{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T20:09:00Z","timestamp":1789070940509,"version":"build-2803163510"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Molecular Modelling and Artificial Intelligence"},{"DOI":"10.13039\/501100009594","name":"University of P\u00e9cs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009594","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hungarian Academy of Sciences: J\u00e1nos Bolyai Research Scholarship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cross-immunity, defined as the ability of T-cells to recognize multiple antigen peptide-major histocompatibility complexes, is a fundamental feature of adaptive immunity. However, the prediction of different peptide epitopes that can be recognized by the same T-cell receptor remains challenging. Currently, artificial intelligent (AI)-based machine learning (ML) methods can be successfully used for pattern recognition in epitope molecular space by detecting the functional similarity between peptide sequences. In this study, using literature-based experimental data, we examined ML-based binary classification models trained on small datasets to predict the activity of nine-amino-acid-long peptides. Our results suggest that the consensus function of well-established similarity matrix-based representations and structural-based descriptors of epitopes yields better performance because representation-specific noises are reduced and individual model weaknesses are partially compensated. We also sought to determine the extent to which the predictive power of the applied AIs procedure depended on the physicochemical content of the descriptor set during the training process. In addition, challenging the models, we applied them to an independent experimental dataset to examine the effects of diverse laboratory conditions on a regulated biological measurement. In summary, applying a consensus function can capture the biological complexity of cross-reactivity at the binary classification level, even when applied to relatively small datasets.<\/jats:p>","DOI":"10.1093\/bib\/bbag484","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T11:32:59Z","timestamp":1788521579000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based prediction of cross-immunity"],"prefix":"10.1093","volume":"27","author":[{"given":"Vivien Erzs\u00e9bet","family":"Resch","sequence":"first","affiliation":[{"name":"Department of Medicinal Chemistry, University of Szeged , D\u00f3m t\u00e9r 8, H-6720 Szeged ,","place":["Hungary"]},{"name":"Institute of Physics, University of P\u00e9cs , Ifj\u00fas\u00e1g \u00fatja 6, H-7625 P\u00e9cs ,","place":["Hungary"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L\u00e1szl\u00f3","family":"T\u00f3th","sequence":"additional","affiliation":[{"name":"Institute of Informatics, University of Szeged , \u00c1rp\u00e1d t\u00e9r 2, 6720 Szeged ,","place":["Hungary"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8271-9841","authenticated-orcid":false,"given":"Anita","family":"R\u00e1cz","sequence":"additional","affiliation":[{"name":"Plasma Chemistry Research Group, HUN-REN Research Centre for Natural Sciences , Magyar Tud\u00f3sok K\u00f6r\u00fatja 2, H-1117 Budapest ,","place":["Hungary"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9456-7993","authenticated-orcid":false,"given":"Dezs\u0151","family":"Virok","sequence":"additional","affiliation":[{"name":"Department of Medical Microbiology, Albert Szent-Gy\u00f6rgyi Health Center and Albert Szent-Gy\u00f6rgyi Medical School, University of Szeged , Semmelweis Str. 6, H-6725 Szeged ,","place":["Hungary"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5408-1748","authenticated-orcid":false,"given":"G\u00e1bor","family":"Paragi","sequence":"additional","affiliation":[{"name":"Department of Medicinal Chemistry, University of Szeged , D\u00f3m t\u00e9r 8, H-6720 Szeged ,","place":["Hungary"]},{"name":"Institute of Physics, University of P\u00e9cs , Ifj\u00fas\u00e1g \u00fatja 6, H-7625 P\u00e9cs ,","place":["Hungary"]},{"name":"Department of Theoretical Physics, University of Szeged , Tisza L. krt. 84-86, H-7625 P\u00e9cs ,","place":["Hungary"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"2026091015403420500_ref1","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.4049\/jimmunol.1501721","article-title":"The length distribution of class I-restricted T-cell epitopes is determined by both peptide supply and MHC allele-specific binding preference","volume":"196","author":"Trolle","year":"2016","journal-title":"J Immunol"},{"key":"2026091015403420500_ref2","doi-asserted-by":"publisher","first-page":"13136","DOI":"10.1073\/pnas.1409155111","article-title":"Diversity and clonal selection in the human T-cell repertoire","volume":"111","author":"Qi","year":"2014","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026091015403420500_ref3","doi-asserted-by":"publisher","first-page":"1212546","DOI":"10.3389\/fimmu.2023.1212546","article-title":"The good and the bad of T-cell cross-reactivity: challenges and opportunities for novel therapeutics in autoimmunity and cancer","volume":"14","author":"Gouttefangeas","year":"2023","journal-title":"Front Immunol"},{"key":"2026091015403420500_ref4","doi-asserted-by":"publisher","first-page":"e1002412","DOI":"10.1371\/journal.pcbi.1002412","article-title":"Degenerate T-cell recognition of peptides on MHC molecules creates large holes in the T-cell repertoire","volume":"8","author":"Calis","year":"2012","journal-title":"PLoS Comput Biol"},{"key":"2026091015403420500_ref5","doi-asserted-by":"publisher","first-page":"82813","DOI":"10.7554\/eLife.82813","article-title":"Structure-based prediction of T-cell receptor:peptide-MHC interactions","volume":"20","author":"Bradley","year":"2023","journal-title":"Elife"},{"key":"2026091015403420500_ref6","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1093\/bioinformatics\/btad780","article-title":"MHCSeqNet2\u2014improved peptide-class I MHC binding prediction for alleles with low data","volume":"40","author":"Wongklaew","year":"2023","journal-title":"Bioinformatics"},{"key":"2026091015403420500_ref7","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1093\/bioinformatics\/btp137","article-title":"The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding","volume":"25","author":"Zhang","year":"2009","journal-title":"Bioinformatics"},{"key":"2026091015403420500_ref8","doi-asserted-by":"publisher","first-page":"1142573","DOI":"10.3389\/fimmu.2023.1142573","article-title":"CrossDome: an interactive R package to predict cross-reactivity risk using immunopeptidomics databases","volume":"14","author":"Fonseca","year":"2023","journal-title":"Front Immunol"},{"key":"2026091015403420500_ref9","doi-asserted-by":"publisher","first-page":"1108303","DOI":"10.3389\/fimmu.2023.1108303","article-title":"PepSim: T-cell cross-reactivity prediction via comparison of peptide sequence and peptide-HLA structure","volume":"14","author":"Hall-Swan","year":"2023","journal-title":"Front Immunol"},{"key":"2026091015403420500_ref10","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/s41746-024-01360-w","article-title":"Estimation of minimal data sets sizes for machine learning predictions in digital mental health intervention","volume":"7","author":"Zantvoort","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2026091015403420500_ref11","doi-asserted-by":"publisher","first-page":"bbag048","DOI":"10.1093\/bib\/bbag048","article-title":"Decoding TCR recognition via geometric deep learning of immunological fingerprints","volume":"27","author":"Shang","year":"2026","journal-title":"Brief Bioinform"},{"key":"2026091015403420500_ref12","doi-asserted-by":"publisher","first-page":"2501","DOI":"10.3389\/fimmu.2019.02501","article-title":"TCR fingerprinting and off-target peptide identification","volume":"10","author":"Karapetyan","year":"2019","journal-title":"Front Immunol"},{"key":"2026091015403420500_ref13","doi-asserted-by":"publisher","first-page":"607","DOI":"10.3389\/fimmu.2020.00607","article-title":"Preclinical studies of the off-target reactivity of AFP158-specific TCR engineered T-cells","volume":"11","author":"Cai","year":"2020","journal-title":"Front Immunol"},{"key":"2026091015403420500_ref14","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Networks for Pattern Recognition","author":"Bishop","year":"1995"},{"key":"2026091015403420500_ref15","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026091015403420500_ref16","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026091015403420500_ref17","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"2026091015403420500_ref18","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Heinkoff","year":"1992","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026091015403420500_ref19","doi-asserted-by":"publisher","first-page":"e1000173","DOI":"10.1371\/journal.pcbi.1000173","article-title":"Support vector machines and kernels for computational biology","volume":"4","author":"Ben-Hur","year":"2008","journal-title":"PLoS Comput Biol"},{"key":"2026091015403420500_ref20","volume-title":"A Model of Evolutionary Change in Proteins","author":"Dayhoff","year":"1978"},{"key":"2026091015403420500_ref21","doi-asserted-by":"publisher","first-page":"646","DOI":"10.3390\/ph15050646","article-title":"Drug design by pharmacophore and virtual screening approach","volume":"15","author":"Giordano","year":"2022","journal-title":"Pharmaceuticals"},{"key":"2026091015403420500_ref22","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2026091015403420500_ref23","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2026091015403420500_ref24","volume-title":"Schr\u00f6dinger Release 2025\u20131","year":"2025"},{"key":"2026091015403420500_ref25","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1093\/nar\/gks469","article-title":"Seq2Logo: a method for construction and visualization of amino acid binding motifs and sequence profiles including sequence weighting, pseudo counts and two-sided representation of amino acid enrichment and depletion","volume":"40","author":"Thomsen","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2026091015403420500_ref26","first-page":"237","article-title":"Dragon software: an easy approach to molecular descriptor calculations","volume":"56","author":"Mauri","year":"2006","journal-title":"MATCH Commun Math Comput Chem"},{"key":"2026091015403420500_ref27","volume-title":"Schr\u00f6dinger Release 2025\u20131","year":"2025"},{"key":"2026091015403420500_ref28","volume-title":"Learning from Data","author":"Abu-Mostafa","year":"2012"},{"key":"2026091015403420500_ref29","volume-title":"Knime: The Konstanz Information Miner","author":"Berthold","year":"2007"},{"key":"2026091015403420500_ref30","doi-asserted-by":"publisher","first-page":"3680","DOI":"10.1007\/978-94-007-0753-5_1689","volume-title":"Encyclopedia of Quality of Life and Well-Being Research","author":"Das","year":"2014"},{"key":"2026091015403420500_ref31","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1021\/acs.jcim.9b01057","article-title":"Consensus versus individual QSARs in classification: comparison on a large-scale case study","volume":"60","author":"Valsecchi","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2026091015403420500_ref32","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1007\/s40484-016-0081-2","article-title":"Performance measures in evaluating machine learning based bioinformatics predictors for classifications","volume":"4","author":"Jiao","year":"2016","journal-title":"Quant Biol"},{"key":"2026091015403420500_ref33","volume-title":"Information Retrieval","author":"Van Rijsbergen","year":"1979","edition":"2nd"},{"key":"2026091015403420500_ref34","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem Med (Zagreb)"},{"key":"2026091015403420500_ref35","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recogn"},{"key":"2026091015403420500_ref36","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1038\/nrg3920","article-title":"Machine learning applications in genetics and genomics","volume":"16","author":"Libbrecht","year":"2015","journal-title":"Nat Rev Genet"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag484\/71022394\/bbag484.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag484\/71022394\/bbag484.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T19:40:38Z","timestamp":1789069238000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag484\/8790181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag484","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag484"}}