{"doi":"10.1016/j.immuno.2021.100005","title":"NetMHCphosPan - Pan-specific prediction of MHC class I antigen presentation of phosphorylated ligands","abstract":"Post-translational modifications of proteins play a crucial part in carcinogenesis. Phosphorylated peptides have shown to be presented by MHC class I molecules and recognised by cytotoxic T cells, making them a promising target for immunotherapy. Identification of phosphorylated MHC class I ligands has so far predominantly been done using bioinformatic tools trained on unmodified peptides. Only one tool, PhosMHCpred, has been developed specifically for the prediction of phosphorylated MHC class I ligands so far and this tool has been trained only on a limited number of alleles and provides a limited peptide length coverage (only including 9-mers). Here we propose a method, termed NetMHCphosPan, for the prediction of MHC presented phosphopeptides. The method is trained using the NNAlign_MA framework, which allows incorporating mixed data types and information leverage between data sets resulting in a greatly improved MHC and peptide length coverage and an overall increased predictive power compared to PhosMHCpred. Motif deconvolution suggested a strong preference for phosphosites to be located in position 4 of the binding motif, and enrichment of proline at P5 and arginine at P1. The improved performance, driven by the extended length and allelic coverage, of NetMHCphosPan over current state-of-the-art methods, was further validated on a large benchmark data set independent from the model development. In conclusion, we have confirmed the high power of NNAlign_MA for motif deconvolution of complex immuno-peptidomics data and have developed a novel method for prediction of MHC presented phosphopeptides with improved predictive power and a broader peptide length and MHC coverage compared to current state-of-the-art methods. The developed method is available at http://www.cbs.dtu.dk/services/NetMHCphosPan-1.0.","journal":"ImmunoInformatics","year":2021,"id":184926,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":10,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.944,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":486132,"name":"Carolina Barra","orcid":"0000-0002-6836-4906","position":1,"is_corresponding":false},{"id":411849,"name":"Peng Xu","orcid":"0000-0002-3503-6017","position":2,"is_corresponding":false},{"id":489199,"name":"Nicola Ternette","orcid":"0000-0002-9283-0743","position":3,"is_corresponding":false},{"id":56546,"name":"Morten Nielsen","orcid":"0000-0001-7885-4311","position":4,"is_corresponding":false},{"id":741479,"name":"Carina Thusgaard Refsgaard","orcid":null,"position":0,"is_corresponding":true}],"reference_count":30,"raw_metadata":null,"created_at":"2026-07-18T23:48:34.992499Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}