Prediction of immunogenic peptides derived from FVIII by machine learning approach

Various factors are involved in the development of an immune response to factor eight (FVIII) in hemophiliapatients, among which T cell epitopes (factor eight-derived peptides) play the most important role. Mutationsin T cell epitopes while maintaining the structure of factor eight can be a good solution to this unwantedimmune response. The need for this research is due to the fact that Treatment of patients in whose bodyexogenous factor eight exhibits an immune response (inhibitor patients) It is much more difficult thanhemophiliacs who do not have this problem. Also, the treatment methods and strategies that exist today havea lot of costs and complications which are not very successful. In this study, we build a model using machinelearning algorithms to predict the immunogenicity of immunogenic peptide sequences. We first usedcompositional features to predict the peptides that bind to class II molecules of the Major HistocompatibilityComplex (MHCII). Including: AAC, APAAC, CKSAAGP, CTDC, CTDT, DPC, GDPC and PAAC. Wethen evaluated these features with some classifiers such as Random Forrest, Support Vector Machine,Decision Tree, Naive Bayes Classifier, XGBoost, and Perceptron, and the accuracy for each of theseclassifiers was, ۰.۶۲,۰.۵۱,۰.۳۵,۰.۵۴,۰.۵۸,۰.۶۶ respectively. In the next step some of the best features wereselected. The accuracy of the classifiers including Random Forest (۰.۵۱), Support Vector Machine (۰.۵۹),Decision Tree (۰.۴۴), Naive Bayes (۰.۵۸), XGBoost (۰.۵۱) and Perceptron (۰.۴۶) were not good enough. Thedata that used in this method cover all types of human HLA-DR. Also, the features used were the most upto-date features related to peptide-MHCII Binding. We hope to achieve higher accuracy by enhancing them.

کلیدواژه ها:

T cell epitopes ، immunogenic peptides ، prediction ، machine learning ، FVIII