In Silico Prediction of Peptide-MHC Binding Affinity Using SVRMHC

Wen Liu, Ji Wan, Xiangshan Meng, Darren R. Flower, Tongbin Li

Methods in molecular biology · 2007 · 13 citations · 22 references

Concepts

Abstract

The binding between peptide epitopes and major histocompatibility complex (MHC) proteins is a major event in the cellular immune response. Accurate prediction of the binding between short peptides and class I or class II MHC molecules is an important task in immunoinformatics. SVRMHC which is a novel method to model peptide-MHC binding affinities based on support rector machine regression (SVR) is described in this chapter. SVRMHC is among a small handful of quantitative modeling methods that make predictions about precise binding affinities between a peptide and an MHC molecule. As a kernel-based learning method, SVRMHC has rendered models with demonstrated appealing performance in the practice of modeling peptide-MHC binding.

References

22