{"id":"https://openalex.org/W4362499537","doi":"https://doi.org/10.1007/978-3-031-29119-7_2","title":"Spectrum Preserving Tilings Enable Sparse and\u00a0Modular Reference Indexing","display_name":"Spectrum Preserving Tilings Enable Sparse and\u00a0Modular Reference Indexing","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362499537","doi":"https://doi.org/10.1007/978-3-031-29119-7_2"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-29119-7_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-29119-7_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-29119-7_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-29119-7_2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001911878","display_name":"Jason Fan","orcid":"https://orcid.org/0000-0001-7617-4814"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Fan","raw_affiliation_strings":["University of Maryland, College Park, MD, 20440, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, 20440, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072999292","display_name":"Jamshed Khan","orcid":"https://orcid.org/0000-0002-5129-9749"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamshed Khan","raw_affiliation_strings":["University of Maryland, College Park, MD, 20440, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, 20440, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010860687","display_name":"Giulio Ermanno Pibiri","orcid":"https://orcid.org/0000-0003-0724-7092"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Ermanno Pibiri","raw_affiliation_strings":["Ca\u2019 Foscari University of Venice, Venice, Italy","ISTI-CNR, Pisa, Italy","Ca' Foscari University of Venice, Venice, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ca\u2019 Foscari University of Venice, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]},{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Ca' Foscari University of Venice, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014584023","display_name":"Rob Patro","orcid":"https://orcid.org/0000-0001-8463-1675"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob Patro","raw_affiliation_strings":["University of Maryland, College Park, MD, 20440, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, 20440, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014584023"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":21.4975,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99568806,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T12029","display_name":"DNA and Biological Computing","score":0.9652000069618225,"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/tile","display_name":"Tile","score":0.8358708024024963},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7414351105690002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7110646367073059},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.512117862701416},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.49745824933052063},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4634895324707031},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44320785999298096},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4285036027431488},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4201236963272095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3997107446193695},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.19578665494918823},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1775623857975006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11700636148452759},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0945950448513031}],"concepts":[{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.8358708024024963},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7414351105690002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110646367073059},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.512117862701416},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.49745824933052063},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4634895324707031},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44320785999298096},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4285036027431488},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4201236963272095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3997107446193695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19578665494918823},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1775623857975006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11700636148452759},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0945950448513031},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-29119-7_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-29119-7_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-29119-7_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:iris.unive.it:10278/5023385","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5023385","pdf_url":"https://iris.unive.it/bitstream/10278/5023385/1/RECOMB2023.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dnet:people______::969c819827452448c5d34611f2166286","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::969c819827452448c5d34611f2166286","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"RECOMB 2023 - 27th International Conference on Research in Computational Molecular Biology, pp. 21\u201340, Istanbul, Turkey, 16-19/04/2023","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-29119-7_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-29119-7_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-29119-7_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2324004137","display_name":null,"funder_award_id":"R01HG009937","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3146337093","display_name":"CSR: Medium: Approximate Membership Query Data Structures in Computational Biology and Storage","funder_award_id":"1763680","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3184792579","display_name":null,"funder_award_id":"CCF-1750472","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4152515563","display_name":null,"funder_award_id":"101006879","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G6608149694","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1840340","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6624895376","display_name":null,"funder_award_id":"DGE-1840340","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6785428991","display_name":null,"funder_award_id":"CNS-1763680","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7331901853","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8858395165","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362499537.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W1559631118","https://openalex.org/W1860929530","https://openalex.org/W1867886327","https://openalex.org/W2065128082","https://openalex.org/W2323326409","https://openalex.org/W2438121987","https://openalex.org/W2592811885","https://openalex.org/W2759261668","https://openalex.org/W2789843538","https://openalex.org/W2888300707","https://openalex.org/W2952870794","https://openalex.org/W2963158913","https://openalex.org/W2964849163","https://openalex.org/W3012149649","https://openalex.org/W3112768174","https://openalex.org/W3147478436","https://openalex.org/W3150463527","https://openalex.org/W3168724350","https://openalex.org/W3178314485","https://openalex.org/W3186698701","https://openalex.org/W3200242814","https://openalex.org/W4205330988","https://openalex.org/W4225502295","https://openalex.org/W4230945265","https://openalex.org/W4280619572","https://openalex.org/W4281288662","https://openalex.org/W4281396198","https://openalex.org/W4282946044","https://openalex.org/W4295087956","https://openalex.org/W4295190277"],"related_works":["https://openalex.org/W2114959296","https://openalex.org/W38346124","https://openalex.org/W2502442966","https://openalex.org/W2138666621","https://openalex.org/W2383936314","https://openalex.org/W2777914781","https://openalex.org/W1992771654","https://openalex.org/W4246369972","https://openalex.org/W4244869112","https://openalex.org/W2019887508"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"reference":[2,14,80,115,166],"indexing":[3,116,247],"problem":[4,42,117],"for":[5,45,118,219],"$$k$$":[6,29,119,124,140,150,181,203,275],"-mers":[7,120,204,276],"is":[8,43,282],"to":[9,40,75,135,146,225,262],"pre-process":[10],"a":[11,60,69,102,123,129,214,235,268,278],"collection":[12],"of":[13,23,26,63,71,101,105,163,173,179,191,201,216,229,255],"genomic":[15],"sequences":[16,81],"$$\\mathcal":[17,64,83,206],"{R}$$":[18,65,84,207],"so":[19],"that":[20,66,178,221],"the":[21,55,78,88,97,114,149,155,170,174,180,185,189,195,199,227,230,243,253,256],"position":[22],"all":[24],"occurrences":[25],"any":[27],"queried":[28],"-mer":[30,141],"can":[31,143],"be":[32,144],"rapidly":[33],"identified.":[34],"An":[35,108],"efficient":[36],"and":[37,90,99,127,137,286],"scalable":[38],"solution":[39],"this":[41,51],"fundamental":[44],"many":[46],"tasks":[47],"in":[48,82,161,205,242,284],"bioinformatics.":[49],"In":[50],"work,":[52],"we":[53,212],"introduce":[54,213],"spectrum":[56],"preserving":[57],"tiling":[58],"(SPT),":[59],"general":[61,103],"representation":[62],"specifies":[67],"how":[68],"set":[70],"tiles":[72,93],"repeatedly":[73],"occur":[74],"spell":[76],"out":[77],"constituent":[79],".":[85,208,245,290],"By":[86],"encoding":[87],"order":[89],"positions":[91],"where":[92],"occur,":[94],"SPTs":[95,220],"enable":[96],"implementation":[98],"analysis":[100],"class":[104,215],"modular":[106],"indexes.":[107],"index":[109,139,237],"over":[110,248],"an":[111],"SPT":[112],"decomposes":[113],"into:":[121],"(1)":[122],"-mer-to-tile":[125,151,182],"mapping;":[126],"(2)":[128],"tile-to-occurrence":[130,156,175,257],"mapping.":[131,152,232],"Recently":[132],"introduced":[133],"work":[134],"construct":[136],"compactly":[138],"sets":[142],"used":[145],"efficiently":[147],"implement":[148,234],"However,":[153],"implementing":[154],"mapping":[157,176,183,258],"remains":[158],"prohibitively":[159],"costly":[160],"terms":[162],"space.":[164],"As":[165],"collections":[167],"become":[168],"large,":[169],"space":[171],"requirements":[172],"dominates":[177],"since":[184],"former":[186],"depends":[187,197],"on":[188,198],"amount":[190],"total":[192],"sequence":[193],"while":[194,265],"latter":[196],"number":[200],"unique":[202],"To":[209],"address":[210],"this,":[211],"sampling":[217,240],"schemes":[218,241],"trade":[222],"off":[223],"speed":[224],"reduce":[226],"size":[228,254],"tile-to-reference":[231],"We":[233],"practical":[236],"with":[238],"these":[239],"tool":[244],"When":[246],"30,000":[249],"bacterial":[250],"genomes,":[251],"reduces":[252],"from":[259,277],"86.3":[260],"GB":[261,264],"34.6":[263],"incurring":[266],"only":[267],"3.6":[269],"$$\\times":[270],"$$":[271],"slowdown":[272],"when":[273],"querying":[274],"sequenced":[279],"readset.":[280],"Availability:":[281],"implemented":[283],"Rust":[285],"available":[287],"at":[288],"https://github.com/COMBINE-lab/pufferfish2":[289]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-04-05T00:00:00"}
