A SVR-based prediction server for MHC-binding peptides
About SVRMHC server
    The SVRMHC server predicts peptide-MHC binding affinities using SVRMHC models. As of October 10, 2006, 36 class I SVRMHC models and 6 class II SVRMHC models are hosted here.
    Model configurations and statistics can be found here.
About SVRMHC method
    SVRMHC is a quantitative method of modeling the interaction between a peptide and a MHC molecule, based on the support vector machine regression (SVR) method.
References
  • Wan J, Liu W, Xu Q, Ren Y, Flower DR, Li T: SVRMHC prediction server for MHC-binding peptides. BMC Bioinformatics 2006, 7: 463. [PubMed] [Full-text]
  • Liu W, Wan J, Meng X, Flower DR, Li T: In silico prediction of peptide MHC binding affinity using SVRMHC. In Methods in Molecular Biology. Edited by Flower DR. Totawa, NJ: Humana Press; 2006: Immunoinformatics: predicting immunogenicity in silico (in press) ].
  • Liu W, Meng X, Xu Q, Flower DR, Li T: Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models. BMC Bioinformatics 2006, 7: 182. [PubMed] [Full-text]
    • Related Links
  • AntiJen
  • MHCPred
  • BIMAS
  • SYFPEITHI
  • RANKPEP
  • SVMHC
    		•
    		 
    Input a protein sequence (length<2048) Example
    Input a protein sequence in plain or FASTA format:
    Or select a FASTA or plain file:
    Select a class I or class II MHC molecule
    Select Class I or Class II:
    		 Select a MHC molecule:
    Set the threshold value of pIC50 or percentile score
    Threshold value of pIC50 :      Threshold value of Percentile Score: %
    Select the order for display
    Display Order: In order of occurrence in the protein
    Descendingly according to pIC50 values or percentile scores
    		 

    Send questions and comments to SVRMHC@biocompute.umn.edu.
    Copyright 2006 The University of Minnesota. All rights reserved.