3-D structure based prediction of SUMOylation sites

Abstract

SUMOylation is a posttranslational modification that involves lysine residues from eukaryotic proteins. Misregulation of the modification has been linked to neuro-degenrative diseases and cancer. All the presently available tools to predict SUMOylation sites are sequence based. Here, we propose a novel structure based prediction tool to discriminate between SUMOylated and non-SUMOylated lysines. We demonstrate the method by carrying out a proof-of-concept study. The method achieved an accuracy of 81% and a Matthews Correlation Coefficient of 0.4.