论文部分内容阅读
Background: As one of the most important reversible protein post-translation modifications, ubiquitination has been reported to be involved in lots of biological processes.To fully decipher the molecular mechanisms of ubiquitination-related biological processes, an initial but crucial step is the recognition of ubiquitylated substrates and the corresponding ubiquitination sites.Methods: Based on our published ubiqutination site prediction method, a user-friendly web server called CKSAAP_UbSite was constructed.Briefly, CKSAAP_UbSite is an SVMbased predictor and the employed feature vector is the composition of k-spaced amino acid pairs.The protein sequence input to our server should be in RAW or FASTA format.Only the 20 conventional amino acid symbols are supported.The prediction output consists of three items: position, score and ubiquitination site annotations (YES for ubiquitination sites, NO for non-ubiquitination sites).Additionally, graph output is also given in the result page to show all the positions of lysines of a query protein and the corresponding prediction scores.Results: A web server of CKSAAP_UbSite was constructed, which is freely available at http://protein.cau.edu.cn/cksaap_ubsite/.When intensively tested on a set of experimentally verified ubiquitination sites, the class-balanced accuracy and MCC of CKSAAP UbSite reached 73.40% and 0.4694, respectively.Conclusions: CKSAAP_UbSite can be used for proteome-wide ubiquitination site identification.Since the training dataset was selected from the proteome of S.cerevisiae, the application of CKSAAP_UbSite should be favorable in the proteome of S.cerevisiae .