{"id":"https://openalex.org/W4247292500","doi":"https://doi.org/10.1089/cmb.1997.4.311","title":"Improved Splice Site Detection in Genie","display_name":"Improved Splice Site Detection in Genie","publication_year":1997,"publication_date":"1997-01-01","ids":{"openalex":"https://openalex.org/W4247292500","doi":"https://doi.org/10.1089/cmb.1997.4.311"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.1997.4.311","doi":"https://doi.org/10.1089/cmb.1997.4.311","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.1997.4.311","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"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"},"volume":null,"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/A5046968087","display_name":"Martin G. Reese","orcid":"https://orcid.org/0000-0001-8297-245X","observed_orcids":["https://orcid.org/0000-0001-8297-245X"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MARTIN G. REESE","raw_affiliation_strings":["Human Genome Informatics Group, Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA. mgreese@lbl.gov"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Genome Informatics Group, Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA. mgreese@lbl.gov","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109238922","display_name":"Frank H. Eeckman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"FRANK H. EECKMAN","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047269307","display_name":"David Kulp","orcid":"https://orcid.org/0000-0001-6540-0222","observed_orcids":["https://orcid.org/0000-0001-6540-0222"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DAVID KULP","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090849321","display_name":"David H. Haussler","orcid":"https://orcid.org/0000-0003-1533-4575","observed_orcids":["https://orcid.org/0000-0003-1533-4575"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DAVID HAUSSLER","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3745,"has_fulltext":false,"cited_by_count":1573,"citation_normalized_percentile":{"value":0.93614896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"4","issue":"3","first_page":"311","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9589999914169312,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9589999914169312,"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":0.014800000004470348,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00989999994635582,"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/splice-site-prediction","display_name":"splice site prediction","score":0.9200000166893005},{"id":"https://openalex.org/keywords/genie","display_name":"GENIE","score":0.9200000166893005},{"id":"https://openalex.org/keywords/gene-discovery","display_name":"gene discovery","score":0.75},{"id":"https://openalex.org/keywords/generalized-hidden-markov-models","display_name":"generalized hidden Markov models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.7379999756813049},{"id":"https://openalex.org/keywords/dinucleotide-frequency","display_name":"dinucleotide frequency","score":0.9070000052452087},{"id":"https://openalex.org/keywords/gene-structure-prediction","display_name":"gene structure prediction","score":0.6690000295639038},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"false positive rate","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.8802447319030762},{"id":"https://openalex.org/C36823959","wikidata":"https://www.wikidata.org/wiki/Q373027","display_name":"Exon","level":3,"score":0.663118839263916},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.6166623830795288},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5750264525413513},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5516371726989746},{"id":"https://openalex.org/C62257209","wikidata":"https://www.wikidata.org/wiki/Q5487490","display_name":"Splice site mutation","level":5,"score":0.5330758094787598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5152859687805176},{"id":"https://openalex.org/C94671646","wikidata":"https://www.wikidata.org/wiki/Q207551","display_name":"Intron","level":3,"score":0.5042625665664673},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49694445729255676},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4778668284416199},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.4416342079639435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3772348165512085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37620922923088074},{"id":"https://openalex.org/C194583182","wikidata":"https://www.wikidata.org/wiki/Q21114084","display_name":"Alternative splicing","level":4,"score":0.31214165687561035},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.19473275542259216},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.16568127274513245}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1089/cmb.1997.4.311","doi":"https://doi.org/10.1089/cmb.1997.4.311","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.1997.4.311","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"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":"pmh:oai:CiteSeerX.psu:10.1.1.542.5977","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.542.5977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://fruitfly.org:9005/~martinr/papers/Reeseetal.ImprovedSpliceSiteDetectionInGenie.JCompBiol.1997.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1008280890","https://openalex.org/W1966833356","https://openalex.org/W1975937029","https://openalex.org/W1977435924","https://openalex.org/W2014181394","https://openalex.org/W2025692710","https://openalex.org/W2035564383","https://openalex.org/W2036056816","https://openalex.org/W2039680623","https://openalex.org/W2042190395","https://openalex.org/W2052729310","https://openalex.org/W2081530255","https://openalex.org/W2102122585","https://openalex.org/W2105594594","https://openalex.org/W2116390865","https://openalex.org/W2120199531","https://openalex.org/W2144433989"],"related_works":["https://openalex.org/W7098626895","https://openalex.org/W7100661307","https://openalex.org/W2098658564","https://openalex.org/W115623364","https://openalex.org/W2281572985","https://openalex.org/W7100763162","https://openalex.org/W2322243459","https://openalex.org/W2110400205","https://openalex.org/W2996771978","https://openalex.org/W2537075142"],"abstract_inverted_index":{"We":[0,98],"present":[1],"an":[2],"improved":[3],"splice":[4,86,102,168,177,196],"site":[5,87,103,169,178,197],"predictor":[6],"for":[7,43],"the":[8,24,72,80,90,100,125,163,189,194],"genefinding":[9,76],"program":[10],"Genie.":[11],"Genie":[12,106,120,146],"is":[13,77],"based":[14,112],"on":[15,113,198],"a":[16,27,31,35,68,138,154],"generalized":[17],"Hidden":[18],"Markov":[19],"Model":[20],"(GHMM)":[21],"that":[22,61,94,145],"describes":[23],"grammar":[25],"of":[26,30,71,129,141,149,156,191],"legal":[28],"parse":[29],"multi-exon":[32],"gene":[33,44,82,130],"in":[34,75,105,124,135,162],"DNA":[36],"sequence.":[37],"In":[38,166],"Genie,":[39],"probabilities":[40],"are":[41,89],"estimated":[42],"features":[45],"by":[46],"using":[47,137],"dynamic":[48],"programming":[49],"to":[50,64,78,193],"combine":[51],"information":[52],"from":[53,67],"multiple":[54],"content":[55],"and":[56,127,160,180,182],"signal":[57,92],"sensors,":[58,119],"including":[59],"sensors":[60,88,93,104],"integrate":[62],"matches":[63],"homologous":[65],"sequences":[66],"database.":[69],"One":[70],"hardest":[73],"problems":[74],"determine":[79],"complete":[81],"structure":[83,131],"correctly.":[84],"The":[85],"key":[91],"address":[95],"this":[96],"problem.":[97],"replaced":[99],"existing":[101],"with":[107,153],"two":[108],"novel":[109,118],"neural":[110],"networks":[111],"dinucleotide":[114],"frequencies.":[115],"Using":[116],"these":[117],"shows":[121],"significant":[122],"improvements":[123],"sensitivity":[126],"specificity":[128,155],"identification.":[132],"Experimental":[133],"results":[134],"tests":[136],"standard":[139],"set":[140],"annotated":[142],"genes":[143],"showed":[144],"identified":[147],"86%":[148],"coding":[150],"nucleotides":[151],"correctly":[152],"85%,":[157],"versus":[158],"80%":[159],"84%":[161],"older":[164],"system.":[165],"further":[167],"experiments,":[170],"we":[171],"also":[172],"looked":[173],"at":[174,188],"correlations":[175],"between":[176],"scores":[179],"intron":[181],"exon":[183],"lengths,":[184],"as":[185,187],"well":[186],"effect":[190],"distance":[192],"nearest":[195],"false":[199],"positive":[200],"rates.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":78},{"year":2021,"cited_by_count":111},{"year":2020,"cited_by_count":101},{"year":2019,"cited_by_count":83},{"year":2018,"cited_by_count":76},{"year":2017,"cited_by_count":89},{"year":2016,"cited_by_count":90},{"year":2015,"cited_by_count":87},{"year":2014,"cited_by_count":86},{"year":2013,"cited_by_count":84},{"year":2012,"cited_by_count":71}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-05-12T00:00:00"}
