Disulfide Bond Prediction using Neural Network and Secondary Structure Information

In protein-folding prediction, the location of disulfide bonds can strongly reduce the search in the conformational space. Therefore the correct prediction of the disulfide connectivity starting from the protein residue sequence may also help in predicting its 3D structure. In this paper, we describe a method to predict disulfide connectivity in a protein given only the amino acid sequence, using neural network, and given input of symmetric flanking regions of N-terminus and C-terminus cystines augmented with residue secondary structure (helix, sheet, and coil) as well as evolutionary information. 252 protein sequences were selected from the SWISS-PROT database. From the results of 4-fold cross validation, we find that merging protein secondary structure allows us to obtain significant prediction accuracy improvements.