Predicting Secondary Structures, Contact Numbers, and Residue-wise Contact Orders of Native Protein Structure from Amino Acid Sequence by Critical Random Networks

Abstract

Prediction of one-dimensional protein structures such as secondary structures and contact numbers is useful for the three-dimensional structure prediction and important for the understanding of sequence-structure relationship. Here we present a new machine-learning method, critical random networks (CRNs), for predicting one-dimensional structures, and apply it, with position-specific scoring matrices, to the prediction of secondary structures (SS), contact numbers (CN), and residue-wise contact orders (RWCO). The present method achieves, on average, $Q_3$ accuracy of 77.8% for SS, correlation coefficients of 0.726 and 0.601 for CN and RWCO, respectively. The accuracy of the SS prediction is comparable to other state-of-the-art methods, and that of the CN prediction is a significant improvement over previous methods. We give a detailed formulation of critical random networks-based prediction scheme, and examine the context-dependence of prediction accuracies. In order to study the nonlinear and multi-body effects, we compare the CRNs-based method with a purely linear method based on position-specific scoring matrices. Although not superior to the CRNs-based method, the surprisingly good accuracy achieved by the linear method highlights the difficulty in extracting structural features of higher order from amino acid sequence beyond that provided by the position-specific scoring matrices.