Side-chain prediction by neural networks and simulated annealing optimization.

The prediction of the side-chain positions of proteins of known tertiary backbone structure was accomplished by a combination of neural networks and a simulated annealing method. Neural networks were used to generate distributions of side-chain dihedral angles. By eliminating network outputs with low activities, we were able to generate a reduced conformational space in which Monte Carlo-simulated annealing was carried out to optimize side-chain positions. In this study of 12 proteins, the average fractions of correct chi 1, chi 2 and combined chi 1 and chi 2 (to within 40 degrees of actual structure) were 82, 72 and 68% respectively.