{"id":"https://openalex.org/W2129319388","doi":"https://doi.org/10.1093/bioinformatics/bth028","title":"Effects of choice of DNA sequence model structure on gene identification accuracy","display_name":"Effects of choice of DNA sequence model structure on gene identification accuracy","publication_year":2004,"publication_date":"2004-01-29","ids":{"openalex":"https://openalex.org/W2129319388","doi":"https://doi.org/10.1093/bioinformatics/bth028","mag":"2129319388","pmid":"https://pubmed.ncbi.nlm.nih.gov/14751980"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth028","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth028","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/7/993/48905345/bioinformatics_20_7_993.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/20/7/993/48905345/bioinformatics_20_7_993.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042126172","display_name":"Rajeev K. Azad","orcid":"https://orcid.org/0000-0002-6874-6146"},"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":"Rajeev K. Azad","raw_affiliation_strings":["School of Biology, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","School of Biology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biology, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Biology#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057317686","display_name":"Mark Borodovsky","orcid":"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Borodovsky","raw_affiliation_strings":["School of Biology and","School of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","School of Biology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biology and","institution_ids":[]},{"raw_affiliation_string":"School of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0230, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Biology#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042126172"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0777,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.75214951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"7","first_page":"993","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.994700014591217,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9926000237464905,"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/identification","display_name":"Identification (biology)","score":0.6868957281112671},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6580669283866882},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6564916372299194},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5781553983688354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47586411237716675},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4637625217437744},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.44761592149734497},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.40133166313171387},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.32799679040908813},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3025796413421631}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6868957281112671},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6580669283866882},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6564916372299194},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5781553983688354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47586411237716675},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4637625217437744},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.44761592149734497},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.40133166313171387},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.32799679040908813},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3025796413421631},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","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":"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":"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":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","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":"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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth028","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth028","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/7/993/48905345/bioinformatics_20_7_993.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:14751980","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14751980","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.103.4415","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.103.4415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/20/7/993.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth028","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth028","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/7/993/48905345/bioinformatics_20_7_993.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/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2129319388.pdf","grobid_xml":"https://content.openalex.org/works/W2129319388.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W183862812","https://openalex.org/W1597533204","https://openalex.org/W1966812932","https://openalex.org/W1976812874","https://openalex.org/W1992300521","https://openalex.org/W1994920552","https://openalex.org/W2032870665","https://openalex.org/W2039680623","https://openalex.org/W2095963120","https://openalex.org/W2106090237","https://openalex.org/W2133253129","https://openalex.org/W2134237567","https://openalex.org/W2154478075","https://openalex.org/W2160053034","https://openalex.org/W2618338767","https://openalex.org/W2981264952","https://openalex.org/W4251659808"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W623104033","https://openalex.org/W1972473893","https://openalex.org/W2466435674","https://openalex.org/W2765200542","https://openalex.org/W2367893528","https://openalex.org/W3107784576"],"abstract_inverted_index":{"MOTIVATION:":[0],"Markov":[1,51],"chain":[2,52],"models":[3,58,60,104,113,157],"of":[4,16,30,47,50,66,80,82,93],"DNA":[5,87,120,146],"sequences":[6,88,121],"have":[7,44],"frequently":[8],"been":[9,37],"used":[10],"in":[11,74,85,96,114,118,125,131,134,162],"gene":[12],"finding":[13],"algorithms.":[14],"Performance":[15],"the":[17,22,28,32,64,67,78,91,103,126,156],"algorithm":[18],"critically":[19],"depends":[20],"on":[21],"model":[23,33],"structure":[24,34],"and":[25,59,89,129,143],"parameters.":[26],"Still,":[27],"issue":[29],"choosing":[31],"has":[35],"not":[36],"studied":[38],"with":[39,61,122,137,147],"sufficient":[40],"attention.":[41],"RESULTS:":[42],"We":[43,100],"assessed":[45],"performance":[46,71],"several":[48],"types":[49],"models,":[53],"both":[54],"fixed":[55],"order":[56],"(FO)":[57],"interpolation,":[62],"within":[63],"framework":[65],"GeneMark":[68],"algorithm.":[69],"The":[70],"was":[72],"measured":[73],"two":[75],"ways:":[76],"(i)":[77],"accuracy":[79,92],"detection":[81],"protein-coding":[83,116],"potential":[84,117],"artificial":[86,119,142],"(ii)":[90],"identifying":[94],"genes":[95,133],"real":[97,135,144],"prokaryotic":[98],"genomes.":[99],"observed":[101,154],"that":[102,155],"built":[105,158],"by":[106,159,167],"deleted":[107],"interpolation":[108],"(DI)":[109],"slightly":[110,165],"outperformed":[111,166],"other":[112],"detecting":[115,132],"GC":[123,139,151],"content":[124],"medium":[127,138],"range":[128],"also":[130],"genomes":[136],"content.":[140],"For":[141],"genomic":[145],"high":[148],"or":[149],"low":[150],"content,":[152],"we":[153],"DI":[160],"were":[161],"some":[163],"cases":[164],"FO":[168],"models.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
