{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:55:03Z","timestamp":1789084503142,"version":"build-2803163510"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"vor","delay-in-days":44,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62176164"],"award-info":[{"award-number":["62176164"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515010992"],"award-info":[{"award-number":["2023A1515010992"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Committee Foundation of Shenzhen City","award":["JCYJ20220531101217039"],"award-info":[{"award-number":["JCYJ20220531101217039"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Phages, viruses that infect bacteria, offer a promising strategy against antibiotic-resistant pathogens. Phage viral proteins (PVPs) are essential for phage\u2013host interactions, yet their identification and functional annotation remain challenging due to high sequence diversity, limited experimental data, and class imbalance. To address these issues, we propose ProtPhage, a novel framework that leverages the ProtT5 protein language model for richer sequence representation compared to traditional methods. Additionally, ProtPhage incorporates an asymmetric loss function to mitigate class imbalance, significantly improving the prediction of the minority class \u201cminor capsid,\u201d with an F1 score 33.07$\\%$ higher than the best existing model. Extensive experiments demonstrate that ProtPhage outperforms current methods across multiple metrics, including accuracy, precision, recall, and F1 score. A case study on the Mycobacterium phage PDRPxv genome further validates its practical utility, while expanded experiments highlight its potential in phage\u2013host prediction. By integrating advanced deep learning techniques, ProtPhage establishes a new standard for PVP identification and annotation, contributing to the broader field of computational phage biology.<\/jats:p>","DOI":"10.1093\/bib\/bbaf285","type":"journal-article","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T04:13:57Z","timestamp":1749874437000},"source":"Crossref","is-referenced-by-count":5,"title":["ProtPhage: a deep learning framework for phage viral protein identification and functional annotation"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5440-4584","authenticated-orcid":false,"given":"Yuehua","family":"Ou","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , No. 3688 Nanhai Avenue, Nanshan District, Shenzhen, Guangdong, 518060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyi","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , No. 3688 Nanhai Avenue, Nanshan District, Shenzhen, Guangdong, 518060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningyu","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , No. 3688 Nanhai Avenue, Nanshan District, Shenzhen, Guangdong, 518060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Du","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , No. 3688 Nanhai Avenue, Nanshan District, Shenzhen, Guangdong, 518060 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,6,14]]},"reference":[{"key":"2025061400135416700_ref1","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1146\/annurev-virology-100114-054952","article-title":"Viruses as winners in the game of life","volume":"3","author":"G\u00fcemes","year":"2016","journal-title":"Annu Rev Virol"},{"key":"2025061400135416700_ref2","doi-asserted-by":"publisher","first-page":"638","DOI":"10.2471\/BLT.16.020916","article-title":"United nations meeting on antimicrobial resistance","volume":"94","author":"Humphreys","year":"2016","journal-title":"Bull World Health Organ"},{"key":"2025061400135416700_ref3","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1111\/1574-6976.12072","article-title":"Bacteria-phage coevolution as a driver of ecological and evolutionary processes in microbial communities","volume":"38","author":"Koskella","year":"2014","journal-title":"FEMS Microbiol Rev"},{"key":"2025061400135416700_ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104592118","article-title":"Coevolutionary phage training leads to greater bacterial suppression and delays the evolution of phage resistance","volume":"118","author":"Borin","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2025061400135416700_ref5","doi-asserted-by":"publisher","DOI":"10.3390\/v11070587","article-title":"Phages and human health: more than idle hitchhikers","volume":"11","author":"Lawrence","year":"2019","journal-title":"Viruses"},{"key":"2025061400135416700_ref6","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1038\/s41423-020-00532-4","article-title":"Phages and their potential to modulate the microbiome and immunity","volume":"18","author":"Federici","year":"2021","journal-title":"Cell Mol Immunol"},{"key":"2025061400135416700_ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbapap.2020.140406","article-title":"Review and comparative analysis of machine learning-based phage virion protein identification methods","volume":"1868","author":"Meng","year":"2020","journal-title":"Biochim Biophys Acta"},{"key":"2025061400135416700_ref8","first-page":"11","article-title":"Large-scale comparative review and assessment of computational methods for phage virion proteins identification","volume":"21","author":"Kabir","year":"2022","journal-title":"EXCLI J"},{"key":"2025061400135416700_ref9","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.985","article-title":"Virsorter: mining viral signal from microbial genomic data","volume":"3","author":"Roux","year":"2015","journal-title":"PeerJ"},{"key":"2025061400135416700_ref10","doi-asserted-by":"publisher","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":"2025061400135416700_ref11","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1146\/annurev-pathol-020712-164026","article-title":"Diagnostic applications of high-throughput DNA sequencing","volume":"8","author":"Boyd","year":"2013","journal-title":"Annu Rev Pathol: Mech Dis"},{"key":"2025061400135416700_ref12","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/978-1-60327-565-1_14","article-title":"Phage proteomics: applications of mass spectrometry","volume-title":"Bacteriophages: Methods and Protocols, Volume 2 Molecular and Applied Aspects. Methods in Molecular Biology","author":"Lavigne","year":"2009"},{"key":"2025061400135416700_ref13","doi-asserted-by":"publisher","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":"2025061400135416700_ref14","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1007\/s10822-020-00323-z","article-title":"Meta-iPVP: a sequence-based meta-predictor for improving the prediction of phage virion proteins using effective feature representation","volume":"34","author":"Charoenkwan","year":"2020","journal-title":"J Comput Aided Mol Des"},{"key":"2025061400135416700_ref15","doi-asserted-by":"publisher","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":"2025061400135416700_ref16","doi-asserted-by":"publisher","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":"2025061400135416700_ref17","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025061400135416700_ref18","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00015","article-title":"Asymmetric loss for multi-label classification","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ridnik","year":"2021"},{"key":"2025061400135416700_ref19","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3390\/cells9020353","article-title":"PVPred-SCM: improved prediction and analysis of phage virion proteins using a scoring card method","volume":"9","author":"Charoenkwan","year":"2020","journal-title":"Cells"},{"key":"2025061400135416700_ref20","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.tig.2017.12.009","article-title":"The definition of open reading frame revisited","volume":"34","author":"Sieber","year":"2018","journal-title":"Trends Genet"},{"key":"2025061400135416700_ref21","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1145\/130385.130401","article-title":"A training algorithm for optimal margin classifiers","volume-title":"Proceedings of the Fifth Annual Workshop on Computational Learning Theory","author":"Boser","year":"1992"},{"key":"2025061400135416700_ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2021.615711","article-title":"Virionfinder: identification of complete and partial prokaryote virus virion protein from virome data using the sequence and biochemical properties of amino acids","volume":"12","author":"Fang","year":"2021","journal-title":"Front Microbiol"},{"key":"2025061400135416700_ref23","doi-asserted-by":"publisher","first-page":"2219","DOI":"10.1142\/S0218127497001618","article-title":"Cnn: a vision of complexity","volume":"07","author":"Chua","year":"1997","journal-title":"Int J Bifurc Chaos"},{"key":"2025061400135416700_ref24","doi-asserted-by":"publisher","first-page":"i30","DOI":"10.1093\/bioinformatics\/btad229","article-title":"Phavip: phage virion protein classification based on chaos game representation and vision transformer","volume-title":"Bioinformatics","author":"Shang","year":"2023"},{"key":"2025061400135416700_ref25","doi-asserted-by":"publisher","first-page":"6263","DOI":"10.1016\/j.csbj.2021.11.008","article-title":"Chaos game representation and its applications in bioinformatics","volume":"19","author":"L\u00f6chel","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2025061400135416700_ref26","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"2025061400135416700_ref27","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1093\/bioinformatics\/btab681","article-title":"Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning","volume":"38","author":"Ren","year":"2022","journal-title":"Bioinformatics"},{"key":"2025061400135416700_ref28","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1186\/1471-2105-11-119","article-title":"Prodigal: prokaryotic gene recognition and translation initiation site identification","volume":"11","author":"Hyatt","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2025061400135416700_ref29","doi-asserted-by":"crossref","first-page":"W451","DOI":"10.1093\/nar\/gki487","article-title":"Genemark: web software for gene finding in prokaryotes, eukaryotes and viruses","volume":"33","author":"Besemer","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2025061400135416700_ref30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2021171118","article-title":"Deeptfactor: a deep learning-based tool for the prediction of transcription factors","volume":"118","author":"Kim","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2025061400135416700_ref31","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1038\/nbt0308-274","article-title":"Blosum62 miscalculations improve search performance","volume":"26","author":"Styczynski","year":"2008","journal-title":"Nat Biotechnol"},{"key":"2025061400135416700_ref32","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1126\/science.284.5418.1318","article-title":"Bacterial biofilms: a common cause of persistent infections","volume":"284","author":"William Costerton","year":"1999","journal-title":"Science"},{"key":"2025061400135416700_ref33","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"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf285\/63488711\/bbaf285.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf285\/63488711\/bbaf285.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T04:13:59Z","timestamp":1749874439000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf285\/8162444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,1]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf285","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,5]]},"published":{"date-parts":[[2025,5,1]]},"article-number":"bbaf285"}}