On Postprocessing of Neural Network Prediction of Polyproline Type II Secondary Structures: Network Spectrum, Response Analysis, and Scattering

Abstract

In our previous studies, we predicted protein secondary structures of polyproline type II by applying feedforward perceptron neural networks with the backpropagation learning algorithm. With a uniformly distributed test set, prediction succeeded in approximately 74% of cases, which is indeed a highvalue for a prediction problem in bioinformatics. To enable the deeper investigation of the problem of incorrect classifications and the prediction as whole, we developed new techniques for the analysis of learning data and for the decision making of neural networks with the polyproline type II material. We briefly present the results of a neural network in this context, and the techniques developed for postprocessing. The spectrum of a neural network was used for a sophisticated frequency and response analysis to describe the interactions of different amino acids in connection with the windowing employed in the preprocessing of protein data. Scattering by means of Hamming distances was used to search for local clusters and to describe learnability of data in the pattern space.