Abstract
Computational prediction of discontinuous B-cell epitopes remains challenging, but it is an important task in vaccine design. In this study, we developed a novel computational method to predict discontinuous epitope residues by combining the logistic regression model with two important structural features, B-factor and relative accessible surface area (RASA). We conducted five-fold cross-validation on a representative dataset composed of antigen structures bound with antibodies and independent testing on Epitome database, respectively. Experimental results indicate that besides the well-known RASA feature, B-factor can also be used to identify discontinuous epitopes. Furthermore, these two features are complementary and their combination can remarkably improve the prediction performance. Comparison with existing approaches shows that our method can achieve better performance in terms of average AUC value and sensitivity for predicting discontinuous B-cell epitopes.
Highlights
B-cell epitopes are special regions of antigens recognized by the binding sites of immunoglobulin molecules (Van Regenmortel, 1993)
By conducting fivefold cross-validation on a representative dataset collected by Haste Andersen et al (2006) and independent testing on Epitome database (Schlessinger et al, 2006), we found that in addition to the widely used relative accessible surface area (RASA) feature, B-factor can be utilized to recognize epitope residues and the complementarity of these two features is useful to improve the prediction performance
The differences of RASA values of 18 residue types are statistically significant, confirming that epitope residues are more exposed to facilitate their contact with antibodies (Novotny et al, 1986)
Summary
B-cell epitopes are special regions of antigens recognized by the binding sites of immunoglobulin molecules (Van Regenmortel, 1993). Rubinstein et al (2009) developed a naïve Bayesian method based on a large number of physico-chemical and structural-geometrical properties to recognize B-cell epitopes at a patch level. Liang et al (2009) proposed a consensus scoring method to identify the antigenic epitopes based on the unbound antigen structures. These prediction methods have achieved success at different levels, computational identification of discontinuous B-cell epitopes is still far from being resolved
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
