|
Internet Electronic Journal of Molecular Design - IEJMD, ISSN 1538-6414, CODEN IEJMAT
| ABSTRACT - Internet Electron. J. Mol. Des. July 2002, Volume 1, Number 7, 332-338 |
Prediction of Protein Structural Classes by a Neural Network Method
Yu-Dong Cai, Junda Hu, Yi-Xue Li, and Kuo-Chen Chou
Internet Electron. J. Mol. Des. 2002, 1, 332-338
|
Abstract:
Protein structures can be classified as all-α, all-β, α/β,
α+β and ζ according to protein chain folding topologies. Previous
studies have shown evidence that some correlation between the protein structural
class and amino acid composition does exist, and the protein
structural class can be predicted to some extent according to amino
acid composition alone. In this study we apply Kohonen's self-organization
neural network to approach this problem. The results
obtained show that the structural class of a protein is considerably
correlated with its amino acid composition, and the neural network is
a useful tool for predicting the structural classes of proteins.
|