The NetMHCpan-4.1 server predicts binding of peptides to any MHC molecule of known sequence using artificial neural networks (ANNs). The method is trained on a combination of more than 850,000 quantitative Binding Affinity (BA) and Mass-Spectrometry Eluted Ligands (EL) peptides. The BA data covers 201 MHC molecules from human (HLA-A, B, C, E), mouse (H-2), cattle (BoLA), primates (Patr, Mamu, Gogo), swine (SLA) and equine (Eqca). The EL data covers 289 MHC molecules from human (HLA-A, B, C, E), mouse (H-2), cattle (BoLA), primates (Patr, Mamu, Gogo), swine (SLA), equine (Eqca) and dog (DLA). Furthermore, the user can obtain predictions to any custom MHC class I molecule by uploading a full length MHC protein sequence. Predictions can be made for peptides of any length.
The server returns as default the likelihood of a peptide being a natural ligand of the selected MHC(s). If selected, also the predicted binding affinity is rseported.
New in this version: together with Binding Affinity (BA) data, the method has now been trained on EL data from Single Allele (SA, peptides annotated to a single MHC) and Multi Allele (MA, peptides annotated to multiple MHCs) sources. The use of EL MA data is possible due to an upgrade af NNAlign (the core algorithm of NetMHCpan) called NNALign_MA (PMID: 31578220), which enables pseudo-labelling.
View the version history of this server. All previous versions are available online, for comparison and reference.
The project is a collaboration between DTU Bioinformatics, and LIAI.
For publication of results, please cite:
Data resources used to develop this server was obtained from
Would you prefer to run NetMHCpan at your own site? NetMHCpan v. 4.1
is available as a stand-alone software package, with the same
functionality as the service above. Ready-to-ship packages
exist for the most common UNIX platforms. There is a
for academic users; other users are requested to contact
CBS Software Package Manager at
Scientific problems: Technical problems: