{"id":"https://openalex.org/W3174681547","doi":"https://doi.org/10.1145/3448016.3457333","title":"Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO)","display_name":"Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO)","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3174681547","doi":"https://doi.org/10.1145/3448016.3457333","mag":"3174681547"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5007135458","display_name":"Gaurav Gupta","orcid":"https://orcid.org/0000-0003-0607-4994"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gaurav Gupta","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048587169","display_name":"Minghao Yan","orcid":"https://orcid.org/0009-0002-0200-7145"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghao Yan","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103253242","display_name":"Benjamin Coleman","orcid":"https://orcid.org/0000-0002-2010-796X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Coleman","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072499401","display_name":"Bryce Kille","orcid":"https://orcid.org/0000-0003-2946-6915"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryce Kille","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082173235","display_name":"R. A. Leo Elworth","orcid":"https://orcid.org/0000-0002-3945-0661"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. A. Leo Elworth","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059158692","display_name":"Tharun Medini","orcid":"https://orcid.org/0009-0000-0410-2977"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tharun Medini","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054369332","display_name":"Todd J. Treangen","orcid":"https://orcid.org/0000-0002-3760-564X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd Treangen","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshumali Shrivastava","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5007135458"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.8849,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.7247353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2226","last_page":"2234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9944999814033508,"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":0.9944999814033508,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9492405652999878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891266345977783},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6537573337554932},{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.5120545029640198},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4796883761882782},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47278428077697754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47050970792770386},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4439205825328827},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4213974177837372},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2861649990081787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2328609824180603}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9492405652999878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891266345977783},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6537573337554932},{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.5120545029640198},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4796883761882782},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47278428077697754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47050970792770386},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4439205825328827},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4213974177837372},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2861649990081787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2328609824180603},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3457333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W104648112","https://openalex.org/W1974033543","https://openalex.org/W2018423671","https://openalex.org/W2023797161","https://openalex.org/W2043012581","https://openalex.org/W2055043387","https://openalex.org/W2065671211","https://openalex.org/W2080234606","https://openalex.org/W2104677379","https://openalex.org/W2117608012","https://openalex.org/W2123845384","https://openalex.org/W2136986825","https://openalex.org/W2148212498","https://openalex.org/W2148294372","https://openalex.org/W2165446840","https://openalex.org/W2266239166","https://openalex.org/W2560209686","https://openalex.org/W2612224663","https://openalex.org/W2795650864","https://openalex.org/W2809649683","https://openalex.org/W2913847081","https://openalex.org/W2949503312","https://openalex.org/W2950150251","https://openalex.org/W2969627863","https://openalex.org/W2979522844","https://openalex.org/W4251504464"],"related_works":["https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2260589296","https://openalex.org/W4376871908","https://openalex.org/W4283756799","https://openalex.org/W2990494149","https://openalex.org/W2081869611","https://openalex.org/W3157828377","https://openalex.org/W3176416739","https://openalex.org/W744786805"],"abstract_inverted_index":{"DNA":[0],"sequencing,":[1],"especially":[2],"of":[3,13,41,55,90,178,190,216],"microbial":[4],"genomes":[5],"and":[6,36,61,67,78,86,129,135,153,193,201],"metagenomes,":[7],"has":[8,24,37,144],"been":[9,48],"at":[10],"the":[11,33,52,82,91,160,191],"core":[12],"recent":[14,45],"research":[15],"advances":[16],"in":[17,26,29,112,185,208],"large-scale":[18],"comparative":[19],"genomics.":[20],"The":[21,188],"data":[22,92,97],"deluge":[23],"resulted":[25],"exponential":[27],"growth":[28],"genomic":[30],"datasets":[31],"over":[32],"past":[34],"years":[35],"shown":[38],"no":[39,71],"sign":[40],"slowing":[42],"down.":[43],"Several":[44],"attempts":[46],"have":[47],"made":[49],"to":[50,199],"tame":[51],"computational":[53],"burden":[54],"sequence":[56,206],"search":[57,100,161],"on":[58,213],"these":[59],"terabyte":[60],"petabyte-scale":[62],"datasets,":[63],"including":[64],"raw":[65],"reads":[66],"assembled":[68],"genomes.":[69],"However,":[70],"known":[72],"implementation":[73],"provides":[74],"both":[75],"fast":[76],"query":[77,113,136],"construction":[79],"time,":[80],"keeps":[81],"low":[83,150],"false-positive":[84,151],"requirement,":[85],"offers":[87],"cheap":[88,139],"storage":[89],"structure.":[93],"We":[94],"propose":[95],"a":[96,145,149,154,173,179,203,209,214],"structure":[98],"for":[99,141],"called":[101],"RAMBO":[102,158],"(Repeated":[103],"And":[104],"Merged":[105],"BloOm":[106],"Filter)":[107],"which":[108],"is":[109,172],"significantly":[110],"faster":[111],"time":[114],"than":[115],"state-of-the-art":[116],"genome":[117],"indexing":[118],"methods-":[119],"COBS":[120],"(Compact":[121],"bit-sliced":[122],"signature":[123],"index),":[124],"Sequence":[125],"Bloom":[126],"Trees,":[127],"HowDeSBT,":[128],"SSBT.":[130],"Furthermore,":[131],"it":[132,171],"supports":[133],"insertion":[134],"process":[137],"parallelism,":[138],"updates":[140],"streaming":[142],"inputs,":[143],"zero":[146],"false-negative":[147],"rate,":[148,152],"small":[155],"index":[156,202],"size.":[157],"converts":[159],"problem":[162],"into":[163],"set":[164],"membership":[165,180],"testing":[166,181],"among":[167],"K":[168],"documents.":[169],"Interestingly,":[170],"count-min":[174],"sketch":[175],"type":[176],"arrangement":[177],"utility":[182],"(Bloom":[183],"Filter":[184],"our":[186],"case).":[187],"simplicity":[189],"algorithm":[192],"embarrassingly":[194],"parallel":[195],"architecture":[196],"allows":[197],"us":[198],"stream":[200],"170TB":[204],"whole-genome":[205],"dataset":[207],"mere":[210],"9":[211],"hours":[212],"cluster":[215],"100":[217],"nodes":[218],"while":[219],"competing":[220],"methods":[221],"require":[222],"weeks.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
