engleski

Binary coding of the secondary protein structure

Large body of literature relates physical and chemical properties of the amino acids and protein folding, however, relatively little is known about the relationships of the codons and secondary protein structure. Nucleotide strings based protein folding prediction is important because the Genome Project resulted in a large number of gene sequences that code for different proteins, of often unknown structure and function (Štambuk & Konjevoda ; Int J. Quant. Chem., 84: 13-22. 2001). We present a new computational algorithm for the prediction of alpha- and beta-protein folding types from the nucleotide and amino acid sequences. The method is based on the binary coding of nucleotide and amirio acid physicochemical properties and enables quick, simple and accurate prediction of alpha- and beta-protein folds on a personal computer. The analysis of the prediction accuracy and its cross-validations by means of the SMO machine learning algorithm for the support vector machines and classification trees was done on a large dataset of dissimilar protein folds. The results confirmed the method. Genetic code randomisation analysis additionally confirmed the validity of the algorithm with respect to the secondary protein structure prediction and indicated that: a) there is a very low chance that a better code then the one specified by the nature is randomly produced ; b) basic protein units with respect to the genetic code defining of alpha- and beta-protein folding types are not monomers (single amino acids) but dipeptides and tripeptides.

protein folding; binary coding; computational algorithm; nucleotide; amino acid

nije evidentirano