{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:47:02Z","timestamp":1784317622211,"version":"3.55.0"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,3,31]],"date-time":"2024-03-31T00:00:00Z","timestamp":1711843200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide\u2013MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.<\/jats:p>","DOI":"10.1093\/bib\/bbae123","type":"journal-article","created":{"date-parts":[[2024,3,9]],"date-time":"2024-03-09T02:01:43Z","timestamp":1709949703000},"source":"Crossref","is-referenced-by-count":34,"title":["Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5022-2119","authenticated-orcid":false,"given":"William John","family":"Thrift","sequence":"first","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Perera","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sivan","family":"Cohen","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas W","family":"Lounsbury","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hem R","family":"Gurung","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher M","family":"Rose","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieming","family":"Chen","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suchit","family":"Jhunjhunwala","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"Genentech , 1 DNA Way, South San Francisco, California 94080 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"2024033102570974800_ref1","volume-title":"Janeway's Immunobiology","author":"Janeway","year":"2001"},{"key":"2024033102570974800_ref2","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.cels.2020.06.009","article-title":"Computationally optimized SARS-CoV-2 MHC class I and II vaccine formulations predicted to target human haplotype distributions","volume":"11","author":"Liu","year":"2020","journal-title":"Cell Syst"},{"key":"2024033102570974800_ref3","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1038\/s42256-020-00260-4","article-title":"Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines","volume":"2","author":"Tran","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2024033102570974800_ref4","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1038\/s10038-021-00950-w","article-title":"Immunogenomics in personalized cancer treatments","volume":"66","author":"Kiyotani","year":"2021","journal-title":"J Hum Genet"},{"key":"2024033102570974800_ref5","doi-asserted-by":"crossref","first-page":"102714","DOI":"10.1016\/j.jaut.2021.102714","article-title":"Chronic inflammation and extracellular matrix-specific autoimmunity following inadvertent periarticular influenza vaccination","volume":"124","author":"Hirsiger","year":"2021","journal-title":"J Autoimmun"},{"key":"2024033102570974800_ref6","doi-asserted-by":"crossref","first-page":"W449","DOI":"10.1093\/nar\/gkaa379","article-title":"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","volume":"48","author":"Reynisson","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref7","doi-asserted-by":"crossref","first-page":"i399","DOI":"10.1093\/bioinformatics\/btaa479","article-title":"MHCAttnNet: predicting MHC-peptide bindings for MHC alleles classes I and II using an attention-based deep neural model","volume":"36","author":"Venkatesh","year":"2020","journal-title":"Bioinformatics"},{"key":"2024033102570974800_ref8","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.cels.2019.05.004","article-title":"Quantification of uncertainty in peptide-MHC binding prediction improves high-affinity peptide selection for therapeutic design","volume":"9","author":"Zeng","year":"2019","journal-title":"Cell Syst"},{"key":"2024033102570974800_ref9","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"2024033102570974800_ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-15-6815-2_11","article-title":"In silico designing of vaccines: methods, tools, and their limitations","author":"Slathia","year":"2020","journal-title":"Comput Aid Drug Des"},{"key":"2024033102570974800_ref11","doi-asserted-by":"crossref","first-page":"862851","DOI":"10.3389\/fimmu.2022.862851","article-title":"Multiple-allele MHC class II epitope engineering by a molecular dynamics-based evolution protocol","volume":"13","author":"Ochoa","year":"2022","journal-title":"Front Immunol"},{"key":"2024033102570974800_ref12","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1021\/acs.jcim.1c00056","article-title":"MHCEpitopeEnergy, a flexible Rosetta-based biotherapeutic dimmunization platform","volume":"61","author":"Yachnin","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2024033102570974800_ref13","doi-asserted-by":"crossref","DOI":"10.1101\/2022.02.11.479844","article-title":"Improved predictions of MHC-peptide binding using protein language models","volume-title":"Front Bioinform","author":"Hashemi","year":"2022"},{"key":"2024033102570974800_ref14","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2216697120","article-title":"Peptide binding specificity prediction using fine-tuned protein structure prediction networks","volume-title":"Proc Natl Acad Sci U S A","author":"Motmaen","year":"2023"},{"key":"2024033102570974800_ref15","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1208\/s12248-015-9857-y","article-title":"Evaluating and reporting the immunogenicity impacts for biological products\u2014a clinical pharmacology perspective","volume":"18","author":"Wang","year":"2016","journal-title":"AAPS J"},{"key":"2024033102570974800_ref16","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1038\/321522a0","article-title":"Replacing the complementarity-determining regions in a human antibody with those from a mouse","volume":"321","author":"Jones","year":"1986","journal-title":"Nature"},{"key":"2024033102570974800_ref17","doi-asserted-by":"crossref","first-page":"2020203","DOI":"10.1080\/19420862.2021.2020203","article-title":"BioPhi: a platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning","volume":"14","author":"Prihoda","year":"2022","journal-title":"MAbs"},{"key":"2024033102570974800_ref18","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1186\/1471-2105-11-180","article-title":"Optimization algorithms for functional deimmunization of therapeutic proteins","volume":"11","author":"Parker","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2024033102570974800_ref19","doi-asserted-by":"crossref","first-page":"8577","DOI":"10.1073\/pnas.1321126111","article-title":"Removing T-cell epitopes with computational protein design","volume":"111","author":"King","year":"2014","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024033102570974800_ref20","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/978-1-4939-6637-0_20","article-title":"EpiSweep: computationally driven reengineering of therapeutic proteins to reduce immunogenicity while maintaining function","volume":"1529","author":"Choi","year":"2016","journal-title":"Methods Mol Biol"},{"key":"2024033102570974800_ref21","doi-asserted-by":"crossref","DOI":"10.1101\/2021.10.04.463034","article-title":"Protein complex prediction with AlphaFold-Multimer","volume-title":"bioRxiv","author":"Evans"},{"key":"2024033102570974800_ref22","doi-asserted-by":"crossref","first-page":"e4379","DOI":"10.1002\/pro.4379","article-title":"Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants","volume":"31","author":"Yin","year":"2022","journal-title":"Protein Sci"},{"key":"2024033102570974800_ref23","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1038\/s41467-022-28865-w","article-title":"Improved prediction of protein-protein interactions using AlphaFold2","volume":"13","author":"Bryant","year":"2022","journal-title":"Nat Commun"},{"key":"2024033102570974800_ref24","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1038\/s41594-022-00910-8","article-title":"Towards a structurally resolved human protein interaction network","volume":"30","author":"Burke","year":"2023","journal-title":"Nat Struct Mol Biol"},{"key":"2024033102570974800_ref25","doi-asserted-by":"crossref","first-page":"eabm4805","DOI":"10.1126\/science.abm4805","article-title":"Computed structures of core eukaryotic protein complexes","volume":"374","author":"Humphreys","year":"2021","journal-title":"Science"},{"key":"2024033102570974800_ref26","doi-asserted-by":"crossref","first-page":"6028","DOI":"10.1038\/s41467-022-33729-4","article-title":"Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search","volume":"13","author":"Bryant","year":"2022","journal-title":"Nat Commun"},{"key":"2024033102570974800_ref27","doi-asserted-by":"crossref","first-page":"D1262","DOI":"10.1093\/nar\/gkab1136","article-title":"IMGT\u00ae databases, related tools and web resources through three main axes of research and development","volume":"50","author":"Manso","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref28","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1007\/s00251-013-0720-y","article-title":"NetMHCIIpan-3.0, a common pan-specific MHC class II prediction method including all three human MHC class II isotypes, HLA-DR, HLA-DP and HLA-DQ","volume":"65","author":"Karosiene","year":"2013","journal-title":"Immunogenetics"},{"key":"2024033102570974800_ref29","doi-asserted-by":"crossref","first-page":"22219","DOI":"10.1073\/pnas.1014708107","article-title":"Bidirectional binding of invariant chain peptides to an MHC class II molecule","volume":"107","author":"G\u00fcnther","year":"2010","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024033102570974800_ref30","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1111\/j.1365-2567.2012.03579.x","article-title":"Characterizing the binding motifs of 11 common human HLA-DP and HLA-DQ molecules using NNAlign","volume":"136","author":"Andreatta","year":"2012","journal-title":"Immunology"},{"key":"2024033102570974800_ref31","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1016\/j.immuni.2023.03.009","article-title":"Machine learning predictions of MHC-II specificities reveal alternative binding mode of class II epitopes","volume":"56","author":"Racle","year":"2023","journal-title":"Immunity"},{"key":"2024033102570974800_ref32","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1038\/s41587-019-0289-6","article-title":"Robust prediction of HLA class II epitopes by deep motif deconvolution of immunopeptidomes","volume":"37","author":"Racle","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2024033102570974800_ref33","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1158\/2326-6066.CIR-19-0464","article-title":"High-throughput prediction of MHC class I and II neoantigens with MHCnuggets","volume":"8","author":"Shao","year":"2020","journal-title":"Cancer Immunol Res"},{"key":"2024033102570974800_ref34","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"Graph Attention Networks"},{"key":"2024033102570974800_ref35","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J Med Chem"},{"key":"2024033102570974800_ref36","doi-asserted-by":"crossref","first-page":"e1000107","DOI":"10.1371\/journal.pcbi.1000107","article-title":"Quantitative predictions of peptide binding to any HLA-DR molecule of known sequence: NetMHCIIpan","volume":"4","author":"Nielsen","year":"2008","journal-title":"PLoS Comput Biol"},{"key":"2024033102570974800_ref37","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1021\/acs.jproteome.9b00874","article-title":"Improved prediction of MHC II antigen presentation through integration and motif deconvolution of mass spectrometry MHC eluted ligand data","volume":"19","author":"Reynisson","year":"2020","journal-title":"J Proteome Res"},{"key":"2024033102570974800_ref38","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s13073-018-0594-6","article-title":"Footprints of antigen processing boost MHC class II natural ligand predictions","volume":"10","author":"Barra","year":"2018","journal-title":"Genome Med"},{"key":"2024033102570974800_ref39","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1002\/pro.4205","article-title":"Observed antibody space: a diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences","volume":"31","author":"Olsen","year":"2022","journal-title":"Protein Sci"},{"key":"2024033102570974800_ref40","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1007\/s00251-004-0647-4","article-title":"Definition of supertypes for HLA molecules using clustering of specificity matrices","volume":"55","author":"Lund","year":"2004","journal-title":"Immunogenetics"},{"key":"2024033102570974800_ref41","doi-asserted-by":"crossref","first-page":"D1288","DOI":"10.1093\/nar\/gkac813","article-title":"DrugMAP: molecular atlas and pharma-information of all drugs","volume":"51","author":"Li","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref42","doi-asserted-by":"crossref","first-page":"D1450","DOI":"10.1093\/nar\/gkad862","article-title":"TheMarker: a comprehensive database of therapeutic biomarkers","volume":"52","author":"Zhang","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref43","doi-asserted-by":"crossref","first-page":"D1097","DOI":"10.1093\/nar\/gkad831","article-title":"ADCdb: the database of antibody\u2013drug conjugates","volume":"52","author":"Shen","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref44","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1146\/annurev-immunol-032712-095910","article-title":"Pathways of antigen processing","volume":"31","author":"Blum","year":"2013","journal-title":"Annu Rev Immunol"},{"key":"2024033102570974800_ref45","doi-asserted-by":"crossref","first-page":"13126","DOI":"10.1038\/s41598-021-92632-y","article-title":"NetCleave: an open-source algorithm for predicting C-terminal antigen processing for MHC-I and MHC-II","volume":"11","author":"Amengual-Rigo","year":"2021","journal-title":"Sci Rep"},{"key":"2024033102570974800_ref46","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"Bahdanau","year":"2016"},{"key":"2024033102570974800_ref47","doi-asserted-by":"crossref","DOI":"10.1101\/2022.12.08.519673","article-title":"HLApollo: a superior transformer model for pan-allelic peptide-MHC-I presentation prediction, with diverse negative coverage, deconvolution and protein language features","volume-title":"bioRxiv","author":"Thrift"},{"key":"2024033102570974800_ref48","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1038\/nature21433","article-title":"Antigen presentation profiling reveals recognition of lymphoma immunoglobulin neoantigens","volume":"543","author":"Khodadoust","year":"2017","journal-title":"Nature"},{"key":"2024033102570974800_ref49","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.immuni.2019.08.012","article-title":"Defining HLA-II ligand processing and binding rules with mass spectrometry enhances cancer epitope prediction","volume":"51","author":"Abelin","year":"2019","journal-title":"Immunity"},{"key":"2024033102570974800_ref50","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1074\/mcp.TIR117.000383","article-title":"High-throughput and sensitive immunopeptidomics platform reveals profound interferon\u03b3-mediated remodeling of the human leukocyte antigen (HLA) ligandome","volume":"17","author":"Chong","year":"2018","journal-title":"Mol Cell Proteomics"},{"key":"2024033102570974800_ref51","doi-asserted-by":"crossref","DOI":"10.1136\/jitc-2020-002071","article-title":"HLA ligand atlas: a benign reference of HLA-presented peptides to improve T-cell-based cancer immunotherapy","volume":"9","author":"Marcu","year":"2021","journal-title":"J Immunother Cancer"},{"key":"2024033102570974800_ref52","doi-asserted-by":"crossref","first-page":"W502","DOI":"10.1093\/nar\/gkz452","article-title":"IEDB-AR: immune epitope database\u2014analysis resource in 2019","volume":"47","author":"Dhanda","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2024033102570974800_ref53","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.4049\/jimmunol.2000192","article-title":"Immunopeptidome analysis of HLA-DPB1 allelic variants reveals new functional hierarchies","volume":"204","author":"Balen","year":"2020","journal-title":"J Immunol"},{"key":"2024033102570974800_ref54","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1038\/s41587-019-0280-2","article-title":"Predicting HLA class II antigen presentation through integrated deep learning","volume":"37","author":"Chen","year":"2019","journal-title":"Nat Biotechnol"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/3\/bbae123\/57108937\/bbae123.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/3\/bbae123\/57108937\/bbae123.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T22:57:36Z","timestamp":1711839456000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae123\/7636763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3,27]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae123","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.01.19.524779","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5]]},"published":{"date-parts":[[2024,3,27]]},"article-number":"bbae123"}}