Major Histocompatibility Complex Class II Prediction

Major Histocompatibility complex (MHC) molecules play an essential role in introducing and regulation immune system. The MHC molecules are divided into two classes, class I and class II which are differ in size of their binding pockets. Determining which peptides bind to a specific MHC molecule is fundamental to understanding the basis of immunity, and for the development of vaccines and immunotherapeutic for autoimmune diseases and cancer. Due to the variability of the locations of the class II binding cores, the process for predicting the affinity of these peptides is difficult.This paper investigates a new method for predicting peptides binding to MHC class II molecules and its affinity using genetic algorithms and metaheuristics. The algorithm is based on a fitness function that builds a scoring matrix for all suggested motifs in a specific iteration to test the motif ability to be one of the real motifs in the nature. The genetic algorithmpresented here shows increased prediction accuracy with higher number of true positives and negatives on almost of MHC class II alleles,about 80 percent of peptides were correctly classified when testing dataset from IEDB[26]. Generally, these results indicate that GA has a strong ability for MHC Class II binding prediction.