{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T18:21:58Z","timestamp":1774030918613,"version":"3.50.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T00:00:00Z","timestamp":1705449600000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 CA205426"],"award-info":[{"award-number":["R01 CA205426"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35 CA232097"],"award-info":[{"award-number":["R35 CA232097"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Immunologic recognition of peptide antigens bound to class I major histocompatibility complex (MHC) molecules is essential to both novel immunotherapeutic development and human health at large. Current methods for predicting antigen peptide immunogenicity rely primarily on simple sequence representations, which allow for some understanding of immunogenic features but provide inadequate consideration of the full scale of molecular mechanisms tied to peptide recognition. We here characterize contributions that unsupervised and supervised artificial intelligence (AI) methods can make toward understanding and predicting MHC(HLA-A2)-peptide complex immunogenicity when applied to large ensembles of molecular dynamics simulations. We first show that an unsupervised AI method allows us to identify subtle features that drive immunogenicity differences between a cancer neoantigen and its wild-type peptide counterpart. Next, we demonstrate that a supervised AI method for class I MHC(HLA-A2)-peptide complex classification significantly outperforms a sequence model on small datasets corrected for trivial sequence correlations. Furthermore, we show that both unsupervised and supervised approaches reveal determinants of immunogenicity based on time-dependent molecular fluctuations and anchor position dynamics outside the MHC binding groove. We discuss implications of these structural and dynamic immunogenicity correlates for the induction of T cell responses and therapeutic T cell receptor design.<\/jats:p>","DOI":"10.1093\/bib\/bbad504","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T19:10:55Z","timestamp":1705518655000},"source":"Crossref","is-referenced-by-count":11,"title":["Unsupervised and supervised AI on molecular dynamics simulations reveals complex characteristics of HLA-A2-peptide immunogenicity"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5241-9036","authenticated-orcid":false,"given":"Jeffrey K","family":"Weber","sequence":"first","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8550-4854","authenticated-orcid":false,"given":"Joseph A","family":"Morrone","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Seung-gu","family":"Kang","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Leili","family":"Zhang","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Lijun","family":"Lang","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Diego","family":"Chowell","sequence":"additional","affiliation":[{"name":"Precision Immunology Institute, Icahn School of Medicine at Mount Sinai , New York, NY 10029"}]},{"given":"Chirag","family":"Krishna","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard , Cambridge, MA 02142 , USA"}]},{"given":"Tien","family":"Huynh","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Prerana","family":"Parthasarathy","sequence":"additional","affiliation":[{"name":"Center for Immunotherapy and Precision Immuno-Oncology, Cleveland Clinic , Cleveland, OH 44195 USA"},{"name":"Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44015 USA"}]},{"given":"Binquan","family":"Luan","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Tyler J","family":"Alban","sequence":"additional","affiliation":[{"name":"Center for Immunotherapy and Precision Immuno-Oncology, Cleveland Clinic , Cleveland, OH 44195 USA"},{"name":"Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44015 USA"}]},{"given":"Wendy D","family":"Cornell","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center , Yorktown Heights, NY 10598 USA"}]},{"given":"Timothy A","family":"Chan","sequence":"additional","affiliation":[{"name":"Center for Immunotherapy and Precision Immuno-Oncology, Cleveland Clinic , Cleveland, OH 44195 USA"},{"name":"Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44015 USA"},{"name":"Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center , New York, NY 10065 USA"},{"name":"Taussig Cancer Institute, Cleveland Clinic , Cleveland, OH 44015 USA"},{"name":"National Center for Regenerative Medicine, Cleveland Clinic , Cleveland, OH 44015 USA"}]}],"member":"286","published-online":{"date-parts":[[2024,1,16]]},"reference":[{"key":"2024011719101978400_ref1","doi-asserted-by":"crossref","first-page":"S103","DOI":"10.1002\/eji.200737584","article-title":"A brief history of CD8 T cells","volume":"37","author":"Masopust","year":"2007","journal-title":"Eur J Immunol"},{"key":"2024011719101978400_ref2","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/351290a0","article-title":"Allele-specific motifs revealed by sequencing of self-peptides eluted from MHC molecules","volume":"351","author":"Falk","year":"1991","journal-title":"Nature"},{"key":"2024011719101978400_ref3","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1038\/s43018-021-00197-6","article-title":"A machine learning model for ranking candidate HLA class I neoantigens based on known neoepitopes from multiple human tumor types","volume":"2","author":"Gartner","year":"2021","journal-title":"Nat Cancer"},{"key":"2024011719101978400_ref4","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/nbt.4313","article-title":"Deep learning using tumor HLA peptide mass spectrometry datasets improves neoantigen identification","volume":"37","author":"Bulik-Sullivan","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2024011719101978400_ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-24562-2","article-title":"Biochemical and functional characterization of mutant KRAS epitopes validates this oncoprotein for immunological targeting","volume":"12","author":"Bear","year":"2021","journal-title":"Nat Commun"},{"key":"2024011719101978400_ref6","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1016\/j.cell.2020.09.015","article-title":"Key parameters of tumor epitope immunogenicity revealed through a consortium approach improve neoantigen prediction","volume":"183","author":"Wells","year":"2020","journal-title":"Cell"},{"key":"2024011719101978400_ref7","doi-asserted-by":"crossref","first-page":"6470","DOI":"10.1021\/jacs.1c00016","article-title":"Backbone modifications of HLA-A2-restricted antigens induce diverse binding and T cell activation outcomes","volume":"143","author":"Gibadullin","year":"2021","journal-title":"J Am Chem Soc"},{"key":"2024011719101978400_ref8","doi-asserted-by":"crossref","first-page":"E1754","DOI":"10.1073\/pnas.1500973112","article-title":"TCR contact residue hydrophobicity is a hallmark of immunogenic CD8+ T cell epitopes","volume":"112","author":"Chowell","year":"2015","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024011719101978400_ref9","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1038\/s41577-018-0007-5","article-title":"Understanding the drivers of MHC restriction of T cell receptors","volume":"18","author":"La Gruta","year":"2018","journal-title":"Nat Rev Immunol"},{"key":"2024011719101978400_ref10","doi-asserted-by":"crossref","first-page":"e0232849","DOI":"10.1371\/journal.pone.0232849","article-title":"Sequence-structure-function relationships in class I MHC: a local frustration perspective","volume":"15","author":"Ser\u00e7ino\u011flu","year":"2020","journal-title":"PloS One"},{"key":"2024011719101978400_ref11","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.3389\/fimmu.2019.02047","article-title":"Structure based prediction of Neoantigen immunogenicity","volume":"10","author":"Riley","year":"2019","journal-title":"Front Immunol"},{"key":"2024011719101978400_ref12","article-title":"Predicting HLA-I peptide immunogenicity with deep learning and molecular dynamics","author":"Weber","year":"2020","journal-title":"Res Sq"},{"key":"2024011719101978400_ref13","doi-asserted-by":"crossref","first-page":"011201","DOI":"10.1103\/PhysRevE.65.011201","article-title":"Model of a fluid at small and large length scales and the hydrophobic effect","volume":"65","author":"Wolde","year":"2001","journal-title":"Phys Rev E"},{"key":"2024011719101978400_ref14","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1038\/nature03926","article-title":"Observation of a dewetting transition in the collapse of the melittin tetramer","volume":"437","author":"Liu","year":"2005","journal-title":"Nature"},{"key":"2024011719101978400_ref15","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2024011719101978400_ref16","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ymeth.2010.06.002","article-title":"Everything you wanted to know about Markov state models but were afraid to ask","volume":"52","author":"Pande","year":"2010","journal-title":"Methods"},{"key":"2024011719101978400_ref17","doi-asserted-by":"crossref","first-page":"2000","DOI":"10.1021\/ct300878a","article-title":"Improvements in Markov state model construction reveal many non-native interactions in the folding of NTL9","volume":"9","author":"Schwantes","year":"2013","journal-title":"J Chem Theory Comput"},{"key":"2024011719101978400_ref18","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1021\/jacsau.1c00254","article-title":"Markov state models to study the functional dynamics of proteins in the wake of machine learning","volume":"1","author":"Konovalov","year":"2021","journal-title":"JACS Au"},{"key":"2024011719101978400_ref19","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.bpj.2016.10.042","article-title":"MSMBuilder: statistical models for biomolecular dynamics","volume":"112","author":"Harrigan","year":"2017","journal-title":"Biophys J"},{"key":"2024011719101978400_ref20","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1021\/acscentsci.6b00367","article-title":"Low data drug discovery with one-shot learning","volume":"3","author":"Altae-Tran","year":"2017","journal-title":"ACS Cent Sci"},{"key":"2024011719101978400_ref21","doi-asserted-by":"crossref","first-page":"4170","DOI":"10.1021\/acs.jcim.9b00927","article-title":"Combining docking pose rank and structure with deep learning improves protein\u2013ligand binding mode prediction over a baseline docking approach","volume":"60","author":"Morrone","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2024011719101978400_ref22","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1146\/annurev-physchem-042018-052331","article-title":"Machine learning for molecular simulation","volume":"71","author":"No\u00e9","year":"2020","journal-title":"Annu Rev Phys Chem"},{"key":"2024011719101978400_ref23","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1021\/acscentsci.8b00507","article-title":"PotentialNet for molecular property prediction","volume":"4","author":"Feinberg","year":"2018","journal-title":"ACS Cent Sci"},{"key":"2024011719101978400_ref24","first-page":"e1492508","article-title":"Predicting T cell recognition of MHC class I restricted neoepitopes","volume":"7","author":"Ko\u015falo\u011flu-Yal\u00e7\u0131n","year":"2018","journal-title":"Onco Targets Ther"},{"key":"2024011719101978400_ref25","doi-asserted-by":"crossref","first-page":"W569","DOI":"10.1093\/nar\/gkad356","article-title":"TCRmodel2: high-resolution modeling of T cell receptor recognition using deep learning","volume":"51","author":"Yin","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024011719101978400_ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2017\/5974574","article-title":"The immune epitope database: how data are entered and retrieved","volume":"2017","author":"Fleri","year":"2017","journal-title":"J Immunol Res"},{"key":"2024011719101978400_ref27","article-title":"Impact of AlphaFold on structure prediction of protein complexes: the CASP15-CAPRI experiment","volume-title":"Proteins: Struct, Funct, Bioinf","author":"Lensink","year":"2023"},{"key":"2024011719101978400_ref28","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":"2024011719101978400_ref29","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.cels.2020.06.010","article-title":"MHCflurry 2.0: improved pan-allele prediction of MHC I-presented peptides by incorporating antigen processing","volume":"11","author":"O'Donnell","year":"2020","journal-title":"Cell Systems"},{"key":"2024011719101978400_ref30","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/s41587-019-0322-9","article-title":"A large peptidome dataset improves HLA class I epitope prediction across most of the human population","volume":"38","author":"Sarkizova","year":"2020","journal-title":"Nature Biotechnol"},{"key":"2024011719101978400_ref31","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.cels.2022.12.002","article-title":"Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8+ T-cell epitopes","volume":"14","author":"Gfeller","year":"2023","journal-title":"Cell Systems"},{"key":"2024011719101978400_ref32","article-title":"UMAP: uniform manifold approximation and projection for dimension reduction","author":"McInnes","journal-title":"arXiv"},{"key":"2024011719101978400_ref33","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.3389\/fimmu.2017.01503","article-title":"Dual molecular mechanisms govern escape at immunodominant HLA A2-restricted HIV epitope","volume":"8","author":"Cole","year":"2017","journal-title":"Front Immunol"},{"key":"2024011719101978400_ref34","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/0263-7855(96)00018-5","article-title":"VMD: visual molecular dynamics","volume":"14","author":"Humphrey","year":"1996","journal-title":"J Mol Graph"},{"key":"2024011719101978400_ref35","doi-asserted-by":"crossref","first-page":"044130","DOI":"10.1063\/5.0014475","article-title":"Scalable molecular dynamics on CPU and GPU architectures with NAMD","volume":"153","author":"Phillips","year":"2020","journal-title":"J Chem Phys"},{"key":"2024011719101978400_ref36","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/nmeth.4067","article-title":"CHARMM36m: an improved force field for folded and intrinsically disordered proteins","volume":"14","author":"Huang","year":"2017","journal-title":"Nat Methods"},{"key":"2024011719101978400_ref37","doi-asserted-by":"crossref","first-page":"10089","DOI":"10.1063\/1.464397","article-title":"Particle mesh Ewald: an N\u00b7log (N) method for Ewald sums in large systems","volume":"98","author":"Darden","year":"1993","journal-title":"J Chem Phys"},{"key":"2024011719101978400_ref38","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1016\/j.bpj.2015.08.015","article-title":"MDTraj: a modern open library for the analysis of molecular dynamics trajectories","volume":"109","author":"McGibbon","year":"2015","journal-title":"Biophys J"},{"key":"2024011719101978400_ref39","article-title":"Tensorflow: large-scale machine learning on heterogeneous distributed systems","author":"Abadi"},{"key":"2024011719101978400_ref40","article-title":"Adam: a method for stochastic optimization","author":"Kingma"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/1\/bbad504\/56149016\/bbad504.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/1\/bbad504\/56149016\/bbad504.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T19:11:13Z","timestamp":1705518673000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbad504\/7560312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,11,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbad504","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1,1]]},"published":{"date-parts":[[2023,11,22]]},"article-number":"bbad504"}}