{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T09:55:52Z","timestamp":1790589352028,"version":"4.1.0"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Foundation for Research and Innovation","award":["23592-EMISSION"],"award-info":[{"award-number":["23592-EMISSION"]}]},{"DOI":"10.13039\/501100013209","name":"Hellenic Foundation for Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013209","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project to support Postdoctoral Researchers\u2019","award":["28787-VIROMINE"],"award-info":[{"award-number":["28787-VIROMINE"]}]},{"name":"Marie Sk\u0142odowska-Curie Grant agreement","award":["945405"],"award-info":[{"award-number":["945405"]}]},{"DOI":"10.13039\/100008562","name":"University of Texas at Austin","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100008562","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","award":["DE-AC02\u201305CH11231"],"award-info":[{"award-number":["DE-AC02\u201305CH11231"]}],"id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"US Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"US Department of Energy Office of Science","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"https:\/\/ror.org\/00mmn6b08","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The known universe of protein families represents only a small fraction of nature\u2019s molecular diversity. From 40.3 billion predicted open reading frames across 40\u2009446 metagenomes, 9540 metatranscriptomes, and 539 million proteins from 167\u2009415 reference genomes, we identified 608\u2009258 previously uncharacterized putative protein families with \u2265100 members and 6.5 million families with \u226525 members, none matching known Pfam domains or reference proteins. This effort doubles the known repertoire of large families and quadruples that of smaller families. Integration of AlphaFold2-based structural predictions with gene-neighborhood and taxonomic analyses enables the characterization of these previously unannotated proteins, revealing candidates for both novel and known biological functions in understudied microbial lineages and biomes. This expanded repertoire provides insights into microbial adaptation and broadens the molecular toolkit available for biotechnology, highlighting the power of global metagenomics to uncover hidden protein diversity.<\/jats:p>","DOI":"10.1093\/nar\/gkag938","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T18:27:16Z","timestamp":1789756036000},"source":"Crossref","is-referenced-by-count":0,"title":["\u201cQuadrupling\u201d the protein family space with global metagenomics"],"prefix":"10.1093","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0737-4817","authenticated-orcid":false,"given":"Eleni","family":"Aplakidou","sequence":"first","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]},{"name":"Division of Basic Sciences, University of Crete Medical School , Heraklion 71110 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2870-2931","authenticated-orcid":false,"given":"Fotis A","family":"Baltoumas","sequence":"additional","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0336-0515","authenticated-orcid":false,"given":"Maria N","family":"Chasapi","sequence":"additional","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Efthimia","family":"Lamari","sequence":"additional","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iro N","family":"Chasapi","sequence":"additional","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]},{"name":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens , Athens 16122 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"IIias","family":"Georgakopoulos-Soares","sequence":"additional","affiliation":[{"name":"Institute for Personalized Medicine, Department of Biochemistry and Molecular Biology, The Pennsylvania State University College of Medicine , Hershey, PA 17033 ,","place":["United States"]},{"name":"Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute , Austin, TX 78712 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos","family":"Karatzas","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus , Hinxton, Cambridge CB10 1SD ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9079-0565","authenticated-orcid":false,"given":"Ioannis","family":"Iliopoulos","sequence":"additional","affiliation":[{"name":"Division of Basic Sciences, University of Crete Medical School , Heraklion 71110 ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Aydin\u00a0Bulu\u00e7","sequence":"additional","affiliation":[{"name":"Computational Research Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720 ,","place":["United States"]},{"name":"Department of Electrical Engineering and Computer Sciences, University of California , Berkeley, CA 94720 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8626-2148","authenticated-orcid":false,"given":"Robert D","family":"Finn","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus , Hinxton, Cambridge CB10 1SD ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3913-2484","authenticated-orcid":false,"given":"Antonio Pedro","family":"Camargo","sequence":"additional","affiliation":[{"name":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720 ,","place":["United States"]},{"name":"Department of Biochemistry, Institute of Chemistry, University of S\u00e3o Paulo , S\u00e3o Paulo, SP 05508-900 ,","place":["Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6131-0462","authenticated-orcid":false,"given":"Nikos C","family":"Kyrpides","sequence":"additional","affiliation":[{"name":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4577-8276","authenticated-orcid":false,"given":"Georgios\u00a0A","family":"Pavlopoulos","sequence":"additional","affiliation":[{"name":"Institute for Fundamental Biomedical Research, BSRC \u201cAlexander Fleming\u201d , Vari 16672 ,","place":["Greece"]},{"name":"Division of Biological and Life Sciences, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) , Building 1B, Masdar City, Abu Dhabi ,","place":["United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"2026092805050325700_B1","doi-asserted-by":"publisher","first-page":"1157956","DOI":"10.3389\/fbinf.2023.1157956","article-title":"Exploring microbial functional biodiversity at the protein family level\u2014from metagenomic sequence reads to annotated protein clusters","volume":"3","author":"Baltoumas","year":"2023","journal-title":"Front Bioinform"},{"key":"2026092805050325700_B2","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1016\/j.csbj.2024.04.060","article-title":"Visualizing metagenomic and metatranscriptomic data: a comprehensive review","volume":"23","author":"Aplakidou","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"2026092805050325700_B3","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1038\/s41586-023-06955-z","article-title":"Functional and evolutionary significance of unknown genes from uncultivated taxa","volume":"626","author":"Rodr\u00edguez\u00a0del\u00a0R\u00edo","year":"2024","journal-title":"Nature"},{"key":"2026092805050325700_B4","doi-asserted-by":"publisher","first-page":"2073","DOI":"10.1016\/j.cell.2025.12.051","article-title":"Planetary microbiome structure and generalist-driven gene flow across disparate habitats","volume":"189","author":"Kim","year":"2026","journal-title":"Cell"},{"key":"2026092805050325700_B5","doi-asserted-by":"publisher","first-page":"D723","DOI":"10.1093\/nar\/gkac976","article-title":"The IMG\/M data management and analysis system v.7: content updates and new features","volume":"51","author":"Chen","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B6","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":"2026092805050325700_B7","doi-asserted-by":"publisher","first-page":"e67667","DOI":"10.7554\/eLife.67667","article-title":"Unifying the known and unknown microbial coding sequence space","volume":"11","author":"Vanni","year":"2022","journal-title":"eLife"},{"key":"2026092805050325700_B8","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1038\/s41586-023-06583-7","article-title":"Unraveling the functional dark matter through global metagenomics","volume":"622","author":"Pavlopoulos","year":"2023","journal-title":"Nature"},{"key":"2026092805050325700_B9","doi-asserted-by":"publisher","first-page":"D502","DOI":"10.1093\/nar\/gkad800","article-title":"NMPFamsDB: a database of novel protein families from microbial metagenomes and metatranscriptomes","volume":"52","author":"Baltoumas","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B10","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1093\/nar\/29.12.2607","article-title":"GeneMarkS: a self-training method for prediction of gene starts in microbial genomes. Implications for finding sequence motifs in regulatory regions","volume":"29","author":"Besemer","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B11","doi-asserted-by":"publisher","first-page":"e28819","DOI":"10.1371\/journal.pone.0028819","article-title":"Gentle masking of low-complexity sequences improves homology search","volume":"6","author":"Frith","year":"2011","journal-title":"PLoS One"},{"key":"2026092805050325700_B12","doi-asserted-by":"publisher","first-page":"e1002195","DOI":"10.1371\/journal.pcbi.1002195","article-title":"Accelerated profile HMM searches","volume":"7","author":"Eddy","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"2026092805050325700_B13","doi-asserted-by":"publisher","first-page":"e100","DOI":"10.1093\/nar\/gkq010","article-title":"Incorporating sequence quality data into alignment improves DNA read mapping","volume":"38","author":"Frith","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1093\/protein\/12.2.85","article-title":"Twilight zone of protein sequence alignments","volume":"12","author":"Rost","year":"1999","journal-title":"Protein Eng"},{"key":"2026092805050325700_B15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nmeth.3176","article-title":"Fast and sensitive protein alignment using DIAMOND","volume":"12","author":"Buchfink","year":"2015","journal-title":"Nat Methods"},{"key":"2026092805050325700_B16","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026092805050325700_B17","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1038\/nbt.3893","article-title":"Minimum information about a single amplified genome (MISAG) and a metagenome-assembled genome (MIMAG) of bacteria and archaea","volume":"35","author":"The Genome Standards Consortium","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026092805050325700_B18","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1101\/gr.186072.114","article-title":"CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes","volume":"25","author":"Parks","year":"2015","journal-title":"Genome Res"},{"key":"2026092805050325700_B19","doi-asserted-by":"publisher","first-page":"e00804","DOI":"10.1128\/mSystems.00804-20","article-title":"DOE JGI Metagenome workflow","volume":"6","author":"Clum","year":"2021","journal-title":"mSystems"},{"key":"2026092805050325700_B20","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol Biol Evol"},{"key":"2026092805050325700_B21","doi-asserted-by":"publisher","first-page":"473","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":"2026092805050325700_B22","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","article-title":"ColabFold: making protein folding accessible to all","volume":"19","author":"Mirdita","year":"2022","journal-title":"Nat Methods"},{"key":"2026092805050325700_B23","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026092805050325700_B24","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41587-023-01773-0","article-title":"Fast and accurate protein structure search with Foldseek","volume":"42","author":"van\u00a0Kempen","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026092805050325700_B25","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1186\/1479-7364-4-3-207","article-title":"The CATH database","volume":"4","author":"Knudsen","year":"2010","journal-title":"Hum Genomics"},{"key":"2026092805050325700_B26","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B27","doi-asserted-by":"publisher","first-page":"D368","DOI":"10.1093\/nar\/gkad1011","article-title":"AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences","volume":"52","author":"Varadi","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B28","doi-asserted-by":"publisher","first-page":"R46","DOI":"10.1186\/gb-2014-15-3-r46","article-title":"Kraken: ultrafast metagenomic sequence classification using exact alignments","volume":"15","author":"Wood","year":"2014","journal-title":"Genome Biol"},{"key":"2026092805050325700_B29","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1038\/s41597-022-01420-4","article-title":"Improvement of eukaryotic protein predictions from soil metagenomes","volume":"9","author":"Belliardo","year":"2022","journal-title":"Sci Data"},{"key":"2026092805050325700_B30","doi-asserted-by":"publisher","first-page":"3029","DOI":"10.1093\/bioinformatics\/btab184","article-title":"Fast and sensitive taxonomic assignment to metagenomic contigs","volume":"37","author":"Mirdita","year":"2021","journal-title":"Bioinformatics"},{"key":"2026092805050325700_B31","doi-asserted-by":"publisher","first-page":"mgen000823 b","DOI":"10.1099\/mgen.0.000823","article-title":"Whokaryote: distinguishing eukaryotic and prokaryotic contigs in metagenomes based on gene structure","volume":"8","author":"Pronk","year":"2022","journal-title":"Microb Genom"},{"key":"2026092805050325700_B32","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1101\/gr.228429.117","article-title":"Genome-reconstruction for eukaryotes from complex natural microbial communities","volume":"28","author":"West","year":"2018","journal-title":"Genome Res"},{"key":"2026092805050325700_B33","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1038\/s41587-023-01982-7","article-title":"Fast and accurate identification of plasmids and viruses in sequencing data using geNomad","volume":"42","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2026092805050325700_B34","doi-asserted-by":"publisher","first-page":"D723","DOI":"10.1093\/nar\/gkaa983","article-title":"Genomes OnLine Database (GOLD) v.8: overview and updates","volume":"49","author":"Mukherjee","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B35","doi-asserted-by":"publisher","first-page":"e4466","DOI":"10.1002\/pro.4466","article-title":"Intrinsic protein disorder and conditional folding in AlphaFoldDB","volume":"31","author":"Piovesan","year":"2022","journal-title":"Protein Sci"},{"key":"2026092805050325700_B36","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.3390\/membranes12111161","article-title":"Transmembrane membrane readers form a novel class of proteins that include peripheral phosphoinositide recognition domains and viral spikes","volume":"12","author":"Overduin","year":"2022","journal-title":"Membranes"},{"key":"2026092805050325700_B37","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkae997","article-title":"The Pfam protein families database: embracing AI\/ML","volume":"53","author":"Paysan-Lafosse","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B38","doi-asserted-by":"publisher","first-page":"bas003","DOI":"10.1093\/database\/bas003","article-title":"AntiFam: a tool to help identify spurious ORFs in protein annotation","volume":"2012","author":"Eberhardt","year":"2012","journal-title":"Database"},{"key":"2026092805050325700_B39","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026092805050325700_B40","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.humic.2018.08.005","article-title":"Human microbiomes and antibiotic resistance","volume":"10","author":"Baron","year":"2018","journal-title":"Hum Microb J"},{"key":"2026092805050325700_B41","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.3389\/fmicb.2019.01286","article-title":"Investigating host microbiota relationships through functional metagenomics","volume":"10","author":"Laville","year":"2019","journal-title":"Front Microbiol"},{"key":"2026092805050325700_B42","doi-asserted-by":"publisher","first-page":"e1008324","DOI":"10.1371\/journal.pgen.1008324","article-title":"The plant mobile domain proteins MAIN and MAIL1 interact with the phosphatase PP7L to regulate gene expression and silence transposable elements in Arabidopsis thaliana","volume":"16","author":"Nicolau","year":"2020","journal-title":"PLoS Genet"},{"key":"2026092805050325700_B43","doi-asserted-by":"publisher","first-page":"101203","DOI":"10.1016\/j.xplc.2024.101203","article-title":"Pentatricopeptide repeat proteins in plants: cellular functions, action mechanisms, and potential applications","volume":"6","author":"Wang","year":"2025","journal-title":"Plant Commun"},{"key":"2026092805050325700_B44","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1093\/jxb\/ern045","article-title":"Structure\u2013function analysis of the NB-ARC domain of plant disease resistance proteins","volume":"59","author":"Van\u00a0Ooijen","year":"2008","journal-title":"J Exp Bot"},{"key":"2026092805050325700_B45","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.3390\/ijms20153837","article-title":"Retrotransposons in plant genomes: structure, identification, and classification through bioinformatics and machine learning","volume":"20","author":"Orozco-Arias","year":"2019","journal-title":"Int J Mol Sci"},{"key":"2026092805050325700_B46","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1016\/j.str.2016.08.013","article-title":"Common evolutionary origin of procapsid proteases, phage tail tubes, and tubes of bacterial type VI secretion systems","volume":"24","author":"Fokine","year":"2016","journal-title":"Structure"},{"key":"2026092805050325700_B47","doi-asserted-by":"publisher","first-page":"e0006824","DOI":"10.1128\/jvi.00068-24","article-title":"Structural morphing in the viral portal vertex of bacteriophage lambda","volume":"98","author":"Gu","year":"2024","journal-title":"J Virol"},{"key":"2026092805050325700_B48","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1038\/s41564-024-01876-7","article-title":"Unravelling viral ecology and evolution over 20 years in a freshwater lake","volume":"10","author":"Zhou","year":"2025","journal-title":"Nat Microbiol"},{"key":"2026092805050325700_B49","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1007\/s13205-022-03190-7","article-title":"Metagenomic mining of Indian river confluence reveal functional microbial community with lignocelluloytic potential","volume":"12","author":"Rajput","year":"2022","journal-title":"3 Biotech"},{"key":"2026092805050325700_B50","doi-asserted-by":"publisher","first-page":"3694","DOI":"10.1038\/ncomms4694","article-title":"Adjustment of microbial nitrogen use efficiency to carbon:nitrogen imbalances regulates soil nitrogen cycling","volume":"5","author":"Mooshammer","year":"2014","journal-title":"Nat Commun"},{"key":"2026092805050325700_B51","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1038\/s41586-023-06583-7","article-title":"Unraveling the functional dark matter through global metagenomics","volume":"622","author":"Pavlopoulos","year":"2023","journal-title":"Nature"},{"key":"2026092805050325700_B52","doi-asserted-by":"publisher","first-page":"679982","DOI":"10.3389\/fcimb.2021.679982","article-title":"STAS domain only proteins in bacterial gene regulation","volume":"11","author":"Moy","year":"2021","journal-title":"Front Cell Infect Microbiol"},{"key":"2026092805050325700_B53","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s002530051618","article-title":"Enhanced production of penicillin V acylase from Streptomyces lavendulae","volume":"53","author":"Torres","year":"1999","journal-title":"Appl Microbiol Biotechnol"},{"key":"2026092805050325700_B54","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1016\/S0141-0229(96)00176-7","article-title":"Penicillin V acylase: its potential in the production of 6-aminopenicillanic acid","volume":"20","author":"Shewale","year":"1997","journal-title":"Enzyme Microb Technol"},{"key":"2026092805050325700_B55","doi-asserted-by":"publisher","first-page":"e01756","DOI":"10.1128\/aem.01756-23","article-title":"The biotechnological potential of the chloroflexota phylum","volume":"90","author":"Freches","year":"2024","journal-title":"Appl Environ Microbiol"},{"key":"2026092805050325700_B56","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.1110\/ps.9.12.2329","article-title":"Structural comparison of ntn-hydrolases","volume":"9","author":"Oinonen","year":"2000","journal-title":"Protein Sci"},{"key":"2026092805050325700_B57","doi-asserted-by":"publisher","first-page":"D724","DOI":"10.1093\/nar\/gkaf1115","article-title":"gcMeta 2025: a global repository of metagenome-assembled genomes enabling cross-ecosystem microbial discovery and function research","volume":"54","author":"Sun","year":"2026","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B58","doi-asserted-by":"publisher","first-page":"D777","DOI":"10.1093\/nar\/gkad943","article-title":"SPIRE: a searchable, planetary-scale mIcrobiome REsource","volume":"52","author":"Schmidt","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092805050325700_B59","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-021-04233-4","article-title":"Towards the biogeography of prokaryotic genes","volume":"601","author":"Coelho","year":"2022","journal-title":"Nature"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/54\/18\/gkag938\/71431655\/gkag938.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/54\/18\/gkag938\/71431655\/gkag938.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T09:05:13Z","timestamp":1790586313000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/doi\/10.1093\/nar\/gkag938\/8840863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":59,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkag938","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10,14]]},"published":{"date-parts":[[2026,9,22]]},"article-number":"gkag938"}}