Protein secondary structure prediction by a neural network architecture with simple positioning algorithm techniques

Abstract

Protein secondary structure is an immense achievement of bioinformatics. It's an amino acid residue in a polypeptide backbone. In this paper, an innovative method has been proposed for predicting protein secondary structures based on 3-state protein secondary structure by neural network architecture with simple positioning algorithm (SIMPA) technique. Q3 (3-state prediction of protein secondary structure) is a fundamental methodology for our approach. Initially, the prediction of the secondary structure of the protein using the Q3 prediction method has been done. For this, a model has been built from its primary structure. Then it will retrieve the percentage of amino acid sequences from the original sequence to the accuracy of the predicted sequence. Utilizing the SIMPA technique from the 3-state secondary structure predicted sequence, the percentage of dissimilar residues of the three types (α-helix, β-sheet and coil) of Q3 has been extracted. Then the verification of the Q3 predicted accuracy through the SIMPA technique was done. Finally using a new method of neural network, it is verified that the Q3 prediction method gives good results from the neural network approach.