Header image  
Based on Evolutionary Information of Proteins  
September 24, 2017


Protein Phosphorylation Site Prediction System

One of the most critical cellular phenomenon is phosphorylation of proteins as it is involved in signal transduction in various processes including cell cycle, proliferation and apoptosis. This phenomenon is catalyzed by protein kinases that affect certain acceptor residues (Serine, Threonine and Tyrosine) in substrate sequences. Experiments by 2D-gel electrophoresis indicate that 30-50% of the proteins in an eukaryotic cell undergo phosphorylation. So, accurate prediction of the phosphorylation sites of eukaryotic proteins will help in understanding the overall intracellular events.

Both experimental and computational methods have been developed to investigate the phosphorylation sites. In vivo and in vitro methods are often time-consuming, expensive and even limited by the restriction of enzymatic reactions. On the other hand, in silico prediction of phosphorylation sites from computational approaches can afford fast and automatic annotation for candidate phosphorylation sites which eventually will be an important breakthrough in many aspects of current molecular biology and very helpful for disease-related research and drug design.

We have developed a prediction system (PPRED) that incorporates the evolutionary information of proteins to train the SVMs, which is applicable to predict accurately the phosphorylation sites from given protein sequences and to analysis the importance of such information to devise generalized prediction systems.

Photo at the header courtesy to Pearson Education, Inc., publishing as Benjamin Cummings.