Improving protein secondary structure prediction by using the residue conformational classes

In this paper, based on the 340 protein sequences and their corresponding secondary structures retrieved from the protein data bank (PDB), we group the 20 different amino acid residues into 3 conformational categories: f (Former), b (Breaker) and n (Neutral), which reflect the intrinsic preference of the residue for a given type of secondary structure (α-helix, β-sheets and Coil). Then, based on radial basis function neural network (RBFNN) technique, we use this information to reconstruct the input vectors and try to improve globulin protein secondary structure prediction (SSP) accuracy. The experimental results indicate that our approach outperforms the previous conventional methods.