{"id":"https://openalex.org/W7141836698","doi":"https://doi.org/10.1093/bioinformatics/btag147","title":"GlycanGT: a pretrained graph transformer framework for glycan graph representation and generative learning","display_name":"GlycanGT: a pretrained graph transformer framework for glycan graph representation and generative learning","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141836698","doi":"https://doi.org/10.1093/bioinformatics/btag147","pmid":"https://pubmed.ncbi.nlm.nih.gov/41896185"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag147","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag147","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Akihiro Kitani","orcid":"https://orcid.org/0009-0004-2220-8109"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Kitani","raw_affiliation_strings":["Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","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,"],"raw_orcid":"https://orcid.org/0009-0004-2220-8109","affiliations":[{"raw_affiliation_string":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"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,","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bingyuan Zhang","orcid":"https://orcid.org/0000-0002-4892-323X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bingyuan Zhang","raw_affiliation_strings":["Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,"],"raw_orcid":"https://orcid.org/0000-0002-4892-323X","affiliations":[{"raw_affiliation_string":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Koichi Himori","orcid":"https://orcid.org/0009-0006-8878-9473"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Himori","raw_affiliation_strings":["Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,"],"raw_orcid":"https://orcid.org/0009-0006-8878-9473","affiliations":[{"raw_affiliation_string":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yusuke Matsui","orcid":"https://orcid.org/0000-0003-3977-4313"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Matsui","raw_affiliation_strings":["Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","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,"],"raw_orcid":"https://orcid.org/0000-0003-3977-4313","affiliations":[{"raw_affiliation_string":"Institute for Glyco-core Research (iGCORE), Nagoya University Systems Biology Division, , 1-7 Furo-cho, Chikusa-ku , Nagoya, Aichi, 464-0814,","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"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,","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":13.3617,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98727607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"42","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.18780000507831573,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.18780000507831573,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.10520000010728836,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.09459999948740005,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6815999746322632},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.64410001039505},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5372999906539917},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5232999920845032},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.382099986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639999985694885},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6815999746322632},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.64410001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6043999791145325},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5232999920845032},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45719999074935913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C206212055","wikidata":"https://www.wikidata.org/wiki/Q2553138","display_name":"Glycan","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2784999907016754}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098842","descriptor_name":"Generative Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011134","descriptor_name":"Polysaccharides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011134","descriptor_name":"Polysaccharides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011134","descriptor_name":"Polysaccharides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag147","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag147","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41896185","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41896185","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13105845","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13105845/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag147","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag147","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W145329232","https://openalex.org/W1182461782","https://openalex.org/W2083299750","https://openalex.org/W2084231038","https://openalex.org/W2085677500","https://openalex.org/W2098195379","https://openalex.org/W2140409722","https://openalex.org/W2743571801","https://openalex.org/W2962802538","https://openalex.org/W3009592511","https://openalex.org/W3036138343","https://openalex.org/W3095652813","https://openalex.org/W3097005383","https://openalex.org/W3165985851","https://openalex.org/W3171689166","https://openalex.org/W3174429003","https://openalex.org/W3195123625","https://openalex.org/W3196665029","https://openalex.org/W4283216796","https://openalex.org/W4375955654","https://openalex.org/W4385836591","https://openalex.org/W4401349719","https://openalex.org/W4402172725","https://openalex.org/W4410199045","https://openalex.org/W4413812868"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Glycans":[1,55],"are":[2,29,153,165],"highly":[3],"diverse":[4],"biological":[5],"sequences,":[6,114],"but":[7,36],"their":[8],"functional":[9],"understanding":[10],"has":[11],"lagged":[12],"behind":[13],"proteins":[14],"and":[15,42,62,65,93,104,122,144],"nucleic":[16],"acids.":[17],"Many":[18],"glycans":[19],"remain":[20],"ambiguously":[21],"annotated,":[22],"limiting":[23],"computational":[24,27],"analyses.":[25],"Existing":[26],"approaches":[28],"primarily":[30],"graph-based,":[31],"capturing":[32],"local":[33],"structural":[34],"features":[35],"struggling":[37],"to":[38],"model":[39,52,67,151],"global":[40],"patterns":[41],"incomplete":[43],"sequences.":[44],"RESULTS:":[45],"We":[46],"present":[47],"GlycanGT,":[48],"a":[49,71],"graph-transformer-based":[50],"pretrained":[51,69,150],"for":[53,90,112,119],"glycans.":[54],"were":[56],"represented":[57],"as":[58],"graphs":[59],"of":[60],"monosaccharides":[61],"glycosidic":[63,123],"bonds,":[64],"the":[66],"was":[68],"using":[70],"masked":[72],"language":[73],"modeling":[74],"objective.":[75],"GlycanGT":[76,108],"demonstrated":[77],"higher":[78],"performance":[79],"than":[80],"existing":[81],"methods":[82],"across":[83],"8":[84],"benchmark":[85],"tasks":[86],"(e.g.,":[87],"0.844":[88],"AUPRC":[89],"immunogenicity":[91],"classification),":[92],"its":[94],"embeddings":[95],"formed":[96],"biologically":[97],"relevant":[98],"clusters":[99],"that":[100],"recovered":[101],"known":[102],"N-":[103],"O-glycan":[105],"categories.":[106],"Moreover,":[107],"accurately":[109],"proposed":[110],"candidates":[111],"ambiguous":[113],"maintaining":[115],">80%":[116],"top-5":[117],"accuracy":[118],"both":[120],"monosaccharide":[121],"bond":[124],"predictions":[125],"under":[126],"high":[127],"masking":[128],"levels.":[129],"AVAILABILITY":[130],"AND":[131],"IMPLEMENTATION:":[132],"The":[133],"source":[134],"code":[135],"used":[136],"in":[137],"this":[138],"study":[139],"is":[140],"available":[141,166],"at":[142,167],"https://github.com/matsui-lab/GlycanGT":[143],"archived":[145],"on":[146],"Zenodo":[147],"(DOI:":[148],"10.5281/zenodo.18636040);":[149],"weights":[152],"provided":[154],"via":[155],"Hugging":[156],"Face":[157],"(https://huggingface.co/Akikitani295/GlycanGT).":[158],"CONTACT:":[159],"matsui.yusuke.d4@f.mail.nagoya-u.ac.jp.":[160],"SUPPLEMENTARY":[161],"INFORMATION:":[162],"Supplementary":[163],"data":[164],"Bioinformatics":[168],"online.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-02-16T00:00:00"}