{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T01:39:31Z","timestamp":1775612371109,"version":"3.50.1"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31730110"],"award-info":[{"award-number":["31730110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91940303"],"award-info":[{"award-number":["91940303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31661143031"],"award-info":[{"award-number":["31661143031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Protein sequence database search and multiple sequence alignment generation is a fundamental task in many bioinformatics analyses. As the data volume of sequences continues to grow rapidly, there is an increasing need for efficient and scalable multiple sequence query algorithms for super-large databases without expensive time and computational costs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce Chorus, a novel protein sequence query system that leverages parallel model and heterogeneous computation architecture to enable users to query thousands of protein sequences concurrently against large protein databases on a desktop workstation. Chorus achieves over 100\u00d7 speedup over BLASTP without sacrificing sensitivity. We demonstrate the utility of Chorus through a case study of analyzing a \u223c1.5-TB large-scale metagenomic datasets for novel CRISPR-Cas protein discovery within 30\u2009min.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Chorus is open-source and its code repository is available at https:\/\/github.com\/Bio-Acc\/Chorus.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae151","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T19:34:54Z","timestamp":1711654494000},"source":"Crossref","is-referenced-by-count":3,"title":["Rapid multiple protein sequence search by parallel and heterogeneous computation"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2174-4717","authenticated-orcid":false,"given":"Jiefu","family":"Li","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences , 320 Yueyang Road , Shanghai 200031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2701-719X","authenticated-orcid":false,"given":"Ziyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University , Shanghai 201210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuwei","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University , Shanghai 201210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Yao","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Computing Technology, Chinese Academy of Sciences , 88 Jinjihu Avenue , Suzhou, Jiangsu 215000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences , 320 Yueyang Road , Shanghai 200031, China"},{"name":"Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences , 320 Yueyang Road , Shanghai 200031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University , Shanghai 201210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-3637","authenticated-orcid":false,"given":"Zefeng","family":"Wang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences , 320 Yueyang Road , Shanghai 200031, China"},{"name":"Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences , 320 Yueyang Road , Shanghai 200031, China"},{"name":"School of Life Science, Southern University of Science and Technology , Shenzhen, Guangdong 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"2024041705000946900_btae151-B1","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":"2024041705000946900_btae151-B2","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nmeth.3176","article-title":"Fast and sensitive protein alignment using DIAMOND","volume":"12","author":"Buchfink","year":"2014","journal-title":"Nat Methods"},{"key":"2024041705000946900_btae151-B3","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","article-title":"Sensitive protein alignments at tree-of-life scale using DIAMOND","volume":"18","author":"Buchfink","year":"2021","journal-title":"Nat Methods"},{"key":"2024041705000946900_btae151-B4","doi-asserted-by":"crossref","first-page":"e23","DOI":"10.1093\/nar\/gkq1212","article-title":"A new repeat-masking method enables specific detection of homologous sequences","volume":"39","author":"Frith","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2024041705000946900_btae151-B5","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1016\/j.cell.2018.02.033","article-title":"Transcriptome engineering with RNA-targeting type VI-D CRISPR effectors","volume":"173","author":"Konermann","year":"2018","journal-title":"Cell"},{"key":"2024041705000946900_btae151-B6","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1038\/nature25795","article-title":"Pan-cancer genome and transcriptome analyses of 1,699 paediatric leukaemias and solid tumours","volume":"555","author":"Ma","year":"2018","journal-title":"Nature"},{"key":"2024041705000946900_btae151-B7","doi-asserted-by":"crossref","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":"2024041705000946900_btae151-B8","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nmeth.1818","article-title":"HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment","volume":"9","author":"Remmert","year":"2012","journal-title":"Nat Methods"},{"key":"2024041705000946900_btae151-B9","doi-asserted-by":"crossref","first-page":"e2112279118","DOI":"10.1073\/pnas.2112279118","article-title":"Metagenomic discovery of CRISPR-associated transposons","volume":"118","author":"Rybarski","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024041705000946900_btae151-B10","doi-asserted-by":"crossref","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":"2024041705000946900_btae151-B11","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1038\/s41592-021-01124-4","article-title":"Programmable RNA editing with compact CRISPR\u2013Cas13 systems from uncultivated microbes","volume":"18","author":"Xu","year":"2021","journal-title":"Nat Methods"},{"key":"2024041705000946900_btae151-B12","doi-asserted-by":"crossref","first-page":"100044","DOI":"10.1016\/j.cellin.2022.100044","article-title":"Multi-color RNA imaging with CRISPR-Cas13b systems in living cells","volume":"1","author":"Yang","year":"2022","journal-title":"Cell Insight"},{"key":"2024041705000946900_btae151-B13","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1093\/bioinformatics\/btw769","article-title":"H-BLAST: a fast protein sequence alignment toolkit on heterogeneous computers with GPUs","volume":"33","author":"Ye","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae151\/57114675\/btae151.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae151\/57245910\/btae151.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae151\/57245910\/btae151.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T05:00:36Z","timestamp":1713330036000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae151\/7636964"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,28]]},"references-count":13,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae151","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,3,28]]},"article-number":"btae151"}}