{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T05:47:03Z","timestamp":1781934423396,"version":"3.54.5"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:00:00Z","timestamp":1774656000000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Human Glycome Atlas Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Glycans are highly diverse biological sequences, but their functional understanding has lagged behind proteins and nucleic acids. Many glycans remain ambiguously annotated, limiting computational analyses. Existing computational approaches are primarily graph-based, capturing local structural features but struggling to model global patterns and incomplete sequences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present GlycanGT, a graph-transformer-based pretrained model for glycans. Glycans were represented as graphs of monosaccharides and glycosidic bonds, and the model was pretrained using a masked language modeling objective. GlycanGT demonstrated higher performance than existing methods across 8 benchmark tasks (e.g., 0.844 AUPRC for immunogenicity classification), and its embeddings formed biologically relevant clusters that recovered known N- and O-glycan categories. Moreover, GlycanGT accurately proposed candidates for ambiguous sequences, maintaining &amp;gt;80% top-5 accuracy for both monosaccharide and glycosidic bond predictions under high masking levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code used in this study is available at https:\/\/github.com\/matsui-lab\/GlycanGT and archived on Zenodo (DOI: 10.5281\/zenodo.18636040); pretrained model weights are provided via Hugging Face (https:\/\/huggingface.co\/Akikitani295\/GlycanGT).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Contact<\/jats:title>\n                    <jats:p>matsui.yusuke.d4@f.mail.nagoya-u.ac.jp<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag147","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:46:27Z","timestamp":1774529187000},"source":"Crossref","is-referenced-by-count":2,"title":["GlycanGT: a pretrained graph transformer framework for glycan graph representation and generative learning"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2220-8109","authenticated-orcid":false,"given":"Akihiro","family":"Kitani","sequence":"first","affiliation":[{"name":"Nagoya University Graduate School of Medicine Biomedical and Health Informatics Unit, Department of Integrated Health Sciences, , 1-1-20 Daiko-minami, Higashi-ku , Nagoya, Aichi, 461-8673,","place":["Japan"]},{"name":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-323X","authenticated-orcid":false,"given":"Bingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8878-9473","authenticated-orcid":false,"given":"Koichi","family":"Himori","sequence":"additional","affiliation":[{"name":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3977-4313","authenticated-orcid":false,"given":"Yusuke","family":"Matsui","sequence":"additional","affiliation":[{"name":"Nagoya University Graduate School of Medicine Biomedical and Health Informatics Unit, Department of Integrated Health Sciences, , 1-1-20 Daiko-minami, Higashi-ku , Nagoya, Aichi, 461-8673,","place":["Japan"]},{"name":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"2026042409465219700_btag147-B1","doi-asserted-by":"crossref","first-page":"4988","DOI":"10.1038\/s41467-021-25183-5","article-title":"Correcting for sparsity and interdependence in glycomics by accounting for glycan biosynthesis","volume":"12","author":"Bao","year":"2021","journal-title":"Nat Commun"},{"key":"2026042409465219700_btag147-B2","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S1674-8301(11)60031-6","article-title":"The role of intracellular protein O-glycosylation in cell adhesion and disease","volume":"25","author":"Bektas","year":"2011","journal-title":"J Biomed Res"},{"key":"2026042409465219700_btag147-B3","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.chom.2020.10.004","article-title":"Deep-learning resources for studying glycan-mediated host-microbe interactions","volume":"29","author":"Bojar","year":"2021","journal-title":"Cell Host Microbe"},{"key":"2026042409465219700_btag147-B4","first-page":"144","author":"Boser","year":"1992"},{"key":"2026042409465219700_btag147-B5","doi-asserted-by":"publisher","first-page":"109251","DOI":"10.1016\/j.celrep.2021.109251","article-title":"Using graph convolutional neural networks to learn a representation for glycans","volume":"35","author":"Burkholz","year":"2021","journal-title":"Cell Rep"},{"key":"2026042409465219700_btag147-B6","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/s12859-020-3374-4","article-title":"Identifying glycan motifs using a novel subtree mining approach","volume":"21","author":"Coff","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2026042409465219700_btag147-B7","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2026042409465219700_btag147-B8","doi-asserted-by":"publisher","first-page":"D1529","DOI":"10.1093\/nar\/gkaa947","article-title":"The international glycan repository glytoucan version 3.0","volume":"49","author":"Fujita","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026042409465219700_btag147-B9","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s10719-012-9386-1","article-title":"Potential roles of N-glycosylation in cell adhesion","volume":"29","author":"Gu","year":"2012","journal-title":"Glycoconj J"},{"key":"2026042409465219700_btag147-B10","doi-asserted-by":"publisher","first-page":"112605","DOI":"10.1016\/j.isci.2025.112605","article-title":"Effect of glycosylation on protein folding: From biological roles to chemical protein synthesis","volume":"28","author":"Hao","year":"2025","journal-title":"iScience"},{"key":"2026042409465219700_btag147-B11","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1146\/annurev-biochem-060608-102511","article-title":"Cross talk between O-glcnacylation and phosphorylation: roles in signaling, transcription, and chronic disease","volume":"80","author":"Hart","year":"2011","journal-title":"Annu Rev Biochem"},{"key":"2026042409465219700_btag147-B12","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41392-024-01886-1","article-title":"Glycosylation: mechanisms, biological functions and clinical implications","volume":"9","author":"He","year":"2024","journal-title":"Signal Transduct Target Ther"},{"key":"2026042409465219700_btag147-B13","author":"Joeres","year":"2024"},{"key":"2026042409465219700_btag147-B14","author":"Kaplan","year":"2020"},{"key":"2026042409465219700_btag147-B15","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke"},{"key":"2026042409465219700_btag147-B16","author":"Kim"},{"key":"2026042409465219700_btag147-B17","doi-asserted-by":"publisher","first-page":"108008","DOI":"10.1016\/j.biotechadv.2022.108008","article-title":"Artificial intelligence in the analysis of glycosylation data","volume":"60","author":"Li","year":"2022","journal-title":"Biotechnol Adv"},{"key":"2026042409465219700_btag147-B18","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1007\/s10994-021-05991-y","article-title":"Learning subtree pattern importance for Weisfeiler-Lehman based graph kernels","volume":"110","author":"Nguyen","year":"2021","journal-title":"Mach Learn"},{"key":"2026042409465219700_btag147-B19","author":"Oono"},{"key":"2026042409465219700_btag147-B20","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1038\/s41423-023-01074-1","article-title":"Immune regulatory networks coordinated by glycans and glycan-binding proteins in autoimmunity and infection","volume":"20","author":"Pinho","year":"2023","journal-title":"Cell Mol Immunol"},{"key":"2026042409465219700_btag147-B21","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1038\/nrc3982","article-title":"Glycosylation in cancer: mechanisms and clinical implications","volume":"15","author":"Pinho","year":"2015","journal-title":"Nat Rev Cancer"},{"key":"2026042409465219700_btag147-B22","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1093\/glycob\/cwp187","article-title":"A motif-based analysis of glycan array data to determine the specificities of glycan-binding proteins","volume":"20","author":"Porter","year":"2010","journal-title":"Glycobiology"},{"key":"2026042409465219700_btag147-B23","doi-asserted-by":"publisher","first-page":"2390","DOI":"10.1002\/1873-3468.13541","article-title":"Translation of genome to glycome: role of the golgi apparatus","volume":"593","author":"Pothukuchi","year":"2019","journal-title":"FEBS Lett"},{"key":"2026042409465219700_btag147-B24","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1038\/s41398-023-02446-x","article-title":"Glycosylation and behavioral symptoms in neurological disorders","volume":"13","author":"Pradeep","year":"2023","journal-title":"Transl Psychiatry"},{"key":"2026042409465219700_btag147-B25","author":"Ramp\u00e1\u0161ek"},{"key":"2026042409465219700_btag147-B26","first-page":"593","author":"Schlichtkrull"},{"key":"2026042409465219700_btag147-B27","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1093\/glycob\/cwab067","article-title":"Glycowork: A python package for glycan data science and machine learning","volume":"31","author":"Thom\u00e8s","year":"2021","journal-title":"Glycobiology"},{"key":"2026042409465219700_btag147-B28","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1093\/glycob\/cwx066","article-title":"GlyTouCan: An accessible glycan structure repository","volume":"27","author":"Tiemeyer","year":"2017","journal-title":"Glycobiology"},{"key":"2026042409465219700_btag147-B29","doi-asserted-by":"publisher","first-page":"110641","DOI":"10.1016\/j.jbc.2025.110641","article-title":"Sialic acids in cancer biology and immunity-recent advancements","volume":"301","author":"Van Vliet","year":"2025","journal-title":"J Biol Chem"},{"key":"2026042409465219700_btag147-B30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/glycob\/cww086","article-title":"Biological roles of glycans","volume":"27","author":"Varki","year":"2017","journal-title":"Glycobiology"},{"key":"2026042409465219700_btag147-B31","author":"Vaswani"},{"key":"2026042409465219700_btag147-B32","doi-asserted-by":"publisher","first-page":"2376","DOI":"10.1126\/science.1058714","article-title":"Glycosylation of nucleocytoplasmic proteins: signal transduction and O-glcnac","volume":"291","author":"Wells","year":"2001","journal-title":"Science"},{"key":"2026042409465219700_btag147-B33","author":"Xu"},{"key":"2026042409465219700_btag147-B34","author":"Xu"},{"key":"2026042409465219700_btag147-B35","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/s41592-020-0879-8","article-title":"The glycosmos portal: A unified and comprehensive web resource for the glycosciences","volume":"17","author":"Yamada","year":"2020","journal-title":"Nat Methods"},{"key":"2026042409465219700_btag147-B36","author":"Ying"},{"key":"2026042409465219700_btag147-B37","author":"Yun"},{"key":"2026042409465219700_btag147-B38","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.3724\/abbs.2024136","article-title":"Glycosylation in aging and neurodegenerative diseases","volume":"56","author":"Zhang","year":"2024","journal-title":"Acta Biochim Biophys Sin (Shanghai)"},{"key":"2026042409465219700_btag147-B39","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-030-70115-4_11","article-title":"The role of glycosylation in infectious diseases","volume":"1325","author":"Zhang","year":"2021","journal-title":"Adv Exp Med Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag147\/67605188\/btag147.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/4\/btag147\/67605188\/btag147.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/4\/btag147\/67605188\/btag147.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T13:46:59Z","timestamp":1777038419000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag147\/8551567"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag147","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,3,27]]},"article-number":"btag147"}}