Comparative modeling of the conformational stability of chymotrypsin inhibitor 2 protein mutants using amino acid sequence autocorrelation (AASA) and amino acid 3D autocorrelation (AA3DA) vectors and ensembles of Bayesian-regularized genetic neural networks |
| |
| Authors: | Michael Fernández José Ignacio Abreu Julio Caballero Miguel Garriga |
| |
| Institution: | 1. Molecular Modeling Group , Center for Biotechnological Studies, Faculty of Agronomy, University of Matanzas , 44740, Matanzas, Cuba;2. Molecular Modeling Group , Center for Biotechnological Studies, Faculty of Agronomy, University of Matanzas , 44740, Matanzas, Cuba;3. Artificial Intelligence Laboratory , Faculty of Informatics, University of Matanzas , 44740, Matanzas, Cuba;4. Plant Biotechnology Group , Faculty of Agronomy, Center for Biotechnological Studies, University of Matanzas , C.P. 44740, Matanzas, Cuba;5. Centro de Bioinformática y Simulación Molecular, Universidad de Talca, 2 Norte , 685, Casilla 721, Talca, Chile |
| |
| Abstract: | Predicting protein stability changes upon point mutation is important for understanding protein structure and designing new proteins. Autocorrelation vector formalism was extended to amino acid sequences and 3D conformations for encoding protein structural information with modeling purpose. Protein autocorrelation vectors were weighted by 48 amino acid/residue properties selected from the AAindex database. Ensembles of Bayesian-regularized genetic neural networks (BRGNNs) trained with amino acid sequence autocorrelation (AASA) vectors and amino acid 3D autocorrelation (AA3DA) vectors yielded predictive models of the change of unfolding Gibbs free energy change (ΔΔG) of chymotrypsin Inhibitor 2 protein mutants. The ensemble predictor described about 58 and 72% of the data variances in test sets for AASA and AA3DA models, respectively. Optimum sequence and 3D-based ensembles exhibit high effects on relevant structural (volume, solvent-accessible surface area), physico-chemical (hydrophilicity/hydrophobicity-related) and thermodynamic (hydration parameters) properties. |
| |
| Keywords: | Point mutations Artificial neural networks Bayesian regularization Protein stability |
|
|
