{"id":"https://openalex.org/W6929948304","doi":"https://doi.org/10.5281/zenodo.10016500","title":"Datasets and Scripts associated with \"Cryptic endogenous retrovirus subfamilies in the primate lineage\"","display_name":"Datasets and Scripts associated with \"Cryptic endogenous retrovirus subfamilies in the primate lineage\"","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W6929948304","doi":"https://doi.org/10.5281/zenodo.10016500"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10016500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10016500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10016500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen, Xun","orcid":"https://orcid.org/0000-0003-0327-1888"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chen, Xun","raw_affiliation_strings":["Kyoto University"],"raw_orcid":"https://orcid.org/0000-0003-0327-1888","affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zicong","orcid":"https://orcid.org/0000-0003-1444-5054"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhang, Zicong","raw_affiliation_strings":["Kyoto University"],"raw_orcid":"https://orcid.org/0000-0003-1444-5054","affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan, Yizhi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yizhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Goubert, Cl\u00e9ment","orcid":"https://orcid.org/0000-0001-8034-5559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goubert, Cl\u00e9ment","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8034-5559","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bourque, Guillaume","orcid":"https://orcid.org/0000-0002-3933-9656"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bourque, Guillaume","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3933-9656","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Inoue, Fumitaka","orcid":"https://orcid.org/0000-0003-0657-434X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Inoue, Fumitaka","raw_affiliation_strings":["Kyoto University"],"raw_orcid":"https://orcid.org/0000-0003-0657-434X","affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11237","display_name":"Plant Gene Expression Analysis","score":0.18240000307559967,"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/T11237","display_name":"Plant Gene Expression Analysis","score":0.18240000307559967,"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/T12620","display_name":"Signaling Pathways in Disease","score":0.07900000363588333,"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/T11041","display_name":"Ubiquitin and proteasome pathways","score":0.05869999900460243,"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/endogenous-retrovirus","display_name":"Endogenous retrovirus","score":0.8549000024795532},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6736999750137329},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.6294999718666077},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6283000111579895},{"id":"https://openalex.org/keywords/long-terminal-repeat","display_name":"Long terminal repeat","score":0.5774000287055969},{"id":"https://openalex.org/keywords/retrovirus","display_name":"Retrovirus","score":0.4740000069141388},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"Phylogenetics","score":0.41909998655319214}],"concepts":[{"id":"https://openalex.org/C121346293","wikidata":"https://www.wikidata.org/wiki/Q1340715","display_name":"Endogenous retrovirus","level":4,"score":0.8549000024795532},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6736999750137329},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6294999718666077},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C199491388","wikidata":"https://www.wikidata.org/wiki/Q1869477","display_name":"Long terminal repeat","level":4,"score":0.5774000287055969},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.508400022983551},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4844000041484833},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C2778431562","wikidata":"https://www.wikidata.org/wiki/Q189308","display_name":"Retrovirus","level":3,"score":0.4740000069141388},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.41909998655319214},{"id":"https://openalex.org/C41091548","wikidata":"https://www.wikidata.org/wiki/Q26939","display_name":"Epigenetics","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4016000032424927},{"id":"https://openalex.org/C2780509455","wikidata":"https://www.wikidata.org/wiki/Q7380","display_name":"Primate","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C2778950215","wikidata":"https://www.wikidata.org/wiki/Q177601","display_name":"Macaque","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.30070000886917114},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.29409998655319214}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10016500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10016500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10016500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10016500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5839967131614685}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scripts":[0],"and":[1,35,41,48,51,60,73,180,225,232],"datasets":[2],"included":[3],"here":[4],"were":[5],"used":[6],"for":[7,46,109,230],"the":[8,12,20,30,78,88,97,102,120,220,236],"main":[9],"analyses":[10],"in":[11,19,29,222,235],"study":[13],"of":[14,90,112,123,155,176,198,210],"\"Cryptic":[15],"endogenous":[16,26],"retrovirus":[17],"subfamilies":[18,82,127,179,189],"primate":[21,223],"lineage\".":[22],"Study":[23],"abstract:":[24],"Many":[25],"retroviruses":[27],"(ERVs)":[28],"human":[31],"genome":[32],"are":[33,61],"primate-specific":[34],"have":[36,57],"contributed":[37],"novel":[38,195],"cis-regulatory":[39],"elements":[40],"transcripts.":[42],"However,":[43],"current":[44],"approaches":[45],"classifying":[47],"annotating":[49],"ERVs":[50,231],"their":[52,141,233],"long":[53],"terminal":[54],"repeats":[55],"(LTRs)":[56],"limited":[58],"resolution":[59],"inaccurate.":[62],"Here,":[63],"we":[64,86,117,172],"developed":[65],"a":[66,106,129,159,174,194,201],"new":[67,107,126,147,178,228],"annotation":[68,108,209],"based":[69],"on":[70,77],"phylogenetic":[71],"analysis":[72],"cross-species":[74],"conservation.":[75],"Focusing":[76],"evolutionarily":[79],"young":[80],"LTR":[81,170,188],"known":[83],"as":[84],"MER11A/B/C,":[85],"revealed":[87,151],"presence":[89],"four":[91,125],"\u2018new":[92],"subfamilies\u2019,":[93],"that":[94,182],"better":[95,218],"explain":[96],"epigenetic":[98,203],"heterogeneity":[99],"observed":[100],"within":[101],"MER11":[103],"instances,":[104],"suggesting":[105],"412":[110],"(19.8%)":[111],"these":[113,124],"repeat":[114],"elements.":[115],"Furthermore,":[116],"functionally":[118],"validated":[119],"regulatory":[121],"potential":[122],"using":[128],"massively":[130],"parallel":[131],"reporter":[132],"assay":[133],"(MPRA),":[134],"which":[135,199],"also":[136],"identified":[137],"motifs":[138,157],"associated":[139],"with":[140,146,200,206],"differential":[142],"activities.":[143],"Combining":[144],"MPRA":[145],"annotations":[148],"across":[149,167],"primates":[150],"an":[152],"ape-specific":[153],"gain":[154],"SOX-related":[156],"through":[158],"single-nucleotide":[160],"deletion.":[161],"Lastly,":[162],"by":[163],"applying":[164],"our":[165,207],"approach":[166],"53":[168],"simian-enriched":[169,211],"subfamilies,":[171],"defined":[173],"total":[175],"75":[177],"found":[181],"3,807":[183],"(30.0%)":[184],"instances":[185],"from":[186],"26":[187],"could":[190],"be":[191,215],"categorized":[192],"into":[193],"annotation,":[196],"many":[197],"distinct":[202],"profile.":[204],"Thus,":[205],"refined":[208],"LTRs,":[212],"it":[213],"will":[214],"possible":[216],"to":[217],"understand":[219],"evolution":[221],"genomes":[224],"potentially":[226],"identify":[227],"roles":[229],"LTRs":[234],"hosts.":[237]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
