This server offers a fast and accurate protein chemical shift prediction. A neural network was trained to predict the 1H, 13C, and 15N of proteins using their three-dimensional structure as well as experimental conditions as input parameters. It achieves average deviations of 0.22ppm for hydrogen, 0.98ppm for carbon, and 2.08ppm for nitrogen chemical shifts. The model adopts important influences of the covalent structure as well as of the conformation not only for backbone atoms (as e.g. the chemical shift index) but also for side-chain nuclei.

Files are limited to 4MB in size; if you are a Meiler-Lab member, please login to upload files up to 16MB