Prediction of Protein Topologies Using GIOHMMs and GRNNs

We develop and test new machine learning methods for the prediction of topological representations of protein structures in the form of coarseor ne-grained contact or distance maps that are translation and rotation invariant. The methods are based on generalized input-output hidden Markov models (GIOHMMs) and generalized recursive neural networks (GRNNs). The methods are used to predict topology directly in the ne-grained case and, in the coarsegrained case, indirectly by rst learning how to score candidate graphs and then using the scoring function to search the space of possible con gurations. Computer simulations show that the predictors achieve state-of-the-art performance.