{"id":"https://openalex.org/W2731293501","doi":"https://doi.org/10.7490/f1000research.1111767.1","title":"Annotation and evidence based functional curation of RefSeq prokaryotic genomes","display_name":"Annotation and evidence based functional curation of RefSeq prokaryotic genomes","publication_year":2016,"publication_date":"2016-04-22","ids":{"openalex":"https://openalex.org/W2731293501","doi":"https://doi.org/10.7490/f1000research.1111767.1","mag":"2731293501"},"language":"en","primary_location":{"id":"doi:10.7490/f1000research.1111767.1","doi":"https://doi.org/10.7490/f1000research.1111767.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1111767.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"other","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7490/f1000research.1111767.1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071346206","display_name":"Kim D. Pruitt","orcid":"https://orcid.org/0000-0001-7950-1374","observed_orcids":["https://orcid.org/0000-0001-7950-1374"]},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kim Pruitt","raw_affiliation_strings":["National Center for Biotechnology Information NLM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information NLM, USA","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048363065","display_name":"Stacy A. Ciufo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stacy Ciufo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075295949","display_name":"Michael N. DiCuccio","orcid":"https://orcid.org/0000-0003-0585-2862","observed_orcids":["https://orcid.org/0000-0003-0585-2862"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael DiCuccio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027242690","display_name":"Daniel H. Haft","orcid":"https://orcid.org/0000-0001-8101-4938","observed_orcids":["https://orcid.org/0000-0001-8101-4938"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Haft","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446278","display_name":"Wenjun Li","orcid":"https://orcid.org/0000-0003-3460-6695","observed_orcids":["https://orcid.org/0000-0003-3460-6695"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113683944","display_name":"Kathleen O\u2019Neill","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kathleen O'Neill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071346206"],"corresponding_institution_ids":["https://openalex.org/I4210109390"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","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":0.9994999766349792,"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":0.9994999766349792,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":9.999999747378752e-05,"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/T11986","display_name":"Scientific Computing and Data Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prokaryotic-genome-annotation","display_name":"prokaryotic genome annotation","score":0.9129999876022339},{"id":"https://openalex.org/keywords/reference-sequences","display_name":"reference sequences","score":0.7110000252723694},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.7519999742507935},{"id":"https://openalex.org/keywords/pfam","display_name":"Pfam","score":0.7179999947547913},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"comparative genomics","score":0.5960000157356262},{"id":"https://openalex.org/keywords/genome-reannotation","display_name":"genome reannotation","score":0.621999979019165},{"id":"https://openalex.org/keywords/swiss-prot","display_name":"Swiss-Prot","score":0.5770000219345093}],"concepts":[{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.9559893608093262},{"id":"https://openalex.org/C2983643791","wikidata":"https://www.wikidata.org/wiki/Q1999993","display_name":"Open peer review","level":3,"score":0.7677760720252991},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5706734657287598},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5509676933288574},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5486767888069153},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5103356242179871},{"id":"https://openalex.org/C2992936677","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Plant biology","level":2,"score":0.4506169557571411},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.40634748339653015},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.35178977251052856},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.34305110573768616},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.33981800079345703},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.3360656499862671},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27111297845840454},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14829528331756592},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.07495006918907166}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.7490/f1000research.1111767.1","doi":"https://doi.org/10.7490/f1000research.1111767.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1111767.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.7490/f1000research.1111767.1","doi":"https://doi.org/10.7490/f1000research.1111767.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1111767.1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050752","display_name":"Faculty of 1000 Research Ltd","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},{"id":"mag:2731293501","doi":null,"is_oa":true,"landing_page_url":"http://f1000research.com/posters/5-731","pdf_url":null,"source":{"id":"https://openalex.org/S4210239046","display_name":"F1000Research","issn_l":"2046-1402","issn":["2046-1402"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320357","host_organization_name":"Faculty of 1000","host_organization_lineage":["https://openalex.org/P4310320357","https://openalex.org/P4310320547"],"host_organization_lineage_names":["Faculty of 1000","Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":"F1000Research","raw_type":null}],"best_oa_location":{"id":"doi:10.7490/f1000research.1111767.1","doi":"https://doi.org/10.7490/f1000research.1111767.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1111767.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2766648240","https://openalex.org/W4388652965","https://openalex.org/W3109735703","https://openalex.org/W2173732482","https://openalex.org/W2165770381","https://openalex.org/W2107903949","https://openalex.org/W4404225843","https://openalex.org/W2013447902","https://openalex.org/W2042160423","https://openalex.org/W3006515984"],"abstract_inverted_index":{"The":[0,307,411],"National":[1],"Center":[2],"for":[3,62,66,82,111,138,242,340,388,422,448],"Biotechnology":[4],"Information":[5],"(NCBI)":[6],"has":[7],"developed":[8,41],"a":[9,19,45,93,108,134,181,259,446],"robust":[10],"prokaryotic":[11,30,85,99,140,155,166,206,222,418],"genome":[12,156,423],"annotation":[13,33,36,51,59,147,157,174,186,424,431,436],"pipeline":[14,34],"which":[15,39,74,188],"is":[16,25,305],"offered":[17],"as":[18],"service":[20],"to":[21,27,124,133,230,318,335,399],"GenBank":[22],"submitters":[23],"and":[24,50,70,80,84,118,146,159,177,239,255,276,281,294,296,332,359,384,425,430,441,445],"used":[26,76],"annotate":[28],"RefSeq":[29,81,90,165,183,205,221,247,308,365,406,417],"genomes.":[31,86,167],"NCBI\u2019s":[32,154,312],"integrates":[35],"quality":[37,60,148,218,432],"standards":[38,65],"were":[40],"in":[42,153,198,409,454],"part":[43],"through":[44],"series":[46],"of":[47,95,107,130,163,201,219,245,252,343,354,363,381,394,435,451,457],"microbial":[48],"assembly":[49,145,429],"workshops":[52,57],"held":[53],"by":[54,77,283],"NCBI.":[55],"These":[56,103,168],"defined":[58],"criteria":[61,196],"complete":[63],"genomes,":[64],"reporting":[67,401,449],"support":[68,231,356,370,386],"evidence,":[69,176],"protein":[71,114,126,141,232,253,366,407],"naming":[72],"protocols":[73],"are":[75,297],"UniProt,":[78],"GenBank,":[79],"eukaryotic":[83],"In":[87],"2015":[88],"the":[89,98,131,172,199,220,246,277,337,352,355,361,372,376,382,389,392,395,415,455],"project":[91],"implemented":[92],"number":[94],"changes":[96],"impacting":[97],"genomes":[100,207,223,419],"data":[101,136,273],"set.":[102],"include:":[104],"a)":[105],"development":[106],"new":[109,135,228,299],"framework":[110],"evidence":[112,119,257,357,403,453],"based":[113,322],"naming,":[115],"name":[116,178,233,256,272,348,373,390],"curation,":[117,234,444],"tracking;":[120],"b)":[121],"increased":[122,151],"collaboration":[123,440],"improve":[125],"names;":[127],"c)":[128],"completion":[129],"transition":[132],"model":[137],"managing":[139],"sequences;":[142],"d)":[143],"expanded":[144],"testing;":[149],"e)":[150],"capacity":[152],"pipeline;":[158],"f)":[160],"comprehensive":[161],"reannotation":[162],"all":[164,385],"developments":[169],"expand":[170],"on":[171,226,323,405],"established":[173,237],"QA,":[175],"standards.":[179],"As":[180],"result,":[182],"provides":[184],"significant":[185],"consistency":[187],"facilitates":[189],"comparative":[190],"genomics.":[191],"Our":[192],"more":[193],"rigorous":[194],"QA":[195],"resulted":[197],"suppression":[200],"over":[202],"two":[203],"thousand":[204],"that":[208,262],"do":[209],"not":[210],"meet":[211],"these":[212],"criteria,":[213,433],"thus":[214,249],"ensuring":[215],"continued":[216],"high":[217],"dataset.":[224],"Based":[225],"our":[227,427],"infrastructure":[229],"we":[235],"have":[236],"evidence-based":[238],"tracked":[240],"names":[241,254,321,339],"approximately":[243],"25%":[244],"proteins":[248],"far.":[250],"Curation":[251],"uses":[258],"multi-faceted":[260],"approach":[261],"leverages":[263],"Hidden":[264],"Markov":[265],"Models":[266],"(HMMs),":[267,358],"domain":[268,325],"architectures,":[269],"available":[270],"curated":[271],"from":[274,289,439],"Swiss-Prot":[275],"Enzyme":[278],"Commission,":[279],"collaboration,":[280],"curation":[282],"NCBI":[284,345,442,458],"staff.":[285],"We":[286,327,397],"use":[287],"HMMs":[288,300],"several":[290],"sources":[291],"including":[292],"TIGRfams":[293],"Pfams,":[295],"creating":[298],"(NCBIfams)":[301],"when":[302],"further":[303],"refinement":[304],"needed.":[306],"group":[309,317],"collaborates":[310],"with":[311,329],"Conserved":[313],"Domains":[314],"Database":[315,368],"(CDD)":[316],"provide":[319,336],"functional":[320,402,452],"reviewed":[324],"architectures.":[326],"collaborate":[328],"individual":[330,364],"scientists":[331],"expert":[333],"databases":[334],"best":[338],"some":[341],"classes":[342],"proteins.":[344],"staff":[346,443],"curate":[347],"information":[349,404],"both":[350],"at":[351,360,391],"level":[353,362],"names.":[367],"tables":[369],"tracking":[371],"update":[374],"history,":[375],"biocurator":[377],"or":[378],"collaborator":[379],"source":[380],"update,":[383],"evidences":[387],"time":[393],"update.":[396],"plan":[398],"start":[400],"records":[408],"2016.":[410],"presentation":[412],"will":[413],"summarize":[414],"current":[416,428],"process":[420],"flows":[421],"curation/collaboration,":[426],"examples":[434],"improvements":[437],"resulting":[438],"proposal":[447],"sets":[450],"context":[456],"sequence":[459],"displays.":[460]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2017-07-14T00:00:00"}
