{"id":"https://openalex.org/W1994283178","doi":"https://doi.org/10.1109/bibm.2013.6732763","title":"Mining repetitive sequences using a big data ecosystem","display_name":"Mining repetitive sequences using a big data ecosystem","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1994283178","doi":"https://doi.org/10.1109/bibm.2013.6732763","mag":"1994283178"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2013.6732763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2013.6732763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113781818","display_name":"Michael Phinney","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Phinney","raw_affiliation_strings":["Department of Computer Science","[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108505505","display_name":"Hongfei Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfei Cao","raw_affiliation_strings":["Department of Computer Science","[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070316351","display_name":"Andi Dhroso","orcid":"https://orcid.org/0000-0002-6117-0607"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andi Dhroso","raw_affiliation_strings":["Informatics Institute, University of Missouri, Columbia, MO","[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Missouri, Columbia, MO","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013031415","display_name":"Chi\u2010Ren Shyu","orcid":"https://orcid.org/0000-0001-9197-9522"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chi-Ren Shyu","raw_affiliation_strings":["Informatics Institute, University of Missouri, Columbia, MO","[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Missouri, Columbia, MO","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Univ. of Missouri, Columbia, MO, USA]","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.994700014591217,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9940000176429749,"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/genome","display_name":"Genome","score":0.6289539337158203},{"id":"https://openalex.org/keywords/repeated-sequence","display_name":"Repeated sequence","score":0.5691781044006348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5341668725013733},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4884883165359497},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.46894073486328125},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4220290780067444},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4001144468784332},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34420573711395264},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3242214024066925},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2318808138370514},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.22945278882980347},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.20207223296165466}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6289539337158203},{"id":"https://openalex.org/C169802333","wikidata":"https://www.wikidata.org/wiki/Q424473","display_name":"Repeated sequence","level":4,"score":0.5691781044006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5341668725013733},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4884883165359497},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.46894073486328125},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4220290780067444},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4001144468784332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34420573711395264},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3242214024066925},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2318808138370514},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.22945278882980347},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.20207223296165466}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2013.6732763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2013.6732763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306106","display_name":"U.S. Department of Education","ror":"https://ror.org/021adze67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1971846931","https://openalex.org/W1981374009","https://openalex.org/W2100990361","https://openalex.org/W2119565742","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W4212854344","https://openalex.org/W2100295916","https://openalex.org/W2134426176","https://openalex.org/W1999474062","https://openalex.org/W2067334107","https://openalex.org/W1971316784","https://openalex.org/W2306224954","https://openalex.org/W2009299986","https://openalex.org/W1974297084"],"abstract_inverted_index":{"Identifying":[0],"repetitive":[1,64,104,152],"gene":[2],"sequences":[3,7,32,65,105,145,170],"occurring":[4],"within":[5,30],"DNA":[6],"that":[8,17,27,96,142,177],"span":[9],"a":[10,15,50,115],"collection":[11],"of":[12,38,40,78,85,111,118,162],"species":[13],"is":[14,18,49,66,97],"challenge":[16,52],"conceptually":[19],"simple":[20],"yet":[21],"computationally":[22],"challenging.":[23],"Biological":[24],"research":[25],"suggests":[26],"certain":[28],"regions":[29,48],"genomic":[31,144],"may":[33],"be":[34,131],"unchanged":[35],"for":[36,89],"hundreds":[37],"millions":[39],"years;":[41],"understanding":[42,71],"and":[43,74,171],"identifying":[44],"these":[45,63],"highly":[46],"preserved":[47],"major":[51],"faced":[53],"by":[54],"bioinformaticians.":[55],"Taking":[56],"an":[57,140],"evolutionary":[58],"perspective":[59],"on":[60],"DNA,":[61],"pinpointing":[62],"the":[67,83,86,108,160,168],"first":[68],"step":[69],"to":[70,102,120],"functional":[72],"similarities":[73],"diversities.":[75],"The":[76],"difficulty":[77],"this":[79],"problem":[80],"arises":[81],"from":[82],"volume":[84],"data":[87],"required":[88],"analysis;":[90],"it":[91],"grows":[92],"with":[93,175],"every":[94],"genome":[95],"sequenced.":[98],"Traditional":[99],"approaches":[100],"used":[101],"identify":[103],"often":[106],"require":[107],"pair-wise":[109,136],"comparison":[110],"chromosomes,":[112,126],"which":[113,154],"takes":[114],"significant":[116],"amount":[117],"time":[119],"gather":[121],"results.":[122],"When":[123],"comparing":[124],"n":[125],"n(n-l)":[127],"individual":[128],"comparisons":[129],"must":[130],"made.":[132],"To":[133],"avoid":[134],"exhaustive":[135],"comparisons,":[137],"we":[138,165],"designed":[139],"algorithm":[141],"partitions":[143],"into":[146,157],"search":[147],"key":[148],"values":[149],"representing":[150],"potential":[151],"sequences,":[153],"are":[155],"hashed":[156],"bins.":[158],"With":[159],"introduction":[161],"new":[163,169,173],"genomes,":[164],"only":[166],"process":[167],"aggregate":[172],"results":[174],"those":[176],"were":[178],"previously":[179],"processed.":[180]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
