Prediction of phosphorylation sites using SVMs
Bioinformatics
PECB: prediction of enzyme catalytic residues based on Naive Bayes classification
International Journal of Bioinformatics Research and Applications
Hi-index | 0.00 |
Protein phosphorylation at Serine(S), Threonine(T) or Tyrosine(Y) residues is an important reversible post-translational modification, and it is an important mechanism for modulating(regulating) many cellular processes such as proliferation, differentiation and apoptosis. Experimental identification of phosphorylation site is labor-intensive and often limited by the availability and optimization of enzymatic reaction. In silico prediction methods may facilitate the identification of potential phosphorylation sites with ease. Methods based on primary protein sequences is much desirable and popular for its convenience and fast speed. It is obvious that structural-based methods show excellent performance, however, the 3-D structure information of protein is very limited compared to the huge number of protein in the public databases. Here we present a novel and accurate computational method named NNPhosPhoK: sequence and structural-based neural network method of protein phosphorylation sites prediction with considering specific kinase. The data in this paper is from Phospho.ELM[1].We test NNPhosPhoK with both simulational and real data, whatever in speed or in accuracy, we can realize that NNPhosPhoK shows greater computational ability with superior performance compared to two existing phosphorylation sites prediction system: ScanSite 2.0[2] and PredPhospho[3].