الفهرس Only 14 pages are availabe for public view
 |  | from | 113 |  |  |
| | | from | 113 | | |
Abstract
Vaccination is considered one of the most important achievements regarding public health interventions. Immunoinformatics researchers believe that computational methods will help overcome the limitations of the traditional vaccine design methods. One of the main stages in a successful subunit vaccine design process is the accurate prediction of the B- cell and T- cell epitopes. In our thesis, we will propose different algorithms for prediction of different types of epitopes. Accurate discrimination between epitopes does not only rely on the classification tool used but also on the data involved in building a model. Many parameters must be optimized in the data, features and prediction models choice before performance evaluation. Therefore, we addressed all these parameters for each epitope prediction scenario. Different databases are searched and informative features are selected after extraction to form datasets used by different proposed prediction and classification algorithms