{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T17:10:20Z","timestamp":1767892220191,"version":"3.49.0"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T00:00:00Z","timestamp":1707696000000},"content-version":"vor","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["62301139"],"award-info":[{"award-number":["62301139"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225109"],"award-info":[{"award-number":["62225109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Viruses are the most abundant biological entities on earth and are important components of microbial communities. A metagenome contains all microorganisms from an environmental sample. Correctly identifying viruses from these mixed sequences is critical in viral analyses. It is common to identify long viral sequences, which has already been passed thought pipelines of assembly and binning. Existing deep learning-based methods divide these long sequences into short subsequences and identify them separately. This makes the relationships between them be omitted, leading to poor performance on identifying long viral sequences. In this paper, VirGrapher is proposed to improve the identification performance of long viral sequences by constructing relationships among short subsequences from long ones. VirGrapher see a long sequence as a graph and uses a Graph Convolutional Network (GCN) model to learn multilayer connections between nodes from sequences after a GCN-based node embedding model. VirGrapher achieves a better AUC value and accuracy on validation set, which is better than three benchmark methods.<\/jats:p>","DOI":"10.1093\/bib\/bbae036","type":"journal-article","created":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T07:41:51Z","timestamp":1707723711000},"source":"Crossref","is-referenced-by-count":5,"title":["VirGrapher: a graph-based viral identifier for long sequences from metagenomes"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7719-426X","authenticated-orcid":false,"given":"Yan","family":"Miao","sequence":"first","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , Hexing Road, 150040, Heilongjiang Province , China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7993-0194","authenticated-orcid":false,"given":"Zhenyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , Hexing Road, 150040, Heilongjiang Province , China"}]},{"given":"Chenjing","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , Hexing Road, 150040, Heilongjiang Province , China"}]},{"given":"Chen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , Xiangannan Road, 361104, Fujian Province , China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7381-2374","authenticated-orcid":false,"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , Hexing Road, 150040, Heilongjiang Province , China"}]},{"given":"Chunxue","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Landscape Architecture, Northeast Forestry University , Hexing Road, 150040, Heilongjiang Province , China"}]}],"member":"286","published-online":{"date-parts":[[2024,2,11]]},"reference":[{"issue":"1","key":"2024021207413747200_ref1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-023-01533-x","article-title":"Gauge your phage: benchmarking of bacteriophage identification tools in metagenomic sequencing data","volume":"11","author":"Ho","year":"2023","journal-title":"Microbiome"},{"issue":"2","key":"2024021207413747200_ref2","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1111\/brv.12271","article-title":"Deciphering the virus-to-prokaryote ratio (VPR): insights into virus\u2013host relationships in a variety of ecosystems","volume":"92","author":"Parikka","year":"2017","journal-title":"Biol Rev"},{"issue":"11","key":"2024021207413747200_ref3","doi-asserted-by":"crossref","first-page":"3119","DOI":"10.1038\/s41396-021-01012-x","article-title":"Community context matters for bacteria-phage ecology and evolution","volume":"15","author":"Blazanin","year":"2021","journal-title":"ISME J"},{"issue":"5","key":"2024021207413747200_ref4","doi-asserted-by":"crossref","DOI":"10.1084\/jem.20201044","article-title":"The dark side of the gut: virome\u2013host interactions in intestinal homeostasis and disease","volume":"218","author":"Li","year":"2021","journal-title":"J Exp Med"},{"issue":"1","key":"2024021207413747200_ref5","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1038\/s41467-023-35945-y","article-title":"ViralCC retrieves complete viral genomes and virus-host pairs from metagenomic hi-C data","volume":"14","author":"Du","year":"2023","journal-title":"Nat Commun"},{"issue":"2","key":"2024021207413747200_ref6","doi-asserted-by":"crossref","first-page":"vew022","DOI":"10.1093\/ve\/vew022","article-title":"Challenges in the analysis of viral metagenomes","volume":"2","author":"Rose","year":"2016","journal-title":"Virus Evol"},{"issue":"5","key":"2024021207413747200_ref7","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1093\/bioinformatics\/bty695","article-title":"Genome detective: an automated system for virus identification from high-throughput sequencing data","volume":"35","author":"Vilsker","year":"2019","journal-title":"Bioinformatics"},{"issue":"7","key":"2024021207413747200_ref8","doi-asserted-by":"crossref","first-page":"656","DOI":"10.3390\/v11070656","article-title":"Human virome and disease: high-throughput sequencing for virus discovery, identification of phage-bacteria dysbiosis and development of therapeutic approaches with emphasis on the human gut","volume":"11","author":"Santiago-Rodriguez","year":"2019","journal-title":"Viruses"},{"issue":"1","key":"2024021207413747200_ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-023-03142-1","article-title":"MicroPro: using metagenomic unmapped reads to provide insights into human microbiota and disease associations","volume":"25","author":"Zhu","year":"2019","journal-title":"Genome Biol"},{"issue":"1","key":"2024021207413747200_ref10","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s12864-021-08165-1","article-title":"Comparative genome analysis of plant ascomycete fungal pathogens with different lifestyles reveals distinctive virulence strategies","volume":"23","author":"Wang","year":"2022","journal-title":"BMC Genomics"},{"key":"2024021207413747200_ref11","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab094","article-title":"DisBalance: a platform to automatically build balance-based disease prediction models and discover microbial biomarkers from microbiome data","volume":"22","author":"Yang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024021207413747200_ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12866-021-02201-6","article-title":"Ecological and network analyses identify four microbial species with potential significance for the diagnosis\/treatment of ulcerative colitis (UC)","volume":"21","author":"Li","year":"2021","journal-title":"BMC Microbiol"},{"issue":"11","key":"2024021207413747200_ref13","doi-asserted-by":"crossref","first-page":"766","DOI":"10.15252\/msb.20145645","article-title":"Potential of fecal microbiota for early-stage detection of colorectal cancer","volume":"10","author":"Zeller","year":"2014","journal-title":"Mol Syst Biol"},{"key":"2024021207413747200_ref14","article-title":"Expansion of colorectal cancer biomarkers based on gut bacteria and viruses","volume":"14","author":"Zhang","year":"2022","journal-title":"Cancer"},{"key":"2024021207413747200_ref15","doi-asserted-by":"crossref","DOI":"10.3389\/fcimb.2022.918010","article-title":"Metagenomic analyses of multiple gut datasets revealed the association of phage signatures in colorectal cancer","volume":"12","author":"Zuo","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"issue":"6","key":"2024021207413747200_ref16","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1016\/j.cmi.2022.08.027","article-title":"Microbiome-phage interactions in inflammatory bowel disease","volume":"29","author":"Federici","year":"2023","journal-title":"Clin Microbiol Infect"},{"issue":"6914","key":"2024021207413747200_ref17","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1038\/420367a","article-title":"The importance of being erroneous","volume":"420","author":"Bonhoeffer","year":"2002","journal-title":"Nature"},{"key":"2024021207413747200_ref18","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab404","article-title":"Characterizing viral circRNAs and their application in identifying circRNAs in viruses","volume":"23","author":"Niu","year":"2022","journal-title":"Brief Bioinform"},{"issue":"3","key":"2024021207413747200_ref19","first-page":"1","article-title":"RNN-VirSeeker: a deep learning method for identification of short viral sequences from metagenomes","volume":"19","author":"Liu","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2024021207413747200_ref20","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1007\/s40484-019-0187-4","article-title":"Identifying viruses from metagenomic data using deep learning","volume":"8","author":"Ren","year":"2020","journal-title":"Quantitative Biology"},{"key":"2024021207413747200_ref21","doi-asserted-by":"crossref","DOI":"10.1093\/gigascience\/giz066","article-title":"PPR-meta: a tool for identifying phages and plasmids from metagenomic fragments using deep learning","volume":"8","author":"Fang","year":"2019","journal-title":"GigaScience"},{"issue":"5","key":"2024021207413747200_ref22","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1093\/bioinformatics\/btab845","article-title":"Virtifier: a deep learning-based identifier for viral sequences from metagenomes","volume":"38","author":"Miao","year":"2022","journal-title":"Bioinformatics"},{"key":"2024021207413747200_ref23","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.ymeth.2020.05.018","article-title":"CHEER: HierarCHical taxonomic classification for viral mEtagEnomic data via deep leaRning","volume":"189","author":"Shang","year":"2021","journal-title":"Methods"},{"key":"2024021207413747200_ref24","article-title":"Semi-supervised classification with graph convolutional networks","author":"Thomas","year":"2016"},{"issue":"1","key":"2024021207413747200_ref25","first-page":"1","article-title":"VirFinder: a novel k-mer based tool for identifying viral sequences from assembled metagenomic data","volume":"5","author":"Ren","year":"2017","journal-title":"Microbiomel"},{"issue":"3","key":"2024021207413747200_ref26","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"},{"issue":"1","key":"2024021207413747200_ref27","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1101\/gr.142315.112","article-title":"Time series community genomics analysis reveals rapid shifts in bacterial species, strains, and phage during infant gut colonization","volume":"23","author":"Sharon","year":"2013","journal-title":"Genome Res"},{"key":"2024021207413747200_ref28","doi-asserted-by":"crossref","first-page":"1169791","DOI":"10.3389\/fmicb.2023.1169791","article-title":"DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes","volume":"14","author":"Miao","year":"2023","journal-title":"Front Microbiol"},{"key":"2024021207413747200_ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11604","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Li","year":"2018"},{"key":"2024021207413747200_ref30","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2024021207413747200_ref31","article-title":"Bp-transformer: modelling long-range context via binary partitioning","author":"Ye","year":"2019"},{"key":"2024021207413747200_ref32","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N18-2074","article-title":"Self-attention with relative position representations","author":"Shaw","year":"2018"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/2\/bbae036\/56659752\/bbae036.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/2\/bbae036\/56659752\/bbae036.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T07:42:12Z","timestamp":1707723732000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae036\/7606365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,22]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,1,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae036","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3,1]]},"published":{"date-parts":[[2024,1,22]]},"article-number":"bbae036"}}