Progress in predicting inter-residue contacts of proteins with neural networks and correlated mutations

Abstract
This article presents recent progress in predicting inter‐residue contacts of proteins with a neural network‐based method. Improvement over the results obtained at the previous CASP3 competition is attained by using as input to the network a complex code, which includes evolutionary information, sequence conservation, correlated mutations, and predicted secondary structures. The predictor was trained and cross‐validated on a data set comprising the contact maps of 173 non‐homologous proteins as computed from their well‐resolved three‐dimensional structures. The method could assign protein contacts with an average accuracy of 0.21 and with an improvement over a random predictor of a factor greater than 6, which is higher than that previously obtained with methods only based either on neural networks or on correlated mutations. Although far from being ideal, these scores are the highest reported so far for predicting protein contact maps. On 29 targets automatically predicted by the server (CORNET) the average accuracy is 0.14. The predictor is poorly performing on all‐α proteins, not represented in the training set. On all‐β and mixed proteins (22 targets) the average accuracy is 0.16. This set comprises proteins of different complexity and different chain length, suggesting that the predictor is capable of generalization over a broad number of features. Proteins 2001;Suppl 5:157–162.