{"id":"https://openalex.org/W2082627456","doi":"https://doi.org/10.1504/ijdmb.2009.024849","title":"Computational identification of protein-coding sequences by comparative analysis","display_name":"Computational identification of protein-coding sequences by comparative analysis","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2082627456","doi":"https://doi.org/10.1504/ijdmb.2009.024849","mag":"2082627456","pmid":"https://pubmed.ncbi.nlm.nih.gov/19517987"},"language":"en","primary_location":{"id":"doi:10.1504/ijdmb.2009.024849","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijdmb.2009.024849","pdf_url":null,"source":{"id":"https://openalex.org/S35771696","display_name":"International Journal of Data Mining and Bioinformatics","issn_l":"1748-5673","issn":["1748-5673","1748-5681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Mining and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111934795","display_name":"Arnaud Fontaine","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210160005","display_name":"Computer Science Laboratory of Lille","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210160005"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Arnaud Fontaine","raw_affiliation_strings":["LIFL-UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France. arnaud.fontaine@lifl.fr","LIFL &dash; UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIFL-UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France. arnaud.fontaine@lifl.fr","institution_ids":["https://openalex.org/I4210160005","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIFL &dash; UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210138412","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049507162","display_name":"H\u00e9l\u00e8ne Touzet","orcid":"https://orcid.org/0000-0001-5305-9987"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Helene Touzet","raw_affiliation_strings":["LIFL \u2010 UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France","LIFL &dash; UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIFL \u2010 UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIFL &dash; UMR CNRS 8022 University Lille 1, INRIA Lille Nord Europe, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210138412","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111934795"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210138412","https://openalex.org/I4210160005"],"apc_list":null,"apc_paid":null,"fwci":0.5249,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.65857755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"2","first_page":"160","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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":0.996399998664856,"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/genome","display_name":"Genome","score":0.6593974232673645},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"Comparative genomics","score":0.6353360414505005},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.6154512763023376},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5890329480171204},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5647062063217163},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5324336886405945},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4776785969734192},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.45131492614746094},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.43585485219955444},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.417923241853714},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4152846038341522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.33319616317749023},{"id":"https://openalex.org/keywords/phenotype","display_name":"Phenotype","score":0.0851794183254242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08370864391326904}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6593974232673645},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.6353360414505005},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.6154512763023376},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5890329480171204},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5647062063217163},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5324336886405945},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4776785969734192},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.45131492614746094},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.43585485219955444},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.417923241853714},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4152846038341522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33319616317749023},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0851794183254242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08370864391326904},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1504/ijdmb.2009.024849","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijdmb.2009.024849","pdf_url":null,"source":{"id":"https://openalex.org/S35771696","display_name":"International Journal of Data Mining and Bioinformatics","issn_l":"1748-5673","issn":["1748-5673","1748-5681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Mining and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19517987","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19517987","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":"International journal of data mining and bioinformatics","raw_type":null},{"id":"pmh:oai:HAL:hal-00823601v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00823601","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Data Mining and Bioinformatics, 2009, 3 (2), pp.160-76. &#x27E8;10.1504/ijdmb.2009.024849&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1822105579","https://openalex.org/W1966153097","https://openalex.org/W1974736226","https://openalex.org/W1986014242","https://openalex.org/W1996700726","https://openalex.org/W2008900336","https://openalex.org/W2016839209","https://openalex.org/W2034767282","https://openalex.org/W2039925764","https://openalex.org/W2042881722","https://openalex.org/W2057998009","https://openalex.org/W2070510621","https://openalex.org/W2074231493","https://openalex.org/W2085412309","https://openalex.org/W2087892194","https://openalex.org/W2096525273","https://openalex.org/W2106882534","https://openalex.org/W2108787198","https://openalex.org/W2108871359","https://openalex.org/W2112132489","https://openalex.org/W2113000643","https://openalex.org/W2127346557","https://openalex.org/W2128599049","https://openalex.org/W2128607924","https://openalex.org/W2131074700","https://openalex.org/W2136280642","https://openalex.org/W2137144878","https://openalex.org/W2141847640","https://openalex.org/W2143210482","https://openalex.org/W2145191876","https://openalex.org/W2146703483","https://openalex.org/W2148004368","https://openalex.org/W2158714788","https://openalex.org/W2159833474","https://openalex.org/W2161529001","https://openalex.org/W2162264429","https://openalex.org/W2163860567","https://openalex.org/W2166187656","https://openalex.org/W2168783124","https://openalex.org/W2213701196"],"related_works":["https://openalex.org/W1565527690","https://openalex.org/W1493660383","https://openalex.org/W2759519215","https://openalex.org/W2353729507","https://openalex.org/W4318240630","https://openalex.org/W2350466590","https://openalex.org/W1542620732","https://openalex.org/W3031625301","https://openalex.org/W4386771068","https://openalex.org/W2080758876"],"abstract_inverted_index":{"Gene":[0],"prediction":[1],"is":[2,29,84],"an":[3],"essential":[4],"step":[5],"in":[6,23,48,73],"understanding":[7],"the":[8,55,64,102],"genome":[9],"of":[10,54,59,66,101],"a":[11,20,30,39,74,88],"species":[12],"once":[13],"it":[14],"has":[15,70],"been":[16,71],"sequenced.":[17],"For":[18],"that,":[19],"promising":[21],"direction":[22],"current":[24],"research":[25],"on":[26,95],"gene":[27],"finding":[28],"comparative":[31],"genomics":[32],"approach.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38],"novel":[40],"approach":[41],"to":[42,86,91],"identifying":[43],"evolutionarily":[44],"conserved":[45],"protein-coding":[46],"sequences":[47,61],"genomes.":[49],"The":[50],"method":[51],"takes":[52],"advantage":[53],"specific":[56],"substitution":[57],"pattern":[58],"coding":[60],"together":[62],"with":[63],"consistency":[65],"reading":[67],"frames.":[68],"It":[69],"implemented":[72],"software":[75],"called":[76],"PROTEA.":[77],"Large-scale":[78],"experimentation":[79],"shows":[80],"good":[81],"results.":[82],"PROTEA":[83],"intended":[85],"be":[87],"useful":[89],"complement":[90],"existing":[92],"tools":[93],"based":[94],"homology":[96],"search":[97],"or":[98],"statistical":[99],"properties":[100],"sequences.":[103]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
