{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Gfeller D"],"funding":["Horizon 2020 Marie Skłodowska-Curie Actions","Swiss Cancer Research Foundation","Swiss Cancer League","Marie Curie"],"pagination":["72-83.e5"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9811684"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["14(1)"],"pubmed_abstract":["The recognition of pathogen or cancer-specific epitopes by CD8<sup>+</sup> T cells is crucial for the clearance of infections and the response to cancer immunotherapy. This process requires epitopes to be presented on class I human leukocyte antigen (HLA-I) molecules and recognized by the T-cell receptor (TCR). Machine learning models capturing these two aspects of immune recognition are key to improve epitope predictions. Here, we assembled a high-quality dataset of naturally presented HLA-I ligands and experimentally verified neo-epitopes. We then integrated these data in a refined computational framework to predict antigen presentation (MixMHCpred2.2) and TCR recognition (PRIME2.0). The depth of our training data and the algorithmic developments resulted in improved predictions of HLA-I ligands and neo-epitopes. Prospectively applying our tools to SARS-CoV-2 proteins revealed several epitopes. TCR sequencing identified a monoclonal response in effector/memory CD8<sup>+</sup> T cells against one of these epitopes and cross-reactivity with the homologous peptides from other coronaviruses."],"journal":["Cell systems"],"pubmed_title":["Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8<sup>+</sup> T-cell epitopes."],"pmcid":["PMC9811684"],"funding_grant_id":["101027973","KFS-4961-02-2020","H2020-MSCA-IF-2020"],"pubmed_authors":["Gfeller D","Bobisse S","Genolet R","Harari A","Cesbron J","Queiroz L","Schmidt J","Croce G","Racle J","Guillaume P"],"additional_accession":[]},"is_claimable":false,"name":"Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8<sup>+</sup> T-cell epitopes.","description":"The recognition of pathogen or cancer-specific epitopes by CD8<sup>+</sup> T cells is crucial for the clearance of infections and the response to cancer immunotherapy. This process requires epitopes to be presented on class I human leukocyte antigen (HLA-I) molecules and recognized by the T-cell receptor (TCR). Machine learning models capturing these two aspects of immune recognition are key to improve epitope predictions. Here, we assembled a high-quality dataset of naturally presented HLA-I ligands and experimentally verified neo-epitopes. We then integrated these data in a refined computational framework to predict antigen presentation (MixMHCpred2.2) and TCR recognition (PRIME2.0). The depth of our training data and the algorithmic developments resulted in improved predictions of HLA-I ligands and neo-epitopes. Prospectively applying our tools to SARS-CoV-2 proteins revealed several epitopes. TCR sequencing identified a monoclonal response in effector/memory CD8<sup>+</sup> T cells against one of these epitopes and cross-reactivity with the homologous peptides from other coronaviruses.","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Jan","modification":"2026-05-27T23:10:37.047Z","creation":"2025-04-04T13:53:28.11Z"},"accession":"S-EPMC9811684","cross_references":{"pubmed":["36603583"],"doi":["10.1016/j.cels.2022.12.002"]}}