Support vector-based fuzzy system for the prediction of mouse class I MHC peptide binding affinity

The performance of predictive models is crucial in order to accurately determine peptide binding affinity for major histocompatibility complex (MHC) alleles. Data sets extracted to model the relationship between the peptides and their binding affinities are often high-dimensional, complex and non-linear, which require highly sophisticated computational predictive models. Support Vector Machine (SVM)-based predictive methods have been used for such problems and have been shown to deal with such high dimensional data, however failed to take into account of uncertainty that naturally exists in this type of data. In order to address to the uncertainty issue, Fuzzy System (FS) has generally been utilised in various applications. Therefore, a hybrid method that combines FS and SVM is proposed in this study for the prediction of binding affinity of peptides in mouse class I MHC alleles. The hybrid system is successfully applied to two benchmark data sets of class I MHC peptides, each of which contains over 5000 peptide features. The assessments yield as much as 17% improvement over the previous studies that also include SVM-based experiments. The results also suggest positive impact of the concept of fuzziness on SVM-based predictive methods when combined and that the hybrid model can be generalised for similar non-linear system modelling problems.