Proteometric study of ghrelin receptor function variations upon mutations using amino acid sequence autocorrelation vectors and genetic algorithm-based least square support vector machines

Caballero, Julio; Fernandez, Leyden; Garriga, Miguel; Abreu, Jose Ignacio; Collina, Simona; Fernandez, Michael


Functional variations on the human.-hrelin receptor upon mutations have been associated with a syndrome of short stature and obesity, of which the obesity appears to develop around puberty. In this work, we reported a proteometrics analysis of the constitutive and ghrelin-induced activities of wild-type and mutant ghrelin receptors using amino acid sequence autocorrelation (AASA) approach for protein structural information encoding. AASA vectors were calculated by measuring the autocorrelations at sequence lags ranging from I to 15 on the protein primary structure of 48 amino acid/residue properties selected from the AAindex database. Genetic algorithm-based multilinear regression analysis (GA-MRA) and genetic algorithm-based least square support vector machines (GA-LSSVM) were used for building linear and non-linear models of the receptor activity. A genetic optimized radial basis function (RBF) kernel yielded the optimum GA-LSSVM models describing 88% and 95% of the cross-validation variance for the constitutive and ghrelin-induced activities, respectively. AASA vectors in the optimum models mainly appeared weighted by hydrophobicity-related properties. However, differently to the constitutive activity, the ghrelin-induced activity was also highly dependent of the steric features of the receptor. (C) 2006 Elsevier Inc. All rights reserved.

Más información

Título según WOS: ID WOS:000248646500016 Not found in local WOS DB
Volumen: 26
Número: 1
Editorial: Elsevier
Fecha de publicación: 2007
Página de inicio: 166
Página final: 178


Notas: ISI