The Ar_NHPred server predicts the aromatic backbone NH interaction in a given amino acid sequence where the pi ring of aromatic residues interact with the backbone NH groups. The method is based on the neural network training on PSI-BLAST
generated position specific matrices and PSIPRED
predicted secondary structure. Two neural networks with a single hidden layer have been used where the first sequence-to-structure network is trained on PSI-BLAST obtained position specific matrices. Further filtering has been done by using second structure-to-structure network trained on output of first net and PSIPRED predicted secondary structure. The training has been carried out using error backpropagation
with a sum of square error function(SSE).