EPSVR: Antigenic Epitopes Prediction with Support Vector Regression
(Academic use only)
Currently, the server is very busy, and the computing time for one protein structure could be more than one hour. If you have 100 structures, it might take more than one week to get results. And, maybe, you cannot get any results at all, becuase the server will delete job from the queues if those jobs stay in the queue for a long time, such as one day.
Usage:
give us the unbounded structure either by inputing a PDB ID or by uploading a file. For the chain ID, one can input one or more letters. If leave it blank, all chains in the given PDB file will be considered.
Output: The output will be displayed by a web page. The output includes (1)
the predicted antigene residues; (2) the color marked PDB file. If one display the PDB
file as the B factor color, the residues are colored from red to blue according to the predicted possibility to be an epitope residue.
Download: Please download the training set and test set here:
Training Set
and
Test Set
Citation: S. Liang, D. Zheng, D.M. Standley, B. Yao, M. Zacharias, C. Zhang. EPSVR and EPMeta: prediction of antigenic epitopes using support vector regression and multiple server results. BMC Bioinformatics (2010); 11:381.
This project has been supported by funding under the Sixth Research Framework Programme of the European Union (ref. LSHB-CT-2006-037325)
Please address questions or comments to m.zacharias@jacobs-university.de
or czhang5@unl.edu .
Copyright (C) 2010