Identification of Phosphorylation Sites Using SVMs

Protein phosphorylation, which is an important mechanism in posttranslational modification, affects essential cellular processes such as metabolism, cell signaling, differentiation, and membrane transportation. Proteins are phosphorylated by a variety of protein kinases. A predictor is constructed to predict the true and false phosphorylation sites based on support vector machines (SVM), and new encoding method is used for amino sequences. Single variable models and multivariable models are applied to generate the input for the SVM. The main contribution here is that we have developed a kinase-specific phosphorylation site prediction tool with both high sensitivity and specificity.