{"id":"https://openalex.org/W2745994342","doi":"https://doi.org/10.1093/bioinformatics/btx520","title":"MetaCache: context-aware classification of metagenomic reads using minhashing","display_name":"MetaCache: context-aware classification of metagenomic reads using minhashing","publication_year":2017,"publication_date":"2017-08-14","ids":{"openalex":"https://openalex.org/W2745994342","doi":"https://doi.org/10.1093/bioinformatics/btx520","mag":"2745994342","pmid":"https://pubmed.ncbi.nlm.nih.gov/28961782"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx520","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx520","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/23/3740/25168109/btx520.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/23/3740/25168109/btx520.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107834032","display_name":"Andr\u00e9 C. M\u00fcller","orcid":"https://orcid.org/0000-0002-0608-8176"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 M\u00fcller","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027561629","display_name":"Christian Hundt","orcid":"https://orcid.org/0000-0002-7995-1858"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Hundt","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015934308","display_name":"Andreas Hildebrandt","orcid":"https://orcid.org/0000-0003-2180-6516"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Hildebrandt","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003394017","display_name":"Thomas Hankeln","orcid":"https://orcid.org/0000-0002-0677-8417"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Hankeln","raw_affiliation_strings":["Molecular Genetics and Genome Analysis Group, Department of Biology, Department of Biology, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Genetics and Genome Analysis Group, Department of Biology, Department of Biology, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020388832"],"corresponding_institution_ids":["https://openalex.org/I197323543"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.1284,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.88014918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"23","first_page":"3740","last_page":"3748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7351999878883362,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7351999878883362,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.1363999992609024,"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/T10885","display_name":"Gene expression and cancer classification","score":0.010999999940395355,"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/computer-science","display_name":"Computer science","score":0.7538027167320251},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.7424333691596985},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6849737763404846},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.614470362663269},{"id":"https://openalex.org/keywords/refseq","display_name":"RefSeq","score":0.5190477967262268},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5138800144195557},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46183252334594727},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4403844177722931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32930663228034973},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1795727014541626},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13161644339561462},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1095069944858551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538027167320251},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7424333691596985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6849737763404846},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.614470362663269},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.5190477967262268},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5138800144195557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46183252334594727},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4403844177722931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32930663228034973},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1795727014541626},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13161644339561462},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1095069944858551},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btx520","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx520","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/23/3740/25168109/btx520.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:28961782","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28961782","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx520","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx520","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/23/3740/25168109/btx520.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320310862","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2745994342.pdf","grobid_xml":"https://content.openalex.org/works/W2745994342.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1579534339","https://openalex.org/W1599047304","https://openalex.org/W1703384511","https://openalex.org/W1975874700","https://openalex.org/W2001405665","https://openalex.org/W2003347102","https://openalex.org/W2009906332","https://openalex.org/W2042417858","https://openalex.org/W2054520741","https://openalex.org/W2072970694","https://openalex.org/W2124927293","https://openalex.org/W2128964206","https://openalex.org/W2135515858","https://openalex.org/W2142678478","https://openalex.org/W2143842034","https://openalex.org/W2153990926","https://openalex.org/W2159954944","https://openalex.org/W2265709988","https://openalex.org/W2282583203","https://openalex.org/W2337747100","https://openalex.org/W2949351818","https://openalex.org/W2950150251","https://openalex.org/W2951176108","https://openalex.org/W6670160666"],"related_works":["https://openalex.org/W3003110834","https://openalex.org/W4383818008","https://openalex.org/W2921363728","https://openalex.org/W2279684808","https://openalex.org/W2189508481","https://openalex.org/W3217304749","https://openalex.org/W2066142713","https://openalex.org/W2894932706","https://openalex.org/W2377389766","https://openalex.org/W2133994800"],"abstract_inverted_index":{"MOTIVATION:":[0],"Metagenomic":[1],"shotgun":[2],"sequencing":[3,14,52],"studies":[4],"are":[5,233],"becoming":[6],"increasingly":[7],"popular":[8],"with":[9,153,186],"prominent":[10],"examples":[11],"including":[12],"the":[13,32,43,55,87,114,127,202],"of":[15,34,46,59,97,103,113,157,170,204],"human":[16],"microbiomes":[17],"and":[18,54,109,132,139,150,175,221],"diverse":[19],"environments.":[20],"A":[21],"fundamental":[22],"computational":[23],"problem":[24],"in":[25,218],"this":[26],"context":[27],"is":[28,213],"read":[29,36,84,129],"classification,":[30],"i.e.":[31],"assignment":[33],"each":[35],"to":[37,42,126,178],"a":[38,118,154,184],"taxonomic":[39],"label.":[40],"Due":[41],"large":[44,71],"number":[45,58],"reads":[47,98,108],"produced":[48],"by":[49,99],"modern":[50],"high-throughput":[51],"technologies":[53],"rapidly":[56],"increasing":[57,201],"available":[60,234],"reference":[61,115,206],"genomes":[62,152],"corresponding":[63],"software":[64,82,216],"tools":[65],"suffer":[66],"from":[67],"either":[68],"long":[69],"runtimes,":[70],"memory":[72,124,171],"requirements":[73],"or":[74],"low":[75],"accuracy.":[76],"RESULTS:":[77],"We":[78],"introduce":[79],"MetaCache-a":[80],"novel":[81],"for":[83],"classification":[85,96,196],"using":[86,146],"big":[88],"data":[89,232],"technique":[90],"minhashing.":[91],"Our":[92,190],"approach":[93],"performs":[94],"context-aware":[95],"computing":[100],"representative":[101],"subsamples":[102],"k-mers":[104],"within":[105],"both,":[106],"probed":[107],"locally":[110],"constrained":[111],"regions":[112],"genomes.":[116],"As":[117],"result,":[119],"MetaCache":[120,212],"consumes":[121,166],"significantly":[122],"less":[123],"compared":[125],"state-of-the-art":[128],"classifiers":[130],"Kraken":[131,174],"CLARK":[133,176],"while":[134,172],"achieving":[135],"highly":[136],"competitive":[137],"sensitivity":[138],"precision":[140],"at":[141,225,235],"comparable":[142],"speed.":[143],"For":[144],"example,":[145],"NCBI":[147],"RefSeq":[148],"draft":[149],"completed":[151],"total":[155],"length":[156],"around":[158],"140":[159],"billion":[160],"bases":[161],"as":[162],"reference,":[163],"MetaCache's":[164],"database":[165],"only":[167],"62":[168],"GB":[169,188],"both":[173],"fail":[177],"construct":[179],"their":[180],"respective":[181],"databases":[182],"on":[183],"workstation":[185],"512":[187],"RAM.":[189],"experimental":[191],"results":[192],"further":[193],"show":[194],"that":[195],"accuracy":[197],"continuously":[198],"improves":[199],"when":[200],"amount":[203],"utilized":[205],"genome":[207],"data.":[208],"AVAILABILITY":[209],"AND":[210],"IMPLEMENTATION:":[211],"open":[214],"source":[215],"written":[217],"C":[219],"++":[220],"can":[222],"be":[223],"downloaded":[224],"http://github.com/muellan/metacache.":[226],"CONTACT:":[227],"bertil.schmidt@uni-mainz.de.":[228],"SUPPLEMENTARY":[229],"INFORMATION:":[230],"Supplementary":[231],"Bioinformatics":[236],"online.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
