NetMHCpan-4.0: Improved Peptide–MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Binding Affinity Data

Jurtz, Vanessa Isabell; Paul, Sinu; Andreatta, Massimo; Marcatili, Paolo; Peters, Bjoern; Nielsen, Morten

doi:10.4049/jimmunol.1700893

Cited by 1,156 publications

(1,000 citation statements)

References 31 publications

Supporting

Mentioning

906

Contrasting

Unclassified

Order By: Relevance

“…The NNAlign models generated by the MS‐rescue pipeline are conceptually very similar to NetMHCpan, a popular method for the prediction of peptide‐MHC interactions . In fact, NNAlign is the machine‐learning engine at the core of many pieces of software in the NetMHC family .…”

Section: Resultsmentioning

confidence: 99%

MS‐Rescue: A Computational Pipeline to Increase the Quality and Yield of Immunopeptidomics Experiments

Andreatta

Nicastri

et al. 2019

Proteomics

Self Cite

View full text Add to dashboard Cite

LC–MS/MS has become the standard platform for the characterization of immunopeptidomes, the collection of peptides naturally presented by major histocompatibility complex molecules to the cell surface. The protocols and algorithms used for immunopeptidomics data analysis are based on tools developed for traditional bottom‐up proteomics that address the identification of peptides generated by tryptic digestion. Such algorithms are generally not tailored to the specific requirements of MHC ligand identification and, as a consequence, immunopeptidomics datasets suffer from dismissal of informative spectral information and high false discovery rates. Here, a new pipeline for the refinement of peptide‐spectrum matches (PSM) is proposed, based on the assumption that immunopeptidomes contain a limited number of recurring peptide motifs, corresponding to MHC specificities. Sequence motifs are learned directly from the individual peptidome by training a prediction model on high‐confidence PSMs. The model is then applied to PSM candidates with lower confidence, and sequences that score significantly higher than random peptides are rescued as likely true ligands. The pipeline is applied to MHC class I immunopeptidomes from three different species, and it is shown that it can increase the number of identified ligands by up to 20–30%, while effectively removing false positives and products of co‐precipitation. Spectral validation using synthetic peptides confirms the identity of a large proportion of rescued ligands in the experimental peptidome.

show abstract

Section: Resultsmentioning

confidence: 99%

MS‐Rescue: A Computational Pipeline to Increase the Quality and Yield of Immunopeptidomics Experiments

Andreatta

Nicastri

et al. 2019

Proteomics

Self Cite

View full text Add to dashboard Cite

show abstract

“…44 NetMHCpan4 was trained on naturally eluted ligands as well as on binding affinity data and therefore returns two predicted values: likelihood of a peptide becoming a natural ligand (EL), and predicted binding affinity (BA). We used NetMHCpan-4.0 to perform predictions for the NCI dataset.…”

Section: Resultsmentioning

confidence: 99%

“…The newest version of this algorithm, NetMHCpan-4.0, is taking length preferences for naturally eluted ligands directly into consideration during training, and which provides a simpler implementation of length-specific scores, and shows similar improvements in the identification of neo-epitopes. 44,54,55 …”

Section: Discussionmentioning

confidence: 99%

Predicting T cell recognition of MHC class I restricted neoepitopes

et al. 2018

Self Cite

View full text Add to dashboard Cite

Epitopes that arise from a somatic mutation, also called neoepitopes, are now known to play a key role in cancer immunology and immunotherapy. Recent advances in high-throughput sequencing have made it possible to identify all mutations and thereby all potential neoepitope candidates in an individual cancer. However, most of these neoepitope candidates are not recognized by T cells of cancer patients when tested in vivo or in vitro, meaning they are not immunogenic. Especially in patients with a high mutational load, usually hundreds of potential neoepitopes are detected, highlighting the need to further narrow down this candidate list. In our study, we assembled a dataset of known, naturally processed, immunogenic neoepitopes to dissect the properties that make these neoepitopes immunogenic. The tools to use and thresholds to apply for prioritizing neoepitopes have so far been largely based on experience with epitope identification in other settings such as infectious disease and allergy. Here, we performed a detailed analysis on our dataset of curated immunogenic neoepitopes to establish the appropriate tools and thresholds in the cancer setting. To this end, we evaluated different predictors for parameters that play a role in a neoepitope’s immunogenicity and suggest that using binding predictions and length-rescaling yields the best performance in discriminating immunogenic neoepitopes from a background set of mutated peptides. We furthermore show that almost all neoepitopes had strong predicted binding affinities (as expected), but more surprisingly, the corresponding non-mutated peptides had nearly as high affinities. Our results provide a rational basis for parameters in neoepitope filtering approaches that are being commonly used.Abbreviations: SNV: single nucleotide variant; nsSNV: nonsynonymous single nucleotide variant; ROC: receiver operating characteristic; AUC: area under ROC curve; HLA: human leukocyte antigen; MHC: major histocompatibility complex; PD-1: Programmed cell death protein 1; PD-L1 or CTLA-4: cytotoxic T-lymphocyte associated protein 4

show abstract

“…Bioinformatics tools have been developed for different aspects of immunological features such as epitope prediction and mapping, molecular modeling and structural vaccinology (Sirskyj et al 2011). These tools can predict the highly immunogenic epitopes in a short time with high specificity, and can be used for development of an effective vaccine (Jurtz et al 2017). In this study, to design a novel therapeutic vaccine against major high risk HPV types 16, 18, 31 and 45, we used both sequence-based and structural vaccinology immunoinformatics tools.…”

Section: Introductionmentioning

confidence: 99%

Development of HPV16,18,31,45 E5 and E7 peptides-based vaccines predicted by immunoinformatics tools

et al. 2020

View full text Add to dashboard Cite

Objectives Viral oncoproteins are ideal targets in therapeutic vaccines for functional inhibition of human papillomaviruses (HPVs). Herein, we designed the peptide constructs derived from E5 and E7 oncoproteins of high-risk HPV types 16, 18, 31 and 45 using the bioinformatics tools and investigated their potency in mice. Results The framework of the combined in silico/ in vivo analysis included (1) to determine physicochemical properties of the designed constructs, (2) to identify potential IFN-c-inducing epitopes, (3) to assess allergenicity, (4) to recognize linear and discontinuous B cell epitopes using modeling and validation of 3D structure of the designed constructs, and (5) to evaluate immune responses and tumor growth in vivo. Our in silico data determined high potency of the HPV 16,18,31,45 E5 and HPV 16,18,31,45 E7 peptides for trigger B-and T-cell responses, and IFN-c secretion. In vivo study indicated that the mixture of E5 and E7 immunodominant peptides from four types of high-risk HPV could induce Th1 immune response, and protect completely mice against TC-1 tumor cells. Conclusion Generally, the combined in silico/ in vivo approaches showed the ability of the designed E5 and E7 peptide constructs from four major highrisk HPV types for development of therapeutic vaccines.

show abstract

NetMHCpan-4.0: Improved Peptide–MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Binding Affinity Data

Cited by 1,156 publications

References 31 publications

MS‐Rescue: A Computational Pipeline to Increase the Quality and Yield of Immunopeptidomics Experiments

MS‐Rescue: A Computational Pipeline to Increase the Quality and Yield of Immunopeptidomics Experiments

Predicting T cell recognition of MHC class I restricted neoepitopes

Development of HPV16,18,31,45 E5 and E7 peptides-based vaccines predicted by immunoinformatics tools

Contact Info

Product

Resources

About