MHC-NP: predicting peptides naturally processed by the MHC

J Immunol Methods. 2013 Dec 31:400-401:30-6. doi: 10.1016/j.jim.2013.10.003. Epub 2013 Oct 18.


We present MHC-NP, a tool for predicting peptides naturally processed by the MHC pathway. The method was part of the 2nd Machine Learning Competition in Immunology and yielded state-of-the-art accuracy for the prediction of peptides eluted from human HLA-A*02:01, HLA-B*07:02, HLA-B*35:01, HLA-B*44:03, HLA-B*53:01, HLA-B*57:01 and mouse H2-D(b) and H2-K(b) MHC molecules. We briefly explain the theory and motivations that have led to developing this tool. General applicability in the field of immunology and specifically epitope-based vaccine are expected. Our tool is freely available online and hosted by the Immune Epitope Database at

Keywords: Epitope; Immunology; Kernel; MHC; Machine learning; Vaccinology.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Animals
  • Antigen Presentation
  • Artificial Intelligence*
  • Epitope Mapping / methods*
  • H-2 Antigens / chemistry
  • H-2 Antigens / immunology
  • HLA-A2 Antigen / chemistry
  • HLA-A2 Antigen / immunology
  • HLA-B Antigens / chemistry
  • HLA-B Antigens / immunology
  • Histocompatibility Antigen H-2D / chemistry
  • Histocompatibility Antigen H-2D / immunology
  • Humans
  • Major Histocompatibility Complex / immunology*
  • Mice
  • Peptides / chemistry*
  • Peptides / immunology
  • Protein Binding
  • Software*
  • Vaccines


  • H-2 Antigens
  • H-2Kb protein, mouse
  • HLA-A*02:01 antigen
  • HLA-A2 Antigen
  • HLA-B Antigens
  • Histocompatibility Antigen H-2D
  • Peptides
  • Vaccines