{"id":"https://openalex.org/W2160962794","doi":"https://doi.org/10.1145/1654059.1654122","title":"Indexing genomic sequences on the IBM Blue Gene","display_name":"Indexing genomic sequences on the IBM Blue Gene","publication_year":2009,"publication_date":"2009-11-14","ids":{"openalex":"https://openalex.org/W2160962794","doi":"https://doi.org/10.1145/1654059.1654122","mag":"2160962794"},"language":"en","primary_location":{"id":"doi:10.1145/1654059.1654122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","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/A5043552468","display_name":"Amol Ghoting","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amol Ghoting","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033681881","display_name":"Konstantin Makarychev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantin Makarychev","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043552468"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":4.0546,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94174937,"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":"1","last_page":"11"},"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":0.992900013923645,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9724000096321106,"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":0.788536548614502},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.7381727695465088},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6805741190910339},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6260361671447754},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6060622930526733},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.5748006105422974},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5452578067779541},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5231248736381531},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4959164559841156},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.4795638918876648},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.45724985003471375},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4371374845504761},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.2536211907863617},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2076314389705658},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1309458613395691},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12618854641914368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788536548614502},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.7381727695465088},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6805741190910339},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6260361671447754},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6060622930526733},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.5748006105422974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5452578067779541},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5231248736381531},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4959164559841156},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4795638918876648},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.45724985003471375},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4371374845504761},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2536211907863617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2076314389705658},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1309458613395691},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12618854641914368},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1654059.1654122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.862.4538","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.862.4538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.fit.edu/%7Edmitra/Compbio/Resources/ParllSufxTree-a61-ghoting.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W68532121","https://openalex.org/W1540616176","https://openalex.org/W1571053466","https://openalex.org/W1578828659","https://openalex.org/W1807007002","https://openalex.org/W1966318226","https://openalex.org/W1967382114","https://openalex.org/W1974956214","https://openalex.org/W1990061958","https://openalex.org/W2003200876","https://openalex.org/W2055417893","https://openalex.org/W2086022864","https://openalex.org/W2089545095","https://openalex.org/W2095685450","https://openalex.org/W2106013076","https://openalex.org/W2107282968","https://openalex.org/W2108235229","https://openalex.org/W2110291136","https://openalex.org/W2121252285","https://openalex.org/W2124281279","https://openalex.org/W2124348703","https://openalex.org/W2133363953","https://openalex.org/W2137023570","https://openalex.org/W2142473132","https://openalex.org/W2152331922","https://openalex.org/W2533248932","https://openalex.org/W2915063781","https://openalex.org/W4233960312","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2032737507","https://openalex.org/W2082932857","https://openalex.org/W2355763156","https://openalex.org/W3157818565","https://openalex.org/W4293872904","https://openalex.org/W1786707430","https://openalex.org/W2067956663","https://openalex.org/W2939624094","https://openalex.org/W4300504307","https://openalex.org/W2317728333"],"abstract_inverted_index":{"With":[0],"advances":[1],"in":[2,60,140],"sequencing":[3,8],"technology":[4],"and":[5,39],"through":[6,103],"aggressive":[7],"efforts,":[9],"DNA":[10],"sequence":[11,42],"data":[12,43,58,63,71],"sets":[13,72],"have":[14,73],"been":[15,74],"growing":[16],"at":[17],"a":[18,56],"rapid":[19],"pace.":[20],"To":[21],"gain":[22],"from":[23],"these":[24],"advances,":[25],"it":[26],"is":[27,81],"important":[28],"to":[29,37,85,116,118],"provide":[30],"life":[31],"science":[32],"researchers":[33],"with":[34],"the":[35,46,50,123,130],"ability":[36],"process":[38],"query":[40],"large":[41,70],"sets.":[44,64],"For":[45],"past":[47],"three":[48],"decades,":[49],"suffix":[51,78],"tree":[52,66,79,114],"has":[53,93],"served":[54],"as":[55],"fundamental":[57],"structure":[59],"processing":[61],"sequential":[62],"However,":[65],"construction":[67,80,115],"times":[68],"on":[69,137],"excessive.":[75],"While":[76],"parallel":[77,95,105,120],"an":[82],"obvious":[83],"solution":[84],"reduce":[86],"execution":[87],"times,":[88],"poor":[89],"locality":[90],"of":[91],"reference":[92],"limited":[94],"performance.":[96],"In":[97],"this":[98,108],"paper,":[99],"we":[100],"show":[101],"that":[102,129],"careful":[104],"algorithm":[106],"design,":[107],"limitation":[109],"can":[110,134],"be":[111,135],"removed,":[112],"allowing":[113],"scale":[117],"massively":[119],"systems":[121],"like":[122],"IBM":[124],"Blue":[125],"Gene.":[126],"We":[127],"demonstrate":[128],"entire":[131],"Human":[132],"genome":[133],"indexed":[136],"1024":[138],"processors":[139],"under":[141],"15":[142],"minutes.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":19},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}