{"id":"https://openalex.org/W2109407861","doi":"https://doi.org/10.1371/journal.pcbi.0030243","title":"Predicting Gene Expression from Sequence: A Reexamination","display_name":"Predicting Gene Expression from Sequence: A Reexamination","publication_year":2007,"publication_date":"2007-11-27","ids":{"openalex":"https://openalex.org/W2109407861","doi":"https://doi.org/10.1371/journal.pcbi.0030243","mag":"2109407861"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.0030243","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.0030243","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.0030243&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.0030243&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100334810","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0003-4706-7897"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079261300","display_name":"Lei Guo","orcid":"https://orcid.org/0000-0002-0402-4152"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Guo","raw_affiliation_strings":["Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090522460","display_name":"Lei Shen","orcid":"https://orcid.org/0000-0003-4040-8716"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Shen","raw_affiliation_strings":["Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012820890","display_name":"Jun S. Liu","orcid":"https://orcid.org/0000-0002-4450-7239"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jun S Liu","raw_affiliation_strings":["Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Statistics, Harvard University, Cambridge, Massachusetts,#N#                    United States of America","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012820890"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":3.0814,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.91999894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"11","first_page":"e243","last_page":"e243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","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"}},"topics":[{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","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"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9973999857902527,"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":0.996999979019165,"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/bayes-theorem","display_name":"Bayes' theorem","score":0.720562219619751},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5755980014801025},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5001404285430908},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4817952513694763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46666616201400757},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.42817550897598267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4043942093849182},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.38677409291267395},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3766280710697174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3645579516887665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34523290395736694}],"concepts":[{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.720562219619751},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5755980014801025},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5001404285430908},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4817952513694763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46666616201400757},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.42817550897598267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043942093849182},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.38677409291267395},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3766280710697174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3645579516887665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34523290395736694}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.0030243","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.0030243","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.0030243&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:plo:pcbi00:0030243","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.0030243","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:4fb13a0a18e74405840da5835330a9b5","is_oa":true,"landing_page_url":"https://doaj.org/article/4fb13a0a18e74405840da5835330a9b5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 3, Iss 11, p e243 (2007)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/151377","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Predicting_Gene_Expression_from_Sequence_A_Reexamination/151377","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:pubmedcentral.nih.gov:2098866","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2098866","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.0030243","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.0030243","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.0030243&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2109407861.pdf","grobid_xml":"https://content.openalex.org/works/W2109407861.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1530113860","https://openalex.org/W1566768190","https://openalex.org/W1998300401","https://openalex.org/W2070340804","https://openalex.org/W2073727170","https://openalex.org/W2073850887","https://openalex.org/W2084908610","https://openalex.org/W2096139934","https://openalex.org/W2096280725","https://openalex.org/W2103453943","https://openalex.org/W2109970232","https://openalex.org/W2114803986","https://openalex.org/W2119022656","https://openalex.org/W2121761522","https://openalex.org/W2124813964","https://openalex.org/W2126602684","https://openalex.org/W2134307042","https://openalex.org/W2137683543","https://openalex.org/W2140785063","https://openalex.org/W2141408320","https://openalex.org/W2142446963","https://openalex.org/W2142460132","https://openalex.org/W2144710927","https://openalex.org/W2145295592","https://openalex.org/W2157076973","https://openalex.org/W2161965550","https://openalex.org/W2163393712","https://openalex.org/W2167190345","https://openalex.org/W2168157737"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2773861473","https://openalex.org/W1971903861","https://openalex.org/W3047903919","https://openalex.org/W40194678"],"abstract_inverted_index":{"Although":[0],"much":[1],"of":[2,32,47,77,100,114,140,175],"the":[3,11,39,61,78,82,86,97,115,157,164,173,179,218],"information":[4,15,40,113],"regarding":[5],"genes'":[6],"expressions":[7],"is":[8,212],"encoded":[9],"in":[10,35,41],"genome,":[12],"deciphering":[13],"such":[14],"has":[16],"been":[17],"very":[18],"challenging.":[19],"We":[20,136,197],"reexamined":[21],"Beer":[22],"and":[23,85,111,149,166,184,214],"Tavazoie's":[24],"(BT)":[25],"approach":[26,106],"to":[27,96,127,146,172,206],"predict":[28,72],"mRNA":[29],"expression":[30,73],"patterns":[31,74],"2,587":[33],"genes":[34,176],"Saccharomyces":[36],"cerevisiae":[37],"from":[38,177],"their":[42,141,208],"respective":[43],"promoter":[44],"sequences.":[45],"Instead":[46],"fitting":[48],"complex":[49],"Bayesian":[50],"network":[51],"models,":[52],"we":[53],"trained":[54],"na":[55],"ve":[56],"Bayes":[57],"classifiers":[58],"using":[59],"only":[60],"sequence-motif":[62],"matching":[63],"scores":[64],"provided":[65],"by":[66,134,161,204,221],"BT.":[67,101,135],"Our":[68],"simple":[69],"models":[70],"correctly":[71],"for":[75,163],"79%":[76],"genes,":[79],"based":[80],"on":[81],"same":[83,87],"criterion":[84],"cross-validation":[88],"(CV)":[89],"procedure":[90,202],"as":[91],"BT,":[92],"which":[93,178],"compares":[94],"favorably":[95],"73%":[98],"accuracy":[99,211,220],"The":[102],"fact":[103],"that":[104,138,189,200],"our":[105],"did":[107],"not":[108,170],"use":[109],"position":[110],"orientation":[112],"predicted":[116],"binding":[117],"sites":[118],"but":[119],"achieved":[120],"a":[121,129],"higher":[122],"prediction":[123,210,219],"accuracy,":[124],"motivated":[125],"us":[126],"investigate":[128],"few":[130],"biological":[131],"predictions":[132],"made":[133],"found":[137],"some":[139],"predictions,":[142],"especially":[143],"those":[144],"related":[145],"motif":[147],"orientations":[148],"positions,":[150],"are":[151,169,186,190],"at":[152],"best":[153],"circumstantial.":[154],"For":[155],"example,":[156],"combinatorial":[158],"rules":[159,188],"suggested":[160],"BT":[162,205],"PAC":[165],"RRPE":[167],"motifs":[168],"unique":[171],"cluster":[174],"predictive":[180],"model":[181],"was":[182],"inferred,":[183],"there":[185],"simpler":[187],"statistically":[191],"more":[192],"significant":[193],"than":[194],"BT's":[195],"ones.":[196],"also":[198],"show":[199],"CV":[201],"used":[203],"estimate":[207],"method's":[209],"inappropriate":[213],"may":[215],"have":[216],"overestimated":[217],"about":[222],"10%.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}