{"id":"https://openalex.org/W2097959219","doi":"https://doi.org/10.1093/bioinformatics/btg219","title":"A comparative analysis of HGSC and Celera human genome assemblies and gene sets","display_name":"A comparative analysis of HGSC and Celera human genome assemblies and gene sets","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2097959219","doi":"https://doi.org/10.1093/bioinformatics/btg219","mag":"2097959219","pmid":"https://pubmed.ncbi.nlm.nih.gov/12967954"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/13/1597/48930050/bioinformatics_19_13_1597.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/19/13/1597/48930050/bioinformatics_19_13_1597.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100733002","display_name":"Shuyu Li","orcid":"https://orcid.org/0000-0002-3402-4903"},"institutions":[{"id":"https://openalex.org/I1315708478","display_name":"San Francisco VA Medical Center","ror":"https://ror.org/049peqw80","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315708478","https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210125474","https://openalex.org/I4210143381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuyu Li","raw_affiliation_strings":["Tularik, Inc 112 Veterans Blvd, South San Francisco, CA 94080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tularik, Inc 112 Veterans Blvd, South San Francisco, CA 94080, USA","institution_ids":["https://openalex.org/I1315708478"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044725190","display_name":"Gene Cutler","orcid":"https://orcid.org/0000-0002-0885-8904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gene Cutler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002289370","display_name":"Jane Jijun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane Jijun Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079033247","display_name":"Timothy Hoey","orcid":"https://orcid.org/0000-0001-7066-015X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Hoey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032598180","display_name":"Liangbiao Chen","orcid":"https://orcid.org/0000-0002-0717-8536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangbiao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066008654","display_name":"Peter G. Schultz","orcid":"https://orcid.org/0000-0003-3188-1202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter G. Schultz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114231640","display_name":"Jiayu Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayu Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009212787","display_name":"Xuefeng B. Ling","orcid":"https://orcid.org/0000-0002-5386-3884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuefeng Bruce Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100733002"],"corresponding_institution_ids":["https://openalex.org/I1315708478"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6874,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.67804361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"19","issue":"13","first_page":"1597","last_page":"1605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ensembl","display_name":"Ensembl","score":0.9117245674133301},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7505918741226196},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.7134836316108704},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6904021501541138},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6655400395393372},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5705180764198303},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.5463172197341919},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5192192196846008},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5184714198112488},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5115078687667847},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"Comparative genomics","score":0.4783489406108856},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.40931856632232666},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.07413756847381592},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.04987320303916931}],"concepts":[{"id":"https://openalex.org/C141674004","wikidata":"https://www.wikidata.org/wiki/Q1344256","display_name":"Ensembl","level":5,"score":0.9117245674133301},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7505918741226196},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.7134836316108704},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6904021501541138},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6655400395393372},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5705180764198303},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.5463172197341919},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5192192196846008},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5184714198112488},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5115078687667847},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.4783489406108856},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.40931856632232666},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.07413756847381592},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.04987320303916931}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","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":"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016045","descriptor_name":"Human Genome Project","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016045","descriptor_name":"Human Genome Project","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016045","descriptor_name":"Human Genome Project","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","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},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/13/1597/48930050/bioinformatics_19_13_1597.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:12967954","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12967954","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/13/1597/48930050/bioinformatics_19_13_1597.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":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1992404301","https://openalex.org/W1996231070","https://openalex.org/W2004375653","https://openalex.org/W2050923959","https://openalex.org/W2054527274","https://openalex.org/W2099784985","https://openalex.org/W2109656602","https://openalex.org/W2123619788","https://openalex.org/W2124259172","https://openalex.org/W2127230663","https://openalex.org/W2131581981","https://openalex.org/W2136145671","https://openalex.org/W2141885858","https://openalex.org/W2142414282","https://openalex.org/W2151831732","https://openalex.org/W2158714788","https://openalex.org/W2165270659","https://openalex.org/W2166187656","https://openalex.org/W2171856761"],"related_works":["https://openalex.org/W2281531600","https://openalex.org/W4383818008","https://openalex.org/W2510847435","https://openalex.org/W1527507758","https://openalex.org/W4210830088","https://openalex.org/W2128024232","https://openalex.org/W2166654698","https://openalex.org/W2213265806","https://openalex.org/W2155490504","https://openalex.org/W2002883632"],"abstract_inverted_index":{"MOTIVATION:":[0],"Since":[1,152],"the":[2,6,11,47,69,78,81,131,155,167,173,188,192],"simultaneous":[3],"publication":[4],"of":[5,26,29,46,80,87,92,109,138,154],"human":[7],"genome":[8,63,102,160],"assembly":[9,83,161],"by":[10],"International":[12],"Human":[13],"Genome":[14],"Sequencing":[15],"Consortium":[16],"(HGSC)":[17],"and":[18,50,190],"Celera":[19,82],"Genomics,":[20],"several":[21],"comparisons":[22],"have":[23],"been":[24,66],"made":[25],"various":[27],"aspects":[28],"these":[30],"two":[31,48],"assemblies.":[32],"In":[33],"this":[34],"work,":[35],"we":[36,170],"set":[37,142,175],"out":[38],"to":[39,84,166],"provide":[40],"a":[41,75,139],"more":[42,126],"comprehensive":[43],"comparative":[44],"analysis":[45],"assemblies":[49,64,189],"their":[51],"associated":[52],"gene":[53,128,133,141,174],"sets.":[54],"RESULTS:":[55],"The":[56,136],"local":[57,182],"sequence":[58,183],"content":[59,184],"for":[60,77],"both":[61,118,150],"draft":[62],"has":[65,143],"similar":[67,107],"since":[68],"early":[70],"releases,":[71],"however":[72],"it":[73],"took":[74],"year":[76],"quality":[79],"approach":[85,122],"that":[86,172],"HGSC,":[88],"suggesting":[89],"an":[90],"advantage":[91],"HGSC's":[93],"hierarchical":[94],"shotgun":[95,103],"(HS)":[96],"sequencing":[97],"strategy":[98],"over":[99],"Celera's":[100,120],"whole":[101],"(WGS)":[104],"approach.":[105],"While":[106],"numbers":[108],"ab":[110],"initio":[111],"predicted":[112],"genes":[113,157],"can":[114],"be":[115,163],"derived":[116],"from":[117,149,158],"assemblies,":[119],"Otto":[121],"consistently":[123],"generated":[124],"larger,":[125],"varied":[127],"sets":[129],"than":[130],"Ensembl":[132],"build":[134],"system.":[135],"presence":[137],"non-overlapping":[140],"persisted":[144],"with":[145],"successive":[146],"data":[147],"releases":[148],"groups.":[151],"most":[153],"unique":[156],"either":[159],"could":[162],"mapped":[164],"back":[165],"other":[168],"assembly,":[169],"conclude":[171],"discrepancies":[176],"do":[177],"not":[178],"reflect":[179],"differences":[180],"in":[181,187],"but":[185],"rather":[186],"especially":[191],"different":[193],"gene-prediction":[194],"methodologies.":[195]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
