{"id":"https://openalex.org/W2034691490","doi":"https://doi.org/10.1089/1066527041410418","title":"Maximum Entropy Modeling of Short Sequence Motifs with Applications to RNA Splicing Signals","display_name":"Maximum Entropy Modeling of Short Sequence Motifs with Applications to RNA Splicing Signals","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2034691490","doi":"https://doi.org/10.1089/1066527041410418","mag":"2034691490","pmid":"https://pubmed.ncbi.nlm.nih.gov/15285897"},"language":"en","primary_location":{"id":"doi:10.1089/1066527041410418","is_oa":false,"landing_page_url":"https://doi.org/10.1089/1066527041410418","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1466099","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082310752","display_name":"G Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gene Yeo","raw_affiliation_strings":["Department of Biology, Massachusetts Institute of Technology, 77 Massachusetts Avenue Building 68-223, Cambridge, MA 02319","Department of Biology, Massachusetts Institute of Technology, 77 Massachusetts Avenue Building 68-223, Cambridge, MA 02319, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, Massachusetts Institute of Technology, 77 Massachusetts Avenue Building 68-223, Cambridge, MA 02319","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Biology, Massachusetts Institute of Technology, 77 Massachusetts Avenue Building 68-223, Cambridge, MA 02319, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048799588","display_name":"Christopher B. Burge","orcid":"https://orcid.org/0000-0001-9047-5648"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher B. Burge","raw_affiliation_strings":["Department of Brain and Cognitive Sciences, Center for Biological and Computational Learning, MassachusettsInstitute of Technology, Cambridge, MA 02319"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain and Cognitive Sciences, Center for Biological and Computational Learning, MassachusettsInstitute of Technology, Cambridge, MA 02319","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082310752"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":9.1607,"has_fulltext":false,"cited_by_count":2118,"citation_normalized_percentile":{"value":0.98765849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"2-3","first_page":"377","last_page":"394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"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/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10604","display_name":"RNA Research and Splicing","score":0.9987000226974487,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9962000250816345,"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/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.7506352663040161},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6284915804862976},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.5954640507698059},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5489183664321899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5333865284919739},{"id":"https://openalex.org/keywords/splice","display_name":"splice","score":0.49385935068130493},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48205241560935974},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.46667420864105225},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.4329968988895416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41353753209114075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40897780656814575},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.29663002490997314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27698856592178345},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13682708144187927},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1353379487991333},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08375465869903564},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08082520961761475},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.07084739208221436}],"concepts":[{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.7506352663040161},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6284915804862976},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.5954640507698059},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5489183664321899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5333865284919739},{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.49385935068130493},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48205241560935974},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.46667420864105225},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.4329968988895416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41353753209114075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40897780656814575},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.29663002490997314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27698856592178345},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13682708144187927},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1353379487991333},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08375465869903564},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08082520961761475},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.07084739208221436},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1089/1066527041410418","is_oa":false,"landing_page_url":"https://doi.org/10.1089/1066527041410418","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:15285897","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15285897","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:zenodo.org:1466099","is_oa":true,"landing_page_url":"https://zenodo.org/record/1466099","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1466099","is_oa":true,"landing_page_url":"https://zenodo.org/record/1466099","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1970634015","https://openalex.org/W1975279309","https://openalex.org/W1990748933","https://openalex.org/W2023648355","https://openalex.org/W2032558547","https://openalex.org/W2039537118","https://openalex.org/W2052958516","https://openalex.org/W2054283432","https://openalex.org/W2061408624","https://openalex.org/W2085294315","https://openalex.org/W2086799261","https://openalex.org/W2096175520","https://openalex.org/W2102122585","https://openalex.org/W2106673218","https://openalex.org/W2110400205","https://openalex.org/W2110863141","https://openalex.org/W2115149771","https://openalex.org/W2120744807","https://openalex.org/W2125562688","https://openalex.org/W2134451695","https://openalex.org/W2146393977","https://openalex.org/W2158241396","https://openalex.org/W2166187656","https://openalex.org/W4231741839"],"related_works":["https://openalex.org/W2063247976","https://openalex.org/W94633634","https://openalex.org/W3003088367","https://openalex.org/W2033909284","https://openalex.org/W2086574514","https://openalex.org/W2510879953","https://openalex.org/W4230289150","https://openalex.org/W3038107571","https://openalex.org/W1972259667","https://openalex.org/W1544986005"],"abstract_inverted_index":{"We":[0,15,89],"propose":[1],"a":[2],"framework":[3,92],"for":[4],"modeling":[5],"sequence":[6,19],"motifs":[7],"based":[8],"on":[9],"the":[10,23,58,81,108],"maximum":[11,24,49],"entropy":[12,25,50],"principle":[13],"(MEP).":[14],"recommend":[16],"approximating":[17],"short":[18],"motif":[20],"distributions":[21],"with":[22,29],"distribution":[26],"(MED)":[27],"consistent":[28],"low-order":[30],"marginal":[31],"constraints":[32],"estimated":[33],"from":[34,119],"available":[35],"data,":[36],"which":[37],"may":[38],"include":[39],"dependencies":[40,85],"between":[41,69,86],"nonadjacent":[42],"as":[43,45],"well":[44],"adjacent":[46],"positions.":[47,88],"Many":[48],"models":[51,63,102,106],"(MEMs)":[52],"are":[53],"specified":[54],"by":[55],"simply":[56],"changing":[57],"set":[59],"of":[60,84,96,110,127],"constraints.":[61],"Such":[62],"can":[64],"be":[65],"utilized":[66],"to":[67,93],"discriminate":[68],"signals":[70],"and":[71,114],"decoys.":[72,120],"Classification":[73],"performance":[74],"using":[75],"different":[76,87],"MEMs":[77],"gives":[78],"insight":[79],"into":[80],"relative":[82],"importance":[83],"apply":[90],"our":[91],"large":[94],"datasets":[95],"RNA":[97],"splicing":[98],"signals.":[99],"Our":[100],"best":[101],"out-perform":[103],"previous":[104],"probabilistic":[105],"in":[107],"discrimination":[109],"human":[111],"5'":[112],"(donor)":[113],"3'":[115],"(acceptor)":[116],"splice":[117],"sites":[118],"Finally,":[121],"we":[122],"discuss":[123],"mechanistically":[124],"motivated":[125],"ways":[126],"comparing":[128],"models.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":37},{"year":2025,"cited_by_count":133},{"year":2024,"cited_by_count":152},{"year":2023,"cited_by_count":167},{"year":2022,"cited_by_count":191},{"year":2021,"cited_by_count":190},{"year":2020,"cited_by_count":175},{"year":2019,"cited_by_count":150},{"year":2018,"cited_by_count":126},{"year":2017,"cited_by_count":105},{"year":2016,"cited_by_count":97},{"year":2015,"cited_by_count":105},{"year":2014,"cited_by_count":97},{"year":2013,"cited_by_count":65},{"year":2012,"cited_by_count":74}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}
