by Julio Caballero, Leyden Fernández, José Abreu, Michael Fernández
Abstract:
Development of novel computational approaches for modeling protein properties from their primary structure is a main goal in applied proteomics. In this work, we reported the extension of the autocorrelation vector formalism to amino acid sequences for encoding protein structural information with modeling purposes. Amino Acid Sequence Autocorrelation (AASA) vectors were calculated by measuring the autocorrelations at sequence lags ranging from 1 to 15 on the protein primary structure of 48 amino acid/residue properties selected from the AAindex database. A total of 720 AASA descriptors were tested for building predictive models of the thermal unfolding Gibbs free energy change of human lysozyme mutants. In this sense, ensembles of Bayesian-Regularized Genetic Neural Networks (BRGNNs) were used for obtaining an optimum nonlinear model for the conformational stability. The ensemble predictor described about 88% and 68% variance of the data in training and test sets, respectively. Furthermore, the optimum AASA vector subset was shown not only to successfully model unfolding thermal stability but also to distribute wild-type and mutant lysozymes on a stability Self-organized Map (SOM) when used for unsupervised training of competitive neurons. © 2006 American Chemical Society.
Reference:
Amino acid sequence autocorrelation vectors and ensembles of bayesian-regularized genetic neural networks for prediction of conformational stability of human lysozyme mutants (Julio Caballero, Leyden Fernández, José Abreu, Michael Fernández), In Journal of Chemical Information and Modeling, volume 46, 2006. (http://www.scopus.com/inward/record.url?eid=2-s2.0-33745380521&partnerID=40&md5=5a1c77c437fc079967db3f2155a2cb35 http://pubs.acs.org/doi/abs/10.1021/ci050507z?journalCode=jcisd8) (cited By (since 1996) 31)
Bibtex Entry:
Title = {Amino acid sequence autocorrelation vectors and ensembles of bayesian-regularized genetic neural networks for prediction of conformational stability of human lysozyme mutants},
Author = {Julio Caballero and Leyden Fernández and José Abreu and Michael Fernández},
Journal = {Journal of Chemical Information and Modeling},
Year = {2006},
Note = {cited By (since 1996) 31},
Number = {3},
Pages = {1255-1268},
Volume = {46},
Abbrev_source_title = {J. Chem. Inf. Model.},
Abstract = {Development of novel computational approaches for modeling protein properties from their primary structure is a main goal in applied proteomics. In this work, we reported the extension of the autocorrelation vector formalism to amino acid sequences for encoding protein structural information with modeling purposes. Amino Acid Sequence Autocorrelation (AASA) vectors were calculated by measuring the autocorrelations at sequence lags ranging from 1 to 15 on the protein primary structure of 48 amino acid/residue properties selected from the AAindex database. A total of 720 AASA descriptors were tested for building predictive models of the thermal unfolding Gibbs free energy change of human lysozyme mutants. In this sense, ensembles of Bayesian-Regularized Genetic Neural Networks (BRGNNs) were used for obtaining an optimum nonlinear model for the conformational stability. The ensemble predictor described about 88% and 68% variance of the data in training and test sets, respectively. Furthermore, the optimum AASA vector subset was shown not only to successfully model unfolding thermal stability but also to distribute wild-type and mutant lysozymes on a stability Self-organized Map (SOM) when used for unsupervised training of competitive neurons. © 2006 American Chemical Society.},
Affiliation = {Faculty of Agronomy, Molecular Modeling Group, University of Matanzas, 44740 Matanzas, Cuba; Artificial Intelligence Lab., Faculty of Informatics, University of Matanzas, 44740 Matanzas, Cuba},
Chemicals_cas = {lysozyme, 9001-63-2; Muramidase, 3.2.1.17},
Comment = {http://www.scopus.com/inward/record.url?eid=2-s2.0-33745380521&partnerID=40&md5=5a1c77c437fc079967db3f2155a2cb35 http://pubs.acs.org/doi/abs/10.1021/ci050507z?journalCode=jcisd8},
Correspondence_address = {Fernández, M.; Faculty of Agronomy, Molecular Modeling Group, University of Matanzas, 44740 Matanzas, Cuba; email: michael.fernande@umcc.cu},
Document_type = {Article},
Doi = {http://dx.doi.org/10.1021/ci050507z},
ISSN = {15499596},
Keywords = {Amino acids; Conformations; Mutagenesis; Neural networks; Proteins; Stability; Vectors, Amino Acid Sequence Autocorrelation (AASA); Computational approaches; Protein properties; Structural information, Computation theory, lysozyme, algorithm; article; artificial neural network; Bayes theorem; chemistry; genetics; human; mutation; protein conformation, Algorithms; Bayes Theorem; Humans; Muramidase; Mutation; Neural Networks (Computer); Protein Conformation},
Language = {English},
Owner = {2006_J_Chem_Inf_Model 46_1255},
Pubmed_id = {16711745},
Source = {Scopus},
Url = {http://www.ncbi.nlm.nih.gov/pubmed/16711745}
}