{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T15:58:06Z","timestamp":1790438286661,"version":"4.1.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":235,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025YFA0922603"],"award-info":[{"award-number":["2025YFA0922603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573367"],"award-info":[{"award-number":["62573367"]}],"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":["62472363"],"award-info":[{"award-number":["62472363"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fuzhou Inter-institutional Science and Technology Cooperation Project","award":["2024-Y-018"],"award-info":[{"award-number":["2024-Y-018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Taxonomic classification of viral metagenomic contigs remains difficult for short or divergent sequences. Reference-based methods are precise when close homologs exist, whereas representation-based models can generalize beyond direct matches but lack explicit biological evidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Here, we present ViTax-RAG, a retrieval-augmented framework that integrates alignment-derived evidence with learned sequence representations for robust viral classification. ViTax-RAG reformulates BLAST as a domain-specific retrieval module and integrates retrieved homology information into a sequence modeling framework, thereby enabling the complementary use of alignment-based and representation-based signals. We evaluated ViTax-RAG on in-distribution (ID) and within-genus out-of-distribution (OOD) datasets, where it consistently outperformed current viral taxonomy methods at comparable taxonomic endpoints and supported fragment lengths. The pipeline processed all 195\u2009728 GOV 2.0 contigs; 87.2% of predictions terminated at class, demonstrating hierarchical backoff rather than fine-rank accuracy on data without ground truth.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>ViTax-RAG is implemented in Python and is freely available at GitHub (https:\/\/github.com\/Ying-Lab\/ViTax-Rag) under an open-source license. Documentation and example workflows are provided to facilitate integration into metagenomic analysis pipelines.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbag247","type":"journal-article","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T11:44:33Z","timestamp":1787399073000},"source":"Crossref","is-referenced-by-count":0,"title":["ViTax-RAG: a retrieval-augmented language modeling tool for viral contig taxonomic classification"],"prefix":"10.1093","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1813-6411","authenticated-orcid":false,"given":"Feng","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Automation, National Institute for Data Science in Health and Medicine, State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University , Xiamen, Fujian 361102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6141-6864","authenticated-orcid":false,"given":"Lan","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Automation, National Institute for Data Science in Health and Medicine, State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University , Xiamen, Fujian 361102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6845-6173","authenticated-orcid":false,"given":"Yushuang","family":"He","sequence":"additional","affiliation":[{"name":"Department of Automation, National Institute for Data Science in Health and Medicine, State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University , Xiamen, Fujian 361102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxing","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Automation, National Institute for Data Science in Health and Medicine, State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University , Xiamen, Fujian 361102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8766-5950","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, National Institute for Data Science in Health and Medicine, State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University , Xiamen, Fujian 361102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"2026092611013062300_vbag247-B1","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J Mol Biol"},{"key":"2026092611013062300_vbag247-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":"2026092611013062300_vbag247-B3","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-025-02946-9","volume-title":"Nat Biotechnol","author":"Bolduc","year":"2025"},{"key":"2026092611013062300_vbag247-B4","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"Camacho","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2026092611013062300_vbag247-B5","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1038\/s41587-023-01953-y","article-title":"Identification of mobile genetic elements with geNomad","volume":"42","author":"Camargo","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026092611013062300_vbag247-B6","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/j.cell.2019.03.040","article-title":"Marine DNA viral macro- and microdiversity from pole to pole","volume":"177","author":"Gregory","year":"2019","journal-title":"Cell"},{"key":"2026092611013062300_vbag247-B7","doi-asserted-by":"publisher","first-page":"bbaf041","DOI":"10.1093\/bib\/bbaf041","article-title":"Vitax: adaptive hierarchical viral taxonomy classification with a taxonomy belief tree on a foundation model","volume":"26","author":"He","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026092611013062300_vbag247-B8","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":"2026092611013062300_vbag247-B9","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092611013062300_vbag247-B10","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1038\/nature19094","article-title":"Uncovering Earth\u2019s virome","volume":"536","author":"Paez-Espino","year":"2016","journal-title":"Nature"},{"key":"2026092611013062300_vbag247-B11","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1038\/nbt.4306","article-title":"Minimum information about an uncultivated virus genome (MIUViG)","volume":"37","author":"Roux","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026092611013062300_vbag247-B12","doi-asserted-by":"crossref","first-page":"i25","DOI":"10.1093\/bioinformatics\/btab293","article-title":"Bacteriophage classification for assembled contigs using graph convolutional network","volume":"37","author":"Shang","year":"2021","journal-title":"Bioinformatics"},{"key":"2026092611013062300_vbag247-B13","doi-asserted-by":"publisher","first-page":"evae102","DOI":"10.1093\/gbe\/evae102","article-title":"Application and comparison of machine learning and database-based methods in taxonomic classification of high-throughput sequencing data","volume":"16","author":"Tian","year":"2024","journal-title":"Genome Biol Evol"},{"key":"2026092611013062300_vbag247-B14","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1186\/s13059-019-1817-x","article-title":"Robust taxonomic classification of uncharted microbial sequences and bins with CAT and BAT","volume":"20","author":"von Meijenfeldt","year":"2019","journal-title":"Genome Biol"},{"key":"2026092611013062300_vbag247-B15","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with Kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"},{"key":"2026092611013062300_vbag247-B16","doi-asserted-by":"crossref","DOI":"10.1007\/s12539-026-00820-z","article-title":"PhaGCN_Cluster: a scalable and robust framework for automated classification and discovery of viral dark matter from metagenomes","author":"Xia","year":"2026","journal-title":"Interdiscip Sci Comput Life Sci"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/advance-article-pdf\/doi\/10.1093\/bioadv\/vbag247\/70772395\/vbag247.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag247\/70772395\/vbag247.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag247\/70772395\/vbag247.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T15:01:40Z","timestamp":1790434900000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbag247\/8769635"}},"subtitle":[],"editor":[{"given":"Nicola","family":"Mulder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":16,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbag247","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"vbag247"}}