{"id":"https://openalex.org/W7204930023","doi":"https://doi.org/10.64898/2026.08.31.747927","title":"The evolutionarily conserved C-terminal domain of a domesticated transposase-derived protein regulates its DNA integration ability","display_name":"The evolutionarily conserved C-terminal domain of a domesticated transposase-derived protein regulates its DNA integration ability","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204930023","doi":"https://doi.org/10.64898/2026.08.31.747927"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.31.747927","doi":"https://doi.org/10.64898/2026.08.31.747927","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.31.747927","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/31/2026.08.31.747927.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":null,"license_id":null,"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/2026/08/31/2026.08.31.747927.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123831529","display_name":"Aditi Saha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditi Saha","raw_affiliation_strings":["Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148943175","display_name":"Aryaman Ghosh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aryaman Ghosh","raw_affiliation_strings":["Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032494328","display_name":"Sharmistha Majumdar","orcid":"https://orcid.org/0000-0003-4356-7237","observed_orcids":["https://orcid.org/0000-0003-4356-7237"]},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sharmistha Majumdar","raw_affiliation_strings":["Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar"],"raw_orcid":"https://orcid.org/0000-0003-4356-7237","affiliations":[{"raw_affiliation_string":"Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar","institution_ids":["https://openalex.org/I27674431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032494328"],"corresponding_institution_ids":["https://openalex.org/I27674431"],"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.015300000086426735,"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/T10878","display_name":"CRISPR and Genetic Engineering","score":0.003800000064074993,"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/c-terminal-domain","display_name":"C-terminal domain","score":0.878000020980835},{"id":"https://openalex.org/keywords/dna-transposition","display_name":"DNA transposition","score":0.6480000019073486},{"id":"https://openalex.org/keywords/novel-protein-fold","display_name":"novel protein fold","score":0.6840000152587891},{"id":"https://openalex.org/keywords/phylogenetic-analysis","display_name":"phylogenetic analysis","score":0.7879999876022339},{"id":"https://openalex.org/keywords/truncation-mutants","display_name":"truncation mutants","score":0.7960000038146973},{"id":"https://openalex.org/keywords/dna-integration","display_name":"DNA integration","score":0.9110000133514404},{"id":"https://openalex.org/keywords/dna-excision","display_name":"DNA excision","score":0.6430000066757202},{"id":"https://openalex.org/keywords/rag1","display_name":"RAG1","score":0.7260000109672546},{"id":"https://openalex.org/keywords/piggybac","display_name":"piggyBac","score":0.9879999756813049}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7994999885559082},{"id":"https://openalex.org/C4918238","wikidata":"https://www.wikidata.org/wiki/Q121438","display_name":"Transposable element","level":4,"score":0.7551000118255615},{"id":"https://openalex.org/C172510086","wikidata":"https://www.wikidata.org/wiki/Q410629","display_name":"Transposase","level":5,"score":0.7384999990463257},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6402999758720398},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C101425835","wikidata":"https://www.wikidata.org/wiki/Q4051531","display_name":"Tn10","level":5,"score":0.5432000160217285},{"id":"https://openalex.org/C102744134","wikidata":"https://www.wikidata.org/wiki/Q22280388","display_name":"Homologous recombination","level":3,"score":0.5386000275611877},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.534600019454956},{"id":"https://openalex.org/C134387633","wikidata":"https://www.wikidata.org/wiki/Q11395","display_name":"Domestication","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5005999803543091},{"id":"https://openalex.org/C64894306","wikidata":"https://www.wikidata.org/wiki/Q849622","display_name":"Homologous chromosome","level":3,"score":0.4973999857902527},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C160775987","wikidata":"https://www.wikidata.org/wiki/Q411599","display_name":"P element","level":5,"score":0.4490000009536743},{"id":"https://openalex.org/C143065580","wikidata":"https://www.wikidata.org/wiki/Q3285695","display_name":"Mutant","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3361000120639801},{"id":"https://openalex.org/C186055190","wikidata":"https://www.wikidata.org/wiki/Q24788168","display_name":"RING finger domain","level":5,"score":0.33169999718666077},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C166393388","wikidata":"https://www.wikidata.org/wiki/Q856529","display_name":"Molecular evolution","level":4,"score":0.30809998512268066},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C139690037","wikidata":"https://www.wikidata.org/wiki/Q785301","display_name":"Evolution of mammals","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2780104201","wikidata":"https://www.wikidata.org/wiki/Q130888","display_name":"Drosophila melanogaster","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2777379243","wikidata":"https://www.wikidata.org/wiki/Q1054318","display_name":"Drosophilidae","level":4,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.31.747927","doi":"https://doi.org/10.64898/2026.08.31.747927","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.31.747927","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/31/2026.08.31.747927.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.31.747927","doi":"https://doi.org/10.64898/2026.08.31.747927","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.31.747927","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/31/2026.08.31.747927.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204930023.pdf","grobid_xml":"https://content.openalex.org/works/W7204930023.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1984219847","https://openalex.org/W1996429296","https://openalex.org/W2007021068","https://openalex.org/W2015115860","https://openalex.org/W2028249116","https://openalex.org/W2031901496","https://openalex.org/W2082401184","https://openalex.org/W2111647009","https://openalex.org/W2120772351","https://openalex.org/W2144494426","https://openalex.org/W2156407548","https://openalex.org/W2160378127","https://openalex.org/W2163138552","https://openalex.org/W2170747616","https://openalex.org/W2783855936","https://openalex.org/W2804340390","https://openalex.org/W2907872701","https://openalex.org/W2938210236","https://openalex.org/W2981442923","https://openalex.org/W2984340848","https://openalex.org/W3120698206","https://openalex.org/W3164675290","https://openalex.org/W4388979371","https://openalex.org/W4396721167","https://openalex.org/W4400353742","https://openalex.org/W4404531735","https://openalex.org/W6912517022","https://openalex.org/W7127432000","https://openalex.org/W7140171057","https://openalex.org/W7156098070"],"related_works":["https://openalex.org/W4388979371","https://openalex.org/W4226505286","https://openalex.org/W4391387150","https://openalex.org/W2040713238","https://openalex.org/W7211901961","https://openalex.org/W2165403355","https://openalex.org/W2943687287","https://openalex.org/W1996429296","https://openalex.org/W4393118061","https://openalex.org/W3164675290"],"abstract_inverted_index":{"Abstract":[0],"THAP9":[1,22,51,176],"is":[2,12,31,47],"a":[3,9,26,43,113,155],"transposable":[4,225],"element-derived":[5,226],"gene":[6],"which":[7,30,46,90,232],"encodes":[8],"protein":[10],"that":[11,39,122,149,190,210],"homologous":[13],"to":[14,87,93,152,218],"the":[15,40,55,82,96,118,161,172],"active":[16],"Drosophila":[17],"P-element":[18],"transposase":[19],"(DmTNP).":[20],"Both":[21],"and":[23,35,58,105,107,177,187,230],"DmTNP":[24,178],"possess":[25],"C-terminal":[27],"domain":[28],"(CTD)":[29],"functionally":[32],"uncharacterized.":[33],"Sequence":[34],"structural":[36],"analysis":[37,66],"suggest":[38],"THAP9-CTD":[41,75,97],"has":[42],"novel":[44,62],"fold":[45],"only":[48],"found":[49],"in":[50,85,112,206,223],"homologs.":[52],"To":[53],"explore":[54],"evolutionary":[56],"history":[57],"characteristics":[59],"of":[60,140,146,160,184],"this":[61,208],"domain,":[63],"exhaustive":[64],"phylogenetic":[65],"(using":[67],"MSA,":[68],"structure":[69,137],"prediction,":[70],"MSTA-based":[71],"clustering)":[72],"was":[73],"performed.":[74],"homologs":[76,89,98,120],"were":[77,91,99,164],"more":[78,100],"widely":[79],"distributed":[80],"throughout":[81],"animal":[83],"kingdom":[84],"comparison":[86],"DmTNP-CTD":[88,119],"restricted":[92],"arthropods.":[94],"Moreover,":[95,200],"conserved,":[101],"especially":[102],"among":[103],"mammals":[104],"birds":[106],"their":[108,124,191],"average":[109],"length":[110],"increased":[111],"class-specific":[114],"manner.":[115],"Comparison":[116],"with":[117],"demonstrates":[121],"although":[123],"respective":[125,162,192],"CTDs":[126,163,193],"may":[127,215],"have":[128,216,233],"evolved":[129],"independently,":[130],"they":[131],"both":[132,175],"surprisingly":[133],"share":[134],"similar":[135,234],"secondary":[136],"elements":[138],"consisting":[139],"three":[141],"conserved":[142,156],"helical":[143],"regions":[144],"made":[145],"hydrophobic":[147],"residues":[148],"are":[150,181,194],"predicted":[151],"make":[153],"up":[154],"core.":[157],"The":[158],"role":[159],"further":[165],"investigated":[166],"by":[167],"creating":[168],"truncation":[169,179,202],"mutants":[170,180],"lacking":[171],"CTD.":[173],"Interestingly":[174],"still":[182],"capable":[183],"DNA":[185,198,204],"excision":[186],"integration,":[188],"suggesting":[189],"not":[195],"essential":[196],"for":[197],"transposition.":[199],"CTD":[201,211],"favours":[203],"integration":[205],"THAP9:":[207],"suggests":[209],"acquisition":[212],"during":[213],"evolution":[214],"led":[217],"THAP9\u2019s":[219],"domestication":[220],"as":[221],"observed":[222],"other":[224],"genes":[227],"like":[228],"Rag1":[229],"piggybac,":[231],"terminal":[235],"regulatory":[236],"domains.":[237]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-02T00:00:00"}