Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)
Jianhong Zhou
Jianhong Zhou
Search for other works by this author on:
No. of Pages:
ASME Press
Publication date:

Identification of major histocompatibility complex (MHC) class-II restricted peptides is an important goal in human immunological research. These peptides are predominantly recognized by CD4+ T-helper cells, which when turned on, have profound immune regulatory effects. Thus, classification of such MHC class-II binding peptide is very helpful towards epitope based vaccine designing. It is important for the treatment of autoimmune diseases to determine which peptides bind to MHC class II molecules. The experimental methods for identification of these peptides are both time consuming and cost intensive. Therefore, computational methods have been found useful in classifying these peptides as binders or non-binders. The classification using learning requires the sufficient amount of data for training. Limited number of known MHC class — II binders and non-binders is not sufficient for training. Here, we have studied negative selection algorithm, an artificial immune system approach to classify limited number of HLA-DRB1*0401 9-mer binders and 9-mer non-binders. For the evaluation of the algorithm, five fold cross validation has been used. The area under ROC curve was found to be 0.788, 0.762, 0.749, 0.773, and 0.755 indicating good predictive performance as in most of the cases it is nearly equal to 0.8.

Key Words
1 Introduction
2. Methods and Materials
3. Training and Validation Data Set
4. Evaluation Parameters
5. Results and Discussion
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal