{"id":"https://openalex.org/W2963653132","doi":"https://doi.org/10.1186/s13015-019-0148-5","title":"Prefix-free parsing for building big BWTs","display_name":"Prefix-free parsing for building big BWTs","publication_year":2019,"publication_date":"2019-05-24","ids":{"openalex":"https://openalex.org/W2963653132","doi":"https://doi.org/10.1186/s13015-019-0148-5","mag":"2963653132","pmid":"https://pubmed.ncbi.nlm.nih.gov/31149025","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6534911"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-019-0148-5","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-019-0148-5","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-019-0148-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021635660","display_name":"Christina Boucher","orcid":"https://orcid.org/0000-0001-9509-9725"},"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":false,"raw_author_name":"Christina Boucher","raw_affiliation_strings":["CISE, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"CISE, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013172801","display_name":"Travis Gagie","orcid":"https://orcid.org/0000-0003-3689-327X"},"institutions":[{"id":"https://openalex.org/I911713783","display_name":"Diego Portales University","ror":"https://ror.org/03gtdcg60","country_code":"CL","type":"education","lineage":["https://openalex.org/I911713783"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Travis Gagie","raw_affiliation_strings":["EIT, Diego Portales University, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"EIT, Diego Portales University, Santiago, Chile","institution_ids":["https://openalex.org/I911713783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083575259","display_name":"Alan Kuhnle","orcid":"https://orcid.org/0000-0001-6506-1902"},"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":false,"raw_author_name":"Alan Kuhnle","raw_affiliation_strings":["CISE, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"CISE, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009556658","display_name":"Ben Langmead","orcid":"https://orcid.org/0000-0003-2437-1976"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Langmead","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049381844","display_name":"Giovanni Manzini","orcid":"https://orcid.org/0000-0002-5047-0196"},"institutions":[{"id":"https://openalex.org/I123338534","display_name":"Universit\u00e0 degli Studi del Piemonte Orientale \u201cAmedeo Avogadro\u201d","ror":"https://ror.org/04387x656","country_code":"IT","type":"education","lineage":["https://openalex.org/I123338534"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Manzini","raw_affiliation_strings":["University of Eastern Piedmont, Alessandria, Italy"],"affiliations":[{"raw_affiliation_string":"University of Eastern Piedmont, Alessandria, Italy","institution_ids":["https://openalex.org/I123338534"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000946526","display_name":"Taher Mun","orcid":"https://orcid.org/0000-0002-3588-0883"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taher Mun","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827,"provenance":"doaj"},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827,"provenance":"doaj"},"fwci":4.104,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":55,"citation_normalized_percentile":{"value":0.999972,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"14","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9999,"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":0.9999,"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":0.992,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9881,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.7953402},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4559198},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.43434346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855705},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.7953402},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6373154},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5727088},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.51617247},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49331918},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4559198},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.43434346},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.422141},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36918515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36186433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3213473},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.18918249},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16068447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13254261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11678368},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-019-0148-5","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-019-0148-5","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/0740dbfd57f5443c975843203a7b99e9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc6534911","pdf_url":"https://europepmc.org/articles/pmc6534911?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/opus/volltexte/2018/9304/","pdf_url":"https://drops.dagstuhl.de/opus/volltexte/2018/9304/pdf/LIPIcs-WABI-2018-2.pdf","source":{"id":"https://openalex.org/S4306402524","display_name":"Leibniz-Zentrum f\u00fcr Informatik (Schloss Dagstuhl)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"host_organization_lineage_names":["Schloss Dagstuhl \u2013 Leibniz Center for Informatics"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6534911","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://doi.org/10.1101/472399","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1803.11245","pdf_url":"https://arxiv.org/pdf/1803.11245","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31149025","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-019-0148-5","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-019-0148-5","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.48,"id":"https://metadata.un.org/sdg/9"}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"IIS 1618814"}],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W1962019683","https://openalex.org/W1977174119","https://openalex.org/W2011699809","https://openalex.org/W2097341408","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2124985265","https://openalex.org/W2159647614","https://openalex.org/W2170551349","https://openalex.org/W2263875137","https://openalex.org/W2531153203","https://openalex.org/W2564333746","https://openalex.org/W2587250785","https://openalex.org/W2604363154","https://openalex.org/W2612224663","https://openalex.org/W2799324424","https://openalex.org/W2963160145","https://openalex.org/W2963756574","https://openalex.org/W4230945265","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W54192826","https://openalex.org/W3092113474","https://openalex.org/W3011699130","https://openalex.org/W2800763970","https://openalex.org/W2795037468","https://openalex.org/W2395357979","https://openalex.org/W2074308207","https://openalex.org/W2066858118","https://openalex.org/W1976914335","https://openalex.org/W1754202134"],"abstract_inverted_index":{"High-throughput":[0],"sequencing":[1],"technologies":[2],"have":[3],"led":[4],"to":[5,25,53,76],"explosive":[6],"growth":[7],"of":[8,12,18,30,42,57],"genomic":[9,44],"databases;":[10],"one":[11],"which":[13,62],"will":[14],"soon":[15],"reach":[16],"hundreds":[17],"terabytes.":[19],"For":[20],"many":[21,41,64],"applications":[22],"we":[23,70],"want":[24],"build":[26],"and":[27],"store":[28],"indexes":[29,36],"these":[31,43],"databases":[32,45],"but":[33],"constructing":[34],"such":[35],"is":[37],"a":[38,72],"challenge.":[39],"Fortunately,":[40],"are":[46],"highly-repetitive-a":[47],"characteristic":[48],"that":[49],"can":[50],"be":[51],"exploited":[52],"ease":[54],"the":[55,58],"computation":[56],"Burrows-Wheeler":[59],"Transform":[60],"(BWT),":[61],"underlies":[63],"popular":[65],"indexes.":[66],"In":[67],"this":[68],"paper,":[69],"introduce":[71],"preprocessing":[73],"algorithm,":[74],"referred":[75],"as":[77]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2963653132","counts_by_year":[{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-01-02T10:08:40.499689","created_date":"2019-07-30"}