{"id":"https://openalex.org/W2119566134","doi":"https://doi.org/10.1109/csb.2003.1227366","title":"On gene prediction by cross-species comparative sequence analysis","display_name":"On gene prediction by cross-species comparative sequence analysis","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2119566134","doi":"https://doi.org/10.1109/csb.2003.1227366","mag":"2119566134"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5027593470","display_name":"R. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. Chen","raw_affiliation_strings":["Department of Computer Science College of Information Science and Technology, University of Nebraska Omaha, Omaha, NE, USA","Dept. of Comput. Sci., Nebraska Univ., Omaha, NE, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science College of Information Science and Technology, University of Nebraska Omaha, Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Nebraska Univ., Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047703641","display_name":"Hesham Ali","orcid":"https://orcid.org/0000-0001-6675-7987"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Ali","raw_affiliation_strings":["Department of Computer Science College of Information Science and Technology, University of Nebraska Omaha, Omaha, NE, USA","Dept. of Comput. Sci., Nebraska Univ., Omaha, NE, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science College of Information Science and Technology, University of Nebraska Omaha, Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Nebraska Univ., Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027593470"],"corresponding_institution_ids":["https://openalex.org/I122266389"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9995999932289124,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9995999932289124,"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":0.9979000091552734,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9975000023841858,"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/computational-biology","display_name":"Computational biology","score":0.5972216129302979},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5538670420646667},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5531877875328064},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.545111894607544},{"id":"https://openalex.org/keywords/intron","display_name":"Intron","score":0.5399681329727173},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.49348747730255127},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4895728528499603},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.4871525466442108},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.479775995016098},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.43483415246009827},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4192749857902527},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.3501776456832886},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.12723127007484436}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5972216129302979},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5538670420646667},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5531877875328064},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.545111894607544},{"id":"https://openalex.org/C94671646","wikidata":"https://www.wikidata.org/wiki/Q207551","display_name":"Intron","level":3,"score":0.5399681329727173},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.49348747730255127},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4895728528499603},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.4871525466442108},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.479775995016098},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.43483415246009827},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4192749857902527},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3501776456832886},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.12723127007484436}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2003.1227366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.75,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1864675704","https://openalex.org/W1966833356","https://openalex.org/W2105360191","https://openalex.org/W2107499729","https://openalex.org/W2116688916","https://openalex.org/W2130043776","https://openalex.org/W2153632714","https://openalex.org/W2166187656","https://openalex.org/W6676277162"],"related_works":["https://openalex.org/W1510144579","https://openalex.org/W1973164572","https://openalex.org/W2094547232","https://openalex.org/W1972489850","https://openalex.org/W2057750912","https://openalex.org/W2137491265","https://openalex.org/W2109672343","https://openalex.org/W2077151220","https://openalex.org/W2352103023","https://openalex.org/W2367171471"],"abstract_inverted_index":{"Sequencing":[0],"of":[1,4,13,18,27,31,41,43,73,90,100,108],"large":[2],"fragments":[3],"genomic":[5,14,29],"DNA":[6],"makes":[7],"it":[8],"possible":[9],"to":[10,116],"perform":[11],"comparisons":[12],"sequences":[15,30,83,89,126],"for":[16],"identification":[17],"protein-coding":[19],"regions.":[20],"We":[21],"have":[22],"conducted":[23],"a":[24,78],"comparative":[25],"analysis":[26],"homologous":[28],"organisms":[32,145],"with":[33],"different":[34],"evolutionary":[35,135],"distances":[36],"and":[37,71,95,110,112],"determined":[38],"the":[39,44,64,101],"degree":[40],"conservation":[42,62],"noncoding":[45],"regions":[46],"between":[47],"closely":[48],"related":[49],"organisms.":[50],"In":[51],"contrast,":[52],"more":[53],"distance":[54],"shows":[55],"much":[56],"less":[57,61],"intron":[58],"similarity":[59],"but":[60],"on":[63,68],"exon":[65],"structures.":[66],"Based":[67],"this":[69,137],"finding":[70],"training":[72],"data":[74],"sets,":[75],"we":[76],"proposed":[77,102],"model":[79],"by":[80,87,119],"which":[81],"coding":[82],"could":[84,139],"be":[85,128,140],"identified":[86],"comparing":[88],"multiple":[91],"species,":[92],"both":[93],"close":[94],"approximately":[96],"distant.":[97],"The":[98],"reliability":[99],"method":[103],"is":[104],"evaluated":[105],"in":[106,142],"terms":[107],"sensitivity":[109],"specificity,":[111],"results":[113],"are":[114,151],"compared":[115],"those":[117],"obtained":[118],"other":[120,131],"popular":[121],"gene":[122],"prediction":[123],"programs.":[124],"Provided":[125],"can":[127],"found":[129],"from":[130],"species":[132],"at":[133],"appropriate":[134],"distances,":[136],"approach":[138],"applied":[141],"newly":[143],"sequenced":[144],"where":[146],"no":[147],"species-dependent":[148],"statistical":[149],"models":[150],"available.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}