About

About
KinasePhos 3.0

In 2005, our group developed KinasePhos 1.0 for identifying protein kinase-specific phosphorylation sites. The tool constructed models from the kinase-specific groups of the phosphorylation sites based on the profile hidden Markov model (HMM). Then, support vector machines (SVM) with the protein sequence profile and protein coupling pattern was applied to update the tool to Kinasephos 2.0. Due to the rapid development of phosphorylation-related research, the datasets used for training are constantly expanding. As an expansion of KinasePhos 1.0 and 2.0, in this study, we introduce KinasePhos 3.0 to improve the performance of kinase-specific phosphorylation site prediction. Experimentally verified kinase-specific phosphorylation data were collected from PhosphoSitePlus, UniProt, GPS5.0, and Phospho.ELM. In total, 41,421 experimentally verified kinase-specific phosphorylation sites and 1,380 unique kinases were identified, including 753 kinases with known classification information based on KinBase and the other 627 kinases annotated by building an evolutionary tree. Based on this kinase classification, 771 machine learning-based kinase-specific phosphorylation site prediction models were built at kinase group, kinase family, and individual kinase levels, with at least 15 experimentally verified substrate sites considered in each model.

KinasePhos 1.0

KinasePhos is a novel web server for computationally identifying catalytic kinase-specific phosphorylation sites. The known phosphorylation sites from public domain data sources are categorized by their annotated protein kinases. Based on the profile hidden Markov model, computational models are learned from the kinase-specific groups of the phosphorylation sites. After evaluating the learned models, the model with highest accuracy was selected from each kinase-specific group, for use in a web-based prediction tool for identifying protein phosphorylation sites. Therefore, this work developed a kinase-specific phosphorylation site prediction tool with both high sensitivity and specificity. The prediction tool is freely available at http://KinasePhos.mbc.nctu.edu.tw/.

KinasePhos 2.0

Due to the importance of protein phosphorylation in cellular control, many researches are undertaken to predict the kinase-specific phosphorylation sites. Referred to our previous work, KinasePhos 1.0, incorporated profile hidden Markov model (HMM) with flanking residues of the kinase-specific phosphorylation sites. Herein, a new web server, KinasePhos 2.0, incorporates support vector machines (SVM) with the protein sequence profile and protein coupling pattern, which is a novel feature used for identifying phosphorylation sites. The coupling pattern [XdZ] denotes the amino acid coupling-pattern of amino acid types X and Z that are separated by d amino acids. The differences or quotients of coupling strength CXdZ between the positive set of phosphorylation sites and the background set of whole protein sequences from Swiss-Prot are computed to determine the number of coupling patterns for training SVM models. After the evaluation based on k-fold cross-validation and Jackknife cross-validation, the average predictive accuracy of phosphorylated serine, threonine, tyrosine and histidine are 90, 93, 88 and 93%, respectively. KinasePhos 2.0 performs better than other tools previously developed. The proposed web server is freely available at http://KinasePhos2.mbc.nctu.edu.tw/.

KinasePhos 3.0

The tool constructed models from the kinase-specific groups of the phosphorylation sites based on the profile hidden Markov model (HMM). Then, support vector machines (SVM) with the protein sequence profile and protein coupling pattern was applied to update the tool to Kinasephos 2.0. Due to the rapid development of phosphorylation-related research, the datasets used for training are constantly expanding. As an expansion of KinasePhos 1.0 and 2.0, in this study, we introduce KinasePhos 3.0 to improve the performance of kinase-specific phosphorylation site prediction. Experimentally verified kinase-specific phosphorylation data were collected from PhosphoSitePlus, UniProt, GPS5.0, and Phospho.ELM. In total, 41,421 experimentally verified kinase-specific phosphorylation sites and 1,380 unique kinases were identified, including 753 kinases with known classification information based on KinBase and the other 627 kinases annotated by building an evolutionary tree. Based on this kinase classification, 771 machine learning-based kinase-specific phosphorylation site prediction models were built at kinase group, kinase family, and individual kinase levels, with at least 15 experimentally verified substrate sites considered in each model.

History of KinasePhos

Nam vestibulum massa a felis varius, et euismod lacus iaculis. Morbi sit amet turpis posuere, bibendum velit bibendum, dapibus quam. Curabitur non diam at velit pellentesque sollicitudin in sed velit. Vestibulum scelerisque velit massa, eget dictum sem euismod ac.

All Rights Reserved © CUHKsz 2021 - KinasePhos 3.0