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
The PPV of each method on the testing dataset.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4326220&req=5

fig4: The PPV of each method on the testing dataset.

Mentions: In recent years, there are several mimotope-based methods that have been proposed to predict conformational B-cell epitopes. In this work, we compared the new method with three other available mimotope-based conformational B-cell epitope prediction methods: PepSurf, EpiSearch, and Pep-3D-Search. These methods were tested in April of 2014, and the default parameters were adopted for each method. Figures 3, 4, 5, and 6 give the sensitivity, PPV, ACC, and F of each method on the testing dataset. 1ZTX, 1JRH, and 1WLP have no prediction results by EpiSearch due to the restriction of the method that the number of mimotope sequences cannot be larger than 30.


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)

The PPV of each method on the testing dataset.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

fig4: The PPV of each method on the testing dataset.
Mentions: In recent years, there are several mimotope-based methods that have been proposed to predict conformational B-cell epitopes. In this work, we compared the new method with three other available mimotope-based conformational B-cell epitope prediction methods: PepSurf, EpiSearch, and Pep-3D-Search. These methods were tested in April of 2014, and the default parameters were adopted for each method. Figures 3, 4, 5, and 6 give the sensitivity, PPV, ACC, and F of each method on the testing dataset. 1ZTX, 1JRH, and 1WLP have no prediction results by EpiSearch due to the restriction of the method that the number of mimotope sequences cannot be larger than 30.

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