The B cell prediction tools can be found at http://tools.immuneepitope.org/main/html/bcell_tools.html.
Prediction of linear epitopes from protein sequence
Six different tools are provided that predict antibody epitope candidates from amino acid sequences. Five are based on amino acid property scales and a sixth method uses a Hidden Markov Model. Parameters such as hydrophilicity, flexibility, accessibility, and antigenic propensity of polypeptides chains have been correlated with the location of continuous epitopes in a few well-characterized proteins. Based on these observations, amino acid property scales have been developed to predict antigenic determinants. Each scale consists of 20 values assigned to each of the amino acid residues on the basis of their relative propensity to possess the property described by the scale. The following amino acid property scales have been selected and implemented based on their popularity and coverage of different categories.
- Secondary structure - Chou and Fasman beta turn prediction
- Surface exposure - Emini surface accessibility prediction
- Flexibility - Karplus and Schulz flexibility prediction
- Antigenicity - Kolaskar and Tongaonkar antigenicity prediction
- Hydrophobicity/hydrophilicity - Parker hydrophilicity prediction
BepiPred combines the predictions of a hidden Markov model and the propensity scale of Parker et al. It is described in Larsen et al. (Immunome Research, 2006).
DiscoTope - Prediction of epitopes from protein structure
DiscoTope is designed specifically to predict discontinuous epitopes. It uses protein three-dimensional structuraldata in addition sequence data. The method is based on amino acid statistics, spatialinformation, and surface accessibility in a compiled data setof discontinuous epitopes determined by X-ray crystallographyof antibody/antigen protein complexes. The method is described in Haste Andersen et al. (Protein Sci., 2006).
ElliPro - Epitope prediction based upon structural protrusion
ElliPro predicts linear and discontinuous antibody epitopes based on a protein antigen's 3D structure. ElliPro accepts either a protein structure (preferred) or a protein sequence as an input. If a protein sequence is used, ElliPro will predict its 3D structure by homology modeling. Its use if described in the Tutorial tab of the ElliPro section of the Analysis Resource. The method is described in Julia Ponomarenko et al. (BMC Bioinformatics, 2008).
Article is closed for comments.