{"id":"https://openalex.org/W2804476733","doi":"https://doi.org/10.1101/gr.230615.117","title":"Modeling leaderless transcription and atypical genes results in more accurate gene prediction in prokaryotes","display_name":"Modeling leaderless transcription and atypical genes results in more accurate gene prediction in prokaryotes","publication_year":2018,"publication_date":"2018-05-17","ids":{"openalex":"https://openalex.org/W2804476733","doi":"https://doi.org/10.1101/gr.230615.117","mag":"2804476733","pmid":"https://pubmed.ncbi.nlm.nih.gov/29773659","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6028130"},"language":"en","primary_location":{"id":"doi:10.1101/gr.230615.117","doi":"https://doi.org/10.1101/gr.230615.117","is_oa":false,"landing_page_url":"https://doi.org/10.1101/gr.230615.117","pdf_url":null,"source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Research","raw_type":"journal-article"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://europepmc.org/pmc/articles/PMC6028130","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":["Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","1Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","2Gene Probe, Incorporated, Atlanta, Georgia 30324, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","institution_ids":[]},{"raw_affiliation_string":"Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]},{"raw_affiliation_string":"1Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]},{"raw_affiliation_string":"2Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076891738","display_name":"Karl Gemayel","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Gemayel","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","3School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"3School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111698760","display_name":"Shiyuyun Tang","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyuyun Tang","raw_affiliation_strings":["School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","4School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"4School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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":false,"raw_author_name":"Mark Borodovsky","raw_affiliation_strings":["Department of Biological and Medical Physics, Moscow Institute of Physics and Technology, Moscow, 141700, Russia","Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","1Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","2Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","3School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","4School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","5Department of Biological and Medical Physics, Moscow Institute of Physics and Technology, Moscow, 141700, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological and Medical Physics, Moscow Institute of Physics and Technology, Moscow, 141700, Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","institution_ids":[]},{"raw_affiliation_string":"School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]},{"raw_affiliation_string":"1Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I2802612298"]},{"raw_affiliation_string":"2Gene Probe, Incorporated, Atlanta, Georgia 30324, USA","institution_ids":[]},{"raw_affiliation_string":"3School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"4School of Biological Sciences, Georgia Tech, Atlanta, Georgia 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"5Department of Biological and Medical Physics, Moscow Institute of Physics and Technology, Moscow, 141700, Russia","institution_ids":["https://openalex.org/I153845743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":236,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"7","first_page":"1079","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9932000041007996,"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":0.9932000041007996,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.0013000000035390258,"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/ribosome-binding-site","display_name":"ribosome binding site","score":0.8690000176429749},{"id":"https://openalex.org/keywords/shine-dalgarno-sequence","display_name":"Shine-Dalgarno sequence","score":0.8330000042915344},{"id":"https://openalex.org/keywords/horizontal-gene-transfer","display_name":"horizontal gene transfer","score":0.824999988079071},{"id":"https://openalex.org/keywords/gene-expression-regulation","display_name":"gene expression regulation","score":0.5849999785423279},{"id":"https://openalex.org/keywords/promoter","display_name":"promoter","score":0.3499999940395355},{"id":"https://openalex.org/keywords/archaea","display_name":"archaea","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.914409875869751},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6791468858718872},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6507317423820496},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5248242020606995},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44757771492004395},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D009876","descriptor_name":"Operon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D012270","descriptor_name":"Ribosomes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014176","descriptor_name":"Protein Biosynthesis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1101/gr.230615.117","doi":"https://doi.org/10.1101/gr.230615.117","is_oa":false,"landing_page_url":"https://doi.org/10.1101/gr.230615.117","pdf_url":null,"source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Research","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:5285587","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6028130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6028130","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6028130","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Res","raw_type":"Text"},{"id":"pmid:29773659","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29773659","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":"Genome research","raw_type":"Journal Article"},{"id":"pmh:oai:open-archive.highwire.org:genome:28/7/1079","doi":null,"is_oa":false,"landing_page_url":"http://genome.cshlp.org/cgi/content/short/28/7/1079","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"}],"best_oa_location":{"id":"pmh:oai:europepmc.org:5285587","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6028130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},"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"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W217156697","https://openalex.org/W1822648038","https://openalex.org/W1881056157","https://openalex.org/W1945781696","https://openalex.org/W1954517756","https://openalex.org/W1969535465","https://openalex.org/W1984791554","https://openalex.org/W1990453950","https://openalex.org/W1991163952","https://openalex.org/W1992987210","https://openalex.org/W1994926732","https://openalex.org/W2004494938","https://openalex.org/W2017832416","https://openalex.org/W2018962053","https://openalex.org/W2020165438","https://openalex.org/W2029348973","https://openalex.org/W2039680623","https://openalex.org/W2044840666","https://openalex.org/W2048673910","https://openalex.org/W2054522148","https://openalex.org/W2061856039","https://openalex.org/W2062896692","https://openalex.org/W2068242488","https://openalex.org/W2074785456","https://openalex.org/W2076209125","https://openalex.org/W2077460182","https://openalex.org/W2081530255","https://openalex.org/W2085967390","https://openalex.org/W2100594487","https://openalex.org/W2104908438","https://openalex.org/W2105199251","https://openalex.org/W2106090237","https://openalex.org/W2110728874","https://openalex.org/W2114401611","https://openalex.org/W2120172561","https://openalex.org/W2120574189","https://openalex.org/W2122217991","https://openalex.org/W2123863402","https://openalex.org/W2134840548","https://openalex.org/W2136632285","https://openalex.org/W2137390416","https://openalex.org/W2143485490","https://openalex.org/W2151605074","https://openalex.org/W2152180708","https://openalex.org/W2153992812","https://openalex.org/W2155347381","https://openalex.org/W2155606054","https://openalex.org/W2158808847","https://openalex.org/W2161435986","https://openalex.org/W2162111678","https://openalex.org/W2165182519","https://openalex.org/W2166064969","https://openalex.org/W2168232374","https://openalex.org/W2232370058","https://openalex.org/W2434679378","https://openalex.org/W2470052926","https://openalex.org/W2513021116","https://openalex.org/W2589372192","https://openalex.org/W2591306293","https://openalex.org/W4206983698"],"related_works":["https://openalex.org/W2766330166","https://openalex.org/W2061361077","https://openalex.org/W2604046539","https://openalex.org/W4288077667","https://openalex.org/W7042584917","https://openalex.org/W2106090237","https://openalex.org/W2158808847","https://openalex.org/W1834463255","https://openalex.org/W2160053034","https://openalex.org/W2770310767"],"abstract_inverted_index":{"In":[0],"a":[1,27,50,204],"conventional":[2],"view":[3,30],"of":[4,64,84,112,121,155,194,197,206],"the":[5,96,110,146,153,176,189,217],"prokaryotic":[6,158,207],"genome":[7],"organization,":[8],"promoters":[9],"precede":[10,20],"operons":[11],"and":[12,127,170],"ribosome":[13],"binding":[14],"sites":[15,178],"(RBSs)":[16],"with":[17,37,61,145,182,212],"Shine-Dalgarno":[18,190],"consensus":[19],"genes.":[21],"However,":[22],"recent":[23],"experimental":[24],"research":[25],"suggesting":[26],"more":[28],"diverse":[29],"motivated":[31],"us":[32],"to":[33,69,80],"develop":[34],"an":[35,44,62],"algorithm":[36,47],"improved":[38],"gene-finding":[39],"accuracy.":[40],"We":[41,131,172],"describe":[42],"GeneMarkS-2,":[43,113],"ab":[45],"initio":[46],"that":[48,133,175],"uses":[49],"model":[51],"derived":[52],"by":[53,118,161],"self-training":[54],"for":[55,99],"finding":[56],"species-specific":[57],"(native)":[58],"genes,":[59],"along":[60],"array":[63],"precomputed":[65],"\"heuristic\"":[66],"models":[67],"designed":[68,78],"identify":[70,81],"harder-to-detect":[71],"genes":[72,116],"(likely":[73],"horizontally":[74],"transferred).":[75],"Importantly,":[76],"we":[77,114],"GeneMarkS-2":[79,134,162],"several":[82],"types":[83,196],"distinct":[85,213],"sequence":[86,198,214],"patterns":[87,97,215],"(signals)":[88],"involved":[89],"in":[90,139,167,179],"gene":[91,149,201,218],"expression":[92,202],"control,":[93],"among":[94],"them":[95],"characteristic":[98],"leaderless":[100,165],"transcription":[101,166,184],"as":[102,104],"well":[103],"noncanonical":[105],"RBS":[106,177],"patterns.":[107],"To":[108],"assess":[109],"accuracy":[111,141],"used":[115],"validated":[117],"COG":[119],"(Clusters":[120],"Orthologous":[122],"Groups)":[123],"annotation,":[124],"proteomics":[125],"experiments,":[126],"N-terminal":[128],"protein":[129],"sequencing.":[130],"observed":[132,174],"performed":[135],"better":[136],"on":[137],"average":[138],"all":[140],"measures":[142],"when":[143],"compared":[144],"current":[147],"state-of-the-art":[148],"prediction":[150],"tools.":[151],"Furthermore,":[152],"screening":[154],"\u223c5000":[156],"representative":[157],"genomes":[159,208],"made":[160],"predicted":[163],"frequent":[164],"both":[168],"archaea":[169],"bacteria.":[171],"also":[173],"some":[180],"species":[181],"leadered":[183],"did":[185],"not":[186],"necessarily":[187],"exhibit":[188],"consensus.":[191],"The":[192],"modeling":[193],"different":[195],"motifs":[199],"regulating":[200],"prompted":[203],"division":[205],"into":[209],"five":[210],"categories":[211],"around":[216],"starts.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":33},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2018-06-01T00:00:00"}