Prediction of Contact Maps Using Modified Transiently Chaotic Neural Network

摘要

Contact maps are considered one of the most useful strategic steps in protein folding recognition. And there are a variety of measures of residues contact used in the literature. In this paper, we address our question on using a transiently chaotic neural network to predict the contact maps and whether it is reasonable. Our results show that it is more successful that we predict proteins contact maps based on modified transiently chaotic neural network.