{"id":"https://openalex.org/W2969627863","doi":"https://doi.org/10.1093/bioinformatics/btz662","title":"Improved representation of sequence bloom trees","display_name":"Improved representation of sequence bloom trees","publication_year":2019,"publication_date":"2019-08-20","ids":{"openalex":"https://openalex.org/W2969627863","doi":"https://doi.org/10.1093/bioinformatics/btz662","mag":"2969627863","pmid":"https://pubmed.ncbi.nlm.nih.gov/31504157"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz662","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz662","pdf_url":null,"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":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8215923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074817739","display_name":"Robert S. Harris","orcid":"https://orcid.org/0000-0001-5464-6892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert S Harris","raw_affiliation_strings":["Department of Biology , PA 16801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology , PA 16801, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Center for Computational Biology and Bioinformatics, The Pennsylvania State University , University Park, PA 16801, USA","Department of Biochemistry and Molecular Biology , PA 16801, USA","Department of Computer Science and Engineering , PA 16801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology and Bioinformatics, The Pennsylvania State University , University Park, PA 16801, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology , PA 16801, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering , PA 16801, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066909672"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.4337,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.90184664,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"36","issue":"3","first_page":"721","last_page":"727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7943999767303467,"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":0.7943999767303467,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.04439999908208847,"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":0.0210999995470047,"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":0.8395348191261292},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7910418510437012},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7049387097358704},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6599432229995728},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.6574018001556396},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6066299676895142},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5523463487625122},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5481647253036499},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.543921947479248},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44007304310798645},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4254707098007202},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36848515272140503},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3550611138343811},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19243353605270386},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1899857223033905},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11347594857215881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08838069438934326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395348191261292},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7910418510437012},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7049387097358704},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6599432229995728},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.6574018001556396},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6066299676895142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5523463487625122},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5481647253036499},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.543921947479248},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44007304310798645},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4254707098007202},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36848515272140503},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3550611138343811},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19243353605270386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1899857223033905},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11347594857215881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08838069438934326},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":"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":"D014197","descriptor_name":"Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014197","descriptor_name":"Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014197","descriptor_name":"Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","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},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz662","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz662","pdf_url":null,"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:31504157","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31504157","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:pubmedcentral.nih.gov:8215923","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8215923","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8215923","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8215923","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1106789989","display_name":"Y Chromosome Evolution","funder_award_id":"5r01gm130691-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1433495602","display_name":null,"funder_award_id":"R01 GM130691","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W616987689","https://openalex.org/W938539187","https://openalex.org/W1974033543","https://openalex.org/W1990061958","https://openalex.org/W2005228765","https://openalex.org/W2096128575","https://openalex.org/W2123845384","https://openalex.org/W2142678478","https://openalex.org/W2266239166","https://openalex.org/W2406547600","https://openalex.org/W2560209686","https://openalex.org/W2788348538","https://openalex.org/W2795650864","https://openalex.org/W2809649683","https://openalex.org/W2884435343","https://openalex.org/W2951157731","https://openalex.org/W2952379095","https://openalex.org/W3011785159","https://openalex.org/W3085875665","https://openalex.org/W3103672149"],"related_works":["https://openalex.org/W2081869611","https://openalex.org/W2150999591","https://openalex.org/W2011343125","https://openalex.org/W1564712904","https://openalex.org/W2113436622","https://openalex.org/W2623698249","https://openalex.org/W2099972273","https://openalex.org/W2156338408","https://openalex.org/W2086458297","https://openalex.org/W2069074882"],"abstract_inverted_index":{"MOTIVATION:":[0],"Algorithmic":[1],"solutions":[2],"to":[3,18,58,75,88,104,160],"index":[4,60,116],"and":[5,50,92,124,129,150,154],"search":[6],"biological":[7],"databases":[8,30],"are":[9,182],"a":[10,56,83,142,171],"fundamental":[11],"part":[12],"of":[13,40,86,100,121,157],"bioinformatics,":[14],"providing":[15],"underlying":[16],"components":[17],"many":[19],"end-user":[20],"tools.":[21],"Inexpensive":[22],"next":[23],"generation":[24],"sequencing":[25],"has":[26],"filled":[27],"publicly":[28],"available":[29,169,183],"such":[31,61],"as":[32,55,95,97,170],"the":[33,38,45,72,77,90,98,101,115,122,152],"Sequence":[34,46],"Read":[35],"Archive":[36],"beyond":[37],"capacity":[39],"traditional":[41],"indexing":[42],"methods.":[43,163],"Recently,":[44],"Bloom":[47],"Tree":[48],"(SBT)":[49],"its":[51],"derivatives":[52],"were":[53],"proposed":[54],"way":[57],"efficiently":[59],"data":[62,79,181],"for":[63],"queries":[64,133],"about":[65],"transcript":[66],"presence.":[67],"RESULTS:":[68],"We":[69,139],"build":[70],"on":[71,108,176],"SBT":[73,106,162],"framework":[74,144],"construct":[76,114],"HowDe-SBT":[78,112,158,167],"structure,":[80],"which":[81,146],"uses":[82],"novel":[84],"partitioning":[85],"information":[87],"reduce":[89],"construction":[91],"query":[93,155],"time":[94,123],"well":[96],"size":[99],"index.":[102],"Compared":[103],"previous":[105],"methods,":[107],"real":[109],"RNA-seq":[110],"data,":[111],"can":[113,130,148],"in":[117,145],"less":[118,127],"than":[119],"36%":[120],"with":[125],"39%":[126],"space":[128,153],"answer":[131],"small-batch":[132],"at":[134,184],"least":[135],"five":[136],"times":[137],"faster.":[138],"also":[140],"develop":[141],"theoretical":[143],"we":[147],"analyze":[149],"bound":[151],"performance":[156],"compared":[159],"other":[161],"AVAILABILITY":[164],"AND":[165],"IMPLEMENTATION:":[166],"is":[168],"free":[172],"open":[173],"source":[174],"program":[175],"https://github.com/medvedevgroup/HowDeSBT.":[177],"SUPPLEMENTARY":[178],"INFORMATION:":[179],"Supplementary":[180],"Bioinformatics":[185],"online.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
