{"id":"https://openalex.org/W2160053034","doi":"https://doi.org/10.1093/nar/26.4.1107","title":"GeneMark.hmm: new solutions for gene finding","display_name":"GeneMark.hmm: new solutions for gene finding","publication_year":1998,"publication_date":"1998-02-15","ids":{"openalex":"https://openalex.org/W2160053034","doi":"https://doi.org/10.1093/nar/26.4.1107","mag":"2160053034","pmid":"https://pubmed.ncbi.nlm.nih.gov/9461475","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/147337"},"language":"en","primary_location":{"id":"doi:10.1093/nar/26.4.1107","doi":"https://doi.org/10.1093/nar/26.4.1107","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.4.1107","pdf_url":"https://academic.oup.com/nar/article-pdf/26/4/1107/9469816/26-4-1107.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":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2160053034"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/nar/article-pdf/26/4/1107/9469816/26-4-1107.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044248237","display_name":"Alex Lukashin","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":true,"raw_author_name":"A. Lukashin","raw_affiliation_strings":["School of Biology and Schools of Biology and Mathematics, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","School of Biology, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biology and Schools of Biology and Mathematics, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Biology, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"M Borodovsky","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M Borodovsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044248237"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":3992,"currency":"USD","value_usd":3992},"apc_paid":null,"fwci":9.3982,"has_fulltext":true,"cited_by_count":1565,"citation_normalized_percentile":{"value":0.98955857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":"4","first_page":"1107","last_page":"1115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0013000000035390258,"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"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.000699999975040555,"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/gene-prediction","display_name":"gene prediction","score":0.8889999985694885},{"id":"https://openalex.org/keywords/gene-discovery","display_name":"gene discovery","score":0.6980000138282776},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.8460000157356262},{"id":"https://openalex.org/keywords/bacterial-genomes","display_name":"bacterial genomes","score":0.8100000023841858},{"id":"https://openalex.org/keywords/gene-boundaries","display_name":"gene boundaries","score":0.8270000219345093},{"id":"https://openalex.org/keywords/ribosome-binding-site","display_name":"ribosome binding site","score":0.8799999952316284},{"id":"https://openalex.org/keywords/initiation-codon","display_name":"initiation codon","score":0.8539999723434448}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7826349139213562},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7554711103439331},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.6781972646713257},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6219825148582458},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5993520617485046},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5873644351959229},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5584114193916321},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5234622359275818},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4857964515686035},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47119590640068054},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.45864182710647583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3501162528991699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2836182117462158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.264182984828949},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1994512379169464},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005069","descriptor_name":"Evaluation Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1093/nar/26.4.1107","doi":"https://doi.org/10.1093/nar/26.4.1107","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.4.1107","pdf_url":"https://academic.oup.com/nar/article-pdf/26/4/1107/9469816/26-4-1107.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":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:170125","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC147337","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},{"id":"pmid:9461475","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9461475","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":"Comparative Study"},{"id":"pmh:oai:pubmedcentral.nih.gov:147337","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC147337/","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.23.8895","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.8895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nar.oupjournals.org/cgi/reprint/26/4/1107.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.906.2517","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.906.2517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nar.oxfordjournals.org/content/26/4/1107.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/nar/26.4.1107","doi":"https://doi.org/10.1093/nar/26.4.1107","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.4.1107","pdf_url":"https://academic.oup.com/nar/article-pdf/26/4/1107/9469816/26-4-1107.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":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160053034.pdf","grobid_xml":"https://content.openalex.org/works/W2160053034.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W114794679","https://openalex.org/W1586935683","https://openalex.org/W1608218663","https://openalex.org/W1652691445","https://openalex.org/W1947962930","https://openalex.org/W1971403296","https://openalex.org/W1971912858","https://openalex.org/W1972875046","https://openalex.org/W1981053737","https://openalex.org/W1988171432","https://openalex.org/W1992396120","https://openalex.org/W2006273041","https://openalex.org/W2013570924","https://openalex.org/W2041652393","https://openalex.org/W2051035062","https://openalex.org/W2054016888","https://openalex.org/W2054457669","https://openalex.org/W2100882223","https://openalex.org/W2102122585","https://openalex.org/W2110132014","https://openalex.org/W2134153749","https://openalex.org/W2147694156","https://openalex.org/W2152180708","https://openalex.org/W2158714788","https://openalex.org/W2166187656","https://openalex.org/W4239833500","https://openalex.org/W6600820043","https://openalex.org/W6601163776","https://openalex.org/W6601600055","https://openalex.org/W6815452410"],"related_works":["https://openalex.org/W2106090237","https://openalex.org/W1834463255","https://openalex.org/W2158808847","https://openalex.org/W2604046539","https://openalex.org/W2103919457","https://openalex.org/W7042584917","https://openalex.org/W7097482137","https://openalex.org/W2152430884"],"abstract_inverted_index":{"The":[0,29,50,91],"number":[1],"of":[2,45,87,136,148],"completely":[3],"sequenced":[4],"bacterial":[5,102],"genomes":[6],"has":[7],"been":[8],"growing":[9],"fast.":[10],"There":[11],"are":[12,161],"computer":[13],"methods":[14],"available":[15],"for":[16,25],"finding":[17,46,125],"genes":[18],"but":[19],"yet":[20],"there":[21],"is":[22,111,170],"a":[23,173],"need":[24],"more":[26,113],"accurate":[27,114],"algorithms.":[28],"GeneMark.":[30],"hmm":[31],"algorithm":[32,92,110],"presented":[33],"here":[34],"was":[35,52,93,105,127],"designed":[36],"to":[37,53,84],"improve":[38],"the":[39,55,77,108,122,131,146,156,166],"gene":[40,48,66,119,124],"prediction":[41],"quality":[42],"in":[43,117,130],"terms":[44],"exact":[47,118],"boundaries.":[49],"idea":[51],"embed":[54],"GeneMark":[56,116],"models":[57,135],"into":[58],"naturally":[59],"derived":[60,79],"hidden":[61,72],"Markov":[62,134],"model":[63],"framework":[64],"with":[65,155],"boundaries":[67],"modeled":[68],"as":[69,172],"transitions":[70],"between":[71],"states.":[73],"We":[74,144],"also":[75],"used":[76,171],"specially":[78],"ribosome":[80],"binding":[81],"site":[82],"pattern":[83],"refine":[85],"predictions":[86,154],"translation":[88],"initiation":[89],"codons.":[90],"evaluated":[94],"on":[95],"several":[96],"test":[97],"sets":[98],"including":[99],"10":[100],"complete":[101],"genomes.":[103],"It":[104],"shown":[106],"that":[107,158],"new":[109],"significantly":[112],"than":[115],"prediction.":[120],"Interestingly,":[121],"high":[123],"accuracy":[126],"observed":[128],"even":[129],"case":[132],"when":[133],"order":[137],"zero,":[138],"one":[139],"and":[140,151],"two":[141],"were":[142],"used.":[143],"present":[145],"analysis":[147],"false":[149,152],"positive":[150],"negative":[153],"caution":[157],"these":[159],"categories":[160],"not":[162],"precisely":[163],"defined":[164],"if":[165],"public":[167],"database":[168],"annotation":[169],"control.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":51},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":65},{"year":2017,"cited_by_count":49},{"year":2016,"cited_by_count":59},{"year":2015,"cited_by_count":84},{"year":2014,"cited_by_count":83},{"year":2013,"cited_by_count":76},{"year":2012,"cited_by_count":87}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}
