Limits...
Conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis.

Sun P, Ju H, Zhang B, Gu Y, Liu B, Huang Y, Zhang H, Li Y - Biomed Res Int (2015)

Bottom Line: The proposed method gives out the mean F score of 0.42 on the testing dataset.When compared with other publicly available servers by using the testing dataset, the new method yields better performance.The results demonstrate the proposed method is competent for the conformational B-cell epitope prediction.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Information Technology, Northeast Normal University, Changchun 130117, China ; National Engineering Laboratory for Druggable Gene and Protein Screening, Northeast Normal University, Changchun 130024, China ; Key Laboratory of Intelligent Information Processing of Jilin Universities, Northeast Normal University, Changchun 130117, China.

ABSTRACT
Identification of epitopes which invokes strong humoral responses is an essential issue in the field of immunology. Various computational methods that have been developed based on the antigen structures and the mimotopes these years narrow the search for experimental validation. These methods can be divided into two categories: antigen structure-based methods and mimotope-based methods. Though new methods of the two kinds have been proposed in these years, they cannot maintain a high degree of satisfaction in various circumstances. In this paper, we proposed a new conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis. The method classifies the antigen surface residues into "epitopes" and "nonepitopes" by six epitope propensity scales, removing the "nonepitopes" and using the preprocessed antigen for epitope prediction based on mimotope sequences. The proposed method gives out the mean F score of 0.42 on the testing dataset. When compared with other publicly available servers by using the testing dataset, the new method yields better performance. The results demonstrate the proposed method is competent for the conformational B-cell epitope prediction.

Show MeSH
Sensitivity versus 1− specificity scores of the method on testing dataset.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4326220&req=5

fig2: Sensitivity versus 1− specificity scores of the method on testing dataset.

Mentions: Further, we draw Figure 2 to give directly relations between sensitivity and 1− specificity of this method. From Figure 2, we can see that for most test cases this method can precisely localize epitope regions. The predicted results of the method are totally better than random prediction. For 3BT1 and 2HYM, the two points on the x-axis, the method displayed no predictive ability. The main reason is that the second step of the method predicts no epitope residues according to mapping the mimotopes to the surface of the antigen.


Conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis.

Sun P, Ju H, Zhang B, Gu Y, Liu B, Huang Y, Zhang H, Li Y - Biomed Res Int (2015)

Sensitivity versus 1− specificity scores of the method on testing dataset.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4326220&req=5

fig2: Sensitivity versus 1− specificity scores of the method on testing dataset.
Mentions: Further, we draw Figure 2 to give directly relations between sensitivity and 1− specificity of this method. From Figure 2, we can see that for most test cases this method can precisely localize epitope regions. The predicted results of the method are totally better than random prediction. For 3BT1 and 2HYM, the two points on the x-axis, the method displayed no predictive ability. The main reason is that the second step of the method predicts no epitope residues according to mapping the mimotopes to the surface of the antigen.

Bottom Line: The proposed method gives out the mean F score of 0.42 on the testing dataset.When compared with other publicly available servers by using the testing dataset, the new method yields better performance.The results demonstrate the proposed method is competent for the conformational B-cell epitope prediction.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Information Technology, Northeast Normal University, Changchun 130117, China ; National Engineering Laboratory for Druggable Gene and Protein Screening, Northeast Normal University, Changchun 130024, China ; Key Laboratory of Intelligent Information Processing of Jilin Universities, Northeast Normal University, Changchun 130117, China.

ABSTRACT
Identification of epitopes which invokes strong humoral responses is an essential issue in the field of immunology. Various computational methods that have been developed based on the antigen structures and the mimotopes these years narrow the search for experimental validation. These methods can be divided into two categories: antigen structure-based methods and mimotope-based methods. Though new methods of the two kinds have been proposed in these years, they cannot maintain a high degree of satisfaction in various circumstances. In this paper, we proposed a new conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis. The method classifies the antigen surface residues into "epitopes" and "nonepitopes" by six epitope propensity scales, removing the "nonepitopes" and using the preprocessed antigen for epitope prediction based on mimotope sequences. The proposed method gives out the mean F score of 0.42 on the testing dataset. When compared with other publicly available servers by using the testing dataset, the new method yields better performance. The results demonstrate the proposed method is competent for the conformational B-cell epitope prediction.

Show MeSH