IEA/AIE 2006: Advances in Applied Artificial Intelligence pp 935-942 | Cite as
Protein Stability Engineering in Staphylococcal Nuclease Using an AI-Neural Network Hybrid System and a Genetic Algorithm
Abstract
With the recent increases in the use of protein-based therapeutics for the treatment of disease, protein stability engineering is an area of growing importance. Feed forward neural networks are trained to predict mutation induced protein stability changes in Staphylococcal nuclease to an accuracy of 93%. These neural networks are then implemented as part of a larger AI framework that is capable of engineering mutations within a protein sequence to yield the target stability or as the basis for a fitness function of a genetic algorithm capable of producing a population of mutation containing sequences of the desired stability. The AI neural network hybrid and genetic algorithm based approaches are significantly faster than other computational methods of protein engineering and can be utilized for proteins in which structural information is lacking.
Keywords
Genetic Algorithm Protein Stability Network Hybrid Residue Position Target StabilityPreview
Unable to display preview. Download preview PDF.
References
- 1.Cleland, J.L., Jones, A.J.S., Craik, C.S.: Introduction to protein engineering. In: Cleland, J.L., Craik, C.S. (eds.) Protein Engineering: Principles and Practice, pp. 1–32. Wiley-Liss, NY (1996)Google Scholar
- 2.Braxton, S.: Protein engineering for stability. In: Cleland, J.L., Craik, C.S. (eds.) Protein Engineering: Principles and Practice, pp. 299–316. Wiley-Liss, NY (1996)Google Scholar
- 3.Korkegian, A., Black, M.E., Baker, D., Stoddard, B.L.: Computational thermostabilization of an enzyme. Science 308, 857–860 (2005)CrossRefGoogle Scholar
- 4.Borjesson, U., Hunenberger, P.H.: Effect of mutations involving charged residues on the stability of staphylococcal nuclease: a continuum electrostatics study. Protein Engineering 16, 831–840 (2003)CrossRefGoogle Scholar
- 5.Topham, C.M., Srinivasan, N., Blundell, T.L.: Prediction of the stability of protein mutants based on structural environment-dependent amino acid substitution and propensity tables. Protein Engineering 10, 7–21 (1997)CrossRefGoogle Scholar
- 6.Frenz, C.M.: Neural network-based prediction of mutation induced protein stability changes in Staphylococcal nuclease at 20 residue positions. Proteins: Structure, Function, Bioinformatics 59, 147–151 (2005)CrossRefGoogle Scholar
- 7.Capriotti, E., Fariselli, P., Calabrese, R., Casidio, R.: Predicting protein stability changes from sequences using support vector machines. Bioinformatics 21(suppl. 2), 54–58 (2005)Google Scholar
- 8.Cheng, J., Randall, A., Baldi, P.: Prediction of protein stability changes for single-site mutations using support vector machines, Proteins: Structure, Function. Bioinformatics 62, 1125–1132 (2006)Google Scholar
- 9.Jones, D.T., Taylor, W.R., Thornton, J.M.: The rapid generation of mutation data matrices from protein sequences. CABIOS 8, 275–282 (1992)Google Scholar
- 10.Green, S.M., Shortle, D.: Patterns of nonadditivity between pairs of stability mutations in staphylococcal nuclease. Biochemistry 32, 10131–10139 (1993)CrossRefGoogle Scholar
- 11.Tsoukalas, L.H., Zadeh, L.A., Uhrig, R.E., Hines, J.W.: Fuzzy and Neural Approaches in Engineering. Wiley, NY (1996)Google Scholar
- 12.Gustafsson, C., Liao, J., Warmuth, S., Ness, J., Wang, R., Minshull, J.: Engineering proteinase K using machine learning and synthetic genes. PepTalk (2006) (Abstract Book)Google Scholar