Premium
Application of Kohonen neural network to exploratory analyses of synchroton radiation x‐ray fluorescence measurements of sunflower metalloproteins
Author(s) -
Garcia Jerusa S.,
da Silva Gilmare A.,
Arruda Marco A. Z.,
Poppi Ronei J.
Publication year - 2007
Publication title -
x‐ray spectrometry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.447
H-Index - 45
eISSN - 1097-4539
pISSN - 0049-8246
DOI - 10.1002/xrs.950
Subject(s) - sunflower , self organizing map , fluorescence , chemistry , synchrotron radiation , metal ions in aqueous solution , metalloprotein , x ray fluorescence , artificial neural network , metal , analytical chemistry (journal) , materials science , computer science , artificial intelligence , physics , biology , chromatography , optics , organic chemistry , agronomy
This paper describes the utilization of Kohonen neural network in an exploratory analytical study of metalloproteins based on eight metallic descriptors (K, Ca, Cr, Mn, Fe, Co, Ni, Zn). The metal ions were detected by synchroton radiation x‐ray fluorescence (SRXRF) in 43 bands of proteins from sunflower leaves after electrophoretic separation. The application of Kohonen NN reduced the data dimensionality from eight to only two without information loss, making it possible to find a few protein bands that can represent all the sunflower proteins studied. The potentiality of the simultaneous utilization of electrophoresis, SRXRF and Kohonen NN for qualitative/quantitative metallomic studies is demonstrated, mainly when a large number of proteins and metallic ions need to be evaluated. Copyright © 2007 John Wiley & Sons, Ltd.