{"id":"https://openalex.org/W4386554491","doi":"https://doi.org/10.1093/bioinformatics/btad552","title":"\u03bc- PBWT: a lightweight r-indexing of the PBWT for storing and querying UK Biobank data","display_name":"\u03bc- PBWT: a lightweight r-indexing of the PBWT for storing and querying UK Biobank data","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386554491","doi":"https://doi.org/10.1093/bioinformatics/btad552","pmid":"https://pubmed.ncbi.nlm.nih.gov/37688560"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad552","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad552","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad552/51472749/btad552.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad552/51472749/btad552.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021585705","display_name":"Davide Cozzi","orcid":"https://orcid.org/0000-0003-2439-0608"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Cozzi","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca , Milan 20126, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2439-0608","affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca , Milan 20126, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073915297","display_name":"Massimiliano Rossi","orcid":"https://orcid.org/0000-0002-3012-1394"},"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":"Massimiliano Rossi","raw_affiliation_strings":["Department of Computer & Information Science & Engineering, Herbert-Wertheim College of Engineering, University of Florida , Gainesville, Florida 32611, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer & Information Science & Engineering, Herbert-Wertheim College of Engineering, University of Florida , Gainesville, Florida 32611, United States","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030162729","display_name":"Simone Rubinacci","orcid":"https://orcid.org/0000-0002-7725-4813"},"institutions":[{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Simone Rubinacci","raw_affiliation_strings":["Department of Computational Biology, University of Lausanne , Lausanne 1015, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7725-4813","affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Lausanne , Lausanne 1015, Switzerland","institution_ids":["https://openalex.org/I97565354"]}]},{"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/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Travis Gagie","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University , Halifax B3H 4R2, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3689-327X","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University , Halifax B3H 4R2, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071551582","display_name":"Dominik K\u00f6ppl","orcid":"https://orcid.org/0000-0002-8721-4444"},"institutions":[{"id":"https://openalex.org/I125602781","display_name":"Tokyo Medical and Dental University","ror":"https://ror.org/051k3eh31","country_code":"JP","type":"education","lineage":["https://openalex.org/I125602781"]},{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Dominik K\u00f6ppl","raw_affiliation_strings":["Department of Computer Science, University of Muenster , Muenster 48149, Germany","M&D Data Science Center, Tokyo Medical and Dental University , Tokyo 113-8510, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Muenster , Muenster 48149, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"M&D Data Science Center, Tokyo Medical and Dental University , Tokyo 113-8510, Japan","institution_ids":["https://openalex.org/I125602781"]}]},{"author_position":"middle","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":["Department of Computer & Information Science & Engineering, Herbert-Wertheim College of Engineering, University of Florida , Gainesville, Florida 32611, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer & Information Science & Engineering, Herbert-Wertheim College of Engineering, University of Florida , Gainesville, Florida 32611, United States","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038691764","display_name":"Paola Bonizzoni","orcid":"https://orcid.org/0000-0001-7289-4988"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paola Bonizzoni","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca , Milan 20126, Italy"],"raw_orcid":"https://orcid.org/0000-0001-7289-4988","affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca , Milan 20126, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":6,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038691764"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3825,"currency":"EUR","value_usd":4125},"fwci":0.8651,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76616422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"39","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8798999786376953,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8798999786376953,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11213","display_name":"Genomic variations and chromosomal abnormalities","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.013199999928474426,"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":0.7501273155212402},{"id":"https://openalex.org/keywords/biobank","display_name":"Biobank","score":0.6462094783782959},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6285824179649353},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5552637577056885},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5380795001983643},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.49826788902282715},{"id":"https://openalex.org/keywords/haplotype","display_name":"Haplotype","score":0.48619788885116577},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48040273785591125},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.42074185609817505},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4143775701522827},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3803212642669678},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32753220200538635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27995210886001587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12681347131729126},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.11981695890426636},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10982811450958252},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.09277257323265076},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08802372217178345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501273155212402},{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.6462094783782959},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6285824179649353},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5552637577056885},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5380795001983643},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.49826788902282715},{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.48619788885116577},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48040273785591125},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.42074185609817505},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4143775701522827},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3803212642669678},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32753220200538635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27995210886001587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12681347131729126},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11981695890426636},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10982811450958252},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.09277257323265076},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08802372217178345},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btad552","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad552","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad552/51472749/btad552.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37688560","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37688560","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},{"id":"pmh:oai:boa.unimib.it:10281/446438","is_oa":true,"landing_page_url":"https://academic.oup.com/bioinformatics/article/39/9/btad552/7265394?","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/9/btad552/51556136/btad552.pdf","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10502237","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10502237","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10502237/pdf/btad552.pdf","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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:serval.unil.ch:BIB_A05A8B57A5AB","is_oa":true,"landing_page_url":"https://serval.unil.ch/notice/serval:BIB_A05A8B57A5AB","pdf_url":"https://iris.unil.ch/bitstreams/f8174120-616e-4b05-b338-7a1370a297d3/download","source":{"id":"https://openalex.org/S4306401797","display_name":"SERVAL (Universit\u00e9 de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210093590","host_organization_name":"Swiss School of Archaeology in Greece","host_organization_lineage":["https://openalex.org/I4210093590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, vol. 39, no. 9","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unil.ch:iris/184032","is_oa":true,"landing_page_url":"https://iris.unil.ch/handle/iris/184032","pdf_url":null,"source":{"id":"https://openalex.org/S7407055444","display_name":"IRIS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad552","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad552","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad552/51472749/btad552.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G2241781793","display_name":null,"funder_award_id":"R01HG011392","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2344728784","display_name":null,"funder_award_id":"RGPIN071852020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"Horizon2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5050383059","display_name":null,"funder_award_id":"R01HG011392","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5372659370","display_name":"BD Spokes: SPOKE: SOUTH: Large-Scale Medical Informatics for Patient Care Coordination and Engagement","funder_award_id":"1636933","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5899942187","display_name":null,"funder_award_id":"JP21H05847","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6021068785","display_name":null,"funder_award_id":"JP22H03551","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6399886260","display_name":null,"funder_award_id":"1920920","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6697205189","display_name":"Pan-genome Graph Algorithms and Data Integration","funder_award_id":"872539","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6910641553","display_name":"RII Track 2 FEC: Multi-Scale Integrative Approach to Digital Health: Collaborative Research and Education in Smart Health in West Virginia and Arkansas","funder_award_id":"1920920","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7440903218","display_name":"ALgorithms for PAngenome Computational Analysis","funder_award_id":"956229","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7579068829","display_name":null,"funder_award_id":"23H04378","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8675867022","display_name":null,"funder_award_id":"JP21K17701","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386554491.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W783262033","https://openalex.org/W2066871473","https://openalex.org/W2104549677","https://openalex.org/W2143469992","https://openalex.org/W2147477044","https://openalex.org/W2786984148","https://openalex.org/W2889833303","https://openalex.org/W2895486342","https://openalex.org/W2911702276","https://openalex.org/W2949524341","https://openalex.org/W2951570719","https://openalex.org/W2962871655","https://openalex.org/W2966459122","https://openalex.org/W2967058481","https://openalex.org/W2999295646","https://openalex.org/W3017235832","https://openalex.org/W3104299286","https://openalex.org/W3126160703","https://openalex.org/W3131055609","https://openalex.org/W3131443014","https://openalex.org/W4205330988","https://openalex.org/W4206475898","https://openalex.org/W4220680041","https://openalex.org/W4286005461","https://openalex.org/W4310167947","https://openalex.org/W4382631675"],"related_works":["https://openalex.org/W3140834074","https://openalex.org/W2160484851","https://openalex.org/W2023010868","https://openalex.org/W2137587553","https://openalex.org/W2020004724","https://openalex.org/W2010727036","https://openalex.org/W2065747622","https://openalex.org/W1894595501","https://openalex.org/W857360071","https://openalex.org/W1630321625"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,242],"Positional":[2],"Burrows-Wheeler":[3],"Transform":[4],"(PBWT)":[5],"is":[6,186,202,235,244],"a":[7,15,35,91,147,176,209],"data":[8,46,170],"structure":[9,47],"that":[10,17,56,138,164,215],"indexes":[11],"haplotype":[12,21,110],"sequences":[13,25],"in":[14,23,30,73,109,174,206],"manner":[16],"enables":[18],"finding":[19],"maximal":[20,105,223],"matches":[22,106,224],"h":[24],"containing":[26],"w":[27],"variation":[28],"sites":[29],"O(hw)":[31],"time.":[32],"This":[33],"represents":[34],"significant":[36],"improvement":[37],"over":[38,53,226],"classical":[39],"quadratic-time":[40],"approaches.":[41],"However,":[42],"the":[43,67,81,87,98,139,142,153,179,192,197,213,218,227],"original":[44,228],"PBWT":[45,198],"does":[48],"not":[49],"allow":[50],"for":[51,86,94,191,196],"queries":[52,108],"Biobank":[54,133],"panels":[55],"consist":[57],"of":[58,61,66,83,127,149,171,178,181,189,212,221],"several":[59],"millions":[60],"haplotypes,":[62],"if":[63],"an":[64,162,187],"index":[65,163],"haplotypes":[68],"must":[69],"be":[70],"kept":[71],"entirely":[72],"memory.":[74],"RESULTS:":[75],"In":[76,158],"this":[77],"article,":[78],"we":[79,117],"leverage":[80],"notion":[82],"r-index":[84],"proposed":[85],"BWT":[88,195],"to":[89,119,146,152],"present":[90],"memory-efficient":[92],"method":[93],"constructing":[95],"and":[96,102,122,131,200,238],"storing":[97],"run-length":[99,193],"encoded":[100],"PBWT,":[101],"computing":[103],"set":[104,222],"(SMEMs)":[107,225],"sequences.":[111],"We":[112],"implement":[113],"our":[114],"method,":[115],"which":[116],"refer":[118],"as":[120],"\u03bc-PBWT,":[121],"evaluate":[123],"it":[124,201],"on":[125,204],"datasets":[126],"1000":[128],"Genome":[129],"Project":[130],"UK":[132],"data.":[134],"Our":[135,233],"experiments":[136],"demonstrate":[137],"\u03bc-PBWT":[140,160,185],"reduces":[141],"memory":[143,207],"usage":[144],"up":[145],"factor":[148],"20%":[150],"compared":[151],"best":[154],"current":[155],"PBWT-based":[156],"indexing.":[157],"particular,":[159],"produces":[161],"stores":[165],"high-coverage":[166],"whole":[167],"genome":[168],"sequencing":[169],"chromosome":[172],"20":[173],"about":[175],"third":[177],"space":[180],"its":[182],"BCF":[183],"file.":[184],"adaptation":[188],"techniques":[190],"compressed":[194],"(RLPBWT)":[199],"based":[203],"keeping":[205],"only":[208],"succinct":[210],"representation":[211],"RLPBWT":[214],"still":[216],"allows":[217],"efficient":[219],"computation":[220],"panel.":[229],"AVAILABILITY":[230],"AND":[231],"IMPLEMENTATION:":[232],"implementation":[234],"open":[236],"source":[237],"available":[239,245],"at":[240,246],"https://github.com/dlcgold/muPBWT.":[241],"binary":[243],"https://bioconda.github.io/recipes/mupbwt/README.html.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}
