{"id":"https://openalex.org/W1974956214","doi":"https://doi.org/10.1145/1247480.1247572","title":"Genome-scale disk-based suffix tree indexing","display_name":"Genome-scale disk-based suffix tree indexing","publication_year":2007,"publication_date":"2007-06-11","ids":{"openalex":"https://openalex.org/W1974956214","doi":"https://doi.org/10.1145/1247480.1247572","mag":"1974956214"},"language":"en","primary_location":{"id":"doi:10.1145/1247480.1247572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5110168251","display_name":"Benjarath Phoophakdee","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjarath Phoophakdee","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019559411","display_name":"Mohammed J. Zaki","orcid":"https://orcid.org/0000-0003-4711-0234"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed J. Zaki","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110168251"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":11.7336,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.98397953,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958999752998352,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.970300018787384,"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/suffix-tree","display_name":"Suffix tree","score":0.930978536605835},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.8804638385772705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74357008934021},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.7376746535301208},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6741372346878052},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5839120745658875},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5681544542312622},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5242391228675842},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4287453293800354},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4256584048271179},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.42457857728004456},{"id":"https://openalex.org/keywords/trellis","display_name":"Trellis (graph)","score":0.42325687408447266},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42093080282211304},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.41051626205444336},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40642455220222473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3620772957801819},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.32758450508117676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19812750816345215},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1853944957256317},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07204526662826538},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07009151577949524}],"concepts":[{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.930978536605835},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.8804638385772705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74357008934021},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.7376746535301208},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6741372346878052},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5839120745658875},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5681544542312622},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5242391228675842},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4287453293800354},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4256584048271179},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.42457857728004456},{"id":"https://openalex.org/C2781235587","wikidata":"https://www.wikidata.org/wiki/Q7838009","display_name":"Trellis (graph)","level":3,"score":0.42325687408447266},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42093080282211304},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.41051626205444336},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40642455220222473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3620772957801819},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.32758450508117676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19812750816345215},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1853944957256317},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07204526662826538},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07009151577949524},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1247480.1247572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W68532121","https://openalex.org/W245282742","https://openalex.org/W1490578079","https://openalex.org/W1504417041","https://openalex.org/W1540616176","https://openalex.org/W1548907175","https://openalex.org/W1578828659","https://openalex.org/W1603524899","https://openalex.org/W1726445723","https://openalex.org/W1807007002","https://openalex.org/W1967382114","https://openalex.org/W1986324942","https://openalex.org/W2024147613","https://openalex.org/W2055417893","https://openalex.org/W2059513841","https://openalex.org/W2077333702","https://openalex.org/W2087721273","https://openalex.org/W2095685450","https://openalex.org/W2107079154","https://openalex.org/W2107248520","https://openalex.org/W2108706843","https://openalex.org/W2110291136","https://openalex.org/W2121252285","https://openalex.org/W2124348703","https://openalex.org/W2131585788","https://openalex.org/W2133363953","https://openalex.org/W2134616089","https://openalex.org/W2137023570","https://openalex.org/W2142473132","https://openalex.org/W2153527568","https://openalex.org/W2159942118","https://openalex.org/W2533248932","https://openalex.org/W2610179052","https://openalex.org/W4236563753","https://openalex.org/W4240302460","https://openalex.org/W6602746130","https://openalex.org/W6665485777"],"related_works":["https://openalex.org/W2063841356","https://openalex.org/W2405149725","https://openalex.org/W2003608043","https://openalex.org/W2118703123","https://openalex.org/W1527782099","https://openalex.org/W2067974452","https://openalex.org/W4385595111","https://openalex.org/W2124348703","https://openalex.org/W2114699799","https://openalex.org/W1807007002"],"abstract_inverted_index":{"With":[0],"the":[1,45,124,163],"exponential":[2],"growth":[3],"of":[4,84,130,170],"biological":[5],"sequence":[6],"databases,":[7],"it":[8,121],"has":[9],"become":[10],"critical":[11],"to":[12,29,75,79,117,149,161],"develop":[13],"effective":[14],"techniques":[15],"for":[16],"storing,":[17],"querying,":[18],"and":[19,34,42,82,103,136,158,173],"analyzing":[20],"these":[21],"massive":[22],"data.":[23],"Suffix":[24],"trees":[25],"are":[26,88],"widely":[27],"used":[28],"solve":[30],"many":[31],"sequence-based":[32],"problems,":[33],"they":[35,67],"can":[36,122,137],"be":[37],"built":[38],"in":[39,49,63,90,132,168],"linear":[40],"time":[41,172],"space,":[43],"provided":[44],"resulting":[46],"tree":[47,58,93,109,155],"fits":[48],"main-memory.":[50],"To":[51],"index":[52,123],"larger":[53],"sequences,":[54,81],"several":[55,70],"external":[56],"suffix":[57,85,92,108,141,154],"algorithms":[59],"have":[60],"been":[61],"proposed":[62],"recent":[64],"years.":[65],"However,":[66],"suffer":[68],"from":[69],"problems":[71],"such":[72],"as":[73],"susceptibility":[74],"data":[76],"skew,":[77],"non-scalability":[78],"genome-scale":[80,118],"non-existence":[83],"links,":[86],"which":[87,113],"crucial":[89],"various":[91,150],"based":[94],"algorithms.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"target":[100],"DNA":[101],"sequences":[102],"propose":[104],"a":[105],"novel":[106],"disk-based":[107,153],"algorithm":[110],"called":[111],"TRELLIS,":[112],"effectively":[114],"scales":[115],"up":[116],"sequences.":[119],"Specifically,":[120],"entire":[125],"human":[126],"genome":[127],"using":[128],"2GB":[129],"memory,":[131],"about":[133],"4":[134],"hours":[135],"recover":[138],"all":[139],"its":[140],"links":[142],"within":[143],"2":[144],"hours.":[145],"TRELLIS":[146],"was":[147,159],"compared":[148],"state-of-the-art":[151],"persistent":[152],"construction":[156],"algorithms,":[157],"shown":[160],"outperform":[162],"best":[164],"previous":[165],"methods,":[166],"both":[167],"terms":[169],"indexing":[171],"querying":[174],"time.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}