{"id":"https://openalex.org/W3093722121","doi":"https://doi.org/10.1093/bioinformatics/btaa911","title":"Sapling: accelerating suffix array queries with learned data models","display_name":"Sapling: accelerating suffix array queries with learned data models","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3093722121","doi":"https://doi.org/10.1093/bioinformatics/btaa911","mag":"3093722121","pmid":"https://pubmed.ncbi.nlm.nih.gov/33107913"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa911","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa911","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033718626","display_name":"Melanie Kirsche","orcid":"https://orcid.org/0000-0002-6631-4761"},"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":true,"raw_author_name":"Melanie Kirsche","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA"],"raw_orcid":"https://orcid.org/0000-0002-6631-4761","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065014595","display_name":"Arun Das","orcid":"https://orcid.org/0000-0002-0332-1956"},"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":"Arun Das","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA"],"raw_orcid":"https://orcid.org/0000-0002-0332-1956","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058192453","display_name":"Michael C. Schatz","orcid":"https://orcid.org/0000-0002-4118-4446"},"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"]},{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C Schatz","raw_affiliation_strings":["Cold Spring Harbor Laboratory , Cold Spring Harbor, NY 11724, USA","Department of Biology, Johns Hopkins University , Baltimore, MD 21218, USA","Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cold Spring Harbor Laboratory , Cold Spring Harbor, NY 11724, USA","institution_ids":["https://openalex.org/I2750212522"]},{"raw_affiliation_string":"Department of Biology, Johns Hopkins University , Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University , Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033718626"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.6946,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87856571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"6","first_page":"744","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.4731000065803528,"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":0.4731000065803528,"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":0.3813000023365021,"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":0.023000000044703484,"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/computer-science","display_name":"Computer science","score":0.8559145927429199},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.8034570813179016},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.676691472530365},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6215341687202454},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5318552851676941},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.48555800318717957},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4538574814796448},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.4415389597415924},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.42456015944480896},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4186331033706665},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.37579619884490967},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3685472905635834},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34925222396850586},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2373533546924591},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12922745943069458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559145927429199},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.8034570813179016},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.676691472530365},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6215341687202454},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5318552851676941},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.48555800318717957},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4538574814796448},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4415389597415924},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.42456015944480896},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4186331033706665},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.37579619884490967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3685472905635834},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34925222396850586},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2373533546924591},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12922745943069458},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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}],"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa911","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa911","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:33107913","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33107913","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:repository.cshl.edu:40188","is_oa":false,"landing_page_url":"https://repository.cshl.edu/id/eprint/40188/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3855658619","display_name":null,"funder_award_id":"DBI-1350041","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G391706536","display_name":null,"funder_award_id":"IOS-1445025","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7457279682","display_name":null,"funder_award_id":"IOS-1732253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8005149852","display_name":null,"funder_award_id":"IOS-1758800","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1532280479","https://openalex.org/W1972418517","https://openalex.org/W1981509058","https://openalex.org/W1987426253","https://openalex.org/W2055043387","https://openalex.org/W2066852475","https://openalex.org/W2095680943","https://openalex.org/W2103496339","https://openalex.org/W2105805010","https://openalex.org/W2108234281","https://openalex.org/W2114820744","https://openalex.org/W2124985265","https://openalex.org/W2131016694","https://openalex.org/W2137759177","https://openalex.org/W2143531254","https://openalex.org/W2158874082","https://openalex.org/W2169456326","https://openalex.org/W2170551349","https://openalex.org/W2171111703","https://openalex.org/W2767286248","https://openalex.org/W2773466258","https://openalex.org/W2784788330","https://openalex.org/W2950121474","https://openalex.org/W2962771342","https://openalex.org/W2979515141","https://openalex.org/W2990138404","https://openalex.org/W4320930577","https://openalex.org/W4394666350","https://openalex.org/W6674561012","https://openalex.org/W6746023985","https://openalex.org/W6746567838","https://openalex.org/W6769194802"],"related_works":["https://openalex.org/W2063841356","https://openalex.org/W2003608043","https://openalex.org/W2067974452","https://openalex.org/W2405149725","https://openalex.org/W2118703123","https://openalex.org/W4385595111","https://openalex.org/W153119118","https://openalex.org/W4292461527","https://openalex.org/W1527782099","https://openalex.org/W2014650117"],"abstract_inverted_index":{"MOTIVATION:":[0],"As":[1],"genomic":[2],"data":[3,10,25,67,83,171],"becomes":[4],"more":[5,140],"abundant,":[6],"efficient":[7],"algorithms":[8],"and":[9,74,118,133,161],"structures":[11],"for":[12,60],"sequence":[13,61],"alignment":[14],"become":[15],"increasingly":[16],"important.":[17],"The":[18,158],"suffix":[19,72,151],"array":[20,73],"is":[21],"a":[22,44,65,101,125,142],"widely":[23,120],"used":[24,35,121],"structure":[26],"to":[27,36,69,149],"accelerate":[28],"alignment,":[29,62],"but":[30],"the":[31,71,137,150],"binary":[32,115],"search":[33,116],"algorithm":[34,59,138],"query,":[37],"it":[38],"requires":[39],"widespread":[40],"memory":[41,153],"accesses,":[42],"causing":[43],"large":[45,51],"number":[46],"of":[47,82,88,128,144],"cache":[48],"misses":[49],"on":[50,124],"datasets.":[52],"RESULTS:":[53],"Here,":[54],"we":[55],"present":[56],"Sapling,":[57],"an":[58,86,97,113],"which":[63],"uses":[64],"learned":[66],"model":[68],"augment":[70],"enable":[75],"faster":[76],"queries.":[77],"We":[78,107],"investigate":[79],"different":[80,89],"types":[81],"models,":[84],"providing":[85,96],"analysis":[87],"neural":[90],"network":[91],"models":[92],"as":[93,95],"well":[94],"open-source":[98,165],"aligner":[99],"with":[100],"compact,":[102],"practical":[103],"piecewise":[104],"linear":[105],"model.":[106],"show":[108],"that":[109],"Sapling":[110],"outperforms":[111],"both":[112],"optimized":[114],"approach":[117],"multiple":[119],"read":[122],"aligners":[123],"diverse":[126],"collection":[127],"genomes,":[129],"including":[130],"human,":[131],"bacteria":[132],"plants,":[134],"speeding":[135],"up":[136],"by":[139],"than":[141],"factor":[143],"two":[145],"while":[146],"adding":[147],"<1%":[148],"array's":[152],"footprint.":[154],"AVAILABILITY":[155],"AND":[156],"IMPLEMENTATION:":[157],"source":[159],"code":[160],"tutorial":[162],"are":[163,172],"available":[164,173],"at":[166,174],"https://github.com/mkirsche/sapling.":[167],"SUPPLEMENTARY":[168],"INFORMATION:":[169],"Supplementary":[170],"Bioinformatics":[175],"online.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}
