{"id":"https://openalex.org/W2155603715","doi":"https://doi.org/10.1109/isit.2015.7282795","title":"Capacity and expressiveness of genomic tandem duplication","display_name":"Capacity and expressiveness of genomic tandem duplication","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2155603715","doi":"https://doi.org/10.1109/isit.2015.7282795","mag":"2155603715"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2015.7282795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2015.7282795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1509.06029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Siddharth Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Siddharth Jain","raw_affiliation_strings":["Electrical Engineering, California Institute of Technology, Pasadena, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, California Institute of Technology, Pasadena, CA, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Farzad Farnoud","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Farnoud","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, US"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, US","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jehoshua Bruck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jehoshua Bruck","raw_affiliation_strings":["Electrical Engineering, California Institute of Technology, Pasadena, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, California Institute of Technology, Pasadena, CA, U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3556,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80823624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"1946","last_page":"1950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10521","display_name":"RNA and protein synthesis mechanisms","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":0.9994000196456909,"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":0.9988999962806702,"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/gene-duplication","display_name":"Gene duplication","score":0.8148000240325928},{"id":"https://openalex.org/keywords/tandem-exon-duplication","display_name":"Tandem exon duplication","score":0.808899998664856},{"id":"https://openalex.org/keywords/tandem-repeat","display_name":"Tandem repeat","score":0.7278000116348267},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.6158999800682068},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5532000064849854},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5157999992370605},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.48539999127388},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.43369999527931213}],"concepts":[{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.8148000240325928},{"id":"https://openalex.org/C156446351","wikidata":"https://www.wikidata.org/wiki/Q7682435","display_name":"Tandem exon duplication","level":4,"score":0.808899998664856},{"id":"https://openalex.org/C27149982","wikidata":"https://www.wikidata.org/wiki/Q3456514","display_name":"Tandem repeat","level":4,"score":0.7278000116348267},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5157999992370605},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.48669999837875366},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C57808653","wikidata":"https://www.wikidata.org/wiki/Q7446270","display_name":"Segmental duplication","level":5,"score":0.42250001430511475},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4138999879360199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37450000643730164},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C22322919","wikidata":"https://www.wikidata.org/wiki/Q5533501","display_name":"Genomic organization","level":4,"score":0.2786000072956085},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2712000012397766},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.26930001378059387},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C32795469","wikidata":"https://www.wikidata.org/wiki/Q5156430","display_name":"Complementary sequences","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit.2015.7282795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2015.7282795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1509.06029","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.06029","pdf_url":"https://arxiv.org/pdf/1509.06029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1509.06029","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.06029","pdf_url":"https://arxiv.org/pdf/1509.06029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1986404017","https://openalex.org/W2012120492","https://openalex.org/W2068060515","https://openalex.org/W2080892263","https://openalex.org/W2111921000","https://openalex.org/W2168909179","https://openalex.org/W6603325312","https://openalex.org/W6629955121","https://openalex.org/W6764633838"],"related_works":[],"abstract_inverted_index":{"The":[0,188],"majority":[1],"of":[2,7,13,50,60,65,78,106,122,125,133,143,181,190,253],"the":[3,17,34,58,73,104,115,120,123,131,141,173,182,185,194,198,246],"human":[4,18],"genome":[5,19],"consists":[6],"repeated":[8],"sequences.":[9],"An":[10],"important":[11],"type":[12],"repeats":[14,226],"common":[15],"in":[16,33,109,248],"are":[20],"tandem":[21,40,48,76,89,127,144,225],"repeats,":[22],"where":[23],"identical":[24],"copies":[25],"appear":[26],"next":[27],"to":[28,206],"each":[29],"other.":[30],"For":[31],"example,":[32],"sequence":[35],"AGTCTGTGC,":[36],"TGTG":[37],"is":[38,162,175,202,204],"a":[39,47,62,68,126,156,241,250],"repeat,":[41],"namely,":[42],"generated":[43],"from":[44,67,213],"AGTCTGC":[45],"by":[46,75,103,210],"duplication":[49,90,128,145,152,186,238],"length":[51,221],"2.":[52],"In":[53,100],"this":[54,191],"work,":[55],"we":[56,118,164],"investigate":[57],"possibility":[59],"generating":[61,249],"large":[63,251],"number":[64,252],"sequences":[66,108,222,254],"small":[69],"initial":[70],"string":[71,91],"(called":[72],"seed)":[74],"duplications":[77],"bounded":[79],"length.":[80],"Our":[81],"results":[82,235],"include":[83],"exact":[84],"capacity":[85,159,174,195],"values":[86],"for":[87,147,167,228,255],"certain":[88],"systems":[92,146],"with":[93,158,223],"alphabet":[94,149,169,200,229],"sizes":[95,150],"2;":[96],"3;":[97],"and":[98,114,151,184],"4.":[99],"addition,":[101],"motivated":[102],"role":[105,244],"DNA":[107],"expressing":[110,134],"proteins":[111],"via":[112],"RNA":[113],"genetic":[116],"code,":[117],"define":[119],"notion":[121],"expressiveness":[124,142],"system,":[129],"as":[130],"feasibility":[132],"arbitrary":[135,220],"substrings.":[136],"We":[137],"then":[138],"completely":[139],"characterize":[140],"general":[148],"lengths.":[153,187],"Noticing":[154],"that":[155,166,197,217,237],"system":[157],"=":[160],"1":[161],"expressive,":[163],"prove":[165],"an":[168,207],"size":[170,201,230],"\u2265":[171,231],"4,":[172],"strictly":[176],"smaller":[177],"than":[178,245],"1,":[179],"independent":[180],"seed":[183,247],"proof":[189],"limit":[192],"on":[193],"(note":[196],"genomic":[199],"4),":[203],"related":[205],"interesting":[208],"result":[209],"Axel":[211],"Thue":[212],"1906":[214],"which":[215],"states":[216],"there":[218],"exist":[219],"no":[224],"(square-free)":[227],"3.":[232],"Finally,":[233],"our":[234],"illustrate":[236],"lengths":[239],"play":[240],"more":[242],"significant":[243],"these":[256],"systems.":[257]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}
