BCPREDS(B-cell epitope prediction server) is offered by Artificial Intelligence Research Laboratory, College of Information Science and Technology, Penn state University.
Because consensus predictions are often more reliable than individual predictions, BCPREDS allows users to select among three prediction mrthods: AAP, BCPred and FBCPred. Users need to provide an antigen sequence and epitope length and specificity threshold can be specified.
To run BCPREDS and get more information, please click here.
AAP
Amino acid pair (AAP) antigenicity scale is based on the finding that B-cell epitopes favor particular AAPs. It has been demonstrated that, using SVM (support vector machine) classifier, the AAP antigenicity scale approach performs much better than the existing scales based on the single amino acid propensity. The AAP antigenicity scale can reflect some special sequence-coupled feature in the B-cell epitopes, which is the essence why the new approach is superior to the existing ones. It is anticipated that the power of the AAP antigenicity scale approach will be further enhanced with the continuous increase of the known epitope data.
BCPred
BCPred is a method for predicting linear B-cell epitopes using the subsequence kernel. The predictive performance of BCPred (AUC = 0.758) outperforms 11 SVM-based classifiers developed and evaluated in authors’ experiments as well as their implementation of AAP (AUC = 0.7).What calls for special attention is that using data sets of unique B-cell epitopes are likely to yield overly optimistic estimates of performance of evaluated methods. So users may need to carefully reduce the same-origin data set
FBCPred
FBCPred is a method for predicting flexible length linear B-cell epitopes using the subsequence kernel. It is demonstrated that performance of the subsequence kernel based SVM classifier is superior to other SVM classifiers examined.
To get BCPred or FBCPred datasets, click here.
Citation:
Chen J, Liu H, Yang J, Chou K (2007) Prediction of linear B-cell epitopes using amino acid pair antigenicity scale. Amino Acids 33: 423-428.
EL-Manzalawy Y, Dobbs D, Honavar V (2008) Predicting linear B-cell epitopes using string kernels. J Mol Recognit 21: 243-255
EL-Manzalawy Y, Dobbs D, Honavar V (2008) Predicting flexible length linear B-cell epitopes. 7th International Conference on Computational Systems Bioinformatics, Stanford, CA. pp. 121-131