• Improved algorithm implementing insertions and deletions in the alignment.
• Sequence logos for all alleles in the NetMHC library.
• New output format including Rank scores.
• Addition of predictors for several additional alleles.

Publication:

• Gapped sequence alignment using artificial neural networks: application to the MHC class I system.
  Andreatta M, Nielsen M.
  Bioinformatics (2015) - In press

• Retrained on an extented data set covering more than 140 MHC molecules

• Addition of Artificial Neural Network predictors for several additional alleles.
• Average of approximation and directly trained 10mer predictions were applicable.
• Removal of matrix predictions (Obsolete! Use NetMHCpan).

• Addition of Artificial Neural Network predictors for several additional alleles.
• Option for 8-, 10-, and 11-mer predictions
• Additional linked output in tab-seperated text format for open in spreadsheets

Publications:

• Accurate approximation method for prediction of class I MHC affinities for peptides of length 8, 10 and 11 using prediction tools trained on 9mers.
  Lundegaard C, Lund O, Nielsen M.
  Bioinformatics, 24(11):1397-98, 2008.

  View the abstract.

• NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8-11 Lundegaard C, Lamberth K, Harndahl M, Buus S, Lund O, Nielsen M.
  Nucleic Acids Res. 1;36(Web Server issue):W509-12. 2008

  View the abstract.

• Addition of Artificial Neural Network predictors for several additional alleles.
• Selection of optimal predictors for alleles where both Neural networks and Matrix predictors exists.
• Removal of Matrix predictors for alleles for which Neural Network predictors exist.
• Update of Web interface.
• Indication of Strong Binder/Weak Binder on output.

• Improved neural network predictors for alleles belonging to most HLA supertypes.
• Artificial Neural Network ensembles trained using several sequence encoding schemes and optimized training strategy.
• Matrix predictors derived using a Gibbs sampler approach for a large number of alleles are introduced.

Publications:

• Reliable prediction of T-cell epitopes using neural networks with novel sequence representations.
  Nielsen M, Lundegaard C, Worning P, Lauemoller SL, Lamberth K, Buus S, Brunak S, Lund O.
  Protein Sci., 12:1007-17, 2003.

  View the abstract.

• Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach.
  Nielsen M, Lundegaard C, Worning P, Hvid CS, Lamberth K, Buus S, Brunak S, Lund O.
  Bioinformatics, 20(9):1388-97, 2004.

  View the abstract.

• Artificial Neural Network predictors for peptide/MHC binding for HLA-A2 and H-2Kk.
• Integrate predictions of MHC binding and proteasomale cleavage using NetChop version 2.0

Publication:

• Sensitive quantitative predictions of peptide-MHC binding by a 'Query by Committee' artificial neural network approach.
  Buus S, Lauemoller SL, Worning P, Kesmir C, Frimurer T, Corbet S, Fomsgaard A, Hilden J, Holm A, Brunak S.
  Tissue Antigens., 62:378-84, 2003.

  View the abstract.