{"id":"https://openalex.org/W2538136169","doi":"https://doi.org/10.1109/acssc.2006.355081","title":"An Improved Minimum Description Length Learning Algorithm for Nucleotide Sequence Analysis","display_name":"An Improved Minimum Description Length Learning Algorithm for Nucleotide Sequence Analysis","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2538136169","doi":"https://doi.org/10.1109/acssc.2006.355081","mag":"2538136169"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2006.355081","doi":"https://doi.org/10.1109/acssc.2006.355081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2006.355081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 Fortieth Asilomar Conference on Signals, Systems and Computers","raw_type":"proceedings-article"},"volume":null,"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":null,"display_name":"Scott Evans","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2802581893","display_name":"United States Army Medical Research and Development Command","ror":"https://ror.org/03cd02q50","country_code":"US","type":"facility","lineage":["https://openalex.org/I106965489","https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802581893"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Evans","raw_affiliation_strings":["evans@research.ge.com","U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"evans@research.ge.com","institution_ids":[]},{"raw_affiliation_string":"U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD","institution_ids":["https://openalex.org/I2802581893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113788130","display_name":"Steve Markham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2802581893","display_name":"United States Army Medical Research and Development Command","ror":"https://ror.org/03cd02q50","country_code":"US","type":"facility","lineage":["https://openalex.org/I106965489","https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802581893"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Markham","raw_affiliation_strings":["markham@research.ge.com","U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"markham@research.ge.com","institution_ids":[]},{"raw_affiliation_string":"U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD","institution_ids":["https://openalex.org/I2802581893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054982051","display_name":"Andrew S. Torres","orcid":"https://orcid.org/0009-0004-7690-5225","observed_orcids":["https://orcid.org/0009-0004-7690-5225"]},"institutions":[{"id":"https://openalex.org/I2802581893","display_name":"United States Army Medical Research and Development Command","ror":"https://ror.org/03cd02q50","country_code":"US","type":"facility","lineage":["https://openalex.org/I106965489","https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802581893"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Torres","raw_affiliation_strings":["torres@research.ge.com","U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"torres@research.ge.com","institution_ids":[]},{"raw_affiliation_string":"U.S. Army Med. Res. Acquisition Activity, Fort Derrick, MD","institution_ids":["https://openalex.org/I2802581893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063355640","display_name":"Antonis Kourtidis","orcid":"https://orcid.org/0000-0002-8128-6391","observed_orcids":["https://orcid.org/0000-0002-8128-6391"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonis Kourtidis","raw_affiliation_strings":["USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050629526","display_name":"Douglas S. Conklin","orcid":"https://orcid.org/0000-0003-4922-4307","observed_orcids":["https://orcid.org/0000-0003-4922-4307"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Douglas Conklin","raw_affiliation_strings":["USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4793,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63463092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"1843","last_page":"1850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8320000171661377,"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":0.8320000171661377,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.13699999451637268,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.02539999969303608,"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":0.9629999995231628},{"id":"https://openalex.org/keywords/phrase-selection","display_name":"phrase selection","score":0.4659999907016754},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphisms","display_name":"single nucleotide polymorphisms","score":0.8500000238418579},{"id":"https://openalex.org/keywords/fragile-regions","display_name":"fragile regions","score":0.8040000200271606},{"id":"https://openalex.org/keywords/motif-discovery","display_name":"motif discovery","score":0.8859999775886536},{"id":"https://openalex.org/keywords/microrna-binding-sites","display_name":"microRNA binding sites","score":0.9160000085830688},{"id":"https://openalex.org/keywords/brca","display_name":"BRCA","score":0.6759999990463257},{"id":"https://openalex.org/keywords/overexpressed-genes","display_name":"overexpressed genes","score":0.8569999933242798}],"concepts":[{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.7019146680831909},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6377640962600708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6209383606910706},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4451620578765869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408166706562042},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42800062894821167},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4167957305908203},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34798920154571533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2224377691745758},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1839873194694519},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2006.355081","doi":"https://doi.org/10.1109/acssc.2006.355081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2006.355081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 Fortieth Asilomar Conference on Signals, Systems and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W224821934","https://openalex.org/W1484484268","https://openalex.org/W1528514765","https://openalex.org/W1573613494","https://openalex.org/W1648301895","https://openalex.org/W1970215626","https://openalex.org/W1978337436","https://openalex.org/W2048607934","https://openalex.org/W2061475351","https://openalex.org/W2083381199","https://openalex.org/W2090001706","https://openalex.org/W2092454702","https://openalex.org/W2105686649","https://openalex.org/W2116813167","https://openalex.org/W2120323371","https://openalex.org/W2134406094","https://openalex.org/W2145021085","https://openalex.org/W2147492358","https://openalex.org/W2150696691","https://openalex.org/W2158714788","https://openalex.org/W2163199119","https://openalex.org/W2913341645"],"related_works":["https://openalex.org/W2049797130","https://openalex.org/W7099461090","https://openalex.org/W2969471489","https://openalex.org/W770215098","https://openalex.org/W134625690","https://openalex.org/W2116813167","https://openalex.org/W7096345312","https://openalex.org/W3213273699","https://openalex.org/W7099915706","https://openalex.org/W1502399419"],"abstract_inverted_index":{"We":[0,165],"present":[1],"an":[2,149],"improved":[3,163],"minimum":[4],"description":[5],"length":[6,70],"(MDL)":[7],"learning":[8],"algorithm":[9,142],"-":[10,12],"MDLCompress":[11,47,88,138,171],"for":[13,114,203],"nucleotide":[14,127],"sequence":[15,103],"analysis":[16,172],"that":[17,36,49,74],"outperforms":[18],"the":[19,46,53,57,77,80,117,132],"compression":[20],"of":[21,62,69,76,87,122,148,156,162,173],"other":[22],"Grammar":[23],"Based":[24],"Coding":[25],"methods":[26],"such":[27,73],"as":[28],"DNA":[29],"Sequitur":[30],"while":[31],"retaining":[32],"a":[33,63,67,179],"two-part":[34,92],"code":[35],"highlights":[37],"biologically":[38,101],"significant":[39],"phrases.":[40],"Phrases":[41],"are":[42,50,200],"recursively":[43],"added":[44],"to":[45,99,109],"model":[48,81,119],"not":[51],"necessarily":[52],"longest":[54],"matches,":[55],"or":[56],"most":[58,133],"often":[59],"repeated":[60],"phrase":[61,78],"certain":[64,197],"length,":[65],"but":[66],"combination":[68],"and":[71,153,199],"repetition":[72],"inclusion":[75],"in":[79,112,116,143,154,204],"maximizes":[82],"compression.":[83],"The":[84,107],"deep":[85],"recursion":[86],"combined":[89],"with":[90],"its":[91],"coding":[93],"nature":[94],"makes":[95],"it":[96],"uniquely":[97],"able":[98],"identify":[100],"meaningful":[102],"without":[104],"limiting":[105],"assumptions.":[106],"ability":[108],"quantify":[110],"cost":[111],"bits":[113],"phrases":[115],"MDL":[118],"promotes":[120],"prediction":[121],"fragile":[123],"regions":[124],"where":[125],"single":[126],"polymorphisms":[128],"(SNPs)":[129],"may":[130],"have":[131,193],"impact":[134],"on":[135],"biological":[136],"activity.":[137],"improves":[139],"our":[140],"previous":[141],"runtime":[144],"performance":[145],"through":[146,160],"use":[147,161],"innovative":[150],"data":[151],"structure":[152],"specificity":[155],"motif":[157],"detection":[158],"(compression)":[159],"heuristics.":[164],"also":[166],"discuss":[167],"recent":[168],"results":[169],"from":[170,178],"144":[174],"known":[175],"overexpressed":[176],"genes":[177,198],"breast":[180],"cancer":[181],"cell":[182],"line,":[183],"BT474.":[184],"Novel":[185],"motifs,":[186],"including":[187],"potential":[188],"microRNA":[189],"(miRNA)":[190],"binding":[191],"sites,":[192],"been":[194],"identified":[195],"within":[196],"being":[201],"considered":[202],"vitro":[205],"validation":[206],"studies.":[207]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-10-28T00:00:00"}