{"id":"https://openalex.org/W4414509253","doi":"https://doi.org/10.1093/database/baaf045","title":"The state of the human coding gene catalogues","display_name":"The state of the human coding gene catalogues","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414509253","doi":"https://doi.org/10.1093/database/baaf045","pmid":"https://pubmed.ncbi.nlm.nih.gov/40996716"},"language":"en","primary_location":{"id":"doi:10.1093/database/baaf045","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf045","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf045/64394874/baaf045.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf045/64394874/baaf045.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114658859","display_name":"Miguel Maquedano","orcid":"https://orcid.org/0009-0001-2460-4429"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Miguel Maquedano","raw_affiliation_strings":["Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001297339","display_name":"Daniel Cerd\u00e1n-V\u00e9lez","orcid":"https://orcid.org/0000-0003-4499-6201"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Daniel Cerd\u00e1n-V\u00e9lez","raw_affiliation_strings":["Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088945131","display_name":"Michael L. Tress","orcid":"https://orcid.org/0000-0001-9046-6370"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Michael L Tress","raw_affiliation_strings":["Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,"],"raw_orcid":"https://orcid.org/0000-0001-9046-6370","affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, Spanish National Cancer Research Centre (CNIO), Calle Melchor Fernandez Almagro , 3, 28029 Madrid ,","institution_ids":["https://openalex.org/I4210089594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114658859"],"corresponding_institution_ids":["https://openalex.org/I4210089594"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":1.4227,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83521204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"2025","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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":0.9994000196456909,"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/T11482","display_name":"RNA modifications and cancer","score":0.9958999752998352,"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":0.9958999752998352,"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/coding","display_name":"Coding (social sciences)","score":0.7901999950408936},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.6434999704360962},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.6129999756813049},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.4683000147342682},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.4431000053882599}],"concepts":[{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.7901999950408936},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.6129999756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5953999757766724},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.4683000147342682},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4431000053882599},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.33959999680519104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25099998712539673}],"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":"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":"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":"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":"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":"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":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/database/baaf045","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf045","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf045/64394874/baaf045.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:40996716","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40996716","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:europepmc.org:11271103","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12462614","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12462614","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12462614/","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baaf045","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf045","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf045/64394874/baaf045.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1905050360","display_name":null,"funder_award_id":"HG007234","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6997730276","display_name":null,"funder_award_id":"U41 HG007234","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414509253.pdf","grobid_xml":"https://content.openalex.org/works/W4414509253.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1604834232","https://openalex.org/W1973609313","https://openalex.org/W1988974499","https://openalex.org/W1994847588","https://openalex.org/W1997113958","https://openalex.org/W1998623279","https://openalex.org/W2002539556","https://openalex.org/W2003219506","https://openalex.org/W2005120335","https://openalex.org/W2012034410","https://openalex.org/W2024594909","https://openalex.org/W2033362920","https://openalex.org/W2055043387","https://openalex.org/W2072327326","https://openalex.org/W2089627071","https://openalex.org/W2092170757","https://openalex.org/W2108736057","https://openalex.org/W2120892748","https://openalex.org/W2126297491","https://openalex.org/W2127230663","https://openalex.org/W2127982470","https://openalex.org/W2131636453","https://openalex.org/W2135917681","https://openalex.org/W2139658526","https://openalex.org/W2147948271","https://openalex.org/W2161811833","https://openalex.org/W2168909179","https://openalex.org/W2172189660","https://openalex.org/W2178557511","https://openalex.org/W2264540270","https://openalex.org/W2415174329","https://openalex.org/W2417483443","https://openalex.org/W2542446037","https://openalex.org/W2605215238","https://openalex.org/W2810156064","https://openalex.org/W2824109127","https://openalex.org/W2996375460","https://openalex.org/W3016860841","https://openalex.org/W3021759774","https://openalex.org/W3028516693","https://openalex.org/W3048028982","https://openalex.org/W3133859624","https://openalex.org/W3198652121","https://openalex.org/W3214315533","https://openalex.org/W4220999759","https://openalex.org/W4224014283","https://openalex.org/W4285084440","https://openalex.org/W4296780093","https://openalex.org/W4306698946","https://openalex.org/W4306804088","https://openalex.org/W4307843054","https://openalex.org/W4308834638","https://openalex.org/W4309506674","https://openalex.org/W4365133590","https://openalex.org/W4376133202","https://openalex.org/W4386113054","https://openalex.org/W4388022000","https://openalex.org/W4388615950","https://openalex.org/W4389367121","https://openalex.org/W4392287022","https://openalex.org/W4396721167","https://openalex.org/W4396835689","https://openalex.org/W4399045473","https://openalex.org/W4403988423","https://openalex.org/W4404408324","https://openalex.org/W4404434589","https://openalex.org/W4404535307","https://openalex.org/W4404733368"],"related_works":[],"abstract_inverted_index":{"In":[0,183],"2018,":[1],"we":[2,54,101,185],"analysed":[3],"the":[4,9,19,25,57,63,90,106,121,129,171],"three":[5,20,64,75,107],"main":[6],"repositories":[7],"for":[8,174],"human":[10],"proteome:":[11],"Ensembl/GENCODE,":[12],"RefSeq,":[13],"and":[14,36,86,198],"UniProtKB.":[15],"At":[16],"that":[17,40,103,143,158,187],"time":[18],"gene":[21,66,109],"sets":[22,76,110],"disagreed":[23],"on":[24,89,120,180],"coding":[26,34,80,122,147,163,181,197],"status":[27,91,123],"of":[28,30,45,62,92,124,170],"one":[29,97,152],"every":[31],"eight":[32],"annotated":[33,94,201],"genes,":[35,81,95,204],"our":[37],"results":[38],"suggested":[39],"as":[41,43,188,190,196,202],"many":[42,189],"4234":[44],"these":[46],"genes":[47,127,136,148,173,192],"might":[48],"not":[49,161,178],"be":[50,162,194,200],"correctly":[51],"classified.":[52],"Here,":[53],"have":[55,72,111,118,137],"repeated":[56],"analysis":[58,131],"with":[59,149],"updated":[60],"versions":[61],"reference":[65,108],"sets.":[67],"Superficially,":[68],"little":[69],"appears":[70],"to":[71,113,156],"changed.":[73],"The":[74],"annotate":[77],"21":[78],"871":[79],"slightly":[82],"fewer":[83],"than":[84],"previously,":[85],"still":[87,141],"disagree":[88],"2603":[93,172],"almost":[96],"in":[98],"eight.":[99],"However,":[100],"show":[102],"collaborations":[104],"between":[105],"led":[112],"greater":[114],"consensus.":[115],"Reference":[116],"catalogues":[117],"agreed":[119],"another":[125],"249":[126],"since":[128],"last":[130],"while":[132],"at":[133,150],"least":[134,151],"700":[135],"been":[138],"reclassified.":[139],"We":[140],"find":[142],"there":[144],"are":[145],">2000":[146],"potential":[153],"non-coding":[154,203],"feature":[155],"indicate":[157],"they":[159],"may":[160,193],"genes.":[164],"This":[165],"includes":[166],"a":[167],"large":[168],"majority":[169],"which":[175],"annotators":[176],"do":[177],"agree":[179],"status.":[182],"total,":[184],"believe":[186],"3000":[191],"misclassified":[195],"could":[199],"pseudogenes,":[205],"or":[206],"cancer":[207],"antigens.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}
