{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T14:41:29Z","timestamp":1794321689578,"version":"4.9.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004189","name":"Max-Planck-Gesellschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004189","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Methods"],"published-print":{"date-parts":[[2021,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We are at the beginning of a genomic revolution in which all known species are planned to be sequenced. Accessing such data for comparative analyses is crucial in this new age of data-driven biology. Here, we introduce an improved version of DIAMOND that greatly exceeds previous search performances and harnesses supercomputing to perform tree-of-life scale protein alignments in hours, while matching the sensitivity of the gold standard BLASTP.<\/jats:p>","DOI":"10.1038\/s41592-021-01101-x","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T12:05:23Z","timestamp":1617797123000},"page":"366-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5593,"title":["Sensitive protein alignments at tree-of-life scale using DIAMOND"],"prefix":"10.1038","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-731X","authenticated-orcid":false,"given":"Benjamin","family":"Buchfink","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6869-7877","authenticated-orcid":false,"given":"Klaus","family":"Reuter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1567-306X","authenticated-orcid":false,"given":"Hajk-Georg","family":"Drost","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,7]]},"reference":[{"key":"1101_CR1","doi-asserted-by":"publisher","first-page":"4325","DOI":"10.1073\/pnas.1720115115","volume":"115","author":"HA Lewin","year":"2018","unstructured":"Lewin, H. A. et al. Earth BioGenome Project: sequencing life for the future of life. Proc. Natl Acad. Sci. USA 115, 4325\u20134333 (2018).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"1101_CR2","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1111\/tpj.14631","volume":"102","author":"M Exposito-Alonso","year":"2020","unstructured":"Exposito-Alonso, M., Drost, H.-G., Burbano, H. A. & Weigel, D. The Earth BioGenome project: opportunities and challenges for plant genomics and conservation. Plant J. 102, 222\u2013229 (2020).","journal-title":"Plant J."},{"key":"1101_CR3","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul, S. F. et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 25, 3389\u20133402 (1997).","journal-title":"Nucleic Acids Res."},{"key":"1101_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2014-15-3-r46","volume":"15","author":"DE Wood","year":"2014","unstructured":"Wood, D. E. & Salzberg, S. L. Kraken: ultrafast metagenomic sequence classification using exact alignments. Genome Biol. 15, R46 (2014).","journal-title":"Genome Biol."},{"key":"1101_CR5","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1101\/gr.1161903","volume":"13","author":"G Caetano-Anoll\u00e9s","year":"2003","unstructured":"Caetano-Anoll\u00e9s, G. & Caetano-Anoll\u00e9s, D. An evolutionarily structured universe of protein architecture. Genome Res. 13, 1563\u20131571 (2003).","journal-title":"Genome Res."},{"key":"1101_CR6","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.tig.2013.07.001","volume":"29","author":"JA Capra","year":"2013","unstructured":"Capra, J. A., Stolzer, M., Durand, D. & Pollard, K. S. How old is my gene? Trends Genet. 29, 659\u2013668 (2013).","journal-title":"Trends Genet."},{"key":"1101_CR7","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1093\/icb\/ict068","volume":"53","author":"CW Dunn","year":"2013","unstructured":"Dunn, C. W., Luo, X. & Wu, Z. Phylogenetic analysis of gene expression. Integr. Comp. Biol. 53, 847\u2013856 (2013).","journal-title":"Integr. Comp. Biol."},{"key":"1101_CR8","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1093\/molbev\/msz150","volume":"36","author":"N Glover","year":"2019","unstructured":"Glover, N. et al. Advances and applications in the quest for orthologs. Mol. Biol. Evol. 36, 2157\u20132164 (2019).","journal-title":"Mol. Biol. Evol."},{"key":"1101_CR9","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.1093\/bioinformatics\/btq461","volume":"26","author":"RC Edgar","year":"2010","unstructured":"Edgar, R. C. Search and clustering orders of magnitude faster than BLAST. Bioinformatics 26, 2460\u20132461 (2010).","journal-title":"Bioinformatics"},{"key":"1101_CR10","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1101\/gr.113985.110","volume":"21","author":"SM Kie\u0142basa","year":"2011","unstructured":"Kie\u0142basa, S. M., Wan, R., Sato, K., Horton, P. & Frith, M. C. Adaptive seeds tame genomic sequence comparison. Genome Res. 21, 487\u2013493 (2011).","journal-title":"Genome Res."},{"key":"1101_CR11","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","volume":"35","author":"M Steinegger","year":"2017","unstructured":"Steinegger, M. & S\u00f6ding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026\u20131028 (2017).","journal-title":"Nat. Biotechnol."},{"key":"1101_CR12","doi-asserted-by":"publisher","first-page":"D304","DOI":"10.1093\/nar\/gkt1240","volume":"42","author":"NK Fox","year":"2014","unstructured":"Fox, N. K., Brenner, S. E. & Chandonia, J.-M. SCOPe: Structural Classification of Proteins\u2013extended, integrating SCOP and ASTRAL data and classification of new structures. Nucleic Acids Res. 42, D304\u2013D309 (2014).","journal-title":"Nucleic Acids Res."},{"key":"1101_CR13","doi-asserted-by":"publisher","first-page":"6073","DOI":"10.1073\/pnas.95.11.6073","volume":"95","author":"SE Brenner","year":"1998","unstructured":"Brenner, S. E., Chothia, C. & Hubbard, T. J. Assessing sequence comparison methods with reliable structurally identified distant evolutionary relationships. Proc. Natl Acad. Sci. USA 95, 6073\u20136078 (1998).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"1101_CR14","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1093\/bioinformatics\/btm098","volume":"23","author":"BE Suzek","year":"2007","unstructured":"Suzek, B. E., Huang, H., McGarvey, P., Mazumder, R. & Wu, C. H. UniRef: comprehensive and non-redundant UniProt reference clusters. Bioinformatics 23, 1282\u20131288 (2007).","journal-title":"Bioinformatics"},{"key":"1101_CR15","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1093\/bioinformatics\/btw006","volume":"32","author":"M Hauser","year":"2016","unstructured":"Hauser, M., Steinegger, M. & S\u00f6ding, J. MMseqs software suite for fast and deep clustering and searching of large protein sequence sets. Bioinformatics 32, 1323\u20131330 (2016).","journal-title":"Bioinformatics"},{"key":"1101_CR16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nmeth.3176","volume":"12","author":"B Buchfink","year":"2015","unstructured":"Buchfink, B., Xie, C. & Huson, D. H. Fast and sensitive protein alignment using DIAMOND. Nat. Methods 12, 59\u201360 (2015).","journal-title":"Nat. Methods"},{"key":"1101_CR17","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1093\/bioinformatics\/18.3.440","volume":"18","author":"B Ma","year":"2002","unstructured":"Ma, B., Tromp, J. & Li, M. PatternHunter: faster and more sensitive homology search. Bioinformatics 18, 440\u2013445 (2002).","journal-title":"Bioinformatics"},{"key":"1101_CR18","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.14778\/1687553.1687564","volume":"2","author":"C Kim","year":"2009","unstructured":"Kim, C. et al. Sort vs. Hash revisited: fast join implementation on modern multi-core CPUs. Proc. VLDB Endow. 2, 1378\u20131389 (2009).","journal-title":"Proc. VLDB Endow."},{"key":"1101_CR19","doi-asserted-by":"publisher","first-page":"2433","DOI":"10.1093\/bioinformatics\/btr368","volume":"27","author":"L Ilie","year":"2011","unstructured":"Ilie, L., Ilie, S. & Bigvand, A. M. SpEED: fast computation of sensitive spaced seeds. Bioinformatics 27, 2433\u20132434 (2011).","journal-title":"Bioinformatics"},{"key":"1101_CR20","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"TF Smith","year":"1981","unstructured":"Smith, T. F. & Waterman, M. S. Identification of common molecular subsequences. J. Mol. Biol. 147, 195\u2013197 (1981).","journal-title":"J. Mol. Biol."},{"key":"1101_CR21","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1093\/bioinformatics\/btl582","volume":"23","author":"M Farrar","year":"2007","unstructured":"Farrar, M. Striped Smith-Waterman speeds database searches six times over other SIMD implementations. Bioinformatics 23, 156\u2013161 (2007).","journal-title":"Bioinformatics"},{"key":"1101_CR22","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1186\/1471-2105-12-221","volume":"12","author":"T Rognes","year":"2011","unstructured":"Rognes, T. Faster Smith-Waterman database searches with inter-sequence SIMD parallelisation. BMC Bioinformatics 12, 221 (2011).","journal-title":"BMC Bioinformatics"},{"key":"1101_CR23","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","volume":"34","author":"H Li","year":"2018","unstructured":"Li, H. Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics 34, 3094\u20133100 (2018).","journal-title":"Bioinformatics"},{"key":"1101_CR24","doi-asserted-by":"publisher","first-page":"5101","DOI":"10.1111\/j.1742-4658.2005.04945.x","volume":"272","author":"SF Altschul","year":"2005","unstructured":"Altschul, S. F. et al. Protein database searches using compositionally adjusted substitution matrices. FEBS J. 272, 5101\u20135109 (2005).","journal-title":"FEBS J."},{"key":"1101_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-1103-0","volume":"17","author":"M Jain","year":"2016","unstructured":"Jain, M., Olsen, H. E., Paten, B. & Akeson, M. The Oxford Nanopore MinION: delivery of nanopore sequencing to the genomics community. Genome Biol. 17, 239 (2016).","journal-title":"Genome Biol."},{"key":"1101_CR26","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/0097-8485(93)85006-X","volume":"17","author":"JC Wootton","year":"1993","unstructured":"Wootton, J. C. & Federhen, S. Statistics of local complexity in amino acid sequences and sequence databases. Comput. Chem. 17, 149\u2013163 (1993).","journal-title":"Comput. Chem."},{"key":"1101_CR27","doi-asserted-by":"publisher","first-page":"e23","DOI":"10.1093\/nar\/gkq1212","volume":"39","author":"MC Frith","year":"2011","unstructured":"Frith, M. C. A new repeat-masking method enables specific detection of homologous sequences. Nucleic Acids Res. 39, e23 (2011).","journal-title":"Nucleic Acids Res."},{"key":"1101_CR28","unstructured":"Darling, A. E., Carey, L. & Feng, W. C. The design, implementation, and evaluation of mpiBLAST. In ClusterWorld Conference & Expo and the 4th International Conference on Linux Clusters: The HPC Revolution 2003 https:\/\/public.lanl.gov\/radiant\/pubs\/bio\/cwce03.pdf (2003)."},{"key":"1101_CR29","unstructured":"Sokal, R. R. & Michener, C. D. A Statistical Method for Evaluating Systematic Relationships (University of Kansas, 1958)."},{"key":"1101_CR30","doi-asserted-by":"publisher","unstructured":"Buchfink, B. DIAMOND v2.0.7 benchmark. figshare https:\/\/doi.org\/10.6084\/m9.figshare.c.5053112.v1 (2021).","DOI":"10.6084\/m9.figshare.c.5053112.v1"},{"key":"1101_CR31","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1038\/s41587-019-0202-3","volume":"37","author":"RD Stewart","year":"2019","unstructured":"Stewart, R. D. et al. Compendium of 4,941 rumen metagenome-assembled genomes for rumen microbiome biology and enzyme discovery. Nat. Biotechnol. 37, 953\u2013961 (2019).","journal-title":"Nat. Biotechnol."},{"key":"1101_CR32","doi-asserted-by":"crossref","unstructured":"Bahram, M. et al. Structure and function of the global topsoil microbiome. Nature 560, 233\u2013237 (2018).","DOI":"10.1038\/s41586-018-0386-6"}],"container-title":["Nature Methods"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.nature.com\/articles\/s41592-021-01101-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41592-021-01101-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/s41592-021-01101-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,20]],"date-time":"2023-05-20T18:14:09Z","timestamp":1684606449000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41592-021-01101-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["1101"],"URL":"https:\/\/doi.org\/10.1038\/s41592-021-01101-x","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.739896782.793586885","asserted-by":"object"},{"id-type":"doi","id":"10.3410\/f.739896782.793586904","asserted-by":"object"}]},"ISSN":["1548-7091","1548-7105"],"issn-type":[{"value":"1548-7091","type":"print"},{"value":"1548-7105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]},"assertion":[{"value":"23 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}