NetMHCpan 4.0 Server
Prediction of peptide-MHC class I binding using artificial neural networks (ANNs).
New in this version: the method is trained on naturally eluted ligands AND on binding affinity data.
It returns two properties: likelihood of a peptide becoming a natural ligands, and predicted binding affinity.
View the version history of this server.
All previous versions are available online, for comparison and
NetMHCpan server predicts binding of peptides to any MHC molecule of known sequence using artificial neural networks
(ANNs). The method is trained on a combinatino of more than 180,000 quantitative binding data and MS derived MHC eluted ligands. The binding affinity data covers 172 MHC molecules from human (HLA-A, B, C, E),
mouse (H-2), cattle (BoLA), primates (Patr, Mamu, Gogo) and swine (SLA). The MS eluted ligand data covers 55 HLA and mouse allelee.
The binding motifs displayed here are calculated from the top 0.1% (EL) and top 1% (BA) predicted
binder from a pool of 1,000,000 random natural 9mer peptides. The difference in
the samplede peptide space is chosen to reflect the difference in the
volumen of the space of naturally presented ligands (0.1%) and MHC binders (1%).
The project is a collaboration between CBS, ISIM, and LIAI.