Gto., Mexico
* Author to whom correspondence should be addressed.
Received: 6 December 2012; in revised form: 5 February 2013 / Accepted: 5 March 2013 / Published: 11 March 2013
(This article belongs to the Special Issue Data Processing in Metabolomics)
PDF Full-text Download PDF Full-Text [556 KB, Updated Version, uploaded 12 March 2013 16:03 CET]
The original version is still available [556 KB, uploaded 11 March 2013 14:53 CET]
Abstract: In the last decade, complex networks have widely been applied to the study of many natural and man-made systems, and to the extraction of meaningful information from the interaction structures created by genes and proteins. Nevertheless, less attention has been devoted to metabonomics, due to the lack of a natural network representation of spectral data. Here we define a technique for reconstructing networks from spectral data sets, where nodes represent spectral bins, and pairs of them are connected when their intensities follow a pattern associated with a disease. The structural analysis of the resulting network can then be used to feed standard data-mining algorithms, for instance for the classification of new (unlabeled) subjects. Furthermore, we show how the structure of the network is resilient to the presence of external additive noise, and how it can be used to extract relevant knowledge about the development of the disease.
Keywords: complex networks; data mining; spectroscopy; classification

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Zanin, M.; Papo, D.; Solís, J.L.G.; Espinosa, J.C.M.; Frausto-Reyes, C.; Anda, P.P.; Sevilla-Escoboza, R.; Jaimes-Reategui, R.; Boccaletti, S.; Menasalvas, E.; Sousa, P. Knowledge Discovery in Spectral Data by Means of Complex Networks. Metabolites 2013, 3, 155-167.

AMA Style

Zanin M, Papo D, Solís JLG, Espinosa JCM, Frausto-Reyes C, Anda PP, Sevilla-Escoboza R, Jaimes-Reategui R, Boccaletti S, Menasalvas E, Sousa P. Knowledge Discovery in Spectral Data by Means of Complex Networks. Metabolites. 2013; 3(1):155-167.

Chicago/Turabian Style

Zanin, Massimiliano; Papo, David; Solís, José L.G.; Espinosa, Juan C.M.; Frausto-Reyes, Claudio; Anda, Pascual P.; Sevilla-Escoboza, Ricardo; Jaimes-Reategui, Rider; Boccaletti, Stefano; Menasalvas, Ernestina; Sousa, Pedro. 2013. "Knowledge Discovery in Spectral Data by Means of Complex Networks." Metabolites 3, no. 1: 155-167.

Metabolites EISSN 2218-1989 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert