Prediction of contact map integrated PNN with conformational energy

This paper presents a novel method to solve the protein's three-dimensional structure prediction problem. It is a machine learning approach by integrating probabilistic neural network (PNN) with conformational energy function (CEF) based on chemico-physical knowledge of amino acids. In this method, firstly, the principal components are extracted from selected protein structures with lower sequence identity, and an initial matrix of contact map is constructed by K-L expansion. Secondly, PNN is used for predicting the long-range interaction of amino acids in protein. In particular, this method uses the CEF and chemico-physical characteristics of amino acids to run the PNN predictor. Consequently, it was found that our proposed method is better than existing methods, such as the hybrid method of HMMSTR and the correlated mutation analysis method. As a result, this method can accurately predict 31% of contacts at a distance cutoff of 8/spl Aring/ for proteins whose sequence length is up to 200.