Neural network prediction of 310-helices in proteins

Abstract

Secondary structure prediction from the primary sequence of a protein is fundamental to understanding its structure and folding properties. Although several prediction methodologies are in vogue, their performances are far from being completely satisfactory. Among these, non-linear neural networks have been shown to be relatively effective, especially for

predicting -turns, where dominant interactions are local, arising from four sequence-contiguous residues. Most 3₁₀-helices in proteins arc also short comprising of three sequence-contiguous residues and two capping residues. In order to understand the extent of local interactions in these 3₁₀-helices, we have applied a neural network model with varying

window size to predict 3₁₀-helices in proteins. We found the prediction accuracy of 3₁₀-helices (~ 14%), as judged by the Matthew's Correlation Coefficient, to be less than that of β-turns (~ 20%). The optimal window size for the prediction of 3₁₀-helices was about 9 residues. The significance and implications of these results in understanding the occurrence of 3₁₀-helices and preferences of amino acid residues in 3₁₀-helices are discussed.