Please use this identifier to cite or link to this item:
|Title:||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.|
|ISSN:||0975-0959 (Online); 0301-1208 (Print)|
|Appears in Collections:||IJBB Vol.38(1-2) [February-April 2001]|
Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.