期刊名称：International Journal of Computational Intelligence Techniques
印刷版ISSN：0976-0466
电子版ISSN：0976-0474
出版年度：2011
期号：569
页码：22-25
出版社：Bioinfo Publications
摘要：Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatics method for the prediction of peptide binding to T-cell molecules. The major T-cell contributors are selected for the dataset preparation due to its availability and originality. We used a profile hidden Markov Model (HMM) for the prediction. Sensitivity (96%) and Specificity (~100%) are evaluated for the T cells epitope and nonepitopes from the test data set. The method promises 98 % accuracy and useful for vaccine development.
