{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T17:32:46Z","timestamp":1774546366241,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T00:00:00Z","timestamp":1681171200000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2022YFF1203100"],"award-info":[{"award-number":["2022YFF1203100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou S& Research Plan","award":["202007030010"],"award-info":[{"award-number":["202007030010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Identifying the B-cell epitopes is an essential step for guiding rational vaccine development and immunotherapies. Since experimental approaches are expensive and time-consuming, many computational methods have been designed to assist B-cell epitope prediction. However, existing sequence-based methods have limited performance since they only use contextual features of the sequential neighbors while neglecting structural information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on the recent breakthrough of AlphaFold2 in protein structure prediction, we propose GraphBepi, a novel graph-based model for accurate B-cell epitope prediction. For one protein, the predicted structure from AlphaFold2 is used to construct the protein graph, where the nodes\/residues are encoded by ESM-2 learning representations. The graph is input into the edge-enhanced deep graph neural network (EGNN) to capture the spatial information in the predicted 3D structures. In parallel, a bidirectional long short-term memory neural networks (BiLSTM) are employed to capture long-range dependencies in the sequence. The learned low-dimensional representations by EGNN and BiLSTM are then combined into a multilayer perceptron for predicting B-cell epitopes. Through comprehensive tests on the curated epitope dataset, GraphBepi was shown to outperform the state-of-the-art methods by more than 5.5% and 44.0% in terms of AUC and AUPR, respectively. A web server is freely available at http:\/\/bio-web1.nscc-gz.cn\/app\/graphbepi.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The datasets, pre-computed features, source codes, and the trained model are available at https:\/\/github.com\/biomed-AI\/GraphBepi.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad187","type":"journal-article","created":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T11:07:36Z","timestamp":1681211256000},"source":"Crossref","is-referenced-by-count":58,"title":["Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3145-430X","authenticated-orcid":false,"given":"Yuansong","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"given":"Zhuoyi","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6098-9103","authenticated-orcid":false,"given":"Qianmu","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1428-6778","authenticated-orcid":false,"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7449-3093","authenticated-orcid":false,"given":"Weijiang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9943-4786","authenticated-orcid":false,"given":"Jianzhao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences and LPMC, Nankai University , Tianjin 300072, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6782-2813","authenticated-orcid":false,"given":"Yuedong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"},{"name":"Key Laboratory of Machine Intelligence and Advanced Computing (MOE), Sun Yat-sen University , Guangzhou 510000, China"}]}],"member":"286","published-online":{"date-parts":[[2023,4,11]]},"reference":[{"key":"2023042504402019200_btad187-B1","doi-asserted-by":"crossref","first-page":"bbac035","DOI":"10.1093\/bib\/bbac035","article-title":"LBCEPred: a machine learning model to predict linear B-cell epitopes","volume":"23","author":"Alghamdi","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023042504402019200_btad187-B2","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B3","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/322747a0","article-title":"Continuous and discontinuous protein antigenic determinants","volume":"322","author":"Barlow","year":"1986","journal-title":"Nature"},{"key":"2023042504402019200_btad187-B4","doi-asserted-by":"crossref","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":"2023042504402019200_btad187-B5","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1093\/bioinformatics\/btaa773","article-title":"EpiDope: a deep neural network for linear B-cell epitope prediction","volume":"37","author":"Collatz","year":"2021","journal-title":"Bioinformatics"},{"key":"2023042504402019200_btad187-B6","doi-asserted-by":"crossref","first-page":"bbab423","DOI":"10.1093\/bib\/bbab423","article-title":"epitope3D: a machine learning method for conformational B-cell epitope prediction","volume":"23","author":"da Silva","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023042504402019200_btad187-B7","author":"Devlin","year":"2018"},{"key":"2023042504402019200_btad187-B8","doi-asserted-by":"crossref","first-page":"W474","DOI":"10.1093\/nar\/gkw361","article-title":"SAbPred: a structure-based antibody prediction server","volume":"44","author":"Dunbar","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B9","author":"Elnaggar","year":"2020"},{"key":"2023042504402019200_btad187-B10","doi-asserted-by":"crossref","first-page":"531","DOI":"10.2174\/092986707780059698","article-title":"Synthetic peptides for the immunodiagnosis of human diseases","volume":"14","author":"Gomara","year":"2007","journal-title":"Curr Med Chem"},{"key":"2023042504402019200_btad187-B11","first-page":"9211","author":"Gong","year":"2019"},{"key":"2023042504402019200_btad187-B12","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1110\/ps.062405906","article-title":"Prediction of residues in discontinuous B-cell epitopes using protein 3D structures","volume":"15","author":"Haste Andersen","year":"2006","journal-title":"Protein Sci"},{"key":"2023042504402019200_btad187-B13","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"2023042504402019200_btad187-B14","doi-asserted-by":"crossref","first-page":"W24","DOI":"10.1093\/nar\/gkx346","article-title":"BepiPred-2.0: improving sequence-based B-cell epitope prediction using conformational epitopes","volume":"45","author":"Jespersen","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B15","doi-asserted-by":"crossref","first-page":"W5","DOI":"10.1093\/nar\/gkn201","article-title":"NCBI BLAST: a better web interface","volume":"36","author":"Johnson","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B16","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":"2023042504402019200_btad187-B17","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1002\/bip.360221211","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","author":"Kabsch","year":"1983","journal-title":"Biopolymers"},{"key":"2023042504402019200_btad187-B18","first-page":"1","author":"Kavitha","year":"2013"},{"key":"2023042504402019200_btad187-B19","doi-asserted-by":"crossref","first-page":"e1002829","DOI":"10.1371\/journal.pcbi.1002829","article-title":"Reliable B cell epitope predictions: impacts of method development and improved benchmarking","volume":"8","author":"Kringelum","year":"2012","journal-title":"PLoS Comput Biol"},{"key":"2023042504402019200_btad187-B20","author":"Lin","year":"2022"},{"key":"2023042504402019200_btad187-B21","volume-title":"Roitt's Essential Immunology","author":"Delves","year":"2016"},{"key":"2023042504402019200_btad187-B22","doi-asserted-by":"crossref","first-page":"6108","DOI":"10.1021\/ja0100120","article-title":"Group epitope mapping by saturation transfer difference NMR to identify segments of a ligand in direct contact with a protein receptor","volume":"123","author":"Mayer","year":"2001","journal-title":"J Am Chem Soc"},{"key":"2023042504402019200_btad187-B23","doi-asserted-by":"crossref","first-page":"D170","DOI":"10.1093\/nar\/gkw1081","article-title":"Uniclust databases of clustered and deeply annotated protein sequences and alignments","volume":"45","author":"Mirdita","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B24","volume-title":"Fundamental Immunology","author":"Paul","year":"2012"},{"key":"2023042504402019200_btad187-B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-9-514","article-title":"ElliPro: a new structure-based tool for the prediction of antibody epitopes","volume":"9","author":"Ponomarenko","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2023042504402019200_btad187-B26","doi-asserted-by":"crossref","first-page":"100628","DOI":"10.1016\/j.patter.2022.100628","article-title":"Quantitative evaluation of explainable graph neural networks for molecular property prediction","volume":"3","author":"Rao","year":"2022","journal-title":"Patterns (N Y)"},{"key":"2023042504402019200_btad187-B27","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nmeth.1818","article-title":"HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment","volume":"9","author":"Remmert","year":"2012","journal-title":"Nat Methods"},{"key":"2023042504402019200_btad187-B28","doi-asserted-by":"crossref","first-page":"e62216","DOI":"10.1371\/journal.pone.0062216","article-title":"Improved method for linear B-cell epitope prediction using antigen\u2019s primary sequence","volume":"8","author":"Singh","year":"2013","journal-title":"PLoS One"},{"key":"2023042504402019200_btad187-B29","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1038\/s41592-019-0437-4","article-title":"Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold","volume":"16","author":"Steinegger","year":"2019","journal-title":"Nat Methods"},{"key":"2023042504402019200_btad187-B30","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2023042504402019200_btad187-B31","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1093\/bioinformatics\/btm098","article-title":"UniRef: comprehensive and non-redundant UniProt reference clusters","volume":"23","author":"Suzek","year":"2007","journal-title":"Bioinformatics"},{"key":"2023042504402019200_btad187-B32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41592-022-01490-7","article-title":"ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction","volume":"19","author":"Tubiana","year":"2022","journal-title":"Nat Methods"},{"key":"2023042504402019200_btad187-B33","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1002\/prot.24100","article-title":"A new size-independent score for pairwise protein structure alignment and its application to structure classification and nucleic-acid binding prediction","volume":"80","author":"Yang","year":"2012","journal-title":"Proteins"},{"key":"2023042504402019200_btad187-B34","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1093\/bioinformatics\/btab643","article-title":"Structure-aware protein\u2013protein interaction site prediction using deep graph convolutional network","volume":"38","author":"Yuan","year":"2021","journal-title":"Bioinformatics"},{"issue":"6","key":"2023042504402019200_btad187-B35","doi-asserted-by":"crossref","first-page":"bbac444","DOI":"10.1093\/bib\/bbac444","article-title":"Alignment-free metal ion-binding site prediction from protein sequence through pretrained language model and multi-task learning","volume":"23","author":"Yuan","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023042504402019200_btad187-B36","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1093\/nar\/gkg571","article-title":"LGA: a method for finding 3D similarities in protein structures","volume":"31","author":"Zemla","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2023042504402019200_btad187-B37","author":"Zhang","year":"2022"},{"key":"2023042504402019200_btad187-B38","doi-asserted-by":"crossref","first-page":"W388","DOI":"10.1093\/nar\/gkz413","article-title":"SEPPA 3.0\u2014enhanced spatial epitope prediction enabling glycoprotein antigens","volume":"47","author":"Zhou","year":"2019","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad187\/49841456\/btad187.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad187\/50087105\/btad187.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad187\/50087105\/btad187.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T09:37:47Z","timestamp":1702201067000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad187\/7114029"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad187","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.12.06.519221","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,4,1]]},"published":{"date-parts":[[2023,4,1]]},"article-number":"btad187"}}