{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T21:42:58Z","timestamp":1777326178916,"version":"3.51.4"},"reference-count":9,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":2461,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Summary: CD-HIT is a widely used program for clustering and comparing large biological sequence datasets. In order to further assist the CD-HIT users, we significantly improved this program with more functions and better accuracy, scalability and flexibility. Most importantly, we developed a new web server, CD-HIT Suite, for clustering a user-uploaded sequence dataset or comparing it to another dataset at different identity levels. Users can now interactively explore the clusters within web browsers. We also provide downloadable clusters for several public databases (NCBI NR, Swissprot and PDB) at different identity levels.<\/jats:p>\n               <jats:p>Availability: Free access at http:\/\/cd-hit.org<\/jats:p>\n               <jats:p>Contact: \u00a0liwz@sdsc.edu<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btq003","type":"journal-article","created":{"date-parts":[[2010,1,7]],"date-time":"2010-01-07T02:54:39Z","timestamp":1262832879000},"page":"680-682","source":"Crossref","is-referenced-by-count":2425,"title":["CD-HIT Suite: a web server for clustering and comparing biological sequences"],"prefix":"10.1093","volume":"26","author":[{"given":"Ying","family":"Huang","sequence":"first","affiliation":[{"name":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, CA, USA"}]},{"given":"Beifang","family":"Niu","sequence":"additional","affiliation":[{"name":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, CA, USA"}]},{"given":"Ying","family":"Gao","sequence":"additional","affiliation":[{"name":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, CA, USA"}]},{"given":"Limin","family":"Fu","sequence":"additional","affiliation":[{"name":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, CA, USA"}]},{"given":"Weizhong","family":"Li","sequence":"additional","affiliation":[{"name":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, CA, USA"}]}],"member":"286","published-online":{"date-parts":[[2010,1,6]]},"reference":[{"key":"2023012511005596700_B1","doi-asserted-by":"crossref","first-page":"D229","DOI":"10.1093\/nar\/gkn808","article-title":"SMART 6: recent updates and new developments","volume":"37","author":"Letunic","year":"2009","journal-title":"Nucleic Acids Res."},{"key":"2023012511005596700_B2","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2023012511005596700_B3","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1093\/bioinformatics\/17.3.282","article-title":"Clustering of highly homologous sequences to reduce the size of large protein databases","volume":"17","author":"Li","year":"2001","journal-title":"Bioinformatics"},{"key":"2023012511005596700_B4","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1093\/bioinformatics\/18.1.77","article-title":"Tolerating some redundancy significantly speeds up clustering of large protein databases","volume":"18","author":"Li","year":"2002","journal-title":"Bioinformatics"},{"key":"2023012511005596700_B5","doi-asserted-by":"crossref","first-page":"e3375","DOI":"10.1371\/journal.pone.0003375","article-title":"Probing metagenomics by rapid cluster analysis of very large datasets","volume":"3","author":"Li","year":"2008","journal-title":"PLoS ONE"},{"key":"2023012511005596700_B6","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1093\/bioinformatics\/btm098","article-title":"UniRef: comprehensive and non-redundant UniProt reference clusters","volume":"23","author":"Suzek","year":"2007","journal-title":"Bioinformatics"},{"key":"2023012511005596700_B7","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1038\/nature07540","article-title":"A core gut microbiome in obese and lean twins","volume":"457","author":"Turnbaugh","year":"2009","journal-title":"Nature"},{"key":"2023012511005596700_B8","doi-asserted-by":"crossref","first-page":"e16","DOI":"10.1371\/journal.pbio.0050016","article-title":"The Sorcerer II global ocean sampling expedition: expanding the universe of protein families","volume":"5","author":"Yooseph","year":"2007","journal-title":"PLoS Biol."},{"key":"2023012511005596700_B9","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1186\/1471-2105-9-182","article-title":"Gene identification and protein classification in microbial metametagenomic sequence data via incremental clustering","volume":"9","author":"Yooseph","year":"2008","journal-title":"BMC Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/26\/5\/680\/48860348\/bioinformatics_26_5_680.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/26\/5\/680\/48860348\/bioinformatics_26_5_680.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T11:05:51Z","timestamp":1674644751000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/26\/5\/680\/212234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1,6]]},"references-count":9,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2010,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btq003","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2010,3,1]]},"published":{"date-parts":[[2010,1,6]]}}}