NetMHCIIpan 4.0 Server
The NetMHCIIpan-4.0 server predicts peptide binding to any MHC II molecule of known sequence using Artificial Neural Networks (ANNs). It is trained on an extensive dataset of over 500.000 measurements of Binding Affinity (BA) and Eluted Ligand mass spectrometry (EL), covering the three human MHC class II isotypes HLA-DR, HLA-DQ, HLA-DP, as well as the mouse molecules (H-2). The introduction of EL data extends the number of MHC II molecules covered, since BA data covers 59 molecules and EL data covers 74. As mentioned, the network can predict for any MHC II of known sequence, which the user can specify as FASTA format. The network can predict for peptides of any length.
The output of the model is a prediction score for the likelihood of a peptide to be naturally presented by and MHC II receptor of choice. The output also includes %rank score, which normalizes prediction score by comparing to prediction of a set of random peptides. Optionally, the model also outputs BA prediction and %rank scores.
New in this version: The two output neuron architechture introduced in NetMHCIIpan-4.0 permits the inclusion of EL data, and the new training algorithm NNAlign_MA extends training data to ligands of ambiguous allele assignments. The model also, optionally, encodes ligand context.
Note: If you have downloaded the stand alone version of the tool before Maj 1, 2020, please download the data file again from data.tar.gz. The earlier file was missing a few pre-calculated files to estimate percentile rank values.
Sept 3rd, 2020, tool update to include binding core predictions in excel output, and to include option to encode context extending the protein sequence as A's (set as default option on Nov 19, 2020).
Note (19 Nov 2020): Due to a modification in the set of random natural peptides used for the calibration, the BA percentile rank scores in version 4.0 are generally half the values reported for version 3.2. That is, a BA percentile rank value of 10 with version 3.2 will be reported with a rank value of ~5 using version 4.0.
Note (24 Nov 2020): Default threshold defining strong and weak binders have been updated to 1.0% and 5% rank score values, respectively.
Note (11 Jan 2021): The motifs in the Motif viewer updated (they are now generated excluding context). The original viewer can be found here.
Refer to the instructions page for more details.
The project is a collaboration between DTU Bioinformatics, and LIAI.
View the version history of this server. All previous versions are available online, for comparison and reference.
For publication of results, please cite:
Benchmark data used to develop this server were obtained from:
NetMHCIIpan 4.0 is available
as a stand-alone software package, with the same functionality as the service
above. Ready-to-ship packages exist for Linux and MacOSX. There is a
for academic users; other users are requested to contact CBS Software Package
Manager at firstname.lastname@example.org.
Scientific problems: Technical problems: