Prediction

Introduction

Method

Performance

Query

About the CKSAAP_OGlySite

CKSAAP_OGlySite has been developed to predict mucin-type O-glycosylation serine/threonine (S/T) sites in proteins by using a new encoding scheme named CKSAAP. With the assistance of Support Vector Machine (SVM)(http://svmlight.joachims.org/), the predictor was trained and tested in a new and stringent O-glycosylation site dataset.

The proposed CKSAAP_OGlySite has been proved to be more powerful than the binary encoding based method as well as two existing predictors, suggesting it can serve as a competitive method in predicting mucin-type O-glycosylation sites.

Usage

The input is a single-letter AA code sequence in FASTA format without the FASTA header, the email address is required since the result will be sent to it. A session ID will be generated when you submit a sequence, and you can query the result through this ID when the processing is ready. The result page consists of position, residue name, prediction score and glycosylation annotations (yes or no). A higher absolute value of prediction score implies a more confident prediction. Additionally, graph output is also given in the result page to show all the positions of serine and threonine of a query protein and the corresponding prediction score.

Datasets and source code

Available under request from Yong-Zi CHEN.

Reference

Yong-Zi Chen, Yu-Rong Tang, Zhi-Ya Sheng, Ziding Zhang Prediction of mucin-type O-glycosylation sites in mammalian proteins using the composition of k-spaced amino acid pairs. BMC Bioinformatics 2008, 9:101

Copyright

This server is free available to any user, but without any warranty.