by Michael Fernández, Leyden Fernández, Pedro Sánchez, Julio Caballero, José Abreu
Abstract:
The conformational stability of more than 1500 protein mutants was modelled by a proteometric approach using amino acid sequence autocorrelation vector (AASA) formalism. 48 amino acid/residue properties selected from the AAindex database weighted the AASA vectors. Genetic algorithm-optimised support vector machine (GA-SVM), trained with subset of AASA descriptors, yielded predictive classification and regression models of unfolding Gibbs free energy change (G). Function mapping and binary SVM models correctly predicted about 50 and 80% of G variances and signs in crossvalidation experiments, respectively. Test set prediction showed adequate accuracies about 70% for stable single and double point mutants. Conformational stability depended on autocorrelations at medium and long ranges in the mutant sequences of general structural, physico-chemical and thermodynamical properties relative to protein hydration process. A preliminary version of the predictor is available online at http://gibk21.bse. kyutech.ac.jp/llamosa/ddG-AASA/ddG_AASA.html.
Reference:
Proteometric modelling of protein conformational stability using amino acid sequence autocorrelation vectors and genetic algorithm-optimised support vector machines (Michael Fernández, Leyden Fernández, Pedro Sánchez, Julio Caballero, José Abreu), In Molecular Simulation, volume 34, 2008. (http://www.scopus.com/inward/record.url?eid=2-s2.0-50549087952&partnerID=40&md5=7a510957704e228bf9fbf5a8b9831abb http://onlinelibrary.wiley.com/doi/10.1111/j.1747-0285.2008.00675.x/abstract http://www.citeulike.org/article/3173479) (cited By (since 1996) 2).
Bibtex Entry:
Title = {Proteometric modelling of protein conformational stability using amino acid sequence autocorrelation vectors and genetic algorithm-optimised support vector machines},
Author = {Michael Fernández and Leyden Fernández and Pedro Sánchez and Julio Caballero and José Abreu},
Journal = {Molecular Simulation},
Year = {2008},
Note = {cited By (since 1996) 2},
Number = {9},
Pages = {857-872},
Volume = {34},
Abstract = {The conformational stability of more than 1500 protein mutants was modelled by a proteometric approach using amino acid sequence autocorrelation vector (AASA) formalism. 48 amino acid/residue properties selected from the AAindex database weighted the AASA vectors. Genetic algorithm-optimised support vector machine (GA-SVM), trained with subset of AASA descriptors, yielded predictive classification and regression models of unfolding Gibbs free energy change (G). Function mapping and binary SVM models correctly predicted about 50 and 80% of G variances and signs in crossvalidation experiments, respectively. Test set prediction showed adequate accuracies about 70% for stable single and double point mutants. Conformational stability depended on autocorrelations at medium and long ranges in the mutant sequences of general structural, physico-chemical and thermodynamical properties relative to protein hydration process. A preliminary version of the predictor is available online at http://gibk21.bse. kyutech.ac.jp/llamosa/ddG-AASA/ddG_AASA.html.},
Affiliation = {Molecular Modeling Group, Center for Biotechnological Studies, University of Matanzas, Matanzas, Cuba; Department of Bioscience and Bioinformatics, Kyushu Institute of Technology (KIT), Iizuka, Fukuoka, Japan; Artificial Intelligence Lab., Faculty of Informatics, University of Matanzas, Matanzas, Cuba; Centro de Bioinformática y Simulación Molecular, Universidad de Talca, Talca, Chile},
Author_keywords = {Kernel methods; Point mutations; Protein stability prediction; Structure-property relationship},
Comment = {http://www.scopus.com/inward/record.url?eid=2-s2.0-50549087952&partnerID=40&md5=7a510957704e228bf9fbf5a8b9831abb http://onlinelibrary.wiley.com/doi/10.1111/j.1747-0285.2008.00675.x/abstract http://www.citeulike.org/article/3173479},
Document_type = {Article},
Doi = {http://dx.doi.org/10.1080/08927020802301920},
Owner = {2008_Mol_Simul_34_857},
Source = {Scopus},
Url = {http://www.tandfonline.com/doi/abs/10.1080/08927020802301920}
}