1 - 23 of 23 results


Provides users a support vector machines (SVM) prediction model using Bayes Feature Extraction (BFE) to predict linear B-cell epitopes of diverse lengths (12- to 20-mers). Bayesb is based on the report that linear B-cell epitopes and non-epitope sequences have distinctive residue composition and position-specific propensity patterns which could be used for epitope discrimination in silico. It aims to discriminating epitopes from non-epitopes in benchmark datasets and annotated antigenic proteins.

BEST / Bcell Epitope prediction using Support vector machine Tool

Predicts epitopes from full protein chains using an approach based on averaging selected scores generated from 20-mers by a support vector machine (SVM)-based predictor. BEST uses a sliding window to represent the input antigen chain as a set of 20-mers. It then combines predictions from the SVM using a custom-designed scheme that outputs the propensity of each amino acid (AA) to form of a B-cell epitope. This tool outperforms several modern sequence-based B-cell epitope predictors.

EpIC / a rational pipeline for Epitope Immunogenicity Characterization

Allows the user to easily, quickly, and accurately increase the immunogenicity of peptide epitopes through selective inclusion of endogenous B-cell epitopes that exist within the target protein sequence near the epitope of interest. EpIC identifies the optimal iteration of your target peptide antigen through sequential single amino acid-based expansion of your peptide sequence and analysis of the resulting antigen using the BepiPred program.


Determines linear B-cell epitopes in hepatitis C virus (HCV). Bcell-HCV is a web server that can deal with the amino acid sequences of HCV antigens. It returns the identified B-cell epitopes with location information and their prediction scores. This application is implemented using a carrier-based vector machine (SVM) with 34 informative physico-chemical properties which enables accurate identification of epitopes of HCV B cells to assist in peptide-based vaccine development.


Uses a voting algorithm for combining the predictions of two classifiers, a Gaussian Naïve Bayes and a Random Forest classifier. SEPIa is a conformational epitope prediction method that requires only the amino acid sequence as input and is based on commonly used features, but also on new ones. It utilizes a metalearning approach, which combines the predictions obtained with two different classifiers through a voting procedure and yields a single prediction with improved accuracy.


Predicts the location of linear B-cell epitopes using a combination of a hidden Markov model (HMM) and a propensity scale method. BepiPred is a web server constructed from a large set of structurally defined B cell epitopes. The interface can aid researchers with limited computational knowledge to use and understand the results to their full extent. Additionally, the advanced option allows more experienced researchers to further interpret the output based on additionally predicted structural features.

BEOracle / B-Cell Epitope Oracle

Provides support vector machine (SVM) classifier models. The BROracle classifier utilizes BEOracle scores as features and therefore predicts using the information from local features only. The BEOracle was trained for the identification of continuous B-Cell epitopes with these protein properties as learning features. The BEOracle classifier outperformed the classical methods based on propensity and sophisticated methods like BCPred and Bepipred for B-Cell epitope prediction. The BEOracle classifier also identified peptides for the ChIP-grade antibodies from the modENCODE/ENCODE projects with 96.88% accuracy. High BEOracle score for peptides showed some correlation with the antibody intensity on Immunofluorescence studies done on fly embryos. Furthermore, BROracle was trained with the BEOracle scores as features to predict the performance of antibodies generated with large protein regions with high accuracy. The BROracle classifier achieved accuracies of 75.26-63.88% on a validation set with immunofluorescence, immunohistochemistry, protein arrays and western blot results from Protein Atlas database.


Finds the location of antigenic regions like epitopes on proteins. PREDITOP incorporates more than 20 normalized scales matching to hydrophilicity, accessibility, flexibility, or secondary structure propensities and new scales can be added. This tool owns a hydrophobic moment procedure to define amphiphilic helices. Results can be visualized via a simple graphical super-imposition and a result file can be produced to represent a physicochemical aspect of the studied protein.