{"id":"https://openalex.org/W1980052495","doi":"https://doi.org/10.1093/bioinformatics/bti1205","title":"Incorporation of splice site probability models for non-canonical introns improves gene structure prediction in plants","display_name":"Incorporation of splice site probability models for non-canonical introns improves gene structure prediction in plants","publication_year":2005,"publication_date":"2005-11-01","ids":{"openalex":"https://openalex.org/W1980052495","doi":"https://doi.org/10.1093/bioinformatics/bti1205","mag":"1980052495","pmid":"https://pubmed.ncbi.nlm.nih.gov/16306388"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti1205","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1205","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/Suppl_3/iii20/574871/bti1205.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/Suppl_3/iii20/574871/bti1205.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090188836","display_name":"Michael E. Sparks","orcid":"https://orcid.org/0000-0001-6251-8559"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E. Sparks","raw_affiliation_strings":["Department of Genetics, Development and Cell Biology, Iowa State University 1 \u00a0 1 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Development and Cell Biology, Iowa State University 1 \u00a0 1 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033118239","display_name":"Volker Brendel","orcid":"https://orcid.org/0000-0002-8055-7508"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Volker Brendel","raw_affiliation_strings":["Department of Genetics, Development and Cell Biology, Iowa State University 1 \u00a0 1 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA","Department of Statistics, Iowa State University 2 \u00a0 2 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Development and Cell Biology, Iowa State University 1 \u00a0 1 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Statistics, Iowa State University 2 \u00a0 2 \u00a0 \u00a0 2112 Molecular Biology Building, Ames, IA 50011-3260, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033118239"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.2559,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.76958167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"Suppl_3","first_page":"iii20","last_page":"iii30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10604","display_name":"RNA Research and Splicing","score":0.9703999757766724,"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/T10604","display_name":"RNA Research and Splicing","score":0.9703999757766724,"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":0.018400000408291817,"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/T11482","display_name":"RNA modifications and cancer","score":0.00279999990016222,"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/intron","display_name":"Intron","score":0.7973600625991821},{"id":"https://openalex.org/keywords/splice","display_name":"splice","score":0.6867895126342773},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.5819159746170044},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5237393379211426},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4954153299331665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48344096541404724},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3640024662017822},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3024106025695801},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.12975510954856873}],"concepts":[{"id":"https://openalex.org/C94671646","wikidata":"https://www.wikidata.org/wiki/Q207551","display_name":"Intron","level":3,"score":0.7973600625991821},{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.6867895126342773},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.5819159746170044},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5237393379211426},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4954153299331665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48344096541404724},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3640024662017822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3024106025695801},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.12975510954856873}],"mesh":[{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007438","descriptor_name":"Introns","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D018744","descriptor_name":"DNA, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018744","descriptor_name":"DNA, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018744","descriptor_name":"DNA, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D022821","descriptor_name":"RNA Splice Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti1205","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1205","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/Suppl_3/iii20/574871/bti1205.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16306388","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16306388","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti1205","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1205","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/Suppl_3/iii20/574871/bti1205.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320308883","display_name":"United States - Israel Binational Agricultural Research and Development Fund","ror":"https://ror.org/04e98j339"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1504094643","https://openalex.org/W1519565833","https://openalex.org/W1749816123","https://openalex.org/W1966833356","https://openalex.org/W1978117793","https://openalex.org/W1982118908","https://openalex.org/W2001672954","https://openalex.org/W2012067705","https://openalex.org/W2014181394","https://openalex.org/W2019558608","https://openalex.org/W2020240988","https://openalex.org/W2027265085","https://openalex.org/W2030660517","https://openalex.org/W2051631967","https://openalex.org/W2067096868","https://openalex.org/W2071405543","https://openalex.org/W2081960755","https://openalex.org/W2107694985","https://openalex.org/W2110400205","https://openalex.org/W2118784262","https://openalex.org/W2120185938","https://openalex.org/W2121144555","https://openalex.org/W2124257763","https://openalex.org/W2126598626","https://openalex.org/W2136145671","https://openalex.org/W2137986897","https://openalex.org/W2144885757","https://openalex.org/W2146210238","https://openalex.org/W2147489306","https://openalex.org/W2152497088","https://openalex.org/W2155684118","https://openalex.org/W2158714788","https://openalex.org/W2159833474","https://openalex.org/W2166187656","https://openalex.org/W2166960413"],"related_works":["https://openalex.org/W3090446747","https://openalex.org/W2083872838","https://openalex.org/W2045666137","https://openalex.org/W2056412942","https://openalex.org/W2087463521","https://openalex.org/W1968177409","https://openalex.org/W2093797995","https://openalex.org/W4211196276","https://openalex.org/W4240704896","https://openalex.org/W2171581216"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"vast":[2],"majority":[3],"of":[4,9,29,38,85,114,126,131,147,165,181,207],"introns":[5,30,40,75,133,190],"in":[6,155,193],"protein-coding":[7],"genes":[8,157,194],"higher":[10],"eukaryotes":[11],"have":[12],"a":[13],"GT":[14],"dinucleotide":[15,22],"at":[16,23,48,217,230,242,258],"their":[17,24,49,79],"5'-terminus":[18],"and":[19,45,51,87,108,112,121,160,171,209,224,233,249],"an":[20],"AG":[21,46],"3'":[25],"end.":[26],"About":[27],"1-2%":[28],"are":[31,228],"non-canonical,":[32],"with":[33,123,195,212],"the":[34,110,124,145,204,213],"most":[35],"abundant":[36],"subtype":[37],"non-canonical":[39,74,99,132,148,162],"being":[41],"characterized":[42],"by":[43],"GC":[44,177],"dinucleotides":[47],"5'-":[50],"3'-termini,":[52],"respectively.":[53,235],"Most":[54],"current":[55],"gene":[56,136],"prediction":[57,80,138],"software,":[58],"whether":[59,128],"based":[60],"on":[61],"ab":[62],"initio":[63],"or":[64,76],"spliced":[65],"alignment":[66],"approaches,":[67],"does":[68],"not":[69],"include":[70],"explicit":[71],"models":[72,118,151,166,255],"for":[73,119,203,221,251],"may":[77],"exclude":[78],"altogether.":[81],"With":[82],"present":[83,186],"amounts":[84],"genome":[86],"transcript":[88],"data,":[89],"it":[90],"is":[91,240,256],"now":[92],"possible":[93],"to":[94,98,245],"apply":[95],"statistical":[96],"methodology":[97],"splice":[100,116,149,253],"site":[101,117,150,254],"prediction.":[102],"We":[103,184],"pursued":[104],"one":[105],"such":[106],"approach":[107],"describe":[109],"training":[111,247],"implementation":[113],"GC-donor":[115],"Arabidopsis":[120],"rice,":[122],"goal":[125],"exploring":[127],"specific":[129],"modeling":[130],"can":[134],"enhance":[135],"structure":[137],"accuracy.":[139],"RESULTS:":[140],"Our":[141],"results":[142],"indicate":[143],"that":[144,188],"incorporation":[146],"yields":[152],"dramatic":[153],"improvements":[154],"annotating":[156],"containing":[158],"GC-AG":[159,189],"AT-AC":[161],"introns.":[163],"Comparison":[164],"shows":[167],"differences":[168],"between":[169],"monocot":[170],"dicot":[172],"species,":[173],"but":[174],"also":[175,185],"suggests":[176],"intron-specific":[178],"biases":[179],"independent":[180],"taxonomic":[182],"clade.":[183],"evidence":[187],"occur":[191],"preferentially":[192],"atypically":[196],"high":[197],"exon":[198],"counts.":[199],"AVAILABILITY:":[200],"Source":[201],"code":[202],"updated":[205],"versions":[206],"GeneSeqer":[208,214],"SplicePredictor":[210,237],"(distributed":[211],"code)":[215],"isavailable":[216],"http://bioinformatics.iastate.edu/bioinformatics2go/gs/download.html.":[218],"Web":[219],"servers":[220],"Arabidopsis,":[222],"rice":[223],"other":[225],"plant":[226],"species":[227],"accessible":[229],"http://www.plantgdb.org/PlantGDB-cgi/GeneSeqer/AtGDBgs.cgi,":[231],"http://www.plantgdb.org/PlantGDB-cgi/GeneSeqer/OsGDBgs.cgi":[232],"http://www.plantgdb.org/PlantGDB-cgi/GeneSeqer/PlantGDBgs.cgi,":[234],"A":[236],"web":[238],"server":[239],"available":[241,257],"http://bioinformatics.iastate.edu/cgi-bin/sp.cgi.":[243],"Software":[244],"generate":[246],"data":[248],"parameterizations":[250],"Bayesian":[252],"http://gremlin1.gdcb.iastate.edu/~volker/SB05B/BSSM4GSQ/":[259]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
