{"id":"https://openalex.org/W4413807019","doi":"https://doi.org/10.1038/s43588-025-00855-0","title":"MetaKSSD: boosting the scalability of the reference taxonomic marker database and the performance of metagenomic profiling using sketch operations","display_name":"MetaKSSD: boosting the scalability of the reference taxonomic marker database and the performance of metagenomic profiling using sketch operations","publication_year":2025,"publication_date":"2025-08-29","ids":{"openalex":"https://openalex.org/W4413807019","doi":"https://doi.org/10.1038/s43588-025-00855-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/40883605"},"language":"en","primary_location":{"id":"doi:10.1038/s43588-025-00855-0","is_oa":false,"landing_page_url":"https://doi.org/10.1038/s43588-025-00855-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210228084","display_name":"Nature Computational Science","issn_l":"2662-8457","issn":["2662-8457"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Computational Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040873566","display_name":"Huiguang Yi","orcid":"https://orcid.org/0000-0002-9676-7438"},"institutions":[{"id":"https://openalex.org/I4210088191","display_name":"Agricultural Genomics Institute at Shenzhen","ror":"https://ror.org/0066zpp98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210088191","https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210138501","display_name":"Chinese Academy of Agricultural Sciences","ror":"https://ror.org/0313jb750","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210151987","display_name":"Ministry of Agriculture and Rural Affairs","ror":"https://ror.org/05ckt8b96","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huiguang Yi","raw_affiliation_strings":["Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China. yihuiguang@caas.cn","Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China. yihuiguang@caas.cn","institution_ids":["https://openalex.org/I4210088191"]},{"raw_affiliation_string":"Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210088191","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101086021","display_name":"Xiaoxin Lu","orcid":"https://orcid.org/0009-0008-9546-6052"},"institutions":[{"id":"https://openalex.org/I4210088191","display_name":"Agricultural Genomics Institute at Shenzhen","ror":"https://ror.org/0066zpp98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210088191","https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210138501","display_name":"Chinese Academy of Agricultural Sciences","ror":"https://ror.org/0313jb750","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210151987","display_name":"Ministry of Agriculture and Rural Affairs","ror":"https://ror.org/05ckt8b96","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxin Lu","raw_affiliation_strings":["Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210088191","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004161103","display_name":"Qing Chang","orcid":"https://orcid.org/0000-0001-5138-8760"},"institutions":[{"id":"https://openalex.org/I4210088191","display_name":"Agricultural Genomics Institute at Shenzhen","ror":"https://ror.org/0066zpp98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210088191","https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210138501","display_name":"Chinese Academy of Agricultural Sciences","ror":"https://ror.org/0313jb750","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210151987","display_name":"Ministry of Agriculture and Rural Affairs","ror":"https://ror.org/05ckt8b96","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Chang","raw_affiliation_strings":["Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210088191","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040873566"],"corresponding_institution_ids":["https://openalex.org/I4210088191","https://openalex.org/I4210138501","https://openalex.org/I4210151987"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1999905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":"10","first_page":"884","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.7570152878761292},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7345579862594604},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7056348323822021},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6641509532928467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6367400884628296},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.486932635307312},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45858949422836304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3587197959423065},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3325028121471405},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3216085731983185},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19544750452041626},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0632060170173645},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.060224950313568115},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.04964753985404968}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7570152878761292},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7345579862594604},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7056348323822021},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6641509532928467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367400884628296},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.486932635307312},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45858949422836304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587197959423065},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3325028121471405},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3216085731983185},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19544750452041626},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0632060170173645},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.060224950313568115},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.04964753985404968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1038/s43588-025-00855-0","is_oa":false,"landing_page_url":"https://doi.org/10.1038/s43588-025-00855-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210228084","display_name":"Nature Computational Science","issn_l":"2662-8457","issn":["2662-8457"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Computational Science","raw_type":"journal-article"},{"id":"pmid:40883605","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40883605","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature computational science","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W176201993","https://openalex.org/W1971061059","https://openalex.org/W1985514943","https://openalex.org/W2006075770","https://openalex.org/W2023615726","https://openalex.org/W2031371243","https://openalex.org/W2071841602","https://openalex.org/W2087278385","https://openalex.org/W2110065044","https://openalex.org/W2116041602","https://openalex.org/W2118001436","https://openalex.org/W2124927293","https://openalex.org/W2150550043","https://openalex.org/W2151372451","https://openalex.org/W2152825437","https://openalex.org/W2305300412","https://openalex.org/W2344543878","https://openalex.org/W2345658906","https://openalex.org/W2463312000","https://openalex.org/W2469986620","https://openalex.org/W2586360538","https://openalex.org/W2756958651","https://openalex.org/W2758005814","https://openalex.org/W2773939681","https://openalex.org/W2775608308","https://openalex.org/W2889019390","https://openalex.org/W2917207851","https://openalex.org/W2920716817","https://openalex.org/W2951676949","https://openalex.org/W2952204926","https://openalex.org/W2968450569","https://openalex.org/W2983698537","https://openalex.org/W2991034244","https://openalex.org/W3019706413","https://openalex.org/W3022598036","https://openalex.org/W3033913804","https://openalex.org/W3048090444","https://openalex.org/W3048417385","https://openalex.org/W3087332590","https://openalex.org/W3091672414","https://openalex.org/W3106215385","https://openalex.org/W3121407008","https://openalex.org/W3137871957","https://openalex.org/W3158733686","https://openalex.org/W3159504416","https://openalex.org/W3161593331","https://openalex.org/W3162300015","https://openalex.org/W3176930333","https://openalex.org/W3200103613","https://openalex.org/W3216588755","https://openalex.org/W4224868124","https://openalex.org/W4225258284","https://openalex.org/W4229074162","https://openalex.org/W4294001681","https://openalex.org/W4297498241","https://openalex.org/W4306412223","https://openalex.org/W4310461160","https://openalex.org/W4310663915","https://openalex.org/W4315707395","https://openalex.org/W4321611856","https://openalex.org/W4368360101","https://openalex.org/W4385984744","https://openalex.org/W4387541035","https://openalex.org/W4394987863","https://openalex.org/W4399387478","https://openalex.org/W4403228370","https://openalex.org/W6892614885","https://openalex.org/W6929853851","https://openalex.org/W6930981735","https://openalex.org/W6948996410","https://openalex.org/W6949010820","https://openalex.org/W6967617076","https://openalex.org/W6968005219"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2067869703"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}
