Prediction of Contact Maps by Recurrent Neural Network Architectures and Hidden Context Propagation From All Four Cardinal Corners

ABSTRACT Motivation: Accurate prediction of protein contact maps is an important step in computational structural proteomics. Because contact maps provide a translation and rotation invariant topological representation of a protein, they can be used as a fundamental intermediary step in protein structure prediction. Results: We develop a new set of flexible machine learning architectures for the prediction of contact maps, as well as other information processing and pattern recognition tasks. The architectures can be viewed as recurrent neural network parameterizations of a class of Bayesian networks we call generalized input-output HMMs. For the specific case of contact maps, contextual information is propagated laterally through four hidden planes, one for each cardinal corner. We show that these architectures can be trained from examples and yield contact map predictors that outperform previously reported methods. While several extensions and improvements are in progress, the current version can accurately predict 60.5% of contacts at a distance cutoff of ̊ and 45% of distant contacts at ̊ , for proteins of length up to 300. Availability and Contact: The contact map predictor will be made available through http://promoter.ics.uci.edu/BRNNPRED/ as part of an existing suite of proteomics predictors. Email: gpollast,pfbaldi @ics.uci.edu.