Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models

Abstract

Background: The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.

Results: We developed a quantitative support vector machine regression (SVR) approach, called SVRMHC, to model peptide-MHC binding affinities. As a non-linear method, SVRMHC was able to generate models that out-performed existing linear models, such as the "additive method". By adopting a new "11-factor encoding" scheme, SVRMHC takes into account similarities in the physicochemical properties of the amino acids constituting the input peptides. When applied to MHC-peptide binding data for three mouse class I MHC alleles, the SVRMHC models produced more accurate predictions than those produced previously. Furthermore, comparisons based on Receiver Operating Characteristic (ROC) analysis indicated that SVRMHC was able to out-perform several prominent methods in identifying strongly binding peptides.

Conclusion: As a method with demonstrated performance in the quantitative modeling of MHC-peptide binding and in identifying strong binders, SVRMHC is a promising immunoinformatics tool with not inconsiderable future potential.

Figure 1

A schematic diagram of the five-fold cross-validation scheme for the training and testing of the SVRMHC model constructed for H2-Kk (154 peptides), with enclosing parameter searching modules in which leave-one-out (LOO) cross-validation was used. The models for the other two datasets (for H2-Db and H2-Kb) were constructed similarly, with the exception that the computationally more expensive LOO cross-validation (rather than five-fold cross-validation) was used on the outer-loop model training and testing procedure.

Figure 2

Comparison of the six predicting methods – SVRMHC, additive, SYFPEITHI, BIMAS, RANKPEP and SVMHC by ROC analysis (for H2-Db and H2-Dk). The ROC curves of different predicting methods are plotted in different colors. A_ROC (area underneath the ROC curve) is provided following the label of each predicting method.