{"id":"https://openalex.org/W2129296076","doi":"https://doi.org/10.1093/nar/gku557","title":"Integration of mapped RNA-Seq reads into automatic training of eukaryotic gene finding algorithm","display_name":"Integration of mapped RNA-Seq reads into automatic training of eukaryotic gene finding algorithm","publication_year":2014,"publication_date":"2014-07-02","ids":{"openalex":"https://openalex.org/W2129296076","doi":"https://doi.org/10.1093/nar/gku557","mag":"2129296076","pmid":"https://pubmed.ncbi.nlm.nih.gov/24990371","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4150757"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gku557","doi":"https://doi.org/10.1093/nar/gku557","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku557","pdf_url":"https://academic.oup.com/nar/article-pdf/42/15/e119/28909747/gku557.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/nar/article-pdf/42/15/e119/28909747/gku557.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083410058","display_name":"Alexandre Lomsadze","orcid":"https://orcid.org/0000-0003-0491-1648","observed_orcids":["https://orcid.org/0000-0003-0491-1648"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2802612298","display_name":"The Wallace H. Coulter Department of Biomedical Engineering","ror":"https://ror.org/02j15s898","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444","https://openalex.org/I150468666","https://openalex.org/I2802612298"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandre Lomsadze","raw_affiliation_strings":["Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113679013","display_name":"Paul D. Burns","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2802612298","display_name":"The Wallace H. Coulter Department of Biomedical Engineering","ror":"https://ror.org/02j15s898","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444","https://openalex.org/I150468666","https://openalex.org/I2802612298"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul D. Burns","raw_affiliation_strings":["Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057317686","display_name":"Mark Yu. Borodovsky","orcid":"https://orcid.org/0000-0002-1401-4046","observed_orcids":["https://orcid.org/0000-0002-1401-4046"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]},{"id":"https://openalex.org/I2802612298","display_name":"The Wallace H. Coulter Department of Biomedical Engineering","ror":"https://ror.org/02j15s898","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444","https://openalex.org/I150468666","https://openalex.org/I2802612298"]}],"countries":["RU","US"],"is_corresponding":true,"raw_author_name":"Mark Borodovsky","raw_affiliation_strings":["Department of Bioinformatics, Moscow Institute of Physics and Technology, Moscow, Russia 141700","Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332","School of Computational Science and Engineering, Georgia Tech, Atlanta, GA, USA 30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioinformatics, Moscow Institute of Physics and Technology, Moscow, Russia 141700","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Joint Georgia Tech and Emory Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA 30332","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]},{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Tech, Atlanta, GA, USA 30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057317686"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I153845743","https://openalex.org/I2802612298"],"apc_list":{"value":3992,"currency":"USD","value_usd":3992},"apc_paid":{"value":3992,"currency":"USD","value_usd":3992},"fwci":4.0774,"has_fulltext":true,"cited_by_count":557,"citation_normalized_percentile":{"value":0.95255733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"42","issue":"15","first_page":"e119","last_page":"e119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0003000000142492354,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ab-initio-gene-prediction","display_name":"ab initio gene prediction","score":0.8029999732971191},{"id":"https://openalex.org/keywords/rna-seq-alignment","display_name":"RNA-seq alignment","score":0.9369999766349792},{"id":"https://openalex.org/keywords/eukaryotic-genomes","display_name":"eukaryotic genomes","score":0.8159999847412109},{"id":"https://openalex.org/keywords/genome-annotation","display_name":"genome annotation","score":0.9620000123977661},{"id":"https://openalex.org/keywords/aedes-aegypti","display_name":"Aedes aegypti","score":0.9330000281333923},{"id":"https://openalex.org/keywords/sensitivity-and-specificity","display_name":"sensitivity and specificity","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.698907732963562},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.68436598777771},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6032429337501526},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5580061674118042},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5521605014801025},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5477601289749146},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.5404058694839478},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.5290569067001343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46104854345321655},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4499179720878601},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.41350236535072327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3858333230018616},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.37352898716926575},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3348109722137451},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.15358534455299377},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.08665469288825989}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009033","descriptor_name":"Culicidae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017344","descriptor_name":"Genes, Insect","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/nar/gku557","doi":"https://doi.org/10.1093/nar/gku557","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku557","pdf_url":"https://academic.oup.com/nar/article-pdf/42/15/e119/28909747/gku557.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:4150757","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4150757","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"},{"id":"pmid:24990371","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24990371","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,"listed_in":[],"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":"Nucleic acids research","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/nar/gku557","doi":"https://doi.org/10.1093/nar/gku557","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku557","pdf_url":"https://academic.oup.com/nar/article-pdf/42/15/e119/28909747/gku557.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5047612491","display_name":"Gene Prediction by Markov Models and Complementary Methods","funder_award_id":"R01HG000783","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G6891423054","display_name":null,"funder_award_id":"HG000783","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2129296076.pdf","grobid_xml":"https://content.openalex.org/works/W2129296076.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1484347389","https://openalex.org/W1968050693","https://openalex.org/W1989174554","https://openalex.org/W2071501400","https://openalex.org/W2097065948","https://openalex.org/W2099753867","https://openalex.org/W2101786683","https://openalex.org/W2110155683","https://openalex.org/W2112849898","https://openalex.org/W2117688129","https://openalex.org/W2117936709","https://openalex.org/W2121840477","https://openalex.org/W2122657809","https://openalex.org/W2128242967","https://openalex.org/W2130395351","https://openalex.org/W2131074700","https://openalex.org/W2134014174","https://openalex.org/W2141458291","https://openalex.org/W2141572089","https://openalex.org/W2141652419","https://openalex.org/W2143235667","https://openalex.org/W2144845731","https://openalex.org/W2153569313","https://openalex.org/W2157115023","https://openalex.org/W2166187656","https://openalex.org/W2171158206"],"related_works":["https://openalex.org/W2216234219","https://openalex.org/W3025319533","https://openalex.org/W2997726442","https://openalex.org/W2770310767","https://openalex.org/W2030165834","https://openalex.org/W2604046539","https://openalex.org/W4316344924","https://openalex.org/W2306323567","https://openalex.org/W4399560589","https://openalex.org/W4380320469"],"abstract_inverted_index":{"We":[0,100],"present":[1],"a":[2,9,69,168],"new":[3,63],"approach":[4],"to":[5,31,171],"automatic":[6,22,55,176],"training":[7,23,56],"of":[8,19,37,82,93,109,111,118,127,133,151,175],"eukaryotic":[10,51],"ab":[11,59],"initio":[12,60],"gene":[13,47,119,140,177],"finding":[14,48],"algorithm.":[15],"With":[16],"the":[17,35,45,78,106,116,123,130,139,148,155,172],"advent":[18],"Next-Generation":[20],"Sequencing,":[21],"has":[24],"become":[25],"paramount,":[26],"allowing":[27],"genome":[28,38,126],"annotation":[29,160],"pipelines":[30],"keep":[32],"pace":[33],"with":[34,68],"speed":[36],"sequencing.":[39],"Earlier":[40],"we":[41],"developed":[42],"GeneMark-ES,":[43],"currently":[44],"only":[46],"algorithm":[49],"for":[50,122,157],"genomes":[52],"that":[53,72,105],"performs":[54],"in":[57,97,102],"unsupervised":[58],"mode.":[61],"The":[62],"algorithm,":[64],"GeneMark-ET":[65,165],"augments":[66],"GeneMark-ES":[67,144],"novel":[70],"method":[71,108],"integrates":[73],"RNA-Seq":[74,84,113],"read":[75],"alignments":[76],"into":[77],"self-training":[79],"procedure.":[80],"Use":[81],"'assembled'":[83],"transcripts":[85],"is":[86,161],"far":[87],"from":[88],"trivial;":[89],"significant":[90],"error":[91],"rate":[92],"assembly":[94],"was":[95],"revealed":[96],"recent":[98],"assessments.":[99],"demonstrated":[101],"computational":[103],"experiments":[104],"proposed":[107],"incorporation":[110],"'unassembled'":[112],"reads":[114],"improves":[115],"accuracy":[117],"prediction;":[120],"particularly,":[121],"1.3":[124],"GB":[125],"Aedes":[128],"aegypti":[129],"mean":[131],"value":[132],"prediction":[134,178],"Sensitivity":[135],"and":[136],"Specificity":[137],"at":[138],"level":[141],"increased":[142],"over":[143],"by":[145],"24.5%.":[146],"In":[147],"current":[149],"surge":[150],"genomic":[152],"data":[153],"when":[154],"need":[156],"accurate":[158],"sequence":[159],"higher":[162],"than":[163],"ever,":[164],"will":[166],"be":[167],"valuable":[169],"addition":[170],"narrow":[173],"arsenal":[174],"tools.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":75},{"year":2024,"cited_by_count":90},{"year":2023,"cited_by_count":70},{"year":2022,"cited_by_count":77},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":57},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":35},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}