The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations

The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations | 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 The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations View ORCID Profile Riccardo Pianezza , View ORCID Profile Sarah Saadain , Matthew Beaumont , View ORCID Profile Sarah Signor , View ORCID Profile Robert Kofler doi: https://doi.org/10.1101/2025.10.01.679930 Riccardo Pianezza 1 Institut für Populationsgenetik, Vetmeduni Vienna , Veterinärplatz 1, 1210 Vienna, Austria 2 Vienna Graduate School of Population Genetics, Vetmeduni Vienna , Vienna, Austria Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Riccardo Pianezza For correspondence: rpianezza97{at}gmail.com Sarah Saadain 1 Institut für Populationsgenetik, Vetmeduni Vienna , Veterinärplatz 1, 1210 Vienna, Austria 2 Vienna Graduate School of Population Genetics, Vetmeduni Vienna , Vienna, Austria Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Sarah Saadain Matthew Beaumont 1 Institut für Populationsgenetik, Vetmeduni Vienna , Veterinärplatz 1, 1210 Vienna, Austria 2 Vienna Graduate School of Population Genetics, Vetmeduni Vienna , Vienna, Austria Find this author on Google Scholar Find this author on PubMed Search for this author on this site Sarah Signor 3 Biological Sciences, North Dakota State University , Fargo, North Dakota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Sarah Signor Robert Kofler 1 Institut für Populationsgenetik, Vetmeduni Vienna , Veterinärplatz 1, 1210 Vienna, Austria Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Robert Kofler Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Transposable elements are mobile DNA sequences capable of proliferating within host genomes, occasionally capable of crossing species boundaries via horizontal transfer (HT). Here, we report the discovery and characterization of Kuruka , a newly invading endogenous retrovirus in natural D. melanogaster populations. Kuruka encodes an envelope protein and belongs to the gypsy / gypsy superfamily. Analysis of over 1000 D. melanogaster genomes revealed that Kuruka first appeared in sub-Saharan Africa in 2010. By 2017-2019 Kuruka had spread to Asia, Europe and America in 2017-2019, and is still actively invading Europe and Oceania as of 2021. Phylogenomic analyses suggest that Kuruka entered in D. melanogaster via a recent HT from an Afrotropical Drosophila species, most likely D. erecta . This is the first case of a recent HT from an Afrotropical donor species to D. melanogaster . In D. erecta, Kuruka has a single genomic insertion, which is located within flamenco , a master regulator of TE activity. The presence of an active host defense (piRNAs) suggests that Kuruka is silenced in D. erecta . Our findings establish Kuruka as a valuable model for studying the early stages of TE invasions and the dynamics of genome defense in real time. 1 Introduction Transposable elements (TEs) are genomic sequences that hijack the host machinery to replicate themselves and increase in copy number within the genome. They are ubiquitous across the tree of life, having been detected in every eukaryotic genome studied to date [ Wicker et al., 2007 ]. TEs fall into two major classes: retrotransposons, which use an RNA intermediate and a “copy-and-paste” mechanism to replicate, and DNA transposons, which rely on a “cut-and-paste” strategy without an RNA intermediate [ Finnegan, 1989 ]. Retrotransposons can be further divided into long-terminal repeat (LTR) and non-LTR elements. To control the propagation of TEs, eukaryotic hosts have evolved multiple molecular defense mechanisms to limit TE activity. In Drosophila , this defense is primarily mediated by the PIWI-interacting RNA (piRNA) pathway [ Senti and Brennecke, 2010 , Brennecke et al., 2007 , Gunawardane et al., 2007 ]. piRNAs are small non-coding RNAs that recognize and silence TEs in a sequence-specific manner. They are typically generated from TE copies inserted within specialized genomic regions, known as piRNA clusters [ Brennecke et al., 2007 , Malone et al., 2009 ]. These clusters act as molecular ‘traps’: when a TE inserts into one, it triggers the production of piRNAs that can silence all members of the same TE family [ Bergman et al., 2006 , Brennecke et al., 2007 , Zanni et al., 2013 ]. Distinct piRNA pathways operate in the germline and in the surrounding follicle (somatic) cells [ Malone et al., 2009 , Li et al., 2009a ]. While both pathways rely on piRNAs, they are processed from different clusters that do not function identically. In somatic follicle cells, piRNAs are predominantly derived from a single master cluster, termed flamenco . In the germline, piRNAs are generated by many dispersed clusters [ Pelisson et al., 1994 , Prud’Homme et al., 1995 , Malone et al., 2009 , Brennecke et al., 2007 , Yamanaka et al., 2014 ]. The evolutionary divergence of these two pathways reflects differences in TE expression: while most TEs are active in the germline, others have adapted to be expressed in somatic tissues. In fact, some TEs from the gypsy/gypsy superfamily contain an envelope gene, thought to be derived from DNA Baculoviruses [ Terzian et al., 2001 , Rohrmann and Karplus, 2001 ]. The acquisition of the envelope transformed these elements from intracellular replicating retrotransposons into infectious retroviruses [ Malik et al., 2000 ]. These TEs, known as insect endogenous retroviruses (iERVs) or Errantiviruses, are typically active in the somatic tissue surrounding the germline [ Senti et al., 2025 ]. Virus-like particles generated in the soma may infect the germline, and lead to novel TE insertions that will be transmitted to the next generation [ Brasset et al., 2006 ] Despite the presence of sophisticated host defense mechanisms, TEs often persist over evolutionary timescales. However, once silenced by the host, TEs will accumulate mutations and gradually degenerate. Some TEs manage to escape this fate through horizontal transfer (HT) into new species, where they can potentially re-establish activity in a naive genomic environment. Although the molecular mechanisms enabling HT of TEs are not fully understood, accumulating evidence shows that HT is widespread across eukaryotes [ Zhang et al., 2020 , Peccoud et al., 2017 , Schaack et al., 2010 , Bartolomé et al., 2009 ]. Until recently, HT was thought to occur on deep evolutionary timescales, with estimated rates of one invasion per species every several hundred thousand years [ Bartolomé et al., 2009 , Peccoud et al., 2017 ]. Indeed, only a few cases of recent HT have been documented [ Bucheton et al., 1992 , Periquet et al., 1989 , Daniels et al., 1990 , Schwarz et al., 2021 , Scarpa et al., 2023 , Pianezza et al., 2024a , Scarpa et al., 2025 , Anxolabéh`ere et al., 1988]. The most striking examples are the recent invasion of 11 TEs in D. melanogaster during the last 200 years [ Pianezza et al., 2025 ]. This rate of TE invasions is significantly higher than previously envisioned. Of these, three TEs were horizontally transferred from Neotropical Drosophila species, while the remaining eight are likely derived from D. simulans , the closest relative of D. melanogaster [ Pianezza and Kofler, 2025 ]. Of the 11 recent invaders only Tirant , which spread in D. melanogaster populations around 1940, contains an envelope protein. However, our ability to discover such recent invasions remains limited. Several of these invasions were discovered from phenotypic effects caused by TEs (hybrid dysgenesis) or a sudden increase in the number of copies of known TE families [ Scarpa et al., 2023 , Pianezza et al., 2024a , Anxolabéh`ere et al., 1988, Kidwell, 1983 , Bucheton et al., 1992 , Periquet et al., 1989 ]. We recently developed a novel approach that circumvents the need for prior knowledge of TE sequences. By identifying genomic regions present in assemblies of recently collected strains but absent from short-read data of older strains, it is possible to detect TE invasions that occurred between the two sampling points[ Pianezza et al., 2025 , 2024b ]., such recent TE invasions may still be detectable through the extensive short-read data available for more recently collected strains [ Chen et al., 2024 ]. However this approach exclusively identifies invasions present in the investigated assemblies. Since suitable long-read assemblies are available only for strains collected before 2018, it is possible that very recent invasions were missed [ Rech et al., 2022 , Pianezza et al., 2025 ]. Nevertheless, the extensive short-read data from more recently collected strains could still capture such recent events [ Chen et al., 2024 ]. Using a novel pipeline to detect TE invasions from short-read sequencing data, we discovered a new iERV currently spreading in D. melanogaster populations, which we have named Kuruka . Phylogenetic and genomic analyses suggest that Kuruka entered the D. melanogaster genome via a recent HT from D. erecta . With high resolution spatio-temporal data, we reconstructed the detailed timing of Kuruka ’s spread across global D. melanogaster populations. This work establishes Kuruka as a new model for studying both the dynamics of iERV invasions and the real-time genomic responses of host populations. 2 Results 2.1 The discovery of Kuruka based on short-read data To test whether novel TE invasions were captured by short-read data from recently sampled D. melanogaster strains we developed a novel pipeline. The idea is that a very recent TE invasion should lead to TE sequences being present in short-read data of recently collected strains but absent in the assemblies of older strains. Our pipeline thus aims to identify TE sequences that are absent in a reference genome. A similar strategy had previously been used to identify DNA viruses in Drosophila sequencing data [ Wallace et al., 2021 ]. Briefly, short-reads are mapped to the reference genome, and unmapped or poorly mapped reads are extracted. Reads from known contaminants (e.g., Homo sapiens, Wolbachia ) are filtered out, and the remaining reads are assembled de novo . The assembled contigs are aligned to a TE protein database and high-confidence matches are retained. Final candidates are manually curated based on metrics such as coverage depth and sequence length. A schematic overview of the pipeline is shown in Fig. S1. We applied this pipeline to several recently collected D. melanogaster samples [ Chen et al., 2024 ]. Our pipeline successfully recovered previously documented invasions of TEs such as P -element, Spoink, McLE , Souslik , and Transib1 . This confirms that our pipeline may detect invasions of TEs not present in a reference assembly. In addition to these known TEs, we detected a previously unannotated ∼9kb sequence that is frequently present in samples collected from China between 2017 and 2020. To generate a high-quality consensus of this unknown element, we sequenced wild-caught flies from North Dakota (USA) in 2023 on a MinION long-read platform. The raw reads contained 12 sequences matching this element. We generate a consensus sequence of this novel element based on a multiple sequence alignment of the 12 sequences (Fig. S2). A BLASTn search did not reveal a significant match with any known D. melanogaster TE family [ Rech et al., 2022 , Quesneville et al., 2005 , Hubley et al., 2016 ], except for weak similarity (∼68% identity over ∼20% of the sequence) to both Gypsy5 and Tirant . We refer to this novel element as Kuruka , derived from the Swahili word for “jump”. 2.2 Kuruka is an endogenous retrovirus of the Gypsy / Gypsy superfamily Kuruka is 8833 bp long and features two perfectly identical LTRs of 514 bp. Based on ORF prediction (ORFinder) and BLASTp analysis, it encodes a gag protein, a pol polyprotein, and an envelope ( env) protein ( Fig. 1a ). Download figure Open in new tab Figure 1: Structural and phylogenetic characterization of Kuruka . a) Features of the 8833 bp Kuruka consensus sequence, showing two LTRs and protein-coding domains for gag, pol , and env . b) Dot plot of the Kuruka sequence, highlighting the two LTRs and a low-complexity region within the first 2 kb. c) Bayesian phylogenetic tree of the reverse transcriptase domains from known D. melanogaster TEs and Kuruka. Kuruka clusters within the Gypsy / Gypsy superfamily. A dot plot of Kuruka against itself revealed two LTRs, but also a ∼ 800bp repetitive region located within the first 2kb ( Fig. 1b ). This low-complexity region lies within the non-coding portion of the element. A 313 bp portion of this repetitive region is present in some insertions and absent in others (Fig. S2), representing a structural variant among insertions of the TE family. To determine the classification of Kuruka , we constructed a Bayesian phylogenetic tree based on the reverse transcriptase domains of known D. melanogaster TEs ( Fig. 1c ). The resulting tree places Kuruka within the Gypsy / Gypsy superfamily, close to Tirant . This classification is consistent with the presence of an env gene in the sequence of Kuruka [ Kapitonov and Jurka, 2003 ]. Similar to other Gypsy / Gypsy transposons, Kuruka may thus be active in the somatic follicle cells around the ovary. 2.3 Timing and geographic spread of Kuruka in D. melanogaster populations To reveal the spatio-temporal spread of Kuruka in D. melanogaster populations, we analyzed 1072 publicly available short read datasets [ Grenier et al., 2015 , Schwarz et al., 2021 , Lange et al., 2021 , Rech et al., 2022 , Kapun et al., 2021 , Shpak et al., 2023 , Pool et al., 2012 , Chen et al., 2024 , Nunez et al., 2025 ]. The sequenced flies were were collected from ∼ 1815 (museum collections) through 2021 from populations across the globe. This genomic time-series data enables us to explore the spread of Kuruka at a high-resolution. We used DeviaTE [ Weilguny and Kofler, 2019 ] to estimate the copy number of Kuruka in each sample based on coverage depth. DeviaTE estimates the copy number of a TE by normalizing the coverage of the TE by the coverage of single copy genes. We considered Kuruka to be present in a sample if 90% of its sequence had a normalized coverage > 1. Our time-series data revealed that Kuruka was completely absent from all samples collected before 2010 ( Fig. 2a ). It first appeared in 2010 but was not detected again until 2017, when it reached its maximum estimated copy number (∼ 50). In subsequent years, Kuruka was consistently present in some samples while remaining absent in others ( Fig. 2b ). Download figure Open in new tab Figure 2: Temporal and geographic spread of Kuruka in D. melanogaster populations. a) Timeline of the Kuruka invasion, based on short-read data. The presence (red) and absence (green) of Kuruka was inferred from the normalized coverage. Kuruka is absent in all samples prior to 2010, and present in some (but not all) samples thereafter. b) Zoomed-in view of the timeline from 2000 to 2018. From 2017 onward, Kuruka is found each year in at least a few samples. c) The invasion of Kuruka in natural D. melanogaster populations. Kuruka is first detected in samples from Africa in 2010. Around 2017–2019, Kuruka is also found in samples from Asia and the Americas, and sporadically in Europe. By 2020–2021 Kuruka is found in the Americas, East Asia and multiple samples from Europe but not in Australia. To better understand this peculiar temporal distribution, we examined the geographic origin of the samples ( Fig. 2c ). Kuruka first appeared in Africa in 2010, but was not detected elsewhere until 2017. Between 2017 and 2019, Kuruka began to spread into East Asia, the Americas, and a few samples from Europe. By 2020–2021, all samples from the Americas and East Asia carried Kuruka , while it remained absent from Australian samples and roughly half of the European samples. Our data suggest that in 2021 the Kuruka invasion was still ongoing in natural D. melanogaster populations. As additional time-points, our newly collected and sequenced samples from 2023 in North America (ND1-4) had Kuruka insertions. We also sequenced two iso-female lines of D. melanogaster collected in 2025 in North Dakota and Washington, D.C. using ONT, and they both carried multiple Kuruka insertions. We identified at minimum 16 full-length insertions of Kuruka across all major chromosome arms (per haplotype). We sought to determine whether flamenco insertions of Kuruka are present in this recently collected D. melanogaster , which would be a sign that the TE is now silenced. In the strain collected in Washington, D.C we found a Kuruka insertion in flamenco , however this was absent in the strain from North Dakota. This could mean that Kuruka is only partially silenced in American populations by 2025 or that other insertions triggered the silencing of Kuruka . 2.4 Origins of Kuruka Because Kuruka first appears in D. melanogaster populations from Africa, we hypothesized that the donor species responsible for the HT initiating the Kuruka invasion may also have an African origin. To identify the donor species, we searched for the Kuruka sequence in over 1500 arthropod genomes, including 49 D. melanogaster assemblies, 305 other drosophilids, and 1211 non-drosophilid arthropods. Since Kuruka has never been reported in D. melanogaster , we did not expect to find it in any genome of this species. Only a fragment resembling Kuruka was detected in 35 out of 49 of the D. melanogaster assemblies. This fragment is 4 kb long, 11% diverged from Kuruka and contains no LTRs (Fig. S3). The insertion site of this sequence is identical in each of the 35 assemblies, suggesting an ancient origin. Among the non-drosophilid arthropods, there is no relevant match for Kuruka (Fig. S4). The situation is drastically different in drosophilids: several species show strong matches with Kuruka , both in terms of alignment length and sequence identity. The best matches were found in D. erecta (8658bp with 98.85% sequence identity) and D. bocqueti (7497bp with 98.96% sequence identity). Interestingly, all species having insertions strongly resembling Kuruka are Afrotropical Drosophila species of the melanogaster group ( Fig. 3A ). Download figure Open in new tab Figure 3: Origins of Kuruka . a) Sequences resembling Kuruka in 334 drosophilid assemblies. The graph shows alignment length and sequence similarity between Kuruka and the best match in each species. Species are colored by their ancestral biogeographic realm. Insertions with the highest sequence similarity to Kuruka were found in D. erecta and D. bocqueti , where the match is longer in D. erecta . b) PCR confirms that Kuruka is present in D. erecta and a D. melanogaster strain sampled in 2024, yet absent from D. simulans and an older D. melanogaster strain (w 118 ). c) Bayesian phylogenetic tree of full-length Kuruka insertions across multiple Drosophila species. The 12 insertions identified in our ONT data ( D. melanogaster strain collected 2023 in North Dakota) form a monophyletic clade, consistent with a recent expansion from a single introduction. Insertions from D. erecta and D. bocqueti are most closely related to the D. melanogaster insertions. To validate the presence–absence pattern of Kuruka in selected Drosophila species, we performed PCR ( Fig. 3B ). PCR confirmed our previous results, with Kuruka being found in D. erecta , as well as in D. melanogaster samples collected in 2023 (ND1-4), while it was absent from an older D. melanogaster strain ( w 118 and D. simulans [ Qiu et al., 2017 ]. This patchy taxonomic distribution, with Kuruka being present in D. melanogaster and the distantly related D. erecta but absent in the closely related D. simulans , is a classic signature of HT [ Bartolomé et al., 2009 , Loreto et al., 2008 ]. To further investigate the potential donor species, we constructed a Bayesian phylogenetic tree with all full length-insertions of Kuruka across all species ( Fig. 3C ). The tree also includes the 12 Kuruka insertions in D. melanogaster identified in our long-read data. These 12 insertions form a monophyletic group and cluster closely together, confirming their low sequence divergence and supporting the hypothesis of a recent invasion. Located very close to the D. melanogaster clade were insertions from D. erecta and D. bocqueti . To our surprise, only a single insertion of Kuruka was found in each of these two species. The Bayesian tree solely considers the matching nucleotide sequences of the alignment and ignores indels. Given that a substantially larger portion of Kuruka aligns with D. erecta (8658 bp) than with D. bocqueti (7497 bp), we argue that D. erecta is the most likely donor. In summary, Kuruka is found exclusively in D. melanogaster and in African Drosophila species within the melanogaster group. The Kuruka invasion was most likely triggered by HT from an African Drosophila species, with D. erecta being the most probable donor. 2.5 The single Kuruka insertion in D. erecta likely generates piRNAs in somatic cells The likely donor species, D. erecta , contains a single Kuruka insertion. Although somewhat unexpected, it is not impossible that a species with just a single TE insertion could trigger a novel invasion in D. melanogaster . We wanted to investigate the Kuruka insertion in D. erecta in further detail. First, we confirmed that only a single insertion of Kuruka is present in D. erecta . To do so, we re-sequenced and assembled the D. erecta strain 14021-0224.01 that was used to generate the reference genome. The new assembly contains fewer contigs than the reference, while showing higher N50 and N90, (see Table S1), indicating improved completeness and continuity. This newly generated assembly of D. erecta still contains only a single Kuruka insertion ( Fig. 4A ). Download figure Open in new tab Figure 4: The single Kuruka insertion in D. erecta is located in flamenco and generates piRNAs. (a) A single insertion of Kuruka is found in our novel D. erecta genome assembly, consistent with the reference genome. The insertion is located within the flamenco locus. (b) We found antisense Kuruka piRNAs in the ovary (germline + soma) but not in the embryo (germline) of D. erecta flies. A weak ping-pong signature in ovarian piRNAs suggests that the germline pathway may contribute to silencing of Kuruka . Our data suggest that Kuruka is largely silenced by the somatic piRNA pathway in D. erecta . The Kuruka insertion in D. erecta is located within flamenco ( Fig. 4A , see Materials and Methods), a somatic piRNA cluster. This is in agreement with Kuruka likely being active in the soma (as suggested from the presence of an envelope protein and its classification in the Gypsy / Gypsy superfamily). The insertion in flamenco further suggests that Kuruka is silenced by the somatic piRNA pathway in D. erecta . To further investigate this, we analyzed publicly available small RNA data extracted from different D. erecta tissues [ Selvaraju et al., 2024 ]. We mapped piRNAs to the Kuruka consensus sequence, along with other TE families present in D. erecta as controls. In samples derived from ovaries, which contain piRNAs from both the germline and the somatic pathway, many piRNAs aligned to Kuruka ( Fig. 4B , S5). By contrast, in the embryo, which only contains piRNAs from the germline, very few small RNAs map to Kuruka ( Fig. 4B ). This suggests that Kuruka is largely silenced by the somatic piRNA pathway. As a control, other TEs are targeted by piRNAs in both the ovary and the embryo (Fig. S6). In ovaries we found a weak ping-pong signature for Kuruka , which is a hallmark of the germline piRNA pathway ( Fig. 4B ). It is unclear if the germline piRNA pathway contributes to silencing of Kuruka . To summarize, the potential donor of Kuruka, D. erecta , has a single Kuruka insertion in flamenco and Kuruka is likely silenced by the piRNA pathway in D. erecta . 3 Discussion Our work reveals the ongoing invasion of a new iERV, which we named Kuruka , in natural populations of D. melanogaster . Phylogenetic and genomic evidence strongly supports a HT event likely originating from D. erecta , an Afrotropical species of the melanogaster group. This represents the 12th documented TE invasion in D. melanogaster over the past 200 years. Although our pipeline for finding novel TEs in short read data identified the Kuruka invasion and recovered previously known cases (e.g., P -element, Spoink ), it is possible that it may have missed other invading TEs. Detecting recent TE invasions using short reads is challenging due to their limited length and the potential inclusion of exogenous sequences (e.g., bacterial, viral), which complicates the identification of novel TEs, especially those present at low copy number. In contrast, our tool GenomeDelta [ Pianezza et al., 2024b ] enables more accurate detection of newly invading TE families, but it requires high-quality long-read data of recently collected strains, which are scarce. Although we consider it unlikely, we can therefore not rule out that additional TEs may have spread in D. melanogaster very recently. In this work we precisely reconstructed the spatiotemporal spread of Kuruka in natural D. melanogaster populations. This level of resolution was only possible thanks to the global sampling efforts of projects like DrosEU and DrosRTEC [ Kapun et al., 2021 , Nunez et al., 2025 ], which have generated and made available hundreds of natural population datasets over time. Sustained initiatives of this kind are critical for identifying and characterizing additional ongoing TE invasions in real time. By 2021 Kuruka was still absent in Oceania and some European populations, while it spread in the Americas and East Asia. This suggests that the Kuruka invasion was still ongoing by 2021. Also the absence of Kuruka insertions in flamenco in one of the two strains sampled in 2025 in North America suggests that the Kuruka invasion is not yet fully silenced by the piRNA pathway. However, we cannot rule out that the host defense has been triggered by alternative mechanism, such as antisense insertions of Kuruka in 3’ UTRs of host genes [ Rafanel et al., 2025 ]. With the likely donor being D. erecta (or another Afrotropical Drosophila species), Kuruka is the first HT event in D. melanogaster in the last 200 years that does not originate from a species of the D. simulans complex or the D. willistoni group. While phylogenetic studies have suggested many ancient HT of TEs from other Afrotropical drosophilid species into D. melanogaster [ Carareto, 2011 , Bartolomé et al., 2009 , Modolo et al., 2014 , Pianezza and Kofler, 2025 ], Kuruka is the first documented case that has occurred during the last 200 years. This further shows that the high-rate of recent TE invasions in D. melanogaster and some related Drosophilidae is not limited to a very few donor species. The habitat expansion of D. melanogaster into the Americas during the past 100-200 years, which was suggested as cause for several of the previous invasions (including invasions where the cosmopolitan D. simulans acted as donor, e.g. due to potent vectors of HT with habitats in the Americas), can not explain all recent invasions [ Daniels et al., 1990 , Scarpa et al., 2025 , Pianezza et al., 2024a , 2025 ]. Remarkably, we identified only a single Kuruka insertion in the putative donor species, D. erecta , where the TE is likely silenced by the somatic piRNA pathway. A single Kuruka insertion is also found in the potential alternative donor species, D. bocqueti , but we do not have any information about the piRNAs in this species. However, assuming that D. erecta is the donor, this raises important questions about the dynamics of Kuruka in this species, and the mechanisms that enabled its successful invasion of D. melanogaster . Two main hypotheses could explain the presence of only one insertion in the donor species. First, it is possible that Kuruka invaded these genomes long ago, and that all insertions except the single insertion in flamenco were gradually lost through genetic drift or negative selection. Alternatively, Kuruka may have inserted early on into a piRNA-producing locus which would have triggered its immediate silencing and prevented further spread. It is feasible that some somatic TEs have a strong insertion bias into flamenco . For example, Shellder , a TE that spread in D. simulans within the last 50 years, has multiple independent insertions in flamenco . Moreover, many independent Tirant insertions in flamenco were found in different D. melanogaster strains [ Rafanel et al., 2025 ]. Notably, Tirant is closely related to Kuruka and also invaded D. melanogaster fairly recently (∼ 1940 [ Schwarz et al., 2021 ]). A strong insertion bias of somatic TEs into flamenco could halt the invasions of somatic TEs at their earliest stages. If D. erecta is the donor of the HT, our results would imply that a silenced TE, with just a single copy in a genome, may still be horizontally transmitted and trigger a novel invasion in a naive host. This is not impossible, given that the host defense (e.g. piRNAs) is likely not transmitted along with the TE during a HT. However, we cannot exclude the possibility that the actual donor lineage was a different species, or an unsampled population of D. erecta . Kuruka is only the second TE, after Transib1 , for which the spatio-temporal dynamics of invasion have been precisely reconstructed [ Pianezza et al., 2025 ]. Interestingly, Kuruka seems to spread much slower in natural populations than Transib1 . Despite first appearing in 2010, Kuruka has not spread to the whole European population as of 2021. By contrast, the DNA transposon Transib1 , spread globally within just two years from its initial appearance in 2014 [ Pianezza et al., 2025 ]. Why is Kuruka spreading slower than Transib1 ? Interestingly, Tirant , a somatic TE closely related to Kuruka that invaded D. melanogaster around 1940 is still absent in some strains sampled > 2000, i.e. 60 years after the start of the invasion [ Rech et al., 2022 , Pianezza et al., 2025 , Rafanel et al., 2025 ]). This suggests that Tirant may also be spreading slowly in natural D. melanogaster populations. Kuruka and Tirant are the only iERVs encoding envelope proteins among the 12 recent invaders. Their unique life cycle, requiring somatic expression, production of virus-like particles, and transfer to the germline, may impose biological constraints that limit transposition rates and slow down global spread. We can speculate that somatic TEs (i.e. Kuruka and Tirant ) spread more slowly than TEs that are active in the germline (e.g. Transib1 ). Together, our findings show that the high rate of recent TE invasions in D. melanogaster is still ongoing and that we can expect further TE invasions in the next years. Our work positions Kuruka as a powerful new model to study the invasion dynamics of iERVs and the interplay between TEs and the host silencing system in real time. 4 Materials and Methods 4.1 Detection of Kuruka in short-read datasets Short-read datasets from various D. melanogaster strains collected in China in 2017 and 2020 [ Chen et al., 2024 ] were mapped to the reference genome (GCA 000001215.4) using bwa mem (v0.7.17-r1188) [ Li and Durbin, 2009 ] with default parameters. Unmapped reads were extracted using samtools (v1.13) [ Li et al., 2009b ], and reads with more than 5% sequence divergence were extracted using a custom Python3 script (badmapped-finder.py). The reads were then filtered to remove potential contaminants by aligning with a custom database containing genomes of common laboratory contaminants (e.g., Homo sapiens, Wolbachia ) using bwa mem. The remaining reads were assembled de novo using SPAdes (v3.13.1) [ Prjibelski et al., 2020 ]. The assembled contigs were queried against a transposable element protein database [ Novak, 2023 ] (v3.1, metazoa) using BLASTx. Only contigs with high confidence TE-related hits were retained for further curation (sequence identity > 80%, alignment length > 250bp). 4.2 Long-read sequencing of D. melanogaster New iso-female lines of D. melanogaster were collected in 2023 and 2025 (col. Tim Greives and David Wright, respectively). For the flies collected in North Dakota in 2023 ( ND1-3 ), three of these lines were pooled and used for long read sequencing at North Dakota State University on a MinION platform (Oxford Nanopore Technologies, Oxford, GB) with base calling using Dorado (1.0, ARM64). Two additional iso-female lines from 2025 were sequenced separately ( DW7 and DC1 ) after being collected in Fargo and Washington D.C. They were sequenced and base called using the aforementioned pipeline. These reads were assembled using hifiasm [ Cheng et al., 2021 , 2025 ]. 4.3 Consensus sequence reconstruction and structural annotation To detect Kuruka insertions in the raw long-reads, we used RepeatMasker (v4.1.2-p1) [Smit et al., 2013-2015] with options -no is -s -nolow and a custom TE library containing only the contig with the Kuruka sequence assembled from the short-reads. Only insertions longer than 80% of the query sequence were retained and aligned using MAFFT (v7.526) [ Katoh et al., 2002 ]. To get a consensus sequence we used a Python3 script (MSA2consensus.py), which applies a majority-rule approach to assign a nucleotide at each position in the multiple sequence alignment. Protein domains encoded in the resulting consensus sequence were identified using ORFfinder, and subsequently aligned against the NCBI protein database using BLASTx to identify similar proteins [ Wheeler et al., 2003 ]. The dot plot was generated using VectorBuilder [ VectorBuilder Inc., 2025 ]. 4.4 Estimating copy numbers using short-reads datasets We estimated the abundance of Kuruka in 1072 publicly available D. melanogaster short-read datasets [ Grenier et al., 2015 , Schwarz et al., 2021 , Lange et al., 2021 , Rech et al., 2022 , Kapun et al., 2021 , Shpak et al., 2023 , Pool et al., 2012 , Chen et al., 2024 , Nunez et al., 2025 ]. We first aligned the reads to a database consisting of the consensus sequences of Kuruka and three single copy genes (BUSCO IDs: 29at7147, 591at7147, 898at7147) with bwa bwasw (v0.7.17-r1188) [ Li and Durbin, 2009 ]. To measure copy numbers, we used our tool DeviaTE [ Weilguny and Kofler, 2019 ], which estimates the copy number of a TE by normalizing the coverage of the TE by the coverage of the single copy genes. 4.5 Long-read sequencing and genome assembly of D. erecta Ovaries from ∼ 300 D. erecta (strain 14021-0224.01) were collected in ice-cold 1×PBS and high-molecular-weight DNA was extracted using the Monarch Genomic DNA Purification Kit (T3060, New England Biolabs). Library preparation and sequencing were performed by the Vienna BioCenter Core Facilities using the Oxford Nanopore Ligation Sequencing Kit V14 (SQK-LSK114) and a PromethION flow cell. Basecalling was done using Guppy (v6.5.7+ca6d6af). Raw reads were filtered to 100× genome coverage and assembled with Canu v2.2 [ Koren et al., 2017 ]. The assembly was polished through three rounds of Minimap2 (v2.30) [ Li, 2018 ] and Racon (v1.5.0) [ Vaser et al., 2017 ], then refined with Pilon (v1.24) [ Walker et al., 2014 ] using Illumina reads from D. erecta populations published by Selvaraju et al. [2024]. To locate flamenco in the newly generated D. erecta assembly, we relied on the coordinates of flamenco in the D. erecta reference genome [ van Lopik et al., 2023 ]. We retrieved the sequence of flamenco and mapped it to our assembly using bwa mem (v0.7.17-r1188) [ Li, 2013 ]. 4.6 Identification of Kuruka in genome assemblies We investigated the presence of Kuruka in 49 D. melanogaster , 305 drosophilids, and other 1211 arthropod genome assemblies. For an overview of all analysed assemblies, see Supplementary File S1. We identified insertions in these assemblies using RepeatMasker (v4.1.2-p1; -no-is -s -nolow) [Smit et al., 2013-2015] and a custom library containing the consensus sequence of Kuruka . For each drosophilid species in our dataset, we manually assigned its ancestral biogeographic realm based on Markow and O’Grady [2005] and if no information was available for a given species, the portal GBIF [GBIF, 2024]. 4.7 Bayesian phylogenetic analysis To infer the phylogenetic classification of Kuruka , we identified the RT regions in the consensus sequences of known D. melanogaster TEs and Kuruka using BLASTx against the NCBI protein database. We performed a multiple sequence alignment with MAFFT (v7.526) [ Katoh et al., 2002 ] and a Bayesian tree was generated with the BEAST package (v2.7.5) [ Bouckaert et al., 2019 ]. To generate a phylogenetic tree for the Kuruka insertions in the different Drosophila species, we used the RepeatMasker output and bedtools (v2.30.0) [ Quinlan and Hall, 2010 ] to extract the sequences of Kuruka including 3kb flanking regions. Then, we used the LTRharvest tool from GenomeTools (v1.6.5) [ Gremme et al., 2013 ] to select only insertions with two LTRs, removing any flanking region and fragmented insertions. The trees were built with MAFFT and BEAST [ Katoh et al., 2002 , Bouckaert et al., 2019 ]. 4.8 PCR amplification of Kuruka insertions PCR primers were designed based on Kuruka sequence in D. erecta . The primers are as follows: (F CCC-CTCCTGCTTGTTTACGT, R TGGTACGGTCAACTTCCAGC Invitrogen). The presence of Kuruka was screened in DNA from D. erecta (14021-0224.01), D. simulans ( SZ129 [ Signor et al., 2018 ]), D. melanogaster from prior to the Kuruka invasion ( w 118 ), and four D. melanogaster strains collected in Fargo, North Dakota in the Fall of 2023. D. erecta functions as a positive control, while D. simulans and D. melanogaster w 118 are negative controls. 4.9 Estimation of piRNA production The abundance of piRNAs, the distribution of piRNAs within the P -element and the ping-pong signature were computed using previously described Python scripts [ Kofler et al., 2018 , Selvaraju et al., 2024 ]. D. erecta TEs used as controls were identified by annotating TEs de novo in the D. erecta reference genome using EarlGrey (v4.4.5; option -c yes) [ Baril et al., 2024 ]. Author contributions R.P. conceived the project and discovered the invasion of Kuruka . R.P., S.Sa., M.B. and S.Si. analysed the data. S.Sa. extracted the D. erecta genomic DNA and generated the genome assembly. S.Si. collected D. melanogaster strains, performed ONT sequencing and performed PCR. R.P. and R.K. wrote the manuscript. S.Sa., M.B. and S.Si. contributed to writing. R.K. supervised the project. Funding This work was supported by the Austrian Science Fund (FWF) grants P35093 and P34965 to R.K. as well as the National Institutes of Health grant R35GM155272 to S.Si. Conflicts of Interest The author(s) declare(s) that there is no conflict of interest with respect to the publication of this article. Data Availability The newly assembled D. erecta genome and raw reads for D. melanogaster lines ND1-4 are available at NCBI under accession number xxx. The analysis performed in this work have been documented with RMarkdown and have been made publicly available, together with the resulting figures and the library of D. erecta TE families consensus sequences generated with EarlGrey, at GitHub ( https://github.com/rpianezza/Kuruka ). Acknowledgments R.P. would like to thank Pauline King’ori for her linguistic assistance in naming the TE, and Almor`o Scarpa for the precious scientific discussions. Funder Information Declared FWF Austrian Science Fund, https://ror.org/013tf3c58 , P35093 , P34965 National Institutes of Health, https://ror.org/01cwqze88 , R35GM155272 Footnotes https://github.com/rpianezza/Kuruka References ↵ Thomas Wicker , François Sabot , Aurélie Hua-Van , Jeffrey L Bennetzen , Pierre Capy , Boulos Chalhoub , Andrew Flavell , Philippe Leroy , Michele Morgante , Olivier Panaud , et al. A unified classification system for eukaryotic transposable elements . Nature Reviews Genetics , 8 ( 12 ): 973 – 982 , 2007 . OpenUrl CrossRef PubMed ↵ David J Finnegan . Eukaryotic transposable elements and genome evolution . Trends in Genetics , 5 ( 4 ): 103 – 107 , 1989 . OpenUrl CrossRef PubMed Web of Science ↵ Kirsten-André Senti and Julius Brennecke . The pirna pathway: a fly’s perspective on the guardian of the genome . Trends in Genetics , 26 ( 12 ): 499 – 509 , 2010 . OpenUrl CrossRef PubMed Web of Science ↵ Julius Brennecke , Alexei A Aravin , Alexander Stark , Monica Dus , Manolis Kellis , Ravi Sachidanandam , and Gregory J Hannon . Discrete small RNA-generating loci as master regulators of transposon activity in Drosophila . Cell , 128 ( 6 ): 1089 – 1103 , 2007 . OpenUrl CrossRef PubMed Web of Science ↵ Lalith S Gunawardane , Kuniaki Saito , Kazumichi M Nishida , Keita Miyoshi , Yoshinori Kawamura , Tomoko Nagami , Haruhiko Siomi , and Mikiko C Siomi . A slicer-mediated mechanism for repeat-associated sirna 5’end formation in drosophila . science , 315 ( 5818 ): 1587 – 1590 , 2007 . OpenUrl Abstract / FREE Full Text ↵ Colin D Malone , Julius Brennecke , Monica Dus , Alexander Stark , W Richard McCombie , Ravi Sachidanandam , and Gregory J Hannon . Specialized pirna pathways act in germline and somatic tissues of the drosophila ovary . Cell , 137 ( 3 ): 522 – 535 , 2009 . OpenUrl CrossRef PubMed Web of Science ↵ Casey M Bergman , Hadi Quesneville , Dominique Anxolabéhère , and Michael Ashburner . Recurrent insertion and duplication generate networks of transposable element sequences in the drosophila melanogaster genome . Genome biology , 7 ( 11 ): R112 , 2006 . OpenUrl CrossRef PubMed ↵ Vanessa Zanni , Angéline Eymery , Michael Coiffet , Matthias Zytnicki , Isabelle Luyten , Hadi Quesneville , Chantal Vaury , and Silke Jensen . Distribution, evolution, and diversity of retrotransposons at the flamenco locus reflect the regulatory properties of pirna clusters . Proceedings of the National Academy of Sciences , 110 ( 49 ): 19842 – 19847 , 2013 . OpenUrl Abstract / FREE Full Text ↵ Chengjian Li , Vasily V Vagin , Soohyun Lee , Jia Xu , Shengmei Ma , Hualin Xi , Hervé Seitz , Michael D Horwich , Monika Syrzycka , Barry M Honda , et al. Collapse of germline pirnas in the absence of argonaute3 reveals somatic pirnas in flies . Cell , 137 ( 3 ): 509 – 521 , 2009a . OpenUrl CrossRef PubMed Web of Science ↵ A Pelisson , SU Song , N Prud’Homme , PA Smith , A Bucheton , and VG Corces . Gypsy transposition correlates with the production of a retroviral envelope-like protein under the tissue-specific control of the drosophila flamenco gene . The EMBO journal , 13 ( 18 ): 4401 – 4411 , 1994 . OpenUrl CrossRef PubMed Web of Science ↵ Nicole Prud’Homme , Madeleine Gans , Michele Masson , Christophe Terzian , and Alain Bucheton . Flamenco, a gene controlling the gypsy retrovirus of drosophila melanogaster . Genetics , 139 ( 2 ): 697 , 1995 . OpenUrl Abstract / FREE Full Text ↵ Soichiro Yamanaka , Mikiko C Siomi , and Haruhiko Siomi . pirna clusters and open chromatin structure . Mobile DNA , 5 ( 1 ): 22 , 2014 . OpenUrl CrossRef PubMed ↵ Christophe Terzian , Alain Pélisson , and Alain Bucheton . Evolution and phylogeny of insect endogenous retroviruses . BMC evolutionary biology , 1 : 1 – 8 , 2001 . OpenUrl PubMed ↵ George F Rohrmann and P Andrew Karplus . Relatedness of baculovirus and gypsy retrotransposon envelope proteins . BMC Evolutionary Biology , 1 : 1 – 9 , 2001 . OpenUrl PubMed ↵ Harmit S Malik , Steve Henikoff , and Thomas H Eickbush . Poised for contagion: evolutionary origins of the infectious abilities of invertebrate retroviruses . Genome research , 10 ( 9 ): 1307 – 1318 , 2000 . OpenUrl Abstract / FREE Full Text ↵ Kirsten-André Senti , Baptiste Rafanel , Dominik Handler , Carolin Kosiol , Christian Schlötterer , and Julius Brennecke . Co-evolving infectivity and expression patterns drive the diversification of endogenous retro-viruses . The EMBO Journal , pages 1 – 20 , 2025 . ↵ Emilie Brasset , Anna Rita Taddei , Frederick Arnaud , Babacar Faye , Anna Maria Fausto , Massimo Mazzini , Franco Giorgi , and Chantal Vaury . Viral particles of the endogenous retrovirus zam from drosophila melanogaster use a pre-existing endosome/exosome pathway for transfer to the oocyte . Retrovirology , 3 ( 1 ): 25 , 2006 . OpenUrl CrossRef PubMed ↵ Hua-Hao Zhang , Jean Peccoud , Min-Rui-Xuan Xu , Xiao-Gu Zhang , and Clément Gilbert . Horizontal transfer and evolution of transposable elements in vertebrates . Nature communications , 11 ( 1 ): 1362 , 2020 . OpenUrl PubMed ↵ Jean Peccoud , Vincent Loiseau , Cordaux , and Clément Gilbert . Massive horizontal transfer of transposable elements in insects . Proc Natl Acad Sci U S A , 114 ( 18 ): 4721 – 26 , 2017 . OpenUrl Abstract / FREE Full Text ↵ Sarah Schaack , Clément Gilbert , and Cédric Feschotte . Promiscuous dna: horizontal transfer of transposable elements and why it matters for eukaryotic evolution . Trends in ecology & evolution , 25 ( 9 ): 537 – 546 , 2010 . OpenUrl PubMed ↵ Carolina Bartolomé , Xabier Bello , and Xulio Maside . Widespread evidence for horizontal transfer of transposable elements across drosophila genomes . Genome biology , 10 : 1 – 11 , 2009 . OpenUrl CrossRef ↵ A Bucheton , C Vaury , M C Chaboissier , P Abad , A Pélisson , and M Simonelig . I elements and the Drosophila genome . Genetica , 86 ( 1-3 ): 175 – 90 , 1992 . OpenUrl CrossRef PubMed Web of Science ↵ Georges Periquet , Marie H Hamelin , Yves Bigot , and Antoine Lepissier . Geographical and historical patterns of distribution of hobo elements in Drosophila melanogaster populations . Journal of Evolutionary Biology , 2 ( 3 ): 223 – 229 , 1989 . OpenUrl CrossRef ↵ S B Daniels , K R Peterson , L D Strausbaugh , M G Kidwell , and A Chovnick . Evidence for horizontal transmission of the p transposable element between drosophila species . Genetics , 124 ( 2 ): 339 – 355 , February 1990 . ISSN 1943-2631 . doi: 10.1093/genetics/124.2.339 . URL http://dx.doi.org/10.1093/genetics/124.2.339. OpenUrl Abstract / FREE Full Text ↵ Florian Schwarz , Filip Wierzbicki , Kirsten-André Senti , and Robert Kofler . Tirant Stealthily Invaded Natural Drosophila melanogaster Populations during the Last Century . Molecular Biology and Evolution , 38 ( 4 ): 1482 – 1497 , 2021 . OpenUrl CrossRef PubMed ↵ Almorò Scarpa , Riccardo Pianezza , Filip Wierzbicki , and Robert Kofler . Genomes of historical specimens reveal multiple invasions of ltr retrotransposons in drosophila melanogaster populations during the 19th century . bioRxiv , 2023 . doi: 10.1101/2023.06.06.543830 . OpenUrl Abstract / FREE Full Text ↵ Riccardo Pianezza , Almorò Scarpa , Prakash Narayanan , Sarah Signor , and Robert Kofler . Spoink, a ltr retrotransposon, invaded d. melanogaster populations in the 1990s . PLoS Genetics , 20 ( 3 ): e1011201 , 2024a . OpenUrl ↵ Almorò Scarpa , Riccardo Pianezza , Hannah R Gellert , Anna Haider , Bernard Y Kim , Eric C Lai , Robert Kofler , and Sarah Signor . Double trouble: two retrotransposons triggered a cascade of invasions in drosophila species within the last 50 years . Nature Communications , 16 ( 1 ): 516 , 2025 . OpenUrl PubMed D Anxolabéhère , M G Kidwell , and G Periquet . Molecular characteristics of diverse populations are consistent with the hypothesis of a recent invasion of Drosophila melanogaster by mobile P elements . Molecular Biology and Evolution , 5 ( 3 ): 252 – 269 , 1988 . OpenUrl CrossRef PubMed Web of Science ↵ Riccardo Pianezza , Almorò Scarpa , Anna Haider , Sarah Signor , and Robert Kofler . Spatio-temporal tracking of three novel transposable element invasions in drosophila melanogaster over the last 30 years . Molecular Biology and Evolution , page msaf143 , 2025 . ↵ Riccardo Pianezza and Robert Kofler . Biogeography shapes the te landscape of drosophila melanogaster . bioRxiv , pages 2025 – 05 , 2025 . ↵ M. G. Kidwell . Evolution of hybrid dysgenesis determinants in Drosophila melanogaster . Proceedings of the National Academy of Sciences , 80 ( 6 ): 1655 – 1659 , 1983 . OpenUrl Abstract / FREE Full Text ↵ Riccardo Pianezza , Anna Haider , and Robert Kofler . Genomedelta: detecting recent transposable element invasions without repeat library . Genome Biology , 25 ( 1 ): 315 , 2024b . OpenUrl PubMed ↵ Junhao Chen , Chenlu Liu , Weixuan Li , Wenxia Zhang , Yirong Wang , Andrew G Clark , and Jian Lu . From sub-saharan africa to china: Evolutionary history and adaptation of drosophila melanogaster revealed by population genomics . Science Advances , 10 ( 16 ): eadh3425 , 2024 . OpenUrl CrossRef PubMed ↵ Gabriel E Rech , Santiago Radío , Sara Guirao-Rico , Laura Aguilera , Vivien Horvath , Llewellyn Green , Hannah Lindstadt , Véronique Jamilloux , Hadi Quesneville , and Josefa González . Population-scale long-read sequencing uncovers transposable elements associated with gene expression variation and adaptive signatures in drosophila . Nature Communications , 13 ( 1 ): 1948 , 2022 . OpenUrl PubMed ↵ Megan A Wallace , Kelsey A Coffman , Clément Gilbert , Sanjana Ravindran , Gregory F Albery , Jessica Abbott , Eliza Argyridou , Paola Bellosta , Andrea J Betancourt , Herve Colinet , et al. The discovery, distribution, and diversity of dna viruses associated with drosophila melanogaster in europe . Virus evolution , 7 ( 1 ): veab031 , 2021 . OpenUrl CrossRef PubMed ↵ Hadi Quesneville , Casey M Bergman , Olivier Andrieu , Delphine Autard , Danielle Nouaud , Michael Ashburner , and Dominique Anxolabehere . Combined evidence annotation of transposable elements in genome sequences . PLoS computational biology , 1 ( 2 ): e22 , 2005 . OpenUrl ↵ Robert Hubley , Robert D Finn , Jody Clements , Sean R Eddy , Thomas A Jones , Weidong Bao , Arian FA Smit , and Travis J Wheeler . The dfam database of repetitive dna families . Nucleic acids research , 44 ( D1 ): D81 – D89 , 2016 . OpenUrl CrossRef PubMed ↵ Vladimir V Kapitonov and Jerzy Jurka . Molecular paleontology of transposable elements in the Drosophila melanogaster genome . Proceedings of the National Academy of Sciences of the United States of America , pages 6569 – 74 , 2003 . ISSN 0027-8424 . ↵ Jennifer K Grenier , J Roman Arguello , Margarida Cardoso Moreira , Srikanth Gottipati , Jaaved Mohammed , Sean R Hackett , Rachel Boughton , Anthony J Greenberg , and Andrew G Clark . Global diversity lines– a five-continent reference panel of sequenced Drosophila melanogaster strains . G3: Genes, Genomes, Genetics , 5 ( 4 ): 593 – 603 , 2015 . OpenUrl ↵ Jeremy D Lange , Héloïse Bastide , Justin B Lack , and John E Pool . A Population Genomic Assessment of Three Decades of Evolution in a Natural Drosophila Population . Molecular Biology and Evolution , 39 ( 2 ), 2021 . ↵ Martin Kapun , Joaquin CB Nunez , María Bogaerts-Márquez , Jesús Murga-Moreno , Margot Paris , Joseph Outten , Marta Coronado-Zamora , Courtney Tern , Omar Rota-Stabelli , Maria P García Guerreiro , et al. Drosophila evolution over space and time (dest): a new population genomics resource . Molecular biology and evolution , 38 ( 12 ): 5782 – 5805 , 2021 . OpenUrl CrossRef PubMed ↵ Max Shpak , Hamid R. Ghanavi , Jeremy D. Lange , John E. Pool , and Marcus C. Stensmyr . Genomes from historical drosophila melanogaster specimens illuminate adaptive and demographic changes across more than 200 years of evolution . PLOS Biology , 21 ( 10 ): 1 – 31 , 10 2023 . doi: 10.1371/journal.pbio.3002333 . URL https://doi.org/10.1371/journal.pbio.3002333. OpenUrl CrossRef ↵ John E Pool , Russell B Corbett-Detig , Ryuichi P Sugino , Kristian A Stevens , Charis M Cardeno , Marc W Crepeau , Pablo Duchen , JJ Emerson , Perot Saelao , David J Begun , et al. Population genomics of subsaharan drosophila melanogaster: African diversity and non-african admixture . PLoS genetics , 8 ( 12 ): e1003080 , 2012 . OpenUrl PubMed ↵ Joaquin CB Nunez , Marta Coronado-Zamora , Mathieu Gautier , Martin Kapun , Sonja Steindl , Lino Ometto , Katja Hoedjes , Julia Beets , R Axel W Wiberg , Giovanni R Mazzeo , et al. Footprints of worldwide adaptation in structured populations of drosophila melanogaster through the expanded dest 2.0 genomic resource . Molecular Biology and Evolution , 42 ( 8 ): msaf132 , 2025 . OpenUrl PubMed ↵ Lukas Weilguny and Robert Kofler . DeviaTE: Assembly-free analysis and visualization of mobile genetic element composition . Molecular Ecology Resources , 19 ( 5 ): 1346 – 1354 , 2019 . OpenUrl PubMed ↵ Shuang Qiu , Chengfeng Xiao , and R Meldrum Robertson . Different age-dependent performance in drosophila wild-type canton-s and the white mutant w1118 flies . Comparative Biochemistry and Physiology Part A: Molecular & Integrative Physiology , 206 : 17 – 23 , 2017 . OpenUrl ↵ ELS Loreto , CMA Carareto , and et P Capy . Revisiting horizontal transfer of transposable elements in drosophila . Heredity , 100 ( 6 ): 545 – 554 , 2008 . OpenUrl CrossRef PubMed Web of Science ↵ Divya Selvaraju , Filip Wierzbicki , and Robert Kofler . Experimentally evolving drosophila erecta populations may fail to establish an effective pirna-based host defense against invading p-elements . Genome Research , 34 ( 3 ): 410 – 425 , 2024 . OpenUrl Abstract / FREE Full Text ↵ Baptiste Rafanel , Liudmila Protsenko , Dominik Handler , Julius Brennecke , and Kirsten-Andre Senti . Antisense transposon insertions into host genes trigger pirna mediated immunity . bioRxiv , pages 2025 – 07 , 2025 . ↵ Claudia MA Carareto . Tropical africa as a cradle for horizontal transfers of transposable elements between species of the genera drosophila and zaprionus . Mobile Genetic Elements , 1 ( 3 ): 179 – 186 , 2011 . OpenUrl CrossRef PubMed ↵ Laurent Modolo , Franck Picard , and Emmanuelle Lerat . A new genome-wide method to track horizontally transferred sequences: application to drosophila . Genome biology and evolution , 6 ( 2 ): 416 – 432 , 2014 . OpenUrl CrossRef PubMed ↵ Heng Li and Richard Durbin . Fast and accurate short read alignment with Burrows–Wheeler transform . Bioinformatics , 25 ( 14 ): 1754 – 1760 , 2009 . OpenUrl CrossRef PubMed Web of Science ↵ Heng Li , Bob Handsaker , Alec Wysoker , Tim Fennell , Jue Ruan , Nils Homer , Gabor Marth , Goncalo Abecasis , Richard Durbin , and 1000 Genome Project Data Processing Subgroup . The sequence alignment/map format and samtools . bioinformatics , 25 ( 16 ): 2078 – 2079 , 2009b . OpenUrl CrossRef PubMed Web of Science ↵ Andrey Prjibelski , Dmitry Antipov , Dmitry Meleshko , Alla Lapidus , and Anton Korobeynikov . Using spades de novo assembler . Current protocols in bioinformatics , 70 ( 1 ): e102 , 2020 . OpenUrl CrossRef ↵ Petr Novak . repeatexplorer/rexdb: v1.0 , 2023 . URL https://zenodo.org/doi/10.5281/zenodo.10160279 . ↵ Haoyu Cheng , Gregory T Concepcion , Xiaowen Feng , Haowen Zhang , and Heng Li . Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nature methods , 18 ( 2 ): 170 – 175 , 2021 . OpenUrl PubMed ↵ Haoyu Cheng , Han Qu , Sean McKenzie , Katherine R Lawrence , Rhydian Windsor , Mike Vella , Peter J Park , and Heng Li . Efficient near telomere-to-telomere assembly of nanopore simplex reads . bioRxiv , pages 2025 – 04 , 2025 . A. F. A. Smit , R. Hubley , and P. Green . RepeatMasker Open-4. 0, 2013-2015 . URL http://www.repeatmasker.org . ↵ Kazutaka Katoh , Kazuharu Misawa , Kei-ichi Kuma , and Takashi Miyata . Mafft: a novel method for rapid multiple sequence alignment based on fast fourier transform . Nucleic acids research , 30 ( 14 ): 3059 – 3066 , 2002 . OpenUrl CrossRef PubMed Web of Science ↵ David L Wheeler , Deanna M Church , Scott Federhen , Alex E Lash , Thomas L Madden , Joan U Pontius , Gregory D Schuler , Lynn M Schriml , Edwin Sequeira , Tatiana A Tatusova , et al. Database resources of the national center for biotechnology . Nucleic acids research , 31 ( 1 ): 28 – 33 , 2003 . OpenUrl CrossRef PubMed Web of Science ↵ VectorBuilder Inc . Nucleic acid dot plot tool (sequence dot plot) . https://en.vectorbuilder.com/tool/sequence-dot-plot.html , June 2025 . Last updated June 4, 2025; tool for visualizing direct/inverted repeats, inversions, frameshifts in DNA/RNA sequences. ↵ Sergey Koren , Brian P Walenz , Konstantin Berlin , Jason R Miller , Nicholas H Bergman , and Adam M Phillippy . Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation . Genome Research , 27 ( 5 ): 722 – 736 , 2017 . doi: 10.1101/gr.215087.116 . OpenUrl Abstract / FREE Full Text ↵ Heng Li . Minimap2: pairwise alignment for nucleotide sequences . Bioinformatics , 34 ( 18 ): 3094 – 3100 , 2018 . doi: 10.1093/bioinformatics/bty191 . OpenUrl CrossRef PubMed ↵ Robert Vaser , Ivan Sovic , Niranjan Nagarajan , and Mile Sikic . Fast and accurate de novo genome assembly from long uncorrected reads . Genome Research , 27 ( 5 ): 737 – 746 , 2017 . doi: 10.1101/gr.214270.116 . OpenUrl Abstract / FREE Full Text ↵ Brian J Walker , Thomas Abeel , Terrance Shea , Margaret Priest , Alaa Abouelliel , Sharadha Sakthikumar , Christina A Cuomo , Qiandong Zeng , Jennifer Wortman , Sarah K Young , et al. Pilon: an integrated tool for comprehensive microbial variant detection and genome assembly improvement . PloS one , 9 ( 11 ): e112963 , 2014 . OpenUrl CrossRef PubMed ↵ Jasper van Lopik , Azad Alizada , Maria-Anna Trapotsi , Gregory J Hannon , Susanne Bornelöv , and Benjamin Czech Nicholson . Unistrand pirna clusters are an evolutionarily conserved mechanism to suppress endogenous retroviruses across the drosophila genus . Nature communications , 14 ( 1 ): 7337 , 2023 . OpenUrl PubMed ↵ Heng Li . Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM . 2013 . URL https://arxiv.org/abs/1303.3997 . Therese A Markow and Patrick O’Grady . Drosophila: A guide to species identification and use. 2005 . GBIF. Gbif home page , 2024 . URL https://www.gbif.org . Accessed: 01-05-2024 . ↵ Remco Bouckaert , Timothy G. Vaughan , Joëlle Barido-Sottani , Sebastián Duchêne , Mathieu Fourment , Alexandra Gavryushkina , Joseph Heled , Graham Jones , Denise Kühnert , Nicola De Maio , Michael Matschiner , Fábio K. Mendes , Nicola F. Müller , Huw A. Ogilvie , Louis du Plessis , Alex Popinga , Andrew Rambaut , David Rasmussen , Igor Siveroni , Marc A. Suchard , Chieh-Hsi Wu , Dong Xie , Chi Zhang , Tanja Stadler , and Alexei J. Drummond . BEAST 2.5: An advanced software platform for bayesian evolutionary analysis . PLOS Computational Biology , 15 ( 4 ): e1006650 , April 2019 . OpenUrl ↵ Aaron R Quinlan and Ira M Hall . Bedtools: a flexible suite of utilities for comparing genomic features . Bioinformatics , 26 ( 6 ): 841 – 842 , 2010 . OpenUrl CrossRef PubMed Web of Science ↵ Gordon Gremme , Sascha Steinbiss , and Stefan Kurtz . Genometools: a comprehensive software library for efficient processing of structured genome annotations . IEEE/ACM transactions on computational biology and bioinformatics , 10 ( 3 ): 645 – 656 , 2013 . OpenUrl CrossRef ↵ Sarah A Signor , Felicia N New , and Sergey Nuzhdin . A large panel of drosophila simulans reveals an abundance of common variants . Genome biology and evolution , 10 ( 1 ): 189 – 206 , 2018 . OpenUrl CrossRef PubMed ↵ Robert Kofler , Kirsten-Andre Senti , Viola Nolte , Ray Tobler , and Christian Schlötterer . Molecular dissection of a natural transposable element invasion . Genome research , 28 ( 6 ): 824 – 835 , 2018 . OpenUrl Abstract / FREE Full Text ↵ Tobias Baril , James Galbraith , and Alex Hayward . Earl grey: a fully automated user-friendly transposable element annotation and analysis pipeline . Molecular Biology and Evolution , 41 ( 4 ): msae068 , 2024 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted October 03, 2025. Download PDF Supplementary Material Data/Code 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 The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations 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 The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations Riccardo Pianezza , Sarah Saadain , Matthew Beaumont , Sarah Signor , Robert Kofler bioRxiv 2025.10.01.679930; doi: https://doi.org/10.1101/2025.10.01.679930 Share This Article: Copy Citation Tools The ongoing invasion of the endogenous retrovirus Kuruka in natural Drosophila melanogaster populations Riccardo Pianezza , Sarah Saadain , Matthew Beaumont , Sarah Signor , Robert Kofler bioRxiv 2025.10.01.679930; doi: https://doi.org/10.1101/2025.10.01.679930 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 Genomics Subject Areas All Articles Animal Behavior and Cognition (7642) Biochemistry (17715) Bioengineering (13907) Bioinformatics (42003) Biophysics (21470) Cancer Biology (18624) Cell Biology (25533) Clinical Trials (138) Developmental Biology (13390) Ecology (19935) Epidemiology (2067) Evolutionary Biology (24356) Genetics (15617) Genomics (22529) Immunology (17753) Microbiology (40432) Molecular Biology (17200) Neuroscience (88681) Paleontology (667) Pathology (2840) Pharmacology and Toxicology (4828) Physiology (7653) Plant Biology (15161) Scientific Communication and Education (2046) Synthetic Biology (4304) Systems Biology (9826) Zoology (2271)