Record Details

Neural network prediction of 310-helices in proteins

NOPR - NISCAIR Online Periodicals Repository

View Archive Info
 
 
Field Value
 
Title Neural network prediction of 310-helices in proteins
 
Creator Pal, Lipika
Basu, Gautam
 
Description 107-114
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.
 
Date 2013-07-16T06:32:22Z
2013-07-16T06:32:22Z
2001-04
 
Type Article
 
Identifier 0975-0959 (Online); 0301-1208 (Print)
http://hdl.handle.net/123456789/19808
 
Language en_US
 
Rights CC Attribution-Noncommercial-No Derivative Works 2.5 India
 
Publisher NISCAIR-CSIR, India
 
Source IJBB Vol.38(1-2) [February-April 2001]