{"id":"https://openalex.org/W2121622293","doi":"https://doi.org/10.1109/csb.2003.1227402","title":"An optimal DNA segmentation based on the MDL principle","display_name":"An optimal DNA segmentation based on the MDL principle","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2121622293","doi":"https://doi.org/10.1109/csb.2003.1227402","mag":"2121622293"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","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/A5019536160","display_name":"Wojciech Szpankowski","orcid":"https://orcid.org/0000-0001-9062-0067"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"W. Szpankowski","raw_affiliation_strings":["Department of Computer Science, Purdue University, West Lafayette, IN, USA","Department of Computer Science, Purdue University, West Lafayette IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021646021","display_name":"Weihan Ren","orcid":"https://orcid.org/0009-0000-0868-5305"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Ren","raw_affiliation_strings":["Department of Computer Science, Purdue University, West Lafayette, IN, USA","Department of Computer Science, Purdue University, West Lafayette IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036726954","display_name":"Lukasz Szpankowski","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Szpankowski","raw_affiliation_strings":["Cell and Molecular Biology, University of Michigan, Ann Arbor, MI, USA","(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"Cell and Molecular Biology, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019536160"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.2339,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.53842543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"46","issue":null,"first_page":"541","last_page":"546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9997000098228455,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9997000098228455,"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":0.9980000257492065,"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":0.9976999759674072,"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/minimum-description-length","display_name":"Minimum description length","score":0.7347898483276367},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.487676739692688},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4701789915561676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46145734190940857},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4544551372528076},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.43170350790023804},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.42880022525787354},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.4175780713558197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38267165422439575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33759671449661255},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22392553091049194},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1101166307926178}],"concepts":[{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.7347898483276367},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.487676739692688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4701789915561676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46145734190940857},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4544551372528076},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.43170350790023804},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.42880022525787354},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.4175780713558197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38267165422439575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33759671449661255},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22392553091049194},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1101166307926178},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2003.1227402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W45319280","https://openalex.org/W1490430289","https://openalex.org/W1493951357","https://openalex.org/W1498183065","https://openalex.org/W1586348459","https://openalex.org/W1597723816","https://openalex.org/W1966673552","https://openalex.org/W1969434257","https://openalex.org/W1970751158","https://openalex.org/W1971912858","https://openalex.org/W1981155179","https://openalex.org/W1985134211","https://openalex.org/W2033387638","https://openalex.org/W2038180954","https://openalex.org/W2062827192","https://openalex.org/W2072603366","https://openalex.org/W2075316203","https://openalex.org/W2090388864","https://openalex.org/W2096473018","https://openalex.org/W2099111195","https://openalex.org/W2102179694","https://openalex.org/W2109973210","https://openalex.org/W2116813167","https://openalex.org/W2155832272","https://openalex.org/W2167872870","https://openalex.org/W2500470525","https://openalex.org/W3016218058","https://openalex.org/W3214380909","https://openalex.org/W4244834924","https://openalex.org/W4245668478","https://openalex.org/W6629670641","https://openalex.org/W6733245234"],"related_works":["https://openalex.org/W4298831272","https://openalex.org/W2962916388","https://openalex.org/W2086694237","https://openalex.org/W2095614499","https://openalex.org/W3006682748","https://openalex.org/W2489956408","https://openalex.org/W349256592","https://openalex.org/W4213307346","https://openalex.org/W2037989911","https://openalex.org/W1903687474"],"abstract_inverted_index":{"The":[0,13],"biological":[1,29],"world":[2],"is":[3,33],"highly":[4],"stochastic":[5],"as":[6,8,24,125,127],"well":[7,126],"inhomogeneous":[9,18],"in":[10],"its":[11],"behavior.":[12],"transition":[14],"between":[15,120],"homogeneous":[16],"and":[17,73,108,111,113,122],"regions":[19,124],"of":[20,38,45,91,130],"DNA,":[21],"known":[22],"also":[23],"change":[25,118],"points,":[26],"carry":[27],"important":[28],"information.":[30],"Our":[31],"goal":[32],"to":[34,41,55,88],"employ":[35],"rigorous":[36],"methods":[37],"information":[39],"theory":[40],"quantify":[42],"structural":[43],"properties":[44],"DNA":[46,65],"sequences.":[47],"In":[48],"particular,":[49],"we":[50,80,96,116],"adopt":[51],"the":[52,70,82,128],"Stein-Ziv":[53],"lemma":[54],"find":[56],"asymptotically":[57],"optimal":[58],"discriminant":[59],"function":[60],"that":[61],"determines":[62],"whether":[63],"two":[64],"segments":[66],"are":[67],"generated":[68],"by":[69],"same":[71],"source":[72],"assuring":[74],"exponentially":[75],"small":[76],"false":[77],"positives.":[78],"Then":[79],"apply":[81],"minimum":[83],"description":[84],"length":[85],"(MDL)":[86],"principle":[87],"select":[89],"parameters":[90],"our":[92],"segmentation":[93],"algorithm.":[94],"Finally,":[95],"perform":[97],"extensive":[98],"experimental":[99],"work":[100],"on":[101],"human":[102],"chromosome":[103],"9.":[104],"After":[105],"grouping":[106],"A":[107],"G":[109],"(purines)":[110],"T":[112],"C":[114],"(pyrimidines)":[115],"discover":[117],"points":[119],"coding":[121],"noncoding":[123],"beginning":[129],"a":[131],"CpG":[132],"island.":[133]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}