{"id":"https://openalex.org/W2980087523","doi":"https://doi.org/10.1109/tit.2019.2946846","title":"Evolution of $k$ -Mer Frequencies and Entropy in Duplication and Substitution Mutation Systems","display_name":"Evolution of $k$ -Mer Frequencies and Entropy in Duplication and Substitution Mutation Systems","publication_year":2019,"publication_date":"2019-10-10","ids":{"openalex":"https://openalex.org/W2980087523","doi":"https://doi.org/10.1109/tit.2019.2946846","mag":"2980087523"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2019.2946846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2019.2946846","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://authors.library.caltech.edu/99095/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086990183","display_name":"Hao Lou","orcid":"https://orcid.org/0000-0002-6133-2987"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Lou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0002-6133-2987","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054043026","display_name":"Moshe Schwartz","orcid":"https://orcid.org/0000-0002-1449-0026"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Moshe Schwartz","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0002-1449-0026","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043861677","display_name":"Jehoshua Bruck","orcid":"https://orcid.org/0000-0001-8474-0812"},"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":"Jehoshua Bruck","raw_affiliation_strings":["Department of Electrical Engineering, California Institute of Technology, Pasadena, USA"],"raw_orcid":"https://orcid.org/0000-0001-8474-0812","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, California Institute of Technology, Pasadena, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011621481","display_name":"Farzad Farnoud","orcid":"https://orcid.org/0000-0002-8684-4487"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Farnoud","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0002-8684-4487","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0122,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83103488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"66","issue":"5","first_page":"3171","last_page":"3186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9979000091552734,"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":0.9976000189781189,"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/substring","display_name":"Substring","score":0.8327584862709045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49714186787605286},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.478784441947937},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.42166951298713684},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39314335584640503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.368700236082077},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.33420777320861816},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18506696820259094},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17401954531669617},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08478030562400818}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8327584862709045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49714186787605286},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.478784441947937},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.42166951298713684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39314335584640503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.368700236082077},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33420777320861816},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18506696820259094},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17401954531669617},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08478030562400818},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2019.2946846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2019.2946846","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:authors.library.caltech.edu:99095","is_oa":true,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20191004-142813980","pdf_url":"https://authors.library.caltech.edu/99095/","source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:authors.library.caltech.edu:99095","is_oa":true,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20191004-142813980","pdf_url":"https://authors.library.caltech.edu/99095/","source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2157569152","display_name":null,"funder_award_id":"CCF-1816409","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5619523096","display_name":null,"funder_award_id":"CCF-1816965","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G6023151502","display_name":null,"funder_award_id":"CCF-1717884","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G6151884190","display_name":null,"funder_award_id":"CCF-1755773","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G880093237","display_name":null,"funder_award_id":"2017652","funder_id":"https://openalex.org/F4320320950","funder_display_name":"United States-Israel Binational Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320950","display_name":"United States-Israel Binational Science Foundation","ror":"https://ror.org/00j8z2m73"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980087523.pdf","grobid_xml":"https://content.openalex.org/works/W2980087523.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W745867715","https://openalex.org/W1510807444","https://openalex.org/W1602844557","https://openalex.org/W1608334810","https://openalex.org/W1908746084","https://openalex.org/W1985556836","https://openalex.org/W2006767397","https://openalex.org/W2012120492","https://openalex.org/W2022548193","https://openalex.org/W2038090784","https://openalex.org/W2045342295","https://openalex.org/W2065247540","https://openalex.org/W2073671499","https://openalex.org/W2082173153","https://openalex.org/W2088310213","https://openalex.org/W2089649677","https://openalex.org/W2097415784","https://openalex.org/W2097749295","https://openalex.org/W2099747733","https://openalex.org/W2108278098","https://openalex.org/W2111921000","https://openalex.org/W2113855394","https://openalex.org/W2119309676","https://openalex.org/W2123445896","https://openalex.org/W2124871568","https://openalex.org/W2125598538","https://openalex.org/W2127912200","https://openalex.org/W2135123683","https://openalex.org/W2140921549","https://openalex.org/W2150890731","https://openalex.org/W2168909179","https://openalex.org/W2595770559","https://openalex.org/W2601746657","https://openalex.org/W2606176360","https://openalex.org/W2615068531","https://openalex.org/W2729138484","https://openalex.org/W2735950571","https://openalex.org/W2738842617","https://openalex.org/W2761430568","https://openalex.org/W2768089104","https://openalex.org/W2798579099","https://openalex.org/W2800700497","https://openalex.org/W2887784849","https://openalex.org/W2895634672","https://openalex.org/W2905575949","https://openalex.org/W2920631785","https://openalex.org/W2963103993","https://openalex.org/W2963624396","https://openalex.org/W2964226674","https://openalex.org/W2964233396","https://openalex.org/W2964325683","https://openalex.org/W2969418315","https://openalex.org/W2975938551","https://openalex.org/W3034779354","https://openalex.org/W3103147319","https://openalex.org/W4229487902","https://openalex.org/W4230058301","https://openalex.org/W4243772471","https://openalex.org/W4244872530","https://openalex.org/W4301621763","https://openalex.org/W6630503602","https://openalex.org/W6678795934","https://openalex.org/W6740687179","https://openalex.org/W6741483453"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W2998448420","https://openalex.org/W1974038726","https://openalex.org/W1953626159","https://openalex.org/W1598224733","https://openalex.org/W4304731099","https://openalex.org/W4280502676","https://openalex.org/W2000769876","https://openalex.org/W2120581723","https://openalex.org/W2157233202"],"abstract_inverted_index":{"Genomic":[0],"evolution":[1,104],"can":[2],"be":[3],"viewed":[4],"as":[5],"string-editing":[6],"processes":[7,21],"driven":[8],"by":[9],"mutations.":[10,76],"An":[11],"understanding":[12],"of":[13,23,28,37,50,69,75,105],"the":[14,43,48,78,90,103,124],"statistical":[15],"properties":[16],"resulting":[17],"from":[18],"these":[19,51,109],"mutation":[20],"is":[22],"value":[24],"in":[25,89],"a":[26,73,130],"variety":[27],"tasks":[29],"related":[30],"to":[31,47],"biological":[32],"sequence":[33],"data,":[34],"e.g.,":[35],"estimation":[36],"model":[38],"parameters":[39],"and":[40,57,83,88,122],"compression.":[41],"At":[42],"same":[44],"time,":[45],"due":[46],"complexity":[49],"processes,":[52],"designing":[53],"tractable":[54],"stochastic":[55,96,100],"models":[56,97],"analyzing":[58],"them":[59],"are":[60,86],"challenging.":[61],"In":[62,77],"this":[63],"paper,":[64],"we":[65,114,128],"study":[66,102],"two":[67,110],"kinds":[68],"systems,":[70],"each":[71],"representing":[72],"set":[74],"first":[79],"system,":[80],"tandem":[81],"duplications":[82],"substitution":[84],"mutations":[85],"allowed":[87],"other,":[91],"interspersed":[92],"duplications.":[93],"We":[94],"provide":[95],"and,":[98],"via":[99],"approximation,":[101],"substring":[106],"frequencies":[107,118],"for":[108,132,138],"systems":[111],"separately.":[112],"Specifically,":[113],"show":[115],"that":[116],"k-mer":[117],"converge":[119],"almost":[120],"surely":[121],"determine":[123],"limit":[125],"set.":[126],"Furthermore,":[127],"present":[129],"method":[131],"finding":[133],"upper":[134],"bounds":[135],"on":[136],"entropy":[137],"such":[139],"systems.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}