A Neural Network for Predicting the Stability of DNA/DNA Duplexes

A back-propagation neural network method has been developed to predict the stability of DNA/DNA duplexes. Calculated T_m with the present parameters fits the experimental values within reasonable errors (AD = 1.86 K, SEP = 1.99151, R2 = 0.9894 for NN1; AD = 1.59667 K, SEP = 2.03824, R2 = 0.99371 for NN2), and it has the advantage that the determinations of thermodynamic parameters are not needed.