{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T11:25:10Z","timestamp":1784805910520,"version":"3.55.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"D1","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM140370"],"award-info":[{"award-number":["R01GM140370"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R03OD039979"],"award-info":[{"award-number":["R03OD039979"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000199","name":"United States Department of Agriculture","doi-asserted-by":"publisher","award":["58-8042-3-076"],"award-info":[{"award-number":["58-8042-3-076"]}],"id":[{"id":"10.13039\/100000199","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nebraska Tobacco Settlement Biomedical Research Enhancement Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>CAZymes (Carbohydrate Active EnZymes) play key metabolic functions in human gut microbiomes (HGM). Genes of glycan degrading CAZymes often form physically linked CAZyme Gene Clusters (CGCs) in gut bacterial genomes. Here we developed dbCAN-HGM (https:\/\/pro.unl.edu\/dbCAN_HGM), a comprehensive data repository for human gut bacterial CGCs and CAZymes. dbCAN-HGM has the following unique features: (i) 121 883 CGCs are identified in 6031 high-quality species-level representative metagenome assembled genomes (MAGs), from a wide range of human populations, especially the under-studied African population; (ii) Each CGC page includes metagenomic read mapping results from different diets (vegan, vegetarian, omnivore, flexitarian) and disease statuses (ulcerative colitis [UC and Crohns disease), with interactive coverage plot and Jbrowse alignment tracks; (iii) CGCs are clustered with 1358 polysaccharide utilization loci into CGC families (CGC-Fs) to infer glycan substrates; (iv) Metadata and visualization are available for CGC-Fs by substrate, taxonomy, host geographic distribution, and top abundant CAZyme families; (v) CGCs are fully annotated with CAZymes, transporters, signal transduction proteins, transcriptional factors, sulfatases, peptidases, Pfam families, and protein 3D structure comparison results for unannotated proteins; and (vi) User-friendly and highly interactive web interface is provided for easy browsing and downloading of HGM genomes, CGCs, CGC-Fs by glycan substrates and continents.<\/jats:p>","DOI":"10.1093\/nar\/gkaf1185","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T10:12:58Z","timestamp":1763633578000},"page":"D555-D563","source":"Crossref","is-referenced-by-count":1,"title":["dbCAN-HGM: CAZyme gene clusters in gut microbiomes of diverse human populations"],"prefix":"10.1093","volume":"54","author":[{"given":"Yuchen","family":"Yan","sequence":"first","affiliation":[{"name":"Nebraska Food for Health Center , Department of Food Science and Technology, University of Nebraska\u2013Lincoln, Lincoln, NE 68588 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Revanth Sai Kumar Reddy","family":"Patel","sequence":"additional","affiliation":[{"name":"Nebraska Food for Health Center , Department of Food Science and Technology, University of Nebraska\u2013Lincoln, Lincoln, NE 68588 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N R Siva","family":"Shanmugam","sequence":"additional","affiliation":[{"name":"Nebraska Food for Health Center , Department of Food Science and Technology, University of Nebraska\u2013Lincoln, Lincoln, NE 68588 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jerry","family":"Akresi","sequence":"additional","affiliation":[{"name":"Nebraska Food for Health Center , Department of Food Science and Technology, University of Nebraska\u2013Lincoln, Lincoln, NE 68588 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7667-881X","authenticated-orcid":false,"given":"Yanbin","family":"Yin","sequence":"additional","affiliation":[{"name":"Nebraska Food for Health Center , Department of Food Science and Technology, University of Nebraska\u2013Lincoln, Lincoln, NE 68588 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"2026011523315693800_B1","doi-asserted-by":"publisher","first-page":"D571","DOI":"10.1093\/nar\/gkab1045","article-title":"The carbohydrate-active enzyme database: functions and literature","volume":"50","author":"Drula","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B2","doi-asserted-by":"publisher","first-page":"W95","DOI":"10.1093\/nar\/gky418","article-title":"dbCAN2: a meta server for automated carbohydrate-active enzyme annotation","volume":"46","author":"Zhang","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B3","doi-asserted-by":"publisher","first-page":"D516","DOI":"10.1093\/nar\/gkx894","article-title":"dbCAN-seq: a database of carbohydrate-active enzyme (CAZyme) sequence and annotation","volume":"46","author":"Huang","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B4","doi-asserted-by":"publisher","first-page":"e00860","DOI":"10.1128\/JB.00860-16","article-title":"Polysaccharide utilization loci: fueling microbial communities","volume":"199","author":"Grondin","year":"2017","journal-title":"J Bacteriol"},{"key":"2026011523315693800_B5","doi-asserted-by":"publisher","first-page":"3230","DOI":"10.1016\/j.jmb.2016.06.021","article-title":"Polysaccharide degradation by the intestinal microbiota and its influence on human health and disease","volume":"428","author":"Cockburn","year":"2016","journal-title":"J Mol Biol"},{"key":"2026011523315693800_B6","doi-asserted-by":"publisher","first-page":"e19888","DOI":"10.1016\/j.heliyon.2023.e19888","article-title":"Microbiota-accessible carbohydrates (MACs) as novel gut microbiome modulators in noncommunicable diseases","volume":"9","author":"Ayakda\u015f","year":"2023","journal-title":"Heliyon"},{"key":"2026011523315693800_B7","doi-asserted-by":"publisher","first-page":"999001","DOI":"10.3389\/fmicb.2022.999001","article-title":"Human gut microbiota in health and disease: unveiling the relationship","volume":"13","author":"Afzaal","year":"2022","journal-title":"Front Microbiol"},{"key":"2026011523315693800_B8","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1038\/s41587-020-0603-3","article-title":"A unified catalog of 204,938 reference genomes from the human gut microbiome","volume":"39","author":"Almeida","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2026011523315693800_B9","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1038\/s41586-024-08485-8","article-title":"Expanding the human gut microbiome atlas of Africa","volume":"638","author":"Maghini","year":"2025","journal-title":"Nature"},{"key":"2026011523315693800_B10","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1016\/j.cell.2023.05.046","article-title":"Ultra-deep sequencing of Hadza hunter-gatherers recovers vanishing gut microbes","volume":"186","author":"Carter","year":"2023","journal-title":"Cell"},{"key":"2026011523315693800_B11","doi-asserted-by":"publisher","first-page":"100559","DOI":"10.1016\/j.xgen.2024.100559","article-title":"Gut microbial genomes with paired isolates from China illustrate probiotic and cardiometabolic effects","volume":"4","author":"Huang","year":"2024","journal-title":"Cell Genomics"},{"key":"2026011523315693800_B12","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/j.chom.2019.01.004","article-title":"Distinct genetic and functional traits of human intestinal Prevotella copri strains are associated with different habitual diets","volume":"25","author":"De\u00a0Filippis","year":"2019","journal-title":"Cell Host Microbe"},{"key":"2026011523315693800_B13","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1038\/s41591-020-01183-8","article-title":"Microbiome connections with host metabolism and habitual diet from 1,098 deeply phenotyped individuals","volume":"27","author":"Asnicar","year":"2021","journal-title":"Nat Med"},{"key":"2026011523315693800_B14","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41564-024-01870-z","article-title":"Gut microbiome signatures of vegan, vegetarian and omnivore diets and associated health outcomes across 21,561 individuals","volume":"10","author":"Fackelmann","year":"2025","journal-title":"Nat Microbiol"},{"key":"2026011523315693800_B15","doi-asserted-by":"publisher","first-page":"115067","DOI":"10.1016\/j.celrep.2024.115067","article-title":"Dietary selective effects manifest in the human gut microbiota from species composition to strain genetic makeup","volume":"43","author":"Huang","year":"2024","journal-title":"Cell Reports"},{"key":"2026011523315693800_B16","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1016\/j.cell.2010.05.005","article-title":"Specificity of polysaccharide use in intestinal bacteroides species determines diet-induced microbiota alterations","volume":"141","author":"Sonnenburg","year":"2010","journal-title":"Cell"},{"key":"2026011523315693800_B17","doi-asserted-by":"publisher","first-page":"W115","DOI":"10.1093\/nar\/gkad328","article-title":"dbCAN3: automated carbohydrate-active enzyme and substrate annotation","volume":"51","author":"Zheng","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B18","doi-asserted-by":"publisher","first-page":"D557","DOI":"10.1093\/nar\/gkac1068","article-title":"dbCAN-seq update: cAZyme gene clusters and substrates in microbiomes","volume":"51","author":"Zheng","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B19","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkaa742","article-title":"dbCAN-PUL: a database of experimentally characterized CAZyme gene clusters and their substrates","volume":"49","author":"Ausland","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B20","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":"2026011523315693800_B21","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1038\/ismej.2017.126","article-title":"dRep: a tool for fast and accurate genomic comparisons that enables improved genome recovery from metagenomes through de-replication","volume":"11","author":"Olm","year":"2017","journal-title":"ISME J"},{"key":"2026011523315693800_B22","doi-asserted-by":"publisher","first-page":"5315","DOI":"10.1093\/bioinformatics\/btac672","article-title":"GTDB-Tk v2: memory friendly classification with the genome taxonomy database","volume":"38","author":"Chaumeil","year":"2022","journal-title":"Bioinformatics"},{"key":"2026011523315693800_B23","doi-asserted-by":"publisher","article-title":"De novo discovery of conserved gene clusters in microbial genomes with Spacedust","author":"Zhang","DOI":"10.1101\/2024.10.02.616292"},{"key":"2026011523315693800_B24","doi-asserted-by":"publisher","first-page":"D647","DOI":"10.1093\/nar\/gkac977","article-title":"SulfAtlas, the sulfatase database: state of the art and new developments","volume":"51","author":"Stam","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026011523315693800_B25","doi-asserted-by":"publisher","first-page":"D503","DOI":"10.1093\/nar\/gkt953","article-title":"MEROPS: the database of proteolytic enzymes, their substrates and inhibitors","volume":"42","author":"Rawlings","year":"2014","journal-title":"Nucl Acids Res"},{"key":"2026011523315693800_B26","doi-asserted-by":"publisher","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":"2026011523315693800_B27","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1137\/040608635","article-title":"Graph clustering via a discrete uncoupling process","volume":"30","author":"Van\u00a0Dongen","year":"2008","journal-title":"SIAM J Matrix Anal Appl"},{"key":"2026011523315693800_B28","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1038\/s41586-019-1237-9","article-title":"Multi-omics of the gut microbial ecosystem in inflammatory bowel diseases","volume":"569","author":"Lloyd-Price","year":"2019","journal-title":"Nature"},{"key":"2026011523315693800_B29","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1093\/bioinformatics\/bty648","article-title":"Scaling read aligners to hundreds of threads on general-purpose processors","volume":"35","author":"Langmead","year":"2019","journal-title":"Bioinformatics"},{"key":"2026011523315693800_B30","doi-asserted-by":"crossref","unstructured":"Danecek P, Bonfield JK, Liddle Jet al. Twelve years of SAMtools and BCFtools. Gigascience. 2021;10:giab008.","DOI":"10.1093\/gigascience\/giab008"},{"key":"2026011523315693800_B31","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"BEDTools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"key":"2026011523315693800_B32","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/nature21725","article-title":"Complex pectin metabolism by gut bacteria reveals novel catalytic functions","volume":"544","author":"Ndeh","year":"2017","journal-title":"Nature"},{"key":"2026011523315693800_B33","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":"2026011523315693800_B34","doi-asserted-by":"publisher","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":"2026011523315693800_B35","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":"2026011523315693800_B36","doi-asserted-by":"publisher","first-page":"169001","DOI":"10.1016\/j.jmb.2025.169001","article-title":"CAZyme3D: a database of 3D structures for carbohydrate-active enzymes","volume":"437","author":"Siva\u00a0Shanmugam","year":"2025","journal-title":"J Mol Biol"},{"key":"2026011523315693800_B37","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1038\/s41467-019-10068-5","article-title":"Bacteroidetes use thousands of enzyme combinations to break down glycans","volume":"10","author":"Lap\u00e9bie","year":"2019","journal-title":"Nat Commun"},{"key":"2026011523315693800_B38","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1038\/s41467-021-27917-x","article-title":"Short- and long-read metagenomics of urban and rural South African gut microbiomes reveal a transitional composition and undescribed taxa","volume":"13","author":"Tamburini","year":"2022","journal-title":"Nat Commun"},{"key":"2026011523315693800_B39","doi-asserted-by":"publisher","first-page":"3863","DOI":"10.1038\/s41467-022-31502-1","article-title":"An expanded reference map of the human gut microbiome reveals hundreds of previously unknown species","volume":"13","author":"Leviatan","year":"2022","journal-title":"Nat Commun"},{"key":"2026011523315693800_B40","doi-asserted-by":"publisher","first-page":"5139","DOI":"10.1038\/s41467-022-32805-z","article-title":"A compendium of 32,277 metagenome-assembled genomes and over 80 million genes from the early-life human gut microbiome","volume":"13","author":"Zeng","year":"2022","journal-title":"Nat Commun"},{"key":"2026011523315693800_B41","doi-asserted-by":"publisher","article-title":"Exclusive cataloging of near-complete genomes unveils novel functional insights into the human gut microbiome","author":"Ma","DOI":"10.1101\/2024.12.11.627901"},{"key":"2026011523315693800_B42","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1038\/s41564-022-01270-1","article-title":"A high-quality genome compendium of the human gut microbiome of Inner Mongolians","volume":"8","author":"Jin","year":"2023","journal-title":"Nat Microbiol"},{"key":"2026011523315693800_B43","doi-asserted-by":"publisher","first-page":"6044","DOI":"10.1038\/s41467-022-33782-z","article-title":"Genome-centric analysis of short and long read metagenomes reveals uncharacterized microbiome diversity in Southeast Asians","volume":"13","author":"Gounot","year":"2022","journal-title":"Nat Commun"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/54\/D1\/D555\/65405600\/gkaf1185.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/54\/D1\/D555\/65405600\/gkaf1185.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T04:32:10Z","timestamp":1768537930000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/54\/D1\/D555\/8329101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":43,"journal-issue":{"issue":"D1","published-print":{"date-parts":[[2026,1,6]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkaf1185","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1,6]]},"published":{"date-parts":[[2025,11,20]]}}}