Analysis of peptide-protein binding using amino acid descriptors: prediction and experimental verification for human histocompatibility complex HLA-A*0201

Amino acid descriptors are often used in quantitative structure−activity relationship (QSAR) analysis of proteins and peptides. In the present study, descriptors were used to characterize peptides binding to the human MHC allele HLA-A*0201. Two sets of amino acid descriptors were chosen:  93 descriptors taken from the amino acid descriptor database AAindex and the z descriptors defined by Wold and Sandberg. Variable selection techniques (SIMCA, genetic algorithm, and GOLPE) were applied to remove redundant descriptors. Our results indicate that QSAR models generated using five z descriptors had the highest predictivity and explained variance (q2 between 0.6 and 0.7 and r2 between 0.6 and 0.9). Further to the QSAR analysis, 15 peptides were synthesized and tested using a T2 stabilization assay. All peptides bound to HLA-A*0201 well, and four peptides were identified as high-affinity binders