NetMHCpan 4.0: Improved peptide-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data

By Vanessa Isabell Jurtz, Sinu Paul, Massimo Andreatta, Paolo Marcatili, Bjoern Peters, Morten Nielsen. 2017

1,083 citations recorded by the source corpus.

Cytotoxic T cells are of central importance in the immune system’s response to disease. They recognize defective cells by binding to peptides presented on the cell surface by MHC class I molecules. Peptide binding to MHC molecules is the single most selective step in the Ag-presentation pathway. Therefore, in the quest for T cell epitopes, the prediction of peptide binding to MHC molecules has attracted widespread attention. In the past, predictors of peptide–MHC interactions have primarily been trained on binding affinity data. Recently, an increasing number of MHC-presented peptides identified by mass spectrometry have been reported containing information about peptide-processing steps in the presentation pathway and the length distribution of naturally presented peptides. In this article, we present NetMHCpan-4.0, a method trained on binding affinity and eluted ligand data leveraging the information from both data types. Large-scale benchmarking of the method demonstrates an increase in predictive performance compared with state-of-the-art methods when it comes to identification of naturally processed ligands, cancer neoantigens, and T cell epitopes.

Subfields: Computational Theory and Mathematics, Molecular Biology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Casper Kaae Sønderby
2. Alessandro Sette
3. Bjoern Peters
4. Ole Winther
5. Bing Zhang
6. Sinu Paul
7. J. Rossjohn

In Molecular Biology

1. Bjoern Peters
2. Alessandro Sette
3. Morten Nielsen
4. Sinu Paul
5. John Sidney
6. Alexey I. Nesvizhskii
7. Paolo Marcatili
8. Vanessa Isabell Jurtz

In Radiology, Nuclear Medicine and Imaging

1. Bjoern Peters
2. Alessandro Sette
3. Sinu Paul
4. John Sidney
5. Paolo Marcatili
6. Vanessa Isabell Jurtz
7. Alba Grifoni
8. Morten Nielsen

Citations in the corpus

• NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning (2018, methodology): “In contrast, by using a recent training procedure strategy (14), we can train the model on all residues, including the disordered ones, thus increasing the accuracy of annotated features in the data and reduce the frustration during training.”
• A Sequence Homology and Bioinformatic Approach Can Predict Candidate Targets for Immune Responses to SARS-CoV-2 (2020, positive): “In the case of T cell epitopes, we utilized predictive algorithms (Jurtz et al., 2017; Paul et al., 2016) to map hundreds of potential human epitopes to account for HLA polymorphism and for the fact that T cell epitopes are typically derived from both structural and non-structural proteins and not l”
• Integrated Proteogenomic Characterization of Clear Cell Renal Cell Carcinoma (2019, methodology): “netMHCpan (Jurtz et al., 2017) was then used to predict HLA peptide binding affinity for somatic mutation-derived variant peptides with a length between 8-11 amino acids.”
• A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction (2020, methodology): “This strategy has been commonly used for previous performance benchmarking studies [28, 30, 61, 62].”
• NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data (2020, methodology): “For MHC class I the epitope dataset was taken from Jurtz et . al (12) combined with a comprehensive set of MHC multimer validated epitopes obtained from the IEDB and for MHC class II from Reynisson et al .”