An improved prediction of protein secondary structures based on a multi-mold integrated neural network

The purpose of this proposes an improved prediction of protein secondary structures based on a multi-mold integrated neural network. A structure of modified artificial neural network based on built a 5-child network integrated multi-mold neural networks in which a child for each network using neural network classification is divided into two-level network is presented. Prediction comprehensive result of protein secondary structure from 5 networks is got. Profile of evolutionary information for protein sequences encoded is taken as an input of a level network. Protein sequences code is added sequence information and prediction of protein is refined by the secondary level network. It is shown that high prediction accuracy of protein secondary structure can be got by an improved multi-mold integrated neural network at 73.1%.