{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:36:23Z","timestamp":1783640183895,"version":"3.55.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T00:00:00Z","timestamp":1720915200000},"content-version":"vor","delay-in-days":52,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hong Kong Research Grants Council"},{"name":"General Research Fund","award":["11206819"],"award-info":[{"award-number":["11206819"]}]},{"name":"General Research Fund","award":["11217521"],"award-info":[{"award-number":["11217521"]}]},{"DOI":"10.13039\/501100007156","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"crossref","award":["MRP\/071\/20X"],"award-info":[{"award-number":["MRP\/071\/20X"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Profile hidden Markov models (pHMMs) are able to achieve high sensitivity in remote homology search, making them popular choices for detecting novel or highly diverged viruses in metagenomic data. However, many existing pHMM databases have different design focuses, making it difficult for users to decide the proper one to use. In this review, we provide a thorough evaluation and comparison for multiple commonly used profile HMM databases for viral sequence discovery in metagenomic data. We characterized the databases by comparing their sizes, their taxonomic coverage, and the properties of their models using quantitative metrics. Subsequently, we assessed their performance in virus identification across multiple application scenarios, utilizing both simulated and real metagenomic data. We aim to offer researchers a thorough and critical assessment of the strengths and limitations of different databases. Furthermore, based on the experimental results obtained from the simulated and real metagenomic data, we provided practical suggestions for users to optimize their use of pHMM databases, thus enhancing the quality and reliability of their findings in the field of viral metagenomics.<\/jats:p>","DOI":"10.1093\/bib\/bbae292","type":"journal-article","created":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T11:20:17Z","timestamp":1720956017000},"source":"Crossref","is-referenced-by-count":7,"title":["Utilizing profile hidden Markov model databases for discovering viruses from metagenomic data: a comprehensive review"],"prefix":"10.1093","volume":"25","author":[{"given":"Runzhou","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong , Tat Chee Avenue, Kowloon, Hong Kong , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong , Tat Chee Avenue, Kowloon, Hong Kong , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theo Y C","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong , Tat Chee Avenue, Kowloon, Hong Kong , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanni","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong , Tat Chee Avenue, Kowloon, Hong Kong , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"2024071411200524200_ref1","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1038\/nrmicro1163","article-title":"Viral metagenomics","volume":"3","author":"Edwards","year":"2005","journal-title":"Nat Rev Microbiol"},{"key":"2024071411200524200_ref2","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1038\/nrmicro.2016.177","article-title":"Virus taxonomy in the age of metagenomics","volume":"15","author":"Simmonds","year":"2017","journal-title":"Nat Rev Microbiol"},{"key":"2024071411200524200_ref3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13100-017-0095-y","article-title":"Viral communities of the human gut: metagenomic analysis of composition and dynamics","volume":"8","author":"Aggarwala","year":"2017","journal-title":"Mobile DNA"},{"key":"2024071411200524200_ref4","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011422","article-title":"VIRify: an integrated detection, annotation and taxonomic classification pipeline using virus-specific protein profile hidden Markov models","volume":"19","author":"Rangel-Pineros","year":"2023","journal-title":"PLoS Comput Biol"},{"key":"2024071411200524200_ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-020-00990-y","article-title":"VirSorter2: a multi-classifier, expert-guided approach to detect diverse DNA and RNA viruses","volume":"9","author":"Guo","year":"2021","journal-title":"Microbiome"},{"key":"2024071411200524200_ref6","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1038\/s41587-020-00774-7","article-title":"CheckV assesses the quality and completeness of metagenome-assembled viral genomes","volume":"39","author":"Nayfach","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2024071411200524200_ref7","doi-asserted-by":"crossref","first-page":"btad093","DOI":"10.1093\/bioinformatics\/btad093","article-title":"VirBot: an RNA viral contig detector for metagenomic data","volume":"39","author":"Chen","year":"2023","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref8","first-page":"veac082","article-title":"RdRp-scan: a bioinformatic resource to identify and annotate divergent RNA viruses in metagenomic sequence data. Virus","volume":"8","author":"Charon","year":"2022","journal-title":"Evolution"},{"key":"2024071411200524200_ref9","first-page":"1","article-title":"Identification of mobile genetic elements with genomad","author":"Camargo","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2024071411200524200_ref10","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"Eddy","year":"1998","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref11","doi-asserted-by":"crossref","first-page":"402","DOI":"10.2174\/138920209789177575","article-title":"Hidden Markov models and their applications in biological sequence analysis","volume":"10","author":"Yoon","year":"2009","journal-title":"Curr Genomics"},{"key":"2024071411200524200_ref12","doi-asserted-by":"crossref","first-page":"29","DOI":"10.2147\/AGG.S136574","article-title":"Use of profile hidden markov models in viral discovery: current insights","volume":"7","author":"Reyes","year":"2017","journal-title":"Adv Genom Genet"},{"key":"2024071411200524200_ref13","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0105067","article-title":"Profile hidden Markov models for the detection of viruses within metagenomic sequence data","volume":"9","author":"Skewes-Cox","year":"2014","journal-title":"PLoS One"},{"key":"2024071411200524200_ref14","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0036566","article-title":"Classification of HIV-1 sequences using profile hidden Markov models","volume":"7","author":"Dwivedi","year":"2012","journal-title":"PLoS One"},{"key":"2024071411200524200_ref15","doi-asserted-by":"crossref","first-page":"D491","DOI":"10.1093\/nar\/gkw975","article-title":"Prokaryotic virus orthologous groups (pVOGs): a resource for comparative genomics and protein family annotation","volume":"45","author":"Grazziotin","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref16","first-page":"251","article-title":"Profile hidden Markov model for detection and prediction of hepatitis C virus mutation","volume":"9","author":"El Nahas","year":"2012","journal-title":"Int J Comput Sci"},{"key":"2024071411200524200_ref17","doi-asserted-by":"crossref","first-page":"D412","DOI":"10.1093\/nar\/gkaa913","article-title":"Pfam: the protein families database in 2021","volume":"49","author":"Mistry","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref18","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1093\/bioinformatics\/btz859","article-title":"KofamKOALA: KEGG ortholog assignment based on profile HMM and adaptive score threshold","volume":"36","author":"Aramaki","year":"2020","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref19","doi-asserted-by":"crossref","first-page":"D490","DOI":"10.1093\/nar\/gky1130","article-title":"The SUPERFAMILY 2.0 database: a significant proteome update and a new webserver","volume":"47","author":"Pandurangan","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref20","volume-title":"Virus orthologous groups database"},{"key":"2024071411200524200_ref21","doi-asserted-by":"crossref","first-page":"D250","DOI":"10.1093\/nar\/gkm796","article-title":"eggNOG: automated construction and annotation of orthologous groups of genes","volume":"36","author":"Jensen","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref22","doi-asserted-by":"crossref","first-page":"D309","DOI":"10.1093\/nar\/gky1085","article-title":"Eggnog 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses","volume":"47","author":"Huerta-Cepas","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref23","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref24","doi-asserted-by":"crossref","first-page":"D286","DOI":"10.1093\/nar\/gkv1248","article-title":"eggNOG 4.5: a hierarchical orthology framework with improved functional annotations for eukaryotic, prokaryotic and viral sequences","volume":"44","author":"Huerta-Cepas","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref25","doi-asserted-by":"crossref","first-page":"D389","DOI":"10.1093\/nar\/gkac1022","article-title":"eggNOG 6.0: enabling comparative genomics across 12 535 organisms","volume":"51","author":"Hern\u00e1ndez-Plaza","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref26","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1002\/(SICI)1097-0134(199707)28:3<405::AID-PROT10>3.0.CO;2-L","article-title":"Pfam: a comprehensive database of protein domain families based on seed alignments","volume":"28","author":"Sonnhammer","year":"1997","journal-title":"Proteins: Struct Funct Bioinf"},{"key":"2024071411200524200_ref27","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1002\/0470857897.ch8","article-title":"The KEGG database","volume":"247","author":"Kanehisa","year":"2002","journal-title":"Novartis Found Symp"},{"key":"2024071411200524200_ref28","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1093\/bioinformatics\/btu105","article-title":"Challenges in RNA virus bioinformatics","volume":"30","author":"Marz","year":"2014","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref29","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1093\/nar\/30.1.289","article-title":"SUPFAM\u2014a database of potential protein superfamily relationships derived by comparing sequence-based and structure-based families: implications for structural genomics and function annotation in genomes","volume":"30","author":"Pandit","year":"2002","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref30","doi-asserted-by":"crossref","first-page":"D70","DOI":"10.1093\/nar\/gks1265","article-title":"Dfam: a database of repetitive DNA based on profile hidden Markov models","volume":"41","author":"Wheeler","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref31","doi-asserted-by":"crossref","first-page":"lqab067","DOI":"10.1093\/nargab\/lqab067","article-title":"PHROG: families of prokaryotic virus proteins clustered using remote homology","volume":"3","author":"Terzian","year":"2021","journal-title":"NAR Genom Bioinform"},{"key":"2024071411200524200_ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-3019-7","article-title":"HH-suite3 for fast remote homology detection and deep protein annotation","volume":"20","author":"Steinegger","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2024071411200524200_ref33","doi-asserted-by":"crossref","first-page":"213","DOI":"10.2307\/1218190","article-title":"Evolution and measurement of species diversity","volume":"21","author":"Whittaker","year":"1972","journal-title":"Taxon"},{"key":"2024071411200524200_ref34","doi-asserted-by":"crossref","first-page":"W29","DOI":"10.1093\/nar\/gkr367","article-title":"HMMER web server: interactive sequence similarity searching","volume":"39","author":"Finn","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2024071411200524200_ref35","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":"2024071411200524200_ref36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-019-0633-6","article-title":"CAMISIM: simulating metagenomes and microbial communities","volume":"7","author":"Fritz","year":"2019","journal-title":"Microbiome"},{"key":"2024071411200524200_ref37","article-title":"ELIXIR-EXCELERATE D6. 3: report describing a set of tools, pipelines and search engine for interrogation of marine metagenomic data","author":"Mitchell","year":"2019"},{"key":"2024071411200524200_ref38","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1093\/bioinformatics\/btv033","article-title":"MEGAHIT: an ultra-fast single-node solution for large and complex metagenomics assembly via succinct de Bruijn graph","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref39","doi-asserted-by":"crossref","DOI":"10.1016\/j.cej.2021.131912","article-title":"Anaerobic membrane bioreactor model for design and prediction of domestic wastewater treatment process performance","volume":"426","author":"Shin","year":"2021","journal-title":"Chem Eng J"},{"key":"2024071411200524200_ref40","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14806\/ej.17.1.200","article-title":"Cutadapt removes adapter sequences from high-throughput sequencing reads","volume":"17","author":"Martin","year":"2011","journal-title":"EMBnet J"},{"key":"2024071411200524200_ref41","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","article-title":"Trimmomatic: a flexible trimmer for Illumina sequence data","volume":"30","author":"Bolger","year":"2014","journal-title":"Bioinformatics"},{"key":"2024071411200524200_ref42","doi-asserted-by":"crossref","first-page":"1","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":"2024071411200524200_ref43","article-title":"Accurate identification of bacteriophages from metagenomic data using transformer","volume":"23","author":"Shang","journal-title":"Briefings in Bioinformatics"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae292\/58286642\/bbae292.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae292\/58286642\/bbae292.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T11:21:02Z","timestamp":1720956062000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae292\/7696516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,5,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae292","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,5,23]]},"article-number":"bbae292"}}