Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes

Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes View ORCID Profile Robert J. Gifford doi: https://doi.org/10.1101/2025.03.15.643461 Robert J. Gifford 1 MRC-University of Glasgow Centre for Virus Research, University of Glasgow , Glasgow, UK 2 Centre for Epidemic Response and Innovation, Stellenbosch University , Stellenbosch, South Africa Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Robert J. Gifford For correspondence: robert.gifford{at}glasgow.ac.uk Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Adeno-associated viruses (AAVs) are non-pathogenic DNA viruses with potent gene delivery capabilities, making them essential tools in gene therapy and biomedical research. Despite their therapeutic importance, key aspects of AAV natural biology remain obscure, complicating efforts to explain rare AAV-associated diseases and optimize gene therapy vectors. By analyzing sequence data from virus isolates and endogenous viral elements (EVEs), I reveal a striking evolutionary pattern: while AAV sub-lineages, defined by the replication-associated ( rep ) gene, have broadly co-diverged with host groups over millions of years, capsid ( cap ) diversity has been shaped by extensive recombination. In particular, one capsid lineage, Mammalian-wide ( M-wide ), has spread horizontally across diverse rep lineages and host taxa through multiple recombination events. Furthermore, several AAVs with M-wide capsids - including AAV-4, AAV-12, and bovine AAV (BAAV) - originate from historical adenovirus (Ad) stocks, raising the possibility that laboratory conditions contributed to capsid transfer. Distinguishing natural from laboratory-driven recombination is essential for understanding AAV ecology and its implications for gene therapy. A systematic sequencing effort in human and primate populations is needed to assess the extent of recombinant capsid acquisition, determine the impact of laboratory-driven recombination on circulating AAV diversity, and track ongoing recombination events that could affect vector safety and efficacy. Introduction Adeno-associated viruses (AAVs) are small, non-enveloped, single-stranded DNA viruses of the Dependoparvovirus genus (family Parvoviridae ) [ 1 ]. They require co-infection with helper viruses, such as adenoviruses or herpesviruses, for productive replication [ 2 ]. The AAV genome encodes two primary genes: rep (essential for replication and genome packaging) and cap (encoding the structural proteins of the viral capsid). AAVs are widely used in gene therapy, where the viral coding region is replaced with a therapeutic transgene, and the rep and cap genes are supplied in trans . Recombinant AAV (rAAV) vectors are now approved for treating genetic disorders such as hemophilia and inherited retinal diseases, and show growing potential across a broad range of therapeutic applications [ 3 ]. Capsid proteins, which determine host range and tissue specificity, are key targets for modification to improve gene delivery, transduction efficiency, and tropism, as well as to evade neutralizing antibodies from prior AAV exposure [ 4 ]. Despite decades of research on rAAV vectors, the natural biology of AAVs remains poorly understood. Like other parvoviruses, AAVs exhibit high recombination and mutation rates [ 5 , 6 ], yet their extensive genomic ‘fossil record’, comprised of EVEs, reveals a remarkable degree of sequence conservation over millions of years [ 7 ]. Sequence and serological data indicate that diverse AAVs circulate in humans and non-human primates [ 5 , 8 ], but virus-host interactions remain opaque. While AAVs are generally considered apathogenic [ 2 ], or even beneficial [ 9 ], recent reports linking AAV-2 to unexplained cases of childhood hepatitis [ 10 ], along with emerging evidence of context-dependent pathogenicity [ 11 ], highlight the gaps in our understanding of AAV-host interactions. Clarifying these relationships is critical not only for assessing the risks of naturally circulating AAVs but also for designing safer and more effective gene therapy vectors. Here, I show that AAV capsids have undergone extensive horizontal transfer across divergent lineages, a process that may influence both viral evolution and gene therapy applications. These findings also raise critical questions about the role of laboratory-driven recombination in shaping AAV diversity. Results Phylogenetic analysis of rep genes from AAV isolates and EVEs shows that AAVs form a distinct, well-supported subclade within genus Dependoparvovirus . Among AAVs that infect mammals, rep -based clades broadly align with host orders—Primates, Rodentia, Chiroptera, Artiodactyla— indicating long-term, stable host-virus associations. These ancient relationships are further supported by EVE data [ 7 , 12 ] ( Fig. 1 ). Download figure Open in new tab Figure 1. Tanglegram showing phylogenetic discordance between rep and cap and spread of the M-wide capsid lineage Comparison of rep (left, outgroup-rooted) and cap (right, midpoint-rooted) phylogenies of adeno-associated viruses (AAVs), illustrating recombination. Shaded clades correspond to host taxonomic groups, as indicated in the key. Connecting lines highlight rep/cap discordance and suggest independent acquisitions of the M-wide capsid (pink), found across multiple mammalian orders. Bold labels mark taxa potentially acquiring M-wide. A darker pink region indicates a sub-lineage of M-wide AAVs associated with adenovirus (Ad) stocks. Endogenous parvoviral elements (EPVs) are marked by symbols (see key); orthologous EPVs provide minimum age estimates (rounded to nearest 5 My) at the base of the respective clades—e.g., EPV-dependo . 13-cercopithecidae (>20 My) and EPV-dependo . 46-gliridae (>30 My). Asterisks indicate bootstrap support >70%. In contrast, cap -based phylogenies reveal a markedly different topology. While most cap lineages align with mammalian host orders, one prominent exception stands out: a single capsid lineage – here termed Mammalian-wide-1 ( M-wide ) – appears across multiple rep lineages, consistent with widespread horizontal transfer via recombination ( Fig. 1 ). These incongruent relationships are supported by statistical comparison of tree topologies (Shimodaira–Hasegawa test) and orthogonal recombination analyses, including GARD and split network methods (see Methods ). Strikingly, three AAVs bearing M-wide capsids – AAV-4, AAV-12, and bovine AAV (BAAV) – were originally isolated from adenovirus stocks established in the 1950s ( Fig. 1 , Table 1 ). Their cap genes form a well-supported subclade ( Fig. 1 ), suggesting a shared origin potentially linked to laboratory culture. View this table: View inline View popup Download powerpoint Table 1. Isolation History & Host Associations of Primate and Artiodactyl Adeno-Associated Viruses Discussion AAVs were first identified in the 1960s as contaminants of adenovirus (Ad) stocks [ 13 ]. These stocks – which were derived from primate and bovine tissues—had been established a decade earlier, in an era when few viruses could be propagated outside live hosts. Given the limited virological tools available, AAVs likely remained undetected in early adenovirus cultures for years. These early Ad stocks were often derived from pooled or heterogeneous biological samples, creating an environment conducive to AAV co-infection. The presence of helper viruses, elevated viral titers, and permissive cell lines may have enabled capsid gene exchange through recombination, and inadvertently contributed to the emergence and spread of recombinant AAVs within laboratory cultures. Since the 2000s, AAVs encoding M-wide capsids have been detected in both primate centers and dairy cattle populations [ 15 ]. If these virus lineages did originate in laboratory cultures, they now appear to be established in natural hosts. Notably, one such virus (AAV-11) is >99% identical in the rep gene to AAV-10, which encodes a canonical primate AAV capsid, suggesting that recent recombination events continue to shape AAV diversity. If capsid exchange is ongoing, the functional breadth of M-wide capsids in primate AAVs, spanning epithelial, intestinal, and lymphoid tropisms, implies that such recombination may have significant biological and therapeutic implications [ 3 , 4 ]. While laboratory propagation may have played a role in M-wide’s spread, an alternative possibility is that this capsid lineage was already naturally widespread, with its presence in AAVs derived from Ad stocks reflecting only pre-existing bovine and primate AAV diversity, rather than lab-driven recombination. Disentangling these scenarios is key to understanding AAV ecology and evolution. Modern sequencing technologies can facilitate broad-scale characterization and surveillance of AAV diversity. Such efforts would not only clarify the natural ecology and evolution of AAVs but also inform gene therapy applications by identifying circulating diversity and potential immune interactions. Materials and Methods AAV genome and EVE sequences were obtained from public databases and curated in a reproducible database framework integrating standardized alignments and metadata [ 12 , 16 ]. Phylogenetic trees were reconstructed using maximum likelihood from conserved rep and cap coding regions. Recombination was assessed by comparing tree topologies and applying complementary analytical approaches. All curated sequences, alignments, and analysis workflows are fully documented and openly accessible in the associated repositories, and a Docker image is provided for streamlined, cross-platform reproducibility [ 12 ]. Acknowledgment I thank Professor Robert Kotin for his valuable feedback. Footnotes In this updated version of "Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes," I have made several improvements to clarify key findings and enhance the transparency and reproducibility of the analysis. The horizontal transfer (HT) analysis has been fully restructured using a reproducible GLUE-based pipeline, now documented in the ht_analysis/ directory of the AAV-Atlas GitHub repository. This includes clear definitions of taxon sets, partition schemes, tree-building methods, and rerooting strategies, along with exported metadata for visualization. I have refined the evolutionary interpretation of M-wide.1 capsid acquisitions, separating likely ancient events from those that may reflect more recent, possibly lab-associated recombination. I now emphasize that independent acquisitions of M-wide.1 by different primate AAV lineages raise important questions about the role of historical experimentation in shaping natural diversity. The dependo-13 EVE locus and other supporting data are now more clearly contextualized. To support these interpretations, I have added results from orthogonal recombination detection methods (SplitsTree, GARD) in a new orthogonal/ subdirectory. These complement the phylogenetic evidence for past recombination events involving the AAV capsid gene. Figures have been updated for clarity, with improved legends and rooting information. I have also corrected minor typographical errors and adjusted sections of the main text to improve flow and align better with the underlying data. Overall, this version strengthens the case that AAV capsids have undergone pervasive horizontal transfer and that some of this diversity may have been shaped by historical laboratory conditions. It also provides a foundation for fully reproducible analysis using open-source tools and public data. References 1. ↵ Cotmore , S.F. , et al. , ICTV Virus Taxonomy Profile: Parvoviridae . J Gen Virol , 2019 . 100 ( 3 ): p. 367 – 368 . OpenUrl CrossRef PubMed 2. ↵ Meier , A.F. , C. Fraefel , and M. Seyffert , The Interplay between Adeno-Associated Virus and its Helper Viruses . Viruses , 2020 . 12 ( 6 ). 3. ↵ Wang , J.H. , et al. , Adeno-associated virus as a delivery vector for gene therapy of human diseases . Signal Transduct Target Ther , 2024 . 9 ( 1 ): p. 78 . OpenUrl CrossRef PubMed 4. ↵ Zolotukhin , S. and L.H. Vandenberghe , AAV capsid design: A Goldilocks challenge . Trends Mol Med , 2022 . 28 ( 3 ): p. 183 – 193 . OpenUrl CrossRef PubMed 5. ↵ Gao , G. , et al. , Adeno-associated viruses undergo substantial evolution in primates during natural infections . Proc Natl Acad Sci U S A , 2003 . 100 ( 10 ): p. 6081 – 6 . OpenUrl Abstract / FREE Full Text 6. ↵ Duffy , S. , L.A. Shackelton , and E.C. Holmes , Rates of evolutionary change in viruses: patterns and determinants . Nat Rev Genet , 2008 . 9 ( 4 ): p. 267 – 76 . OpenUrl CrossRef PubMed Web of Science 7. ↵ Campbell , M.A. , et al. , Comparative analysis reveals the long-term coevolutionary history of parvoviruses and vertebrates . PLoS Biol , 2022 . 20 ( 11 ): p. e3001867 . OpenUrl CrossRef PubMed 8. ↵ Gao , G. , et al. , Clades of Adeno-associated viruses are widely disseminated in human tissues . J Virol , 2004 . 78 ( 12 ): p. 6381 – 8 . OpenUrl Abstract / FREE Full Text 9. ↵ Mayor , H.D. , et al. , Antibodies to adeno-associated satellite virus and herpes simplex in sera from cancer patients and normal adults . Am J Obstet Gynecol , 1976 . 126 ( 1 ): p. 100 – 4 . OpenUrl CrossRef PubMed Web of Science 10. ↵ Tacke , F. , Severe hepatitis outbreak in children linked to AAV2 virus . Nature , 2023 . 617 : p. 471 – 472 . OpenUrl CrossRef PubMed 11. ↵ Sant’Anna , T.B. and N.M. Araujo , Adeno-associated virus infection and its impact in human health: an overview . Virology Journal , 2022 . 19 ( 1 ): p. 173 . OpenUrl CrossRef PubMed 12. ↵ Gifford , R.J. AAV-Atlas v1.0 (v1.0) . 2025 . DOI: 10.5281/zenodo.15498088 . OpenUrl CrossRef 13. ↵ Atchison , R.W. , B.C. Casto , and W.M. Hammon , Adenovirus-associated defective virus particles . Science , 1965 . 149 ( 3685 ): p. 754 – 6 . OpenUrl Abstract / FREE Full Text 14. Mori , S. , et al. , Two novel adeno-associated viruses from cynomolgus monkey: pseudotyping characterization of capsid protein . Virology , 2004 . 330 ( 2 ): p. 375 – 83 . OpenUrl CrossRef PubMed 15. ↵ Ng , T.F. , et al. , A metagenomics and case-control study to identify viruses associated with bovine respiratory disease . J Virol , 2015 . 89 ( 10 ): p. 5340 – 9 . OpenUrl Abstract / FREE Full Text 16. ↵ Singer , J.B. , et al. , GLUE: a flexible software system for virus sequence data . BMC Bioinformatics , 2018 . 19 ( 1 ): p. 532 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted June 06, 2025. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes Robert J. Gifford bioRxiv 2025.03.15.643461; doi: https://doi.org/10.1101/2025.03.15.643461 Share This Article: Copy Citation Tools Pervasive Horizontal Transfer of Adeno-Associated Virus Capsid Genes Robert J. Gifford bioRxiv 2025.03.15.643461; doi: https://doi.org/10.1101/2025.03.15.643461 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Evolutionary Biology Subject Areas All Articles Animal Behavior and Cognition (7616) Biochemistry (17625) Bioengineering (13852) Bioinformatics (41825) Biophysics (21397) Cancer Biology (18524) Cell Biology (25417) Clinical Trials (138) Developmental Biology (13350) Ecology (19858) Epidemiology (2067) Evolutionary Biology (24277) Genetics (15581) Genomics (22459) Immunology (17698) Microbiology (40278) Molecular Biology (17134) Neuroscience (88400) Paleontology (666) Pathology (2823) Pharmacology and Toxicology (4812) Physiology (7632) Plant Biology (15106) Scientific Communication and Education (2042) Synthetic Biology (4281) Systems Biology (9807) Zoology (2266)