{"id":"https://openalex.org/W7225313272","doi":"https://doi.org/10.64898/2026.11.04.764337","title":"Provenance-aware handling of identical dengue genome records alters inferred envelope-protein variation in Bangladesh DENV-3","display_name":"Provenance-aware handling of identical dengue genome records alters inferred envelope-protein variation in Bangladesh DENV-3","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225313272","doi":"https://doi.org/10.64898/2026.11.04.764337"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.04.764337","doi":"https://doi.org/10.64898/2026.11.04.764337","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764337","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/05/2026.11.04.764337.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/05/2026.11.04.764337.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134466509","display_name":"Kazi T. Begum","orcid":"https://orcid.org/0000-0001-9086-2234","observed_orcids":["https://orcid.org/0000-0001-9086-2234"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kazi Tanzina Begum","raw_affiliation_strings":["Department of Computational and Integrative Biology, Rutgers University\u2013Camden, Camden, New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0001-9086-2234","affiliations":[{"raw_affiliation_string":"Department of Computational and Integrative Biology, Rutgers University\u2013Camden, Camden, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160892768","display_name":"Kazi Abdul Gofur Rafea","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Kazi Abdul Gofur Rafea","raw_affiliation_strings":["Department of Biochemistry and Biotechnology, University of Science and Technology Chittagong, Chattogram, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Biotechnology, University of Science and Technology Chittagong, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I91090688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5134466509"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T10166","display_name":"Mosquito-borne diseases and control","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10166","display_name":"Mosquito-borne diseases and control","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.002099999925121665,"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/T14053","display_name":"Dengue and Mosquito Control Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dengue-virus","display_name":"dengue virus","score":0.8240000009536743},{"id":"https://openalex.org/keywords/denv-3","display_name":"DENV-3","score":0.9819999933242798},{"id":"https://openalex.org/keywords/envelope-protein","display_name":"envelope protein","score":0.9459999799728394},{"id":"https://openalex.org/keywords/antigenic-variation","display_name":"antigenic variation","score":0.6909999847412109},{"id":"https://openalex.org/keywords/nextstrain","display_name":"Nextstrain","score":0.7749999761581421},{"id":"https://openalex.org/keywords/variant-prioritization","display_name":"variant prioritization","score":0.6729999780654907},{"id":"https://openalex.org/keywords/antibody-epitopes","display_name":"antibody epitopes","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5855000019073486},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4821999967098236},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.4537999927997589},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.40380001068115234},{"id":"https://openalex.org/C533803919","wikidata":"https://www.wikidata.org/wiki/Q30953","display_name":"Dengue fever","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.3368000090122223},{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.3352000117301941},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.30410000681877136},{"id":"https://openalex.org/C2779635636","wikidata":"https://www.wikidata.org/wiki/Q476209","display_name":"Dengue virus","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C191942190","wikidata":"https://www.wikidata.org/wiki/Q4774739","display_name":"Antigenic variation","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C2777510210","wikidata":"https://www.wikidata.org/wiki/Q1331256","display_name":"Flaviviridae","level":4,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.04.764337","doi":"https://doi.org/10.64898/2026.11.04.764337","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764337","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/05/2026.11.04.764337.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.04.764337","doi":"https://doi.org/10.64898/2026.11.04.764337","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764337","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/05/2026.11.04.764337.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.504800021648407,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225313272.pdf","grobid_xml":"https://content.openalex.org/works/W7225313272.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1799716582","https://openalex.org/W1969376060","https://openalex.org/W1983305047","https://openalex.org/W1989555063","https://openalex.org/W1996024572","https://openalex.org/W2001568055","https://openalex.org/W2017081541","https://openalex.org/W2017577931","https://openalex.org/W2024238365","https://openalex.org/W2030991607","https://openalex.org/W2036444473","https://openalex.org/W2044817254","https://openalex.org/W2069331412","https://openalex.org/W2081356962","https://openalex.org/W2083345910","https://openalex.org/W2092644992","https://openalex.org/W2100572232","https://openalex.org/W2100891069","https://openalex.org/W2114296756","https://openalex.org/W2121043049","https://openalex.org/W2122715951","https://openalex.org/W2131849805","https://openalex.org/W2140182479","https://openalex.org/W2144095627","https://openalex.org/W2151240643","https://openalex.org/W2158488625","https://openalex.org/W2167275396","https://openalex.org/W2169886236","https://openalex.org/W2669502811","https://openalex.org/W2897888001","https://openalex.org/W2949155040","https://openalex.org/W2952045272","https://openalex.org/W3017616203","https://openalex.org/W4378516690","https://openalex.org/W4379230597","https://openalex.org/W4386020358","https://openalex.org/W4394063236","https://openalex.org/W4404511392","https://openalex.org/W7128441390","https://openalex.org/W7214346373"],"related_works":["https://openalex.org/W7213079609","https://openalex.org/W2418130832","https://openalex.org/W5237555","https://openalex.org/W245095691","https://openalex.org/W1970295487","https://openalex.org/W1593830980","https://openalex.org/W4386020358","https://openalex.org/W2188641085","https://openalex.org/W1983360668","https://openalex.org/W2075740548"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"reliability":[2],"of":[3,39,102,123],"interpreting":[4],"dengue":[5,202],"virus":[6],"(DENV)":[7],"envelope":[8],"(E)":[9],"protein":[10],"variations":[11],"depends":[12],"on":[13,26],"whether":[14],"identical":[15,70],"public":[16],"sequence":[17],"records":[18,65],"are":[19],"kept":[20],"as":[21],"representatives":[22],"or":[23,216],"eliminated":[24],"based":[25],"provenance":[27],"reviews.":[28],"We":[29],"evaluated":[30],"three":[31],"record-handling":[32],"strategies":[33],"using":[34],"a":[35,45],"frozen":[36],"Bangladesh-associated":[37],"dataset":[38],"426":[40],"E":[41,86],"sequences:":[42],"exact-sequence":[43],"deduplication,":[44],"prespecified":[46],"provenance-sensitive":[47],"exclusion":[48],"method,":[49],"and":[50,98,140,159,166,183],"an":[51,217],"independently":[52],"curated":[53],"Nextstrain":[54,143],"accession":[55],"list.":[56],"Within":[57],"the":[58,75,89,103,113,137,147,160,176],"2021":[59,68],"DENV3":[60,92],"subset":[61],"(96":[62],"accessions),":[63],"18":[64,149],"dated":[66],"August":[67],"were":[69,83,126],"across":[71],"10,707":[72],"nucleotides":[73],"to":[74,129],"older":[76],"Sri":[77],"Lankan":[78],"genome":[79],"AY099336.1":[80],".":[81],"There":[82],"21":[84,110,124],"variable":[85,120,163],"positions":[87,135],"within":[88],"original":[90],"96-accession":[91],"cohort.":[93,142],"Whole-cohort":[94],"deduplication":[95],"(47":[96],"retained)":[97,107,116],"retaining":[99],"one":[100],"representative":[101],"18-record":[104],"group":[105,114,139],"(79":[106],"preserved":[108],"all":[109],"positions.":[111,164],"Excluding":[112],"(78":[115],"resulted":[117],"in":[118,131],"eight":[119,162],"positions:":[121],"13":[122],"(61.9%)":[125],"lost":[127],"due":[128],"differences":[130],"state":[132],"at":[133],"those":[134],"between":[136],"excluded":[138],"retained":[141],"reference-specific":[144],"exclusions":[145],"selected":[146],"same":[148,161],"records;":[150],"applying":[151],"its":[152],"full":[153],"saved":[154],"list":[155],"produced":[156],"77":[157],"accessions":[158],"E270":[165],"E383,":[167],"which":[168],"had":[169],"pre-2021":[170],"antibody-related":[171],"evidence,":[172],"did":[173],"not":[174,190,212],"meet":[175],"sequence-variation":[177],"criteria":[178],"for":[179],"follow-up;":[180],"however,":[181],"E223":[182],"E224":[184],"remained":[185],"variable.":[186],"Antibody-position":[187],"enrichment":[188],"was":[189],"statistically":[191],"significant.":[192],"These":[193],"results":[194],"indicate":[195,213],"that":[196],"cohort":[197],"eligibility":[198],"decisions":[199],"may":[200],"impact":[201],"E-protein":[203],"variant":[204],"prioritization":[205],"despite":[206],"representative-retaining":[207],"deduplication.":[208],"Genome":[209],"identity":[210,215],"does":[211],"specimen":[214],"antigenic":[218],"phenotype.":[219]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-06T00:00:00"}