{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T13:45:04Z","timestamp":1782913504723,"version":"3.54.5"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62531002"],"award-info":[{"award-number":["62531002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425107"],"award-info":[{"award-number":["62425107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373080"],"award-info":[{"award-number":["62373080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The accurate classification of phage proteins is critical for advancing bacteriophage research. Despite the proliferation of machine learning approaches in this domain, the persistent issue of data imbalance continues to hinder performance, particularly for rare protein sequences. Previous attempts to address this by re-weighting minority classes have faced limitations due to insufficient feature extraction capabilities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In this paper, we introduce EAGP, a novel approach that integrates a generative model\u2014functionally equivalent to a WGAN yet tailored for one-dimensional data\u2014with the Evolutionary Scale Modeling (ESM) protein large language model for robust feature extraction. EAGP exhibits exceptional performance in binary classification and protein function annotation tasks. Crucially, our method not only improves overall classification efficacy but also significantly alleviates the performance degradation typically observed in minority classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and Implementation<\/jats:title>\n                    <jats:p>The data and code underlying this article are available in GitHub at https:\/\/github.com\/Innerly\/EAGP and have been archived on Zenodo at https:\/\/doi.org\/10.5281\/zenodo.19928069.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag373","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:04:31Z","timestamp":1781550271000},"source":"Crossref","is-referenced-by-count":0,"title":["EAGP: an efficient generative augmentation framework for phage protein classification under severe class imbalance"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6274-2880","authenticated-orcid":false,"given":"Jiaru","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China , Qingdao, Shandong 266100,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China , Qingdao, Shandong 266100,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3408-5375","authenticated-orcid":false,"given":"Yansu","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China , Chengdu, 610054,","place":["China"]},{"name":"Institute of Digital Health, Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China , Quzhou 324003,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-1142","authenticated-orcid":false,"given":"Quan","family":"Zou","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China , Chengdu, 610054,","place":["China"]},{"name":"Institute of Digital Health, Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China , Quzhou 324003,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongling","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine , Shanghai, 200233,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"2026063023013810800_btag373-B1","first-page":"6754","article-title":"Banach Wasserstein GAN","volume":"31","author":"Adler","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026063023013810800_btag373-B2","doi-asserted-by":"crossref","first-page":"3387","DOI":"10.1093\/bioinformatics\/btx431","article-title":"Deeploc: prediction of protein subcellular localization using deep learning","volume":"33","author":"Almagro Armenteros","year":"2017","journal-title":"Bioinformatics"},{"key":"2026063023013810800_btag373-B3","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.compbiomed.2005.09.002","article-title":"Machine learning in bioinformatics: a brief survey and recommendations for practitioners","volume":"36","author":"Bhaskar","year":"2006","journal-title":"Comput Biol Med"},{"key":"2026063023013810800_btag373-B4","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1038\/s41598-021-81063-4","article-title":"Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins","volume":"11","author":"Boeckaerts","year":"2021","journal-title":"Sci Rep"},{"key":"2026063023013810800_btag373-B5","doi-asserted-by":"crossref","first-page":"e1007845","DOI":"10.1371\/journal.pcbi.1007845","article-title":"PhANNs, a fast and accurate tool and web server to classify phage structural proteins","volume":"16","author":"Cantu","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2026063023013810800_btag373-B6","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume":"32","author":"Cao","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026063023013810800_btag373-B7","doi-asserted-by":"crossref","first-page":"262","DOI":"10.2174\/157016409789973707","article-title":"Pseudo amino acid composition and its applications in bioinformatics, proteomics and system biology","volume":"6","author":"Chou","year":"2009","journal-title":"CP"},{"key":"2026063023013810800_btag373-B8","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1038\/s41579-019-0311-5","article-title":"Phage diversity, genomics and phylogeny","volume":"18","author":"Dion","year":"2020","journal-title":"Nat Rev Microbiol"},{"key":"2026063023013810800_btag373-B9","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: towards cracking the language of life\u2019s code through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026063023013810800_btag373-B10","doi-asserted-by":"crossref","first-page":"giac076","DOI":"10.1093\/gigascience\/giac076","article-title":"DeePVP: identification and classification of phage virion proteins using deep learning","volume":"11","author":"Fang","year":"2022","journal-title":"GigaScience"},{"key":"2026063023013810800_btag373-B11","doi-asserted-by":"publisher","first-page":"6517","DOI":"10.1038\/s41467-023-42114-8","article-title":"Distantly related alteromonas bacteriophages share tail fibers exhibiting properties of transient chaperone caps","volume":"14","author":"Gonzalez-Serrano","year":"2023","journal-title":"Nat Commun"},{"key":"2026063023013810800_btag373-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J Big Data"},{"key":"2026063023013810800_btag373-B13","doi-asserted-by":"crossref","first-page":"100003","DOI":"10.1016\/j.curpro.2025.100003","article-title":"Machine learning-based classification of viral membrane proteins","volume":"22","author":"Kissanga","year":"2025","journal-title":"Curr Proteomics"},{"key":"2026063023013810800_btag373-B14","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.chom.2019.01.014","article-title":"Phage therapy: a renewed approach to combat antibiotic-resistant bacteria","volume":"25","author":"Kortright","year":"2019","journal-title":"Cell Host Microbe"},{"key":"2026063023013810800_btag373-B15","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","article-title":"Learning from imbalanced data: open challenges and future directions","volume":"5","author":"Krawczyk","year":"2016","journal-title":"Prog Artif Intell"},{"key":"2026063023013810800_btag373-B16","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1186\/1471-2180-9-224","article-title":"Classification of Myoviridae bacteriophages using protein sequence similarity","volume":"9","author":"Lavigne","year":"2009","journal-title":"BMC Microbiol"},{"key":"2026063023013810800_btag373-B17","doi-asserted-by":"crossref","first-page":"196","DOI":"10.3390\/v15010196","article-title":"Phage adsorption to gram-positive bacteria","volume":"15","author":"Leprince","year":"2023","journal-title":"Viruses"},{"key":"2026063023013810800_btag373-B18","doi-asserted-by":"crossref","first-page":"170105","DOI":"10.1007\/s11432-024-4485-0","article-title":"From intention to implementation: automating biomedical research via llms","volume":"68","author":"Luo","year":"2025","journal-title":"Sci China Inf Sci"},{"key":"2026063023013810800_btag373-B19","doi-asserted-by":"crossref","first-page":"77121","DOI":"10.18632\/oncotarget.20365","article-title":"MLACP: machine-learning-based prediction of anticancer peptides","volume":"8","author":"Manavalan","year":"2017","journal-title":"Oncotarget"},{"key":"2026063023013810800_btag373-B20","doi-asserted-by":"crossref","first-page":"276","DOI":"10.3389\/fphar.2018.00276","article-title":"AIPpred: sequence-based prediction of anti-inflammatory peptides using random forest","volume":"9","author":"Manavalan","year":"2018","journal-title":"Front Pharmacol"},{"key":"2026063023013810800_btag373-B21","doi-asserted-by":"crossref","first-page":"476","DOI":"10.3389\/fmicb.2018.00476","article-title":"PVP-SVM: sequence-based prediction of phage virion proteins using a support vector machine","volume":"9","author":"Manavalan","year":"2018","journal-title":"Front Microbiol"},{"key":"2026063023013810800_btag373-B22","doi-asserted-by":"crossref","first-page":"2757","DOI":"10.1093\/bioinformatics\/bty1047","article-title":"mAHTPred: a sequence-based meta-predictor for improving the prediction of anti-hypertensive peptides using effective feature representation","volume":"35","author":"Manavalan","year":"2019","journal-title":"Bioinformatics"},{"key":"2026063023013810800_btag373-B23","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"Min","year":"2017","journal-title":"Brief Bioinform"},{"key":"2026063023013810800_btag373-B24","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/S0140-6736(21)02724-0","article-title":"Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis","volume":"399","author":"Murray","year":"2022","journal-title":"Lancet"},{"key":"2026063023013810800_btag373-B25","doi-asserted-by":"publisher","first-page":"bbaf285","DOI":"10.1093\/bib\/bbaf285","article-title":"ProtPhage: a deep learning framework for phage viral protein identification and functional annotation","volume":"26","author":"Ou","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026063023013810800_btag373-B26","doi-asserted-by":"crossref","first-page":"i30","DOI":"10.1093\/bioinformatics\/btad229","article-title":"PhaVIP: Phage VIrion Protein classification based on chaos game representation and vision transformer","volume":"39","author":"Shang","year":"2023","journal-title":"Bioinformatics"},{"key":"2026063023013810800_btag373-B27","doi-asserted-by":"crossref","first-page":"197884","DOI":"10.1016\/j.virusres.2020.197884","article-title":"Characterization and genome analysis of B1 sub-cluster mycobacteriophage PDRPxv","volume":"279","author":"Sinha","year":"2020","journal-title":"Virus Res"},{"key":"2026063023013810800_btag373-B28","first-page":"3645","author":"Strubell","year":"2019"},{"key":"2026063023013810800_btag373-B29","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nature04160","article-title":"Viruses in the sea","volume":"437","author":"Suttle","year":"2005","journal-title":"Nature"},{"key":"2026063023013810800_btag373-B30","doi-asserted-by":"crossref","first-page":"360","DOI":"10.2174\/1574893609666140829204535","article-title":"A review of class imbalance learning methods in bioinformatics","volume":"10","author":"Yu","year":"2015","journal-title":"CBIO"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag373\/68530125\/btag373.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag373\/68530125\/btag373.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag373\/68530125\/btag373.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:50:50Z","timestamp":1782910250000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag373\/8708320"}},"subtitle":[],"editor":[{"given":"Can","family":"Alkan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag373","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,6,1]]},"article-number":"btag373"}}