{"id":"https://openalex.org/W4289828092","doi":"https://doi.org/10.1109/ipdpsw55747.2022.00034","title":"Building scalable indexes that can be efficiently queried","display_name":"Building scalable indexes that can be efficiently queried","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W4289828092","doi":"https://doi.org/10.1109/ipdpsw55747.2022.00034"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw55747.2022.00034","doi":"https://doi.org/10.1109/ipdpsw55747.2022.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw55747.2022.00034","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-abstract","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/A5021635660","display_name":"Christina A. Boucher","orcid":"https://orcid.org/0000-0001-9509-9725","observed_orcids":["https://orcid.org/0000-0001-9509-9725","https://orcid.org/0000-0001-5617-7495"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christina Boucher","raw_affiliation_strings":["University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021635660"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0,"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/r-index","display_name":"R-index","score":0.9440000057220459},{"id":"https://openalex.org/keywords/fm-index","display_name":"FM-index","score":0.9829999804496765},{"id":"https://openalex.org/keywords/maximal-exact-matches","display_name":"maximal exact matches","score":0.9350000023841858},{"id":"https://openalex.org/keywords/exact-pattern-matching","display_name":"exact pattern matching","score":0.656000018119812},{"id":"https://openalex.org/keywords/approximate-pattern-matching","display_name":"approximate pattern matching","score":0.9599999785423279},{"id":"https://openalex.org/keywords/genome-indexing","display_name":"genome indexing","score":0.503000020980835},{"id":"https://openalex.org/keywords/human-chromosomes","display_name":"human chromosomes","score":0.4320000112056732},{"id":"https://openalex.org/keywords/repetitive-dna","display_name":"repetitive DNA","score":0.7630000114440918},{"id":"https://openalex.org/keywords/index-construction","display_name":"index construction","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8198401927947998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653318643569946},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6771801114082336},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.676986813545227},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.6384978890419006},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5985477566719055},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.588791012763977},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.583381175994873},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5269635319709778},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.458482950925827},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4306830167770386},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4158409535884857},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34366175532341003},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26886606216430664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23538720607757568},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1685740351676941},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0929599404335022},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08527970314025879},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw55747.2022.00034","doi":"https://doi.org/10.1109/ipdpsw55747.2022.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw55747.2022.00034","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3180150214","https://openalex.org/W4205330988","https://openalex.org/W4229037677","https://openalex.org/W4205262153","https://openalex.org/W4415854860","https://openalex.org/W4394688386","https://openalex.org/W2951332226","https://openalex.org/W4313452974","https://openalex.org/W2795084201","https://openalex.org/W2100673218"],"abstract_inverted_index":{"Recently,":[0],"Gagie":[1],"et":[2,82],"al.":[3,83],"proposed":[4],"a":[5,21,34],"version":[6],"of":[7,17,87,141,157,193,199],"the":[8,11,30,60,85,96,123,127,139,142,191],"FM-index,":[9],"called":[10,36],"r-index,":[12],"that":[13,91,118],"can":[14,51,147],"store":[15],"thousands":[16],"human":[18,200],"genomes":[19],"on":[20],"commodity":[22],"computer.":[23],"We":[24,113],"later":[25],"showed":[26,90],"how":[27,108],"to":[28,54,109,121,138,162,168,176],"build":[29,122],"r-index":[31,61,97,124],"efficiently":[32,65],"via":[33],"technique":[35],"prefix-free":[37,143],"parsing":[38],"(PFP)":[39],"and":[40,67,89,125,130,134,153,173],"demonstrated":[41],"its":[42],"effectiveness":[43],"for":[44,180,196],"exact":[45,74],"pattern":[46,49,57],"matching.":[47],"Exact":[48],"matching":[50,58],"be":[52],"leveraged":[53],"support":[55,64],"approximate":[56],"but":[59,103],"itself":[62],"cannot":[63],"popular":[66],"important":[68],"queries":[69],"such":[70],"as":[71],"finding":[72,101],"maximal":[73],"matches":[75],"(MEMs).":[76],"To":[77],"address":[78],"this":[79],"shortcoming,":[80],"Bannai":[81],"introduced":[84],"concept":[86],"thresholds,":[88],"storing":[92],"them":[93],"together":[94],"with":[95,136],"enables":[98],"efficient":[99],"MEM":[100],"---":[102],"they":[104],"did":[105],"not":[106],"say":[107],"find":[110,126,149],"those":[111],"thresholds.":[112],"present":[114],"another":[115],"novel":[116],"algorithm":[117],"applies":[119],"PFP":[120],"thresholds":[128],"simultaneously":[129],"in":[131],"linear":[132],"time":[133],"space":[135],"respect":[137],"size":[140,192],"parse.":[144],"Our":[145],"implementation":[146],"rapidly":[148],"MEMs":[150],"between":[151],"reads":[152],"large":[154,197],"sequence":[155],"collections":[156,198],"highly":[158],"repetitive":[159],"sequences.":[160],"Compared":[161],"existing":[163],"methods,":[164],"ours":[165],"used":[166],"2":[167,175],"11":[169],"times":[170,178],"less":[171,187],"memory":[172],"was":[174,186],"32":[177],"faster":[179],"index":[181],"construction.":[182],"Moreover,":[183],"our":[184],"method":[185],"than":[188],"one":[189],"thousandth":[190],"competing":[194],"indexes":[195],"chromosomes.":[201]},"counts_by_year":[],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2022-08-05T00:00:00"}