{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T01:29:50Z","timestamp":1790818190648,"version":"4.1.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-024-00596-6","type":"journal-article","created":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T12:03:31Z","timestamp":1709035411000},"page":"104-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Indexing and real-time user-friendly queries in terabyte-sized complex genomic datasets with kmindex and ORA"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7210-3178","authenticated-orcid":false,"given":"T\u00e9o","family":"Lemane","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nolan","family":"Lezzoche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Lecubin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4228-1712","authenticated-orcid":false,"given":"Eric","family":"Pelletier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magali","family":"Lescot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rayan","family":"Chikhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0776-6407","authenticated-orcid":false,"given":"Pierre","family":"Peterlongo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,26]]},"reference":[{"key":"596_CR1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s41586-021-04332-2","volume":"602","author":"RC Edgar","year":"2022","unstructured":"Edgar, R. C. et al. Petabase-scale sequence alignment catalyses viral discovery. Nature 602, 142\u2013147 (2022).","journal-title":"Nature"},{"key":"596_CR2","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41586-022-04862-3","volume":"607","author":"L Paoli","year":"2022","unstructured":"Paoli, L. et al. Biosynthetic potential of the global ocean microbiome. Nature 607, 111\u2013118 (2022).","journal-title":"Nature"},{"key":"596_CR3","doi-asserted-by":"publisher","first-page":"D387","DOI":"10.1093\/nar\/gkab1053","volume":"50","author":"K Katz","year":"2022","unstructured":"Katz, K. et al. The Sequence Read Archive: a decade more of explosive growth. Nucleic Acids Res. 50, D387\u2013D390 (2022).","journal-title":"Nucleic Acids Res."},{"key":"596_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3445967","volume":"54","author":"R Chikhi","year":"2021","unstructured":"Chikhi, R., Holub, J. & Medvedev, P. Data structures to represent a set of k-long DNA sequences. ACM Comput. Surv. 54, 1\u201322 (2021).","journal-title":"ACM Comput. Surv."},{"key":"596_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1101\/gr.260604.119","volume":"31","author":"C Marchet","year":"2021","unstructured":"Marchet, C. et al. Data structures based on k-mers for querying large collections of sequencing data sets. Genome Res. 31, 1\u201312 (2021).","journal-title":"Genome Res."},{"key":"596_CR6","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.12688\/f1000research.19675.1","volume":"8","author":"NT Pierce","year":"2019","unstructured":"Pierce, N. T., Irber, L., Reiter, T., Brooks, P. & Brown, C. T. Large-scale sequence comparisons with sourmash. F1000Research 8, 1006 (2019).","journal-title":"F1000Research"},{"key":"596_CR7","doi-asserted-by":"publisher","first-page":"4100","DOI":"10.1093\/bioinformatics\/btac492","volume":"38","author":"M Darvish","year":"2022","unstructured":"Darvish, M., Seiler, E., Mehringer, S., Rahn, Ren\u00e9 & Reinert, K. Needle: a fast and space-efficient prefilter for estimating the quantification of very large collections of expression experiments. Bioinformatics 38, 4100\u20134108 (2022).","journal-title":"Bioinformatics"},{"key":"596_CR8","doi-asserted-by":"publisher","unstructured":"Karasikov, M. et al. Metagraph: indexing and analysing nucleotide archives at petabase-scale. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2020.10.01.322164 (2020).","DOI":"10.1101\/2020.10.01.322164"},{"key":"596_CR9","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s13059-020-02135-8","volume":"21","author":"G Holley","year":"2020","unstructured":"Holley, G. & Melsted, P. \u00e1ll Bifrost: highly parallel construction and indexing of colored and compacted de Bruijn graphs. Genome Biol. 21, 249 (2020).","journal-title":"Genome Biol."},{"key":"596_CR10","first-page":"1198","volume":"33","author":"A Cracco","year":"2023","unstructured":"Cracco, A. & Tomescu, A. I. Extremely fast construction and querying of compacted and colored de Bruijn graphs with ggcat. Genome Res. 33, 1198\u20131207 (2023).","journal-title":"Genome Res."},{"key":"596_CR11","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/362686.362692","volume":"13","author":"BH Bloom","year":"1970","unstructured":"Bloom, B. H. Space\/time trade-offs in hash coding with allowable errors. Commun. ACM 13, 422\u2013426 (1970).","journal-title":"Commun. ACM"},{"key":"596_CR12","doi-asserted-by":"crossref","unstructured":"Bingmann, T., Bradley, P., Gauger, F. & Iqbal, Z. COBS: a Compact Bit-Sliced Signature index. String Processing and Information Retrieval, SPIRE 2019. In Lecture Notes in Computer Science, Vol. 11811 (Springer, Cham, 2019).","DOI":"10.1007\/978-3-030-32686-9_21"},{"key":"596_CR13","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1089\/cmb.2017.0265","volume":"25","author":"B Solomon","year":"2018","unstructured":"Solomon, B. & Kingsford, C. Improved search of large transcriptomic sequencing databases using split sequence Bloom trees. J. Comput. Biol. 25, 755\u2013765 (2018).","journal-title":"J. Comput. Biol."},{"key":"596_CR14","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1093\/bioinformatics\/btz662","volume":"36","author":"RS Harris","year":"2020","unstructured":"Harris, R. S. & Medvedev, P. Improved representation of sequence Bloom trees. Bioinformatics 36, 721\u2013727 (2020).","journal-title":"Bioinformatics"},{"key":"596_CR15","doi-asserted-by":"publisher","first-page":"btad101","DOI":"10.1093\/bioinformatics\/btad101","volume":"39","author":"SK Srikakulam","year":"2023","unstructured":"Srikakulam, S. K., Keller, S., Dabbaghie, F., Bals, R. & Kalinina, O. V. Metaprofi: an ultrafast chunked Bloom filter for storing and querying protein and nucleotide sequence data for accurate identification of functionally relevant genetic variants. Bioinformatics 39, btad101 (2023).","journal-title":"Bioinformatics"},{"key":"596_CR16","unstructured":"The Ocean Read Atlas. OSU Institut Pytheas https:\/\/ocean-read-atlas.mio.osupytheas.fr\/ (2023)."},{"key":"596_CR17","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1038\/s41579-020-0364-5","volume":"18","author":"S Sunagawa","year":"2020","unstructured":"Sunagawa, S. et al. Tara Oceans: towards global ocean ecosystems biology. Nat. Rev. Microbiol. 18, 428\u2013445 (2020).","journal-title":"Nat. Rev. Microbiol."},{"key":"596_CR18","doi-asserted-by":"publisher","first-page":"i260","DOI":"10.1093\/bioinformatics\/btad233","volume":"39","author":"JN Alanko","year":"2023","unstructured":"Alanko, J. N., Vuohtoniemi, J., M\u00e4klin, T. & Puglisi, S. J. Themisto: a scalable colored k-mer index for sensitive pseudoalignment against hundreds of thousands of bacterial genomes. Bioinformatics 39, i260\u2013i269 (2023).","journal-title":"Bioinformatics"},{"key":"596_CR19","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/s13059-023-02971-4","volume":"24","author":"S Mehringer","year":"2023","unstructured":"Mehringer, S. et al. Hierarchical interleaved Bloom filter: enabling ultrafast, approximate sequence queries. Genome Biol. 24, 131 (2023).","journal-title":"Genome Biol."},{"key":"596_CR20","doi-asserted-by":"publisher","first-page":"i252","DOI":"10.1093\/bioinformatics\/btad225","volume":"39","author":"C Marchet","year":"2023","unstructured":"Marchet, C. & Limasset, A. Scalable sequence database search using partitioned aggregated Bloom comb trees. Bioinformatics 39, i252\u2013i259 (2023).","journal-title":"Bioinformatics"},{"key":"596_CR21","doi-asserted-by":"publisher","first-page":"vbac029","DOI":"10.1093\/bioadv\/vbac029","volume":"2","author":"T Lemane","year":"2022","unstructured":"Lemane, T., Medvedev, P., Chikhi, R. & Peterlongo, P. kmtricks: efficient and flexible construction of Bloom filters for large sequencing data collections. Bioinform. Adv. 2, vbac029 (2022).","journal-title":"Bioinform. Adv."},{"key":"596_CR22","doi-asserted-by":"publisher","first-page":"W289","DOI":"10.1093\/nar\/gky376","volume":"46","author":"E Villar","year":"2018","unstructured":"Villar, E. et al. The Ocean Gene Atlas: exploring the biogeography of plankton genes online. Nucleic Acids Res. 46, W289\u2013W295 (2018).","journal-title":"Nucleic Acids Res."},{"key":"596_CR23","doi-asserted-by":"publisher","first-page":"W516","DOI":"10.1093\/nar\/gkac420","volume":"50","author":"C Vernette","year":"2022","unstructured":"Vernette, C. et al. The Ocean Gene Atlas v2. 0: online exploration of the biogeography and phylogeny of plankton genes. Nucleic Acids Res. 50, W516\u2013W526 (2022).","journal-title":"Nucleic Acids Res."},{"key":"596_CR24","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s42003-021-02112-2","volume":"4","author":"SG Acinas","year":"2021","unstructured":"Acinas, S. G. et al. Deep ocean metagenomes provide insight into the metabolic architecture of bathypelagic microbial communities. Commun. Biol. 4, 604 (2021).","journal-title":"Commun. Biol."},{"key":"596_CR25","doi-asserted-by":"crossref","unstructured":"Robidou, L. & Peterlongo, P. findere: fast and precise approximate membership query. In International Symposium on String Processing and Information Retrieval 151\u2013163 (Springer, 2021).","DOI":"10.1007\/978-3-030-86692-1_13"},{"key":"596_CR26","unstructured":"fio. GitHub https:\/\/github.com\/axboe\/fio (2023)."},{"key":"596_CR27","doi-asserted-by":"publisher","unstructured":"DOI of the provided ORA server GitLab code. Zenodo https:\/\/doi.org\/10.5281\/zenodo.10462412 (2024).","DOI":"10.5281\/zenodo.10462412"},{"key":"596_CR28","unstructured":"European Nucleotide Archive. European Bioinformatics Institute https:\/\/www.ebi.ac.uk\/ena\/ (2023)."},{"key":"596_CR29","doi-asserted-by":"publisher","unstructured":"Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Registry of all samples from the Tara Oceans Expedition (2009\u20132013). PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875582 (2017).","DOI":"10.1594\/PANGAEA.875582"},{"key":"596_CR30","doi-asserted-by":"publisher","unstructured":"Guidi, L., Gattuso, J.-P. & Pesant, S. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about carbonate chemistry in the targeted environmental feature. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875567 (2017).","DOI":"10.1594\/PANGAEA.875567"},{"key":"596_CR31","doi-asserted-by":"publisher","unstructured":"Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Biodiversity context of all samples from the Tara Oceans Expedition (2009\u20132013). PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.853809 (2015).","DOI":"10.1594\/PANGAEA.853809"},{"key":"596_CR32","doi-asserted-by":"publisher","unstructured":"Guidi, L. et al. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about pigment concentrations (HPLC) in the targeted environmental feature. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875569 (2017).","DOI":"10.1594\/PANGAEA.875569"},{"key":"596_CR33","doi-asserted-by":"publisher","unstructured":"Ardyna, M. et al. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about mesoscale features at the sampling location. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875577 (2017).","DOI":"10.1594\/PANGAEA.875577"},{"key":"596_CR34","doi-asserted-by":"publisher","unstructured":"Guidi, L. et al. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about nutrients in the targeted environmental feature. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875575 (2017).","DOI":"10.1594\/PANGAEA.875575"},{"key":"596_CR35","doi-asserted-by":"publisher","unstructured":"Guidi, L., Picheral, M. & Pesant, S. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about sensor data in the targeted environmental feature. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875576 (2017).","DOI":"10.1594\/PANGAEA.875576"},{"key":"596_CR36","doi-asserted-by":"publisher","unstructured":"Alberti, A. & Pesant, S. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Methodology used in the lab for molecular analyses and links to the Sequence Read Archive of selected samples from the Tara Oceans Expedition (2009\u20132013). PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875581 (2017).","DOI":"10.1594\/PANGAEA.875581"},{"key":"596_CR37","doi-asserted-by":"publisher","unstructured":"Speich, S. et al. Tara Oceans Consortium, Coordinators; Tara Oceans Expedition, Participants. Environmental context of all samples from the Tara Oceans Expedition (2009\u20132013), about the water column features at the sampling location. PANGAEA https:\/\/doi.org\/10.1594\/PANGAEA.875579 (2017).","DOI":"10.1594\/PANGAEA.875579"},{"key":"596_CR38","unstructured":"Overview. Ocean Read Atlas https:\/\/ora.mio.osupytheas.fr\/manual\/pages\/ (2023)."},{"key":"596_CR39","unstructured":"Interfaces. Ocean Read Atlas https:\/\/ora.mio.osupytheas.fr\/manual\/pages\/interfaces.html (2023)."},{"key":"596_CR40","doi-asserted-by":"publisher","unstructured":"pierrepeterlongo\/kmindex_benchmarks: initial release. Zenodo https:\/\/doi.org\/10.5281\/zenodo.10462379 (2024).","DOI":"10.5281\/zenodo.10462379"},{"key":"596_CR41","doi-asserted-by":"publisher","unstructured":"DOI of the kmindex GitHub repository. Zenodo https:\/\/doi.org\/10.5281\/zenodo.10462427 (2024).","DOI":"10.5281\/zenodo.10462427"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00596-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00596-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00596-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T12:05:19Z","timestamp":1709035519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00596-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,26]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["596"],"URL":"https:\/\/doi.org\/10.1038\/s43588-024-00596-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.05.31.543043","asserted-by":"object"}]},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,26]]},"assertion":[{"value":"12 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","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"}}]}}