ISSN:
1573-4951
Keywords:
artificial neural networks
;
nucleic acids
;
prediction
;
torsion angles
Source:
Springer Online Journal Archives 1860-2000
Topics:
Chemistry and Pharmacology
Notes:
Abstract By means of an error back-propagation artificial neural network, a new method to predict the torsion angles χ, ζ and α from torsion angles δ, ∈, β and γ for nucleic acid dinucleotides is introduced. To build a model, training sets and test sets of 163 and 81 dinucleotides, respectively, with known crystal structures, were assembled. With 7 hidden units in a three-layered network a model with good predictive ability is constructed. About 70 to 80% of the residuals for predicted torsion angles are smaller than 10 degrees. This means that such a model can be used to construct trial structures for conformational analysis that can be refined further. Moreover, when reasonable estimates for δ, ∈, β and γ are extracted from COSY experiments, this procedure can easily be extended to predict torsion angles for structures in solution.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1023/A:1007946620744
Permalink