A web server for predicting substrate sites of three protein tyrosine phosphatases. Ptpset is based on the sequence features of manually collected dephosphorylation sites. The total of experimentally validated human substrate sites for PTP1B, SHP-1 and SHP-2 were 51, 42 and 44, respectively. With those reported substrate sites as positive samples and 1000 randomly selected negative samples, we utilized the k-NN algorithm to predict substrate sites for the above-mentioned PTPs. We scanned their possible dephosphorylation sites in the set of phosphorylation sites acquired by mass-spectrometer technique, which could provide numerous candidate substrates for traditional experiments.
Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University Health Science Center, Beijing, China; Institute of Systems Biomedicine, School of Basic Medical Sciences, Peking University Health Science Center, Beijing, China
Ptpset funding source(s)
This work was supported by grants from the National Basic Research Program (2011CBA01104), the National High-tech R&D Program (2012AA020401) of China, the National Natural Science Foundation of China (31371337 and 61105003), and Beijing Higher Education Young Elite Teacher Project (YETP0055).