Services are gradually being migrated to
In the near future, will be retired. Please try out the new site.

NetMHCpan 3.0 Server

Prediction of peptide-MHC class I binding using artificial neural networks (ANNs).

View the version history of this server. All previous versions are available online, for comparison and reference.

NetMHCpan server predicts binding of peptides to any MHC molecule of known sequence using artificial neural networks (ANNs). The method is trained on more than 180,000 quantitative binding data covering 172 MHC molecules from human (HLA-A, B, C, E), mouse (H-2), cattle (BoLA), primates (Patr, Mamu, Gogo) and swine (SLA). Furthermore, the user can obtain binding predictions to the any custom MHC class I molecule by uploading a full length MHC protein sequence.

Version 3.0 has been retrained on an extented data set of 8-13mer peptides using the method described in this paper

Predictions can be made for peptides of any length.
Note that most HLA molecules have a strong preference for binding 9mers.

Link to table (tab seperated) describing the training data Training data table

The project is a collaboration between CBS, ISIM, and LIAI.

< BACK Instructions Output format Sequence motifs Article abstract


Select species/loci

Select Allele

For publication of results, please cite:


Scientific problems:        Technical problems: