<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.4 20241031//EN"  "JATS-archivearticle1-4-mathml3.dtd"><article xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" dtd-version="1.4"><front><journal-meta><journal-id journal-id-type="nlm-ta">elife</journal-id><journal-id journal-id-type="publisher-id">eLife</journal-id><journal-title-group><journal-title>eLife</journal-title></journal-title-group><issn publication-format="electronic" pub-type="epub">2050-084X</issn><publisher><publisher-name>eLife Sciences Publications, Ltd</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">110625</article-id><article-id pub-id-type="doi">10.7554/eLife.110625</article-id><article-id pub-id-type="doi" specific-use="version">10.7554/eLife.110625.3</article-id><article-version article-version-type="publication-state">version of record</article-version><article-categories><subj-group subj-group-type="display-channel"><subject>Research Article</subject></subj-group><subj-group subj-group-type="heading"><subject>Genetics and Genomics</subject></subj-group><subj-group subj-group-type="heading"><subject>Neuroscience</subject></subj-group></article-categories><title-group><article-title>Transposons contribute to splice-isoform diversity in the <italic>Drosophila</italic> brain</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Choucri</surname><given-names>Malak</given-names></name><contrib-id authenticated="true" contrib-id-type="orcid">https://orcid.org/0009-0002-2070-8930</contrib-id><xref ref-type="aff" rid="aff1">1</xref><xref ref-type="fn" rid="con1"/><xref ref-type="fn" rid="conf1"/></contrib><contrib contrib-type="author"><name><surname>Rainey</surname><given-names>Tina</given-names></name><contrib-id authenticated="true" contrib-id-type="orcid">https://orcid.org/0009-0000-0746-0577</contrib-id><xref ref-type="aff" rid="aff1">1</xref><xref ref-type="fn" rid="con2"/><xref ref-type="fn" rid="conf1"/></contrib><contrib contrib-type="author" corresp="yes"><name><surname>Treiber</surname><given-names>Christoph Daniel</given-names></name><contrib-id authenticated="true" contrib-id-type="orcid">https://orcid.org/0000-0002-6994-091X</contrib-id><email>christoph.d.treiber@gmail.com</email><xref ref-type="aff" rid="aff1">1</xref><xref ref-type="fn" rid="con3"/><xref ref-type="fn" rid="conf1"/></contrib><aff id="aff1"><label>1</label><institution-wrap><institution-id institution-id-type="ror">https://ror.org/052gg0110</institution-id><institution>Department of Biology, University of Oxford</institution></institution-wrap><addr-line><named-content content-type="city">Oxford</named-content></addr-line><country>United Kingdom</country></aff></contrib-group><contrib-group content-type="section"><contrib contrib-type="editor"><name><surname>Karimi</surname><given-names>Mohammad M</given-names></name><role>Reviewing Editor</role><aff><institution-wrap><institution-id institution-id-type="ror">https://ror.org/0220mzb33</institution-id><institution>King's College London</institution></institution-wrap><country>United Kingdom</country></aff></contrib><contrib contrib-type="senior_editor"><name><surname>Desplan</surname><given-names>Claude</given-names></name><role>Senior Editor</role><aff><institution-wrap><institution-id institution-id-type="ror">https://ror.org/0190ak572</institution-id><institution>New York University</institution></institution-wrap><country>United States</country></aff></contrib></contrib-group><pub-date publication-format="electronic" date-type="publication"><day>17</day><month>11</month><year>2026</year></pub-date><volume>15</volume><elocation-id>RP110625</elocation-id><pub-history><event><event-desc>Sent for review</event-desc><date date-type="sent-for-review" iso-8601-date="2026-01-22"><day>22</day><month>01</month><year>2026</year></date></event><event><event-desc>Preprint posted</event-desc><date date-type="preprint" iso-8601-date="2026-01-26"><day>26</day><month>01</month><year>2026</year></date><self-uri content-type="preprint" xlink:href="https://doi.org/10.64898/2026.01.22.701052"/></event><event><event-desc>Reviewed preprint v1</event-desc><date date-type="reviewed-preprint" iso-8601-date="2026-04-02"><day>02</day><month>04</month><year>2026</year></date><self-uri content-type="reviewed-preprint" xlink:href="https://doi.org/10.7554/eLife.110625.1"/><self-uri content-type="referee-report" xlink:href="https://doi.org/10.7554/eLife.110625.1.sa2">Reviewer #1 (Public review):</self-uri><self-uri content-type="referee-report" xlink:href="https://doi.org/10.7554/eLife.110625.1.sa1">Reviewer #2 (Public review):</self-uri><self-uri content-type="referee-report" xlink:href="https://doi.org/10.7554/eLife.110625.1.sa0">Reviewer #3 (Public review):</self-uri><self-uri content-type="editor-report" xlink:href="https://doi.org/10.7554/eLife.110625.1.sa3">eLife Assessment</self-uri></event><event><event-desc>Reviewed preprint v2</event-desc><date date-type="reviewed-preprint" iso-8601-date="2026-10-01"><day>01</day><month>10</month><year>2026</year></date><self-uri content-type="reviewed-preprint" xlink:href="https://doi.org/10.7554/eLife.110625.2"/><self-uri content-type="referee-report" xlink:href="https://doi.org/10.7554/eLife.110625.2.sa2">Reviewer #1 (Public review):</self-uri><self-uri content-type="referee-report" xlink:href="https://doi.org/10.7554/eLife.110625.2.sa1">Reviewer #3 (Public review):</self-uri><self-uri content-type="author-comment" xlink:href="https://doi.org/10.7554/eLife.110625.2.sa0">Author response:</self-uri><self-uri content-type="editor-report" xlink:href="https://doi.org/10.7554/eLife.110625.2.sa3">eLife Assessment</self-uri></event></pub-history><permissions><copyright-statement>© 2026, Choucri et al</copyright-statement><copyright-year>2026</copyright-year><copyright-holder>Choucri et al</copyright-holder><ali:free_to_read/><license xlink:href="http://creativecommons.org/licenses/by/4.0/"><ali:license_ref>http://creativecommons.org/licenses/by/4.0/</ali:license_ref><license-p>This article is distributed under the terms of the <ext-link ext-link-type="uri" xlink:href="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution License</ext-link>, which permits unrestricted use and redistribution provided that the original author and source are credited.</license-p></license></permissions><self-uri content-type="pdf" xlink:href="elife-110625-v1.pdf"/><self-uri content-type="figures-pdf" xlink:href="elife-110625-figures-v1.pdf"/><abstract><p>The extraordinary complexity of the brain depends in part on the vast diversity of mRNA isoforms it expresses, often in a cell-type specific manner. In a recent study, we found that intronic transposable elements (TEs) are spliced into neural transcripts and diversify the splice isoform repertoire of neurons and glia (Treiber and Waddell, 2020). A recent paper by Azad et al. revisits these findings using their TIDAL analysis pipeline applied to our published data (Azad et al., 2024). Their analysis did not find any of the splicing reads we reported and although they used RT-PCR to test seven of the 264 TE–gene pairs we had previously reported, they failed to validate TE–gene splicing in any of them. Here, we conduct a quantitative analysis of TE exonisation and show that intronic TE insertions are frequently recruited as alternative exons, with exon usage ranging from rare events to near-complete inclusion in transcripts. We implement this analysis in an improved version of our TEChim software and present clear support for TE–gene splicing at the seven loci tested by Azad et al. We also identify methodological issues in the experimental and computational design of the Azad et al. study that likely explains their failure to detect TE–gene chimeras, while demonstrating that TE–gene splicing can be detected by RT-PCR under appropriate experimental conditions. Together, our data demonstrates that TE splice isoforms are not rare artefacts but measurable and biologically relevant features of the <italic>Drosophila</italic> brain transcriptome that may contribute to the molecular complexity and functional adaptability of the brain.</p></abstract><kwd-group kwd-group-type="author-keywords"><kwd>transposable element</kwd><kwd>alternative splicing</kwd><kwd>exonisation</kwd><kwd>neural transcriptome</kwd><kwd><italic>Drosophila melanogaster</italic></kwd></kwd-group><kwd-group kwd-group-type="research-organism"><title>Research organism</title><kwd><italic>D. melanogaster</italic></kwd></kwd-group><funding-group><award-group id="fund1"><funding-source><institution-wrap><institution-id institution-id-type="ror">https://ror.org/001aqnf71</institution-id><institution>UK Research and Innovation</institution></institution-wrap></funding-source><award-id>EP/X038882/1 'InnovaTEbehaviour'</award-id><principal-award-recipient><name><surname>Choucri</surname><given-names>Malak</given-names></name><name><surname>Rainey</surname><given-names>Tina</given-names></name><name><surname>Treiber</surname><given-names>Christoph Daniel</given-names></name></principal-award-recipient></award-group><funding-statement>The funders had no role in study design, data collection, and interpretation, or the decision to submit the work for publication.</funding-statement></funding-group><custom-meta-group><custom-meta specific-use="meta-only"><meta-name>Author impact statement</meta-name><meta-value>Intronic transposons can become alternative exons that substantially alter the composition of mature neural transcripts.</meta-value></custom-meta><custom-meta specific-use="meta-only"><meta-name>publishing-route</meta-name><meta-value>prc</meta-value></custom-meta></custom-meta-group></article-meta></front><body><sec id="s1" sec-type="intro"><title>Introduction</title><p>Neural transcriptomes are shaped by extensive alternative splicing, which generates a large number of mRNA isoforms that drive the structural and functional diversity within the brain. Among the genomic features that can contribute to this process, transposable elements (TEs) are of particular interest. TEs make up a substantial proportion of eukaryotic genomes and provide a rich and diverse reservoir of potential splice sites. However, their contribution to neural transcript diversity remains poorly understood. In our previous work, we showed that many intronic TEs in the <italic>Drosophila</italic> genome are spliced into mature transcripts in the brain, giving rise to chimeric mRNAs that incorporate TE-derived sequence (<xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref>). By combining high-coverage genomic DNA (gDNA) sequencing (<xref ref-type="bibr" rid="bib20">Treiber and Waddell, 2017</xref>) with strand-specific RNA sequencing from the same fly strain, we identified 264 TE–gene pairs with clear, breakpoint-spanning read support for splicing into and out of TEs.</p><p>TE insertions are not fixed features of genomes but vary extensively between individuals. In <italic>Drosophila</italic>, TE landscapes differ markedly between laboratory strains and even between individuals of an inbred strain (<xref ref-type="bibr" rid="bib20">Treiber and Waddell, 2017</xref>). Comparable levels of inter-individual TE polymorphisms are well documented in mammals (<xref ref-type="bibr" rid="bib2">Akagi et al., 2008</xref>), including humans (<xref ref-type="bibr" rid="bib6">Bennett et al., 2004</xref>; <xref ref-type="bibr" rid="bib13">Ewing and Kazazian, 2011</xref>). Importantly, recent large-scale transcriptomic and proteogenomic analyses in humans demonstrate that intronic TE insertions are frequently exonised, giving rise to thousands of recurrent, translated splice isoforms with distinct structural and functional properties (<xref ref-type="bibr" rid="bib4">Arribas et al., 2024</xref>). Hence, variation in TE landscapes has the capacity to generate inter-individual variation of splice isoform repertoires, and potentially protein structure and abundance. Within the nervous system, TE exonisation therefore provides an intriguing mechanism by which genetic variation in TE landscapes could contribute to inter-individual differences in neural function and behaviour.</p><p>Here, we introduce a quantitative analysis of TE exonisation using an extended version of the TEChim pipeline, allowing us to measure the extent to which individual intronic TE insertions are used as alternative exons. We show that TE exonisation efficiency varies widely across loci, and is often substantial, and that these values are reproducible across biological replicates. We then examine why a recent re-analysis of the same data by <xref ref-type="bibr" rid="bib5">Azad et al., 2024</xref> et al. failed to recover these splice junctions, identifying methodological issues that readily account for their negative results. Finally, we revisit our earlier analysis of TE expression modes to place these splice events within the broader context of autonomous versus non-autonomous TE expression in the brain.</p><p>Together, these lines of evidence support a model in which TE-derived splice isoforms are stable and biologically relevant features of the <italic>Drosophila</italic> brain transcriptome and, in light of growing evidence from other species, part of a conserved strategy by which eukaryotic genomes diversify gene function.</p></sec><sec id="s2" sec-type="results"><title>Results</title><sec id="s2-1"><title>Intronic TE insertions show a broad range of exonisation rates</title><p>To quantify how frequently individual TE sequences are used as exons, we extended our TEChim pipeline to calculate, for each breakpoint at an endogenous exon–intron junction, the ratio of TE-derived splice junctions to canonical exon–exon junctions (<xref ref-type="fig" rid="fig1">Figure 1A</xref>). For each occurrence, TEChim now reports the relative usage of TE-derived splice junctions immediately downstream (for TE-derived splice acceptor sites) or upstream (for donor sites) of the exon–intron junction compared to canonical exon–exon junctions, providing a simple measure of the TE exonisation efficiency for each event. We applied this analysis to our previously published high-coverage RNA sequencing data (<xref ref-type="fig" rid="fig1">Figure 1B</xref>, <xref ref-type="supplementary-material" rid="supp1">Supplementary file 1</xref>). Many of the TE–gene pairs contain more than one chimeric breakpoint, and we therefore obtained splice ratios for 456 individual TE–gene junctions in total.</p><fig id="fig1" position="float"><label>Figure 1.</label><caption><title>Exonisation rates at intronic TE insertion sites.</title><p>(<bold>A</bold>) Schematic of the approach used to quantify exonisation rates. For each TE–gene breakpoint at an endogenous exon–intron junction, TEChim computes the ratio of reads supporting TE-derived splice junctions relative to canonical exon–exon junctions. (<bold>B</bold>) Ranked distribution of TE exonisation efficiencies across intronic and exonic TE insertion sites in the <italic>Drosophila</italic> brain. For each of the 264 TE–gene pairs, the breakpoint with the highest exonisation ratio is shown. Points represent mean exonisation ratios across six biological replicates. Error bars show SEM. The dashed line indicates the mean exonisation rate across all loci. Junction level exonisation ratios, replicate coverage and SEM values are provided in <xref ref-type="supplementary-material" rid="supp1">Supplementary file 1</xref>.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig1-v1.tif"/></fig><p>Across these junctions, splice ratios span almost the full dynamic range from the detection floor to 100%. The median junction has a splice ratio of 3% and a quarter of junctions exceed 15%, indicating that TE-derived exons contribute substantially to the transcript pool at many sites. Where splice ratios can be estimated, values are highly consistent across biological replicates, suggesting that TE exonisation efficiencies are stable properties of individual TE–gene pairs rather than stochastic noise. Overall, these data show that intronic TE insertions in the <italic>Drosophila</italic> brain are frequently recruited as alternative exons, with usage ranging from rare inclusion events to near-constitutive incorporation at the most strongly exonised loci.</p></sec><sec id="s2-2"><title>TE–gene splicing is readily detectable with algorithms that span wider junctions</title><p>RNA sequencing is a highly sensitive method to uncover TE–gene chimeric mRNAs (<xref ref-type="bibr" rid="bib11">Dobin et al., 2013</xref>). Crucially, sequencing reads that span TE–gene breakpoints either exist or they do not: software such as our TEChim approach or Azad et al.’s TIDAL does not infer or predict these reads but simply finds them in the data. In our previous study, TEChim found read support for splicing events into- and out of TEs for 264 TE–gene pairs. For each of these loci we also detected the corresponding TE insertion in gDNA from the same fly strain. For TE families represented in multiple TE–gene pairs, the TE-side breakpoints repeatedly mapped to the same internal position within the TE consensus, rather than being scattered along the TE sequence.</p><p>One clear example is an intronic antisense insertion of the retrotransposon <italic>roo</italic> inside the <italic>mustard (mtd</italic>) gene, which encodes an ecdysone-regulated puff protein. In abCherry flies, TEChim identified 34 reads upstream and 46 reads downstream of the intron–exon junctions in gDNA, confirming the presence and precise location of the insertion (<xref ref-type="fig" rid="fig2">Figure 2A</xref>). In strand-specific RNA-seq data, from six independent biological replicates, TEChim then revealed extensive splicing into- and out of <italic>roo</italic>.</p><fig-group><fig id="fig2" position="float"><label>Figure 2.</label><caption><title>Antisense insertion of roo in mtd introduces cryptic splice donor and acceptor sites.</title><p>(<bold>A</bold>) Schematic of the genomic locus of the mustard gene, including a roo insertion present in abCherry flies. Bar graphs show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim (grey). (<bold>B, C</bold>) Schematic of mustard transcripts -RX, -RF, and -RI, with coding sequences (orange) and UTRs (dark grey). The precise splice acceptor and donor sites on roo are also shown, and sections of roo that are spliced out are shaded in light magenta. Bar graph in B shows the number of breakpoint-spanning reads found in mRNA from abCherry midbrains by TEChim (grey) and TIDAL (red). Bar graphs in C show the number of reads that support splicing events (indicated by light grey lines) between up- and downstream exons, and two conserved loci within roo (grey bars). Each bar is labelled with the precise location of the breakpoint on roo and the reference genome. TIDAL did not find any of these reads. In addition, red arrows indicate the precise location of RT-PCR primers used by Azad et al. Note that one primer of each primer pair maps onto a section of the TE that is actually spliced out. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-v1.tif"/></fig><fig id="fig2s1" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 1.</label><caption><title><italic>roo</italic> repeat regions relative to detected breakpoints.</title><p>Schematic of the <italic>roo</italic> consensus sequence, drawn to scale, with positions shown excluding the long terminal repeats (LTRs; top), and positions of the LTR (bottom). Coloured boxes indicate three annotated repeat features within <italic>roo</italic> (<xref ref-type="bibr" rid="bib12">Domínguez, 2021</xref>): a 99-bp imperfect tandem duplication (positions 277–475), a 25-bp poly-A tract (552–576), and an ~85 bp CAG/AAC microsatellite (641–726). The two breakpoints detected in <italic>mtd</italic> (<xref ref-type="fig" rid="fig2">Figure 2</xref>) at positions 5190 and 5462, fall more than 4 kb downstream of the repeat regions.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp1-v1.tif"/></fig><fig id="fig2s2" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 2.</label><caption><title><italic>tabor</italic> insertion in <italic>CG17698</italic>.</title><p>Upper panel shows a schematic of the genomic locus of the <italic>CG17698</italic> gene, including a <italic>tabor</italic> insertion present in abCherry flies. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Lower panel shows a schematic of the <italic>CG17698-RD</italic> transcript, with coding sequences (orange) and UTRs (dark grey). The splice acceptor site on <italic>tabor</italic> is also shown, and the section of <italic>tabor</italic> that is spliced out is shaded in light magenta. Bar graphs show the number of breakpoint-spanning reads found in mRNA from abCherry midbrains using TEChim (grey) and TIDAL (red). Bar graphs at the bottom show the number of reads that support splicing events (indicated by light grey lines) between two downstream exons and a conserved locus within <italic>tabor</italic> (grey bars). Each bar is labelled with the precise location of the breakpoint on <italic>tabor</italic> and the reference genome. TIDAL did not find any of these reads. In addition, red arrows show the precise location of RT-PCR primers used by Azad et al. Note that one primer maps onto a section of the TE that is actually spliced out. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp2-v1.tif"/></fig><fig id="fig2s3" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 3.</label><caption><title><italic>I-element</italic> insertion in <italic>Pde1C</italic>.</title><p>Upper panel shows a schematic of the genomic locus of the <italic>Pde1C</italic> gene, including an <italic>I-element</italic> insertion present in abCherry flies. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Lower panel shows a schematic of the Pde1C-RB and -RD transcripts, with coding sequences (orange) and UTRs (dark grey). The splice acceptor site on the <italic>I-element</italic> is also shown, and the section of the <italic>I-element</italic> that is spliced out is shaded in light magenta. Bar graphs show the number of breakpoint-spanning reads found in mRNA from abCherry midbrains using TEChim (grey) and TIDAL (red). Bar graph at the bottom shows the number of reads that support splicing events (indicated by light grey line) between the upstream exon and a conserved locus within the <italic>I</italic>-element (grey bar). The bar is labelled with the precise location of the breakpoint on the <italic>I-element</italic> and the reference genome. TIDAL did not find any of these reads. In addition, red arrows show the precise location of RT-PCR primers used by Azad et al. Note that one primer maps onto a section of the TE that is actually spliced out and the other primer to an exon of another splice isoform than reported in abCherry flies. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp3-v1.tif"/></fig><fig id="fig2s4" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 4.</label><caption><title><italic>blood</italic> insertion in <italic>Dscam2</italic>.</title><p>Upper panel shows a schematic of the genomic locus of the <italic>Dscam2</italic> gene, including a <italic>blood</italic> insertion present in abCherry flies. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Lower panel shows a schematic of the <italic>Dscam2-RE</italic> transcript, with coding sequences (orange) and UTRs (dark grey). The splice donor site on <italic>blood</italic> is also shown, and the section of <italic>blood</italic> that is spliced out is shaded in light magenta. Bar graphs show the number of breakpoint-spanning reads found in mRNA from abCherry midbrains using TEChim (grey) and TIDAL (red). Bar graph at the bottom shows the number of reads that support splicing events (indicated by light grey line) between the downstream exons and a conserved locus within <italic>blood</italic> (grey bar). The bar is labelled with the precise location of the breakpoint on <italic>blood</italic> and the reference genome. TIDAL did not find any of these reads. In addition, red arrows show precise location of RT-PCR primers used by Azad et al. Note that one primer maps onto a section of the TE that is actually spliced out. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp4-v1.tif"/></fig><fig id="fig2s5" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 5.</label><caption><title><italic>opus</italic> insertion in <italic>mub</italic>.</title><p>Upper panel shows a schematic of the genomic locus of the <italic>mub</italic> gene, including an <italic>opus</italic> insertion present in abCherry flies. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Lower panel shows a schematic of the <italic>mub-RF</italic> transcript, with UTRs (dark grey). The splice donor site on <italic>opus</italic> is also shown. The first 24 nucleotides of <italic>opus</italic> are spliced out, but this cannot be visualised at the current scale. Bar graphs show the number of breakpoint-spanning reads found in mRNA from abCherry midbrains using TEChim (grey) and TIDAL (red). Bar graph at the bottom shows the number of reads that support splicing events (indicated by light grey line) between the downstream exons and a conserved locus within <italic>opus</italic> (grey bar). The bar is labelled with the precise location of the breakpoint on <italic>opus</italic> and the reference genome. TIDAL did not find any of these reads. In addition, red arrows show precise location of PCR primers used by Azad et al. to genotype their w1118 flies. Note that these primers flank a region ~31 kb upstream of the <italic>opus</italic> insertion in abCherry flies. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp5-v1.tif"/></fig><fig id="fig2s6" position="float" specific-use="child-fig"><label>Figure 2—figure supplement 6.</label><caption><title><italic>mdg3</italic> insertion in <italic>SelR</italic>.</title><p>Upper panel shows a schematic of the genomic locus of the <italic>SelR</italic> gene, including an <italic>mdg3</italic> insertion present in abCherry flies. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Lower panel shows a schematic of the <italic>SelR-RE and -RJ</italic> transcripts, with coding sequences (orange) and UTRs (dark grey). The splice acceptor site on <italic>mdg3</italic> is also shown, and the section of <italic>mdg3</italic> that is spliced out is shaded in light magenta. Bar graphs show the number of breakpoint-spanning reads found in mRNA from abCherry midbrains using TEChim (grey) and TIDAL (red). Bar graph at the bottom shows the number of reads that support splicing events (indicated by light grey line) between the upstream exon and a conserved locus within <italic>mdg3</italic> (grey bar). The bar is labelled with the precise location of the breakpoint on <italic>mdg3</italic> and the reference genome. TIDAL did not find any of these reads. In addition, red arrows show precise location of RT-PCR primers used by Azad et al. Note that one primer maps onto a section of another splice isoform then reported in abCherry flies. Figure is drawn to scale and gDNA and mRNA are aligned to each other.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig2-figsupp6-v1.tif"/></fig></fig-group><p>We found 42 reads that spanned the upstream intron-TE breakpoint of <italic>mtd</italic> pre-mRNA in the midbrain and 21 reads that spanned the downstream breakpoint, consistent with unspliced pre-mRNA (<xref ref-type="fig" rid="fig2">Figure 2B</xref>). In addition, we detected 49 reads that supported splicing between <italic>mtd</italic> exons and internal positions within <italic>roo</italic>. For example, 15 reads spanned a breakpoint that fell precisely at the end of exon 13 and position 5462 within <italic>roo</italic> (<xref ref-type="fig" rid="fig2">Figure 2C</xref>). The antisense sequence leading up to position 5462 resembles the end of an intron and contains a cryptic splice acceptor motif. We also found reads from other upstream exons to the exact same locus within <italic>roo</italic>. Further junctions link position 5190 in <italic>roo</italic> to the next two downstream exons of <italic>mtd</italic>, supported by 28 and 2 reads, respectively. Both breakpoints in <italic>mtd</italic> were supported by reads from all six biological replicates. The <italic>roo</italic> sequence contains an imperfect 99-bp tandem duplication (two copies, spanning positions 277–475), a 25-bp polyA section at 552–576 and a ~85-bp long CAG/AAC microsatellite region at 641–726 (<xref ref-type="bibr" rid="bib12">Domínguez, 2021</xref>) that could, theoretically, interfere with short read mapping. However, these breakpoints map more than 4 kb away from all three regions (<xref ref-type="fig" rid="fig2s1">Figure 2—figure supplement 1</xref>). We also detected the same breakpoints at 28 other genomic loci (26 for pos. 5190, 23 for pos. 5462; <xref ref-type="supplementary-material" rid="supp1">Supplementary file 1</xref>). The precise and recurrent patterns of splicing into canonical sequence sections of <italic>roo</italic> across genomic loci and biological replicates make it extremely unlikely that the breakpoint-spanning reads arise from amplification or mapping artefacts.</p><p>Azad et al. applied TIDAL to our RNA-seq data and detected some pre-mRNA breakpoint-spanning reads at the <italic>mtd-roo</italic> locus (<xref ref-type="fig" rid="fig2">Figure 2B</xref>, red bars), but they failed to recover any reads spanning splicing events between <italic>roo</italic> and neighbouring exons, and reported similar issues for the other TE–gene pairs they examined (see <xref ref-type="fig" rid="fig2s2">Figure 2—figure supplements 2</xref>–<xref ref-type="fig" rid="fig2s6">6</xref>). This likely reflects a limitation of their method rather than an absence of splicing. In particular, TIDAL clusters split reads within a narrow window (twice the read length) around candidate junctions, whereas many TE–gene splice junctions fall outside this range. As a result, genuine splice junctions that are readily detected by TEChim fall below TIDAL’s detection criteria. Taken together with our quantitative exonisation analysis, these locus-level examples show that TE–gene splice isoforms are clearly present in the data and are readily recovered when algorithms are configured to capture the relevant splice junctions.</p></sec><sec id="s2-3"><title>Strain-specific TE landscapes require genotype-matched validation</title><p>TE insertions vary between different lab strains, a well-established phenomenon also documented by the Lau lab (<xref ref-type="bibr" rid="bib18">Rahman et al., 2015</xref>). In our original study, we used abCherry flies, which were the F1 offspring of MB008b males crossed to UAS-mCherry virgin females. Azad et al. attempted to validate the splice events we found in these flies, but used w1118 and OreR flies, which differ substantially in their genotype. They examined 22 of our loci and found that some insertions were conserved, while others were specific to our abCherry flies. Although this result is not surprising given known differences in TE content between strains, Azad et al. nonetheless interpret it as evidence that ‘…the majority (~65%) of the predicted TE insertions using RNA-seq as inputs could potentially be false positives’. This interpretation is problematic and potentially misleading. In summary, conclusions about the reproducibility of TE insertions are not valid when based on genotypically mismatched strains.</p></sec><sec id="s2-4"><title>Accurate primer design enables robust detection of TE–gene splicing</title><p>Strand-specific RNA sequencing enables unbiased, transcriptome-wide detection of splicing events between TEs and genes. Once identified, these events can also be confirmed by a PCR-based approach on cDNA libraries from tissue samples. This requires the careful designing of primers that span both the exon of the gene and the sections of the TE that comprise a given splicing event (<xref ref-type="fig" rid="fig3">Figure 3A</xref>).</p><fig-group><fig id="fig3" position="float"><label>Figure 3.</label><caption><title>Accurate primer design generates independent breakpoint-spanning fragments that confirm splicing between Beadex and opus.</title><p>(<bold>A</bold>) Schematic of the genomic locus of Beadex (Bx) – splice isoform −RA, drawn to scale. Primer pairs used by Azad et al. are shown in red (at the precise point where they map). The primers used here are drawn in black (forward primer: <named-content content-type="sequence">CCTGATCTCACGGTCTCTGT</named-content>; reverse primer: <named-content content-type="sequence">CCTTAATGCCTGTCACCACG</named-content>). The predicted band size for the spliced transcript is 647 bp. (<bold>B</bold>) Electrophoresis gel image of PCR products. The same forward and reverse primers were added to all reactions. The templates for columns 2–4 were three independent biological replicates of +RT samples, columns 5–7 are the matching samples but their −RT control, and column 8 is the no-template-control (NTC). Columns 1 and 9 contain a Quick-load 100  bp ladder. The gel image is cropped around the edges but otherwise unedited (see <xref ref-type="supplementary-material" rid="fig3sdata1 fig3sdata2">Figure 3—source data 1 and 2</xref> for raw image). Dashed box indicates the fragment that was excised and Sanger sequenced. (<bold>C</bold>) Sanger sequencing result of the band from B. Sequence matches the predicted breakpoint between Bx exon 4 and position 902 within opus.</p><p><supplementary-material id="fig3sdata1"><label>Figure 3—source data 1.</label><caption><title>Raw, labelled, uncropped gel of Beadex–opus RT-PCR products from Canton-S midbrain cDNA, with −RT and no-template controls.</title></caption><media mimetype="application/zip" xlink:href="elife-110625-fig3-data1-v1.zip"/></supplementary-material></p><p><supplementary-material id="fig3sdata2"><label>Figure 3—source data 2.</label><caption><title>Labelled gel of Beadex–opus RT-PCR products from Canton-S midbrain cDNA, with −RT and no-template controls.</title></caption><media mimetype="application/zip" xlink:href="elife-110625-fig3-data2-v1.zip"/></supplementary-material></p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig3-v1.tif"/></fig><fig id="fig3s1" position="float" specific-use="child-fig"><label>Figure 3—figure supplement 1.</label><caption><title>Targeted PCR and Sanger sequencing confirms the <italic>opus</italic> insertion in <italic>Bx</italic>, previously identified by whole-genome sequencing of abCherry flies.</title><p>(<bold>A</bold>) Schematic of the genomic locus of <italic>Bx</italic> – splice isoform −RA, drawn to scale. Bar graphs at the top show the number of breakpoint-spanning reads identified in gDNA-sequencing data from abCherry flies, using TEChim. Primer loci are shown in black. The predicted fragment size for a genomic locus with the <italic>opus</italic> insertion is 888 bp for the upstream and 540 bp for the downstream breakpoint. (<bold>B</bold>) Electrophoresis gel image of PCR products. The templates for columns 2–4 and 5–7 are three independent biological replicates of genomic DNA extracted from single CS flies. Columns 1 and 8 contain a Quick-load 100  bp ladder. The gel image is cropped around the edges but otherwise unedited. See the raw, unedited gel image in <xref ref-type="supplementary-material" rid="fig3s1sdata1 fig3s1sdata2">Figure 3—figure supplement 1—source data 1 and 2</xref> for unedited image. Dashed boxes indicate the fragments that were excised and Sanger sequenced. (<bold>C</bold>) Sanger sequencing result of the downstream band from B. The sequence matches the predicted breakpoint between <italic>Bx</italic> and the end of the opus long terminal repeat (LTR). Note that the Sanger sequence was done with the reverse primer, hence the sequence shown is the reverse complement to the positive strand of <italic>Bx</italic> and <italic>opus</italic>. Sanger sequencing of the upstream 888 bp band (also indicated in B) confirmed flanking <italic>Bx</italic> and <italic>opus</italic> sequence, but did not resolve a continuous read across the breakpoint, likely due to a tandem repeat near the <italic>opus</italic> LTR boundary (see published response to reviewers for more details).</p><p><supplementary-material id="fig3s1sdata1"><label>Figure 3—figure supplement 1—source data 1.</label><caption><title>Raw, unlabelled, uncropped gel of genomic PCR products spanning the upstream and downstream opus insertion breakpoints in Beadex.</title></caption><media mimetype="application/zip" xlink:href="elife-110625-fig3-figsupp1-data1-v1.zip"/></supplementary-material></p><p><supplementary-material id="fig3s1sdata2"><label>Figure 3—figure supplement 1—source data 2.</label><caption><title>Labelled gel of genomic PCR products spanning the upstream (888 bp) and downstream (540 bp) opus insertion breakpoints in Beadex.</title></caption><media mimetype="application/zip" xlink:href="elife-110625-fig3-figsupp1-data2-v1.zip"/></supplementary-material></p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig3-figsupp1-v1.tif"/></fig></fig-group><p>Azad et al. intended to test a total of nine genomic loci with this method. However, they made a number of methodological errors in their designs and therefore failed to validate any of the tested splicing events. For five of the insertions, <italic>mtd/roo</italic> (<xref ref-type="fig" rid="fig2">Figure 2</xref>), <italic>Bx/opus</italic> (<xref ref-type="fig" rid="fig3">Figure 3</xref>), <italic>CG17698/tabor</italic> (<xref ref-type="fig" rid="fig2s2">Figure 2—figure supplement 2</xref>), <italic>Pde1C/I-element</italic> (<xref ref-type="fig" rid="fig2s3">Figure 2—figure supplement 3</xref>), <italic>Dscam2/blood</italic> (<xref ref-type="fig" rid="fig2s4">Figure 2—figure supplement 4</xref>), primers were placed within the section of the TE that is spliced out. In one case, <italic>Dscam2/blood</italic>, additional primers within the spliced region produced bands that the authors interpret as pre-spliced transcripts. However, the band size in the Azad et al. Fig. 5Diii (bottom right panel) is not consistent with this interpretation: an unspliced amplicon would be 2165 bp long, whereas a spliced version, as we reported in our study, should be 616 bp. The band appears closer to 616 bp than 2165 bp, although the authors’ decision to crop and combine gels complicates this interpretation.</p><p>Two loci, <italic>Rh7/micropia</italic> and <italic>CaMKII/pogo</italic>, were tested despite the fact we did not report splicing events, and it is therefore unclear which hypothesis was being evaluated. For <italic>mub/opus</italic> (<xref ref-type="fig" rid="fig2s5">Figure 2—figure supplement 5</xref>), the tested insertion in w1118 flies is located 31 kb away from the insertion we reported in abCherry flies and the forward and reverse genomic PCR primers used by Azad et al. flank the wrong site. For <italic>SelR/mdg3</italic> (<xref ref-type="fig" rid="fig2s6">Figure 2—figure supplement 6</xref>), splicing occurs with splice isoforms <italic>SelR-RG</italic>, <italic>-RH</italic>, and <italic>-RJ</italic>, but one of the two primer pairs of Azad et al. was specific to a different splice isoform. Their other primer pair is designed correctly. However, the absence of a band highlights the most important issue with their approach. <italic>Mdg3</italic> is located within the 3′UTR of <italic>SelR</italic>, and this primer pair should produce a PCR fragment even in the absence of splicing. The fact that the authors did not detect a band suggests technical problems with their RT-PCR rather than absence of the underlying transcript.</p><p>RT-PCR requires careful optimisation, and while the presence of a band (and its confirmation using Sanger sequencing) provides strong evidence for the existence of a certain genomic locus or splicing event, the absence of a band cannot reliably be taken as evidence for its absence (<xref ref-type="bibr" rid="bib8">Bustin et al., 2009</xref>).</p><p>To address the concerns raised by Azad et al. directly, we extracted gDNA from Canton-S (CS) flies and designed primer pairs around the upstream- and downstream end of an <italic>opus</italic> insertion within the <italic>Beadex</italic> (<italic>Bx</italic>) gene. We found that CS flies were homozygous for the same insertion that we had found in abCherry flies (<xref ref-type="fig" rid="fig3s1">Figure 3—figure supplement 1</xref>, <xref ref-type="supplementary-material" rid="fig3s1sdata1">Figure 3—figure supplement 1—source data 1</xref>). Next we extracted RNA from three sets of 40 CS fly brains each, generated cDNA libraries and amplified a fragment consistent with our previous observation, where an upstream exon of <italic>Beadex</italic> is spliced into position 902 of <italic>opus</italic> (<xref ref-type="fig" rid="fig3">Figure 3A, B</xref>). We confirmed the band from one of the replicates using Sanger sequencing (<xref ref-type="fig" rid="fig3">Figure 3C</xref>), which precisely matched the predicted breakpoint. A minus RT sample and a water control did not produce a band (<xref ref-type="fig" rid="fig3">Figure 3B</xref>), confirming the amplified bands did not arise from gDNA contamination, or other contaminants in the reagents.</p><p>In summary, the combination of genotypically mismatched strains and suboptimal primer design is sufficient to explain Azad et al.’s negative RT-PCR results. Consistent with our quantitative exonisation analysis and locus-level RNA-seq evidence, TE–gene chimeric transcripts are readily detected when genotype and primer placement are matched to the documented TE insertion and splice junction.</p></sec><sec id="s2-5"><title>TEs in the brain are predominantly expressed as chimeric transcripts</title><p>Our splice-ratio analysis shows that many intronic TE insertions are frequently recruited as alternative exons in neural genes. To place these locus-level observations in a broader context, we next revisit our previous analysis of TE expression modes from our 2020 study (<xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref>). In that study, we asked, at the level of TE families, whether TE-derived sequences detected in brain mRNA arise predominantly from autonomous TE expression, or from co-expression with neighbouring genes as chimeric pre-mRNAs and spliced mature mRNAs. Determining the balance between autonomous and non-autonomous TE expression is challenging because TEs are highly repetitive, which complicates the unambiguous assignment of sequencing reads to specific TE copies.</p><p>In our 2020 study, we addressed this problem using two complementary approaches. First, we compared the average read depth per nucleotide of individual TE families with the abundance of TE–gene breakpoint-spanning reads for those same families (<xref ref-type="fig" rid="fig4">Figure 4A–C</xref>). This analysis indicated that TE expression was most consistent with a non-autonomous origin, arising primarily from co-expression with neighbouring genes. Second, we analysed long terminal repeat (LTR)-containing elements by classifying reads that spanned the LTR and either the internal TE sequence (which can result from both autonomous- and non-autonomous expression), or a flanking genomic region (which can only result from non-autonomous expression). Both approaches supported the conclusion that TEs in the brain are predominantly expressed as part of chimeric mRNAs.</p><fig id="fig4" position="float"><label>Figure 4.</label><caption><title>Schematic highlighting method to assess rate of non-autonomous versus autonomous TE expression.</title><p>(<bold>A, B</bold>) The average read depth per nucleotide within a TE (X) is calculated and compared with the number of breakpoint-spanning reads for the same element (Y). (<bold>C</bold>) Primarily non-autonomously expressed TEs sit in the top left half of the correlation plot, while autonomously expressed TEs are on the bottom right side. The data for this analysis is published in <xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref>.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-fig4-v1.tif"/></fig><p>Azad et al. attempted to revisit this question using a different approach. Instead of quantifying the number of reads supporting chimeric versus non-chimeric transcripts, they compare the rank order of TE families in these two categories. This rank-based comparison lacks a clear biological or statistical interpretation and does not provide a quantitative assessment of TE expression modes. As such, their analysis does not alter the conclusions from our original work that, in the <italic>Drosophila</italic> brain, TE-derived sequences are largely expressed as components of chimeric transcripts, rather than as products of autonomous TE activity.</p></sec></sec><sec id="s3" sec-type="discussion"><title>Discussion</title><p>Here, we show that TE-derived splice isoforms are robust and reproducible features of the <italic>Drosophila</italic> brain transcriptome. By quantifying exonisation rates at 456 TE–gene junctions, we find that intronic TE insertions are frequently recruited as alternative exons, with usage ranging from rare events to near-complete incorporation into mature transcripts at a subset of loci. In-depth analyses of candidate TE–gene pairs, together with RT-PCR validation of the <italic>Bx/opus</italic> junction, reinforce the conclusion that chimeric transcripts are readily detectable with carefully designed experimental and computational approaches. In combination with our previous family-level analysis of TE expression modes, these results support a model in which most TE-derived sequences in the <italic>Drosophila</italic> brain arise from non-autonomous, gene-linked transcripts, rather than widespread autonomous somatic TE expression.</p><p>These observations have important implications for how we think about the architecture of neural genes. Intronic TE insertions do not just add passive sequence, but can act as modular exons that are spliced into mature mRNAs (<xref ref-type="bibr" rid="bib15">Lev-Maor et al., 2003</xref>). Depending on their position within a transcript, TE-derived segments may alter coding sequences, remove protein domains, truncate transcripts, or change untranslated regions that influence RNA stability, localisation, or translational control. Because alternative splicing in the nervous system is strongly cell-type specific, TE-driven splice variants provide a straightforward route for generating cell-type specific versions of the same gene product, with distinct TE-derived variants expressed in different neuronal or glial populations (<xref ref-type="bibr" rid="bib7">Brown et al., 2014</xref>; <xref ref-type="bibr" rid="bib19">Torres-Méndez et al., 2022</xref>). Although the present study does not directly address protein output or physiological function, the exonisation rates we report imply that, for many genes, a substantial fraction of transcripts carries TE-derived sequence. This makes it plausible that TE exonisation contributes to the fine-tuning of neural gene function, rather than representing a negligible by-product of noisy splicing.</p><p>Beyond cell-type specific regulation, TE exonisation also provides a simple genetic route to variability in neural transcriptomes between individuals and strains. We and others have shown that TE insertion landscapes differ markedly between <italic>Drosophila</italic> strains, and even between individuals. For example, Azad et al. independently confirmed that several insertions we describe are specific to the abCherry background. In a framework where intronic TEs are frequently exonised, such genetic differences translate directly into inter-individual differences in the splice-isoform repertoire of neural genes. One consequence is that genetically distinct flies may express overlapping, but non-identical TE landscapes, which could contribute to variability in neural circuit properties and behaviour between individuals. In the future it will be important to combine TE-aware transcriptomics with single-cell sequencing to determine how TE-derived isoforms are distributed across neural cell types.</p><p>A second set of implications concerns methodology. Our re-analysis of the Azad et al. study, especially of their primer sequences, underscores how algorithmic and experimental choices can mask genuine TE–gene splice isoforms. Algorithms like TIDAL, that cluster split reads within narrow genomic windows, or that are not explicitly designed to capture TE–gene architectures, will fail to recover many of the junctions that are visible in the underlying reads. TEChim addresses this by reconstructing full-length fragments from overlapping paired-end reads, mapping these reads to a masked reference genome, and resolving breakpoints with base-pair precision, rather than clustering them within a fixed window. In addition, in TEChim, false discovery rates (FDRs) are estimated empirically: expression-matched immobile genetic elements (IGEs) – coding exons chosen to match the expression level of each TE, which, unlike TEs, cannot themselves relocate in the genome – are used to measure the background rate of spurious chimeric reads, and candidate TE–gene breakpoints are only retained once their support exceeds a set FDR. Likewise, RT-PCR validation is only informative when performed in genotype-matched samples using primers that span the reported splice junctions, and when negative results are interpreted in light of assay sensitivity. Emerging direct long-read RNA sequencing technologies offer an attractive complementary approach for validating TE-derived splice isoforms, capturing full-length transcripts and reducing the ambiguity of mapping short reads onto repetitive TE sequence. Such approaches have recently been used to detect analogous TE–gene fusion transcripts in human stem cells and brain tissue (<xref ref-type="bibr" rid="bib1">Adami et al., 2025</xref>; <xref ref-type="bibr" rid="bib14">Garza et al., 2023</xref>). Direct RNA sequencing of <italic>Drosophila</italic> brain tissue remains challenging, however, due to the limited RNA input available per sample. Current protocols therefore still require an amplification step, which can itself introduce chimeric artefacts (<xref ref-type="bibr" rid="bib20">Treiber and Waddell, 2017</xref>). As long-read protocols that require less input material become available, they are likely to further strengthen the characterisation of TE-derived transcript diversity.</p><p>More generally, TE transcriptomics requires explicit attention to read mapping, breakpoint calling, strain background and primer design. We suggest that the field would benefit from adopting best-practice guidelines similar to those developed for quantitative PCR (<xref ref-type="bibr" rid="bib8">Bustin et al., 2009</xref>), with clear standards for reporting TE-aware RNA-seq analyses and breakpoint-level validation.</p><p>Several limitations of our study point to concrete next steps. First, our quantitative analysis focuses on a curated set of 264 TE–gene pairs, derived from a single <italic>Drosophila</italic> genotype and bulk midbrain RNA-seq data. Many additional TE insertions likely remain below our detection threshold because of limited read depth or cell-type specific expression. Second, splice ratios in bulk RNA-seq data provide a useful summary of exon usage but do not distinguish between different cell types or developmental stages, and they do not directly reveal whether TE-derived isoforms are translated. Addressing these questions will require TE-aware single-cell sequencing, together with targeted proteomics and genetic manipulations that remove or edit individual TE-derived exons. Finally, while our data show that TE-derived isoforms are reproducible and often abundant, their functional consequences for neuronal physiology and behaviour remain to be tested.</p><p>In summary, our work strengthens the view that TEs are not merely genomic parasites or sources of noise, but active contributors to neural gene regulation. Intronic TEs in the <italic>Drosophila</italic> brain are frequently exonised, giving rise to stable chimeric transcripts that expand the splice-isoform repertoire of neuronal and glial genes. By clarifying the methodological requirements for detecting these events and by quantifying their prevalence, we provide a framework for future studies to investigate when and how TE-derived isoforms have been co-opted into neural function.</p></sec><sec id="s4" sec-type="materials|methods"><title>Materials and methods</title><table-wrap id="keyresource" position="anchor"><label>Key resources table</label><table frame="hsides" rules="groups"><thead><tr><th align="left" valign="bottom">Reagent type (species) or resource</th><th align="left" valign="bottom">Designation</th><th align="left" valign="bottom">Source or reference</th><th align="left" valign="bottom">Identifiers</th><th align="left" valign="bottom">Additional information</th></tr></thead><tbody><tr><td align="left" valign="bottom">Strain, strain background (<italic>Drosophila melanogaster</italic>, male and female)</td><td align="left" valign="bottom">Canton-S (CS)</td><td align="left" valign="bottom">Bloomington Drosophila Stock Center</td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:BDSC_64349">BDSC_64349</ext-link></td><td align="left" valign="bottom">Wild-type strain; homozygous for the opus insertion in Bx (<xref ref-type="fig" rid="fig3s1">Figure 3—figure supplement 1</xref>). See Materials and methods, Fly stocks</td></tr><tr><td align="left" valign="bottom">Gene (<italic>D. melanogaster</italic>)</td><td align="left" valign="bottom"><italic>mustard</italic>; <italic>mtd</italic></td><td align="left" valign="bottom">FlyBase</td><td align="left" valign="bottom">FLYB: FBgn0013576</td><td align="left" valign="bottom">Host gene of the antisense roo insertion (<xref ref-type="fig" rid="fig2">Figure 2</xref>)</td></tr><tr><td align="left" valign="bottom">Gene (<italic>D. melanogaster</italic>)</td><td align="left" valign="bottom"><italic>Beadex</italic>; <italic>Bx</italic></td><td align="left" valign="bottom">FlyBase</td><td align="left" valign="bottom">FLYB: FBgn0265598</td><td align="left" valign="bottom">Host gene of the opus insertion; splice isoform Bx-RA (<xref ref-type="fig" rid="fig3">Figure 3</xref>)</td></tr><tr><td align="left" valign="bottom">Other</td><td align="left" valign="bottom"><italic>roo</italic> (transposable element)</td><td align="left" valign="bottom">FlyBase</td><td align="left" valign="bottom">FLYB: FBte0000100</td><td align="left" valign="bottom">LTR retrotransposon; consensus sequence used for breakpoint mapping (<xref ref-type="fig" rid="fig2">Figure 2</xref>, <xref ref-type="fig" rid="fig2s1">Figure 2—figure supplement 1</xref>)</td></tr><tr><td align="left" valign="bottom">Other</td><td align="left" valign="bottom"><italic>opus</italic> (transposable element)</td><td align="left" valign="bottom">FlyBase</td><td align="left" valign="bottom">FLYB FBte0000918</td><td align="left" valign="bottom">LTR retrotransposon; consensus sequence used for breakpoint mapping and primer design (<xref ref-type="fig" rid="fig3">Figure 3</xref>)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_ex_L_fwd_2</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">CCTGATCTCACGGTCTCTGT</named-content>; RT-PCR across the Bx exon 4::opus-902 junction (647 bp product)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_TEs1_L_rev_1</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">CCTTAATGCCTGTCACCACG</named-content>; RT-PCR across the Bx exon 4::opus-902 junction (647 bp product)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_In_L_fwd_1</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">GGGTTGCGGCTAAACAGATC</named-content>; genotyping, upstream Bx intron::opus LTR breakpoint (888 bp product)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_TE_L_rev_1</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">TGACAACCAACATGCTGTGG</named-content>; genotyping, upstream Bx intron::opus LTR breakpoint (888 bp product)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_TE_R_fwd_1</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">GGATATAAAAGCAGCGGGGC</named-content>; genotyping, downstream opus LTR::Bx breakpoint (540 bp product)</td></tr><tr><td align="left" valign="bottom">Sequence-based reagent</td><td align="left" valign="bottom">C003_In_R_rev_2</td><td align="left" valign="bottom">This paper</td><td align="left" valign="bottom">PCR primer</td><td align="left" valign="bottom"><named-content content-type="sequence">GCGTTTTGTGGCGTGTTAAT</named-content>; genotyping, downstream opus LTR::Bx breakpoint (540 bp product)</td></tr><tr><td align="left" valign="bottom">Commercial assay or kit</td><td align="left" valign="bottom">ReliaPrep RNA Tissue Miniprep System</td><td align="left" valign="bottom">Promega</td><td align="left" valign="bottom">Cat#Z6014</td><td align="left" valign="bottom">RNA extraction from midbrains, including DNase I treatment</td></tr><tr><td align="left" valign="bottom">Commercial assay or kit</td><td align="left" valign="bottom">GoScript Reverse Transcription Mix, Oligo(dT)</td><td align="left" valign="bottom">Promega</td><td align="left" valign="bottom">Cat#A279_</td><td align="left" valign="bottom">First-strand cDNA synthesis (+RT and −RT reactions)</td></tr><tr><td align="left" valign="bottom">Commercial assay or kit</td><td align="left" valign="bottom">2X Taq PCR Master Mix</td><td align="left" valign="bottom">APExBIO</td><td align="left" valign="bottom">Cat#M0270L</td><td align="left" valign="bottom">RT-PCR and genomic PCR</td></tr><tr><td align="left" valign="bottom">Commercial assay or kit</td><td align="left" valign="bottom">QIAquick Gel Extraction Kit</td><td align="left" valign="bottom">QIAGEN</td><td align="left" valign="bottom">Cat#28704</td><td align="left" valign="bottom">Gel purification of PCR products for Sanger sequencing</td></tr><tr><td align="left" valign="bottom">Peptide, recombinant protein</td><td align="left" valign="bottom">Proteinase K</td><td align="left" valign="bottom">QIAGEN</td><td align="left" valign="bottom">Cat#19131</td><td align="left" valign="bottom">(200 µg/ml) in squishing buffer for single-fly genomic DNA preparation</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">TEChim</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref> (doi:<ext-link ext-link-type="uri" xlink:href="https://doi.org/10.1101/gr.259200.119">10.1101/gr.259200.119</ext-link>); this paper (<xref ref-type="bibr" rid="bib23">Treiber, 2026</xref>)</td><td align="left" valign="bottom"><ext-link ext-link-type="uri" xlink:href="https://github.com/charliefornia/TEchim/releases/tag/v1.0.0">https://github.com/charliefornia/TEchim/releases/tag/v1.0.0</ext-link></td><td align="left" valign="bottom">Updated version used here (computes TE exonisation ratios). See Materials and methods, TEChim</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">FLASH</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib17">Magoč and Salzberg, 2011</xref></td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:SCR_005531">SCR_005531</ext-link></td><td align="left" valign="bottom">Merging of overlapping paired-end reads</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">STAR</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib11">Dobin et al., 2013</xref></td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:SCR_004463">SCR_004463</ext-link></td><td align="left" valign="bottom">Read alignment</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">SAMtools</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib16">Li et al., 2009</xref></td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:SCR_002105">SCR_002105</ext-link></td><td align="left" valign="bottom">Flag filtering of breakpoint-spanning reads</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">BLAST</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib3">Altschul et al., 1990</xref></td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:SCR_004870">SCR_004870</ext-link></td><td align="left" valign="bottom">Breakpoint resolution</td></tr><tr><td align="left" valign="bottom">Software, algorithm</td><td align="left" valign="bottom">ApE (A plasmid Editor)</td><td align="left" valign="bottom"><xref ref-type="bibr" rid="bib10">Davis and Jorgensen, 2022</xref></td><td align="left" valign="bottom">RRID:<ext-link ext-link-type="uri" xlink:href="https://identifiers.org/RRID:SCR_014266">SCR_014266</ext-link></td><td align="left" valign="bottom">Locus reconstruction and primer design</td></tr><tr><td align="left" valign="bottom">Other</td><td align="left" valign="bottom">SYBR Safe DNA Gel Stain</td><td align="left" valign="bottom">Invitrogen</td><td align="left" valign="bottom">Cat#S33102</td><td align="left" valign="bottom">Agarose gel staining</td></tr><tr><td align="left" valign="bottom">Other</td><td align="left" valign="bottom">Quick-Load 100 bp DNA Ladder</td><td align="left" valign="bottom">New England Biolabs</td><td align="left" valign="bottom">Cat#N0467S</td><td align="left" valign="bottom">Size marker for gel electrophoresis (<xref ref-type="fig" rid="fig3">Figure 3</xref>, <xref ref-type="fig" rid="fig3s1">Figure 3—figure supplement 1</xref>)</td></tr><tr><td align="left" valign="bottom">Other</td><td align="left" valign="bottom">Sanger sequencing service</td><td align="left" valign="bottom">Source Bioscience (Nottingham, UK)</td><td align="left" valign="bottom"/><td align="left" valign="bottom">Sequencing of gel-purified PCR products</td></tr></tbody></table></table-wrap><sec id="s4-1"><title>TEChim</title><p>RNA sequencing data was downloaded from the NCBI BioProject Database (<ext-link ext-link-type="uri" xlink:href="https://www.ncbi.nlm.nih.gov/bioproject/">https://www.ncbi.nlm.nih.gov/bioproject/</ext-link>) with the accession number PRJNA588978 (<xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref>). Chimeric TE–gene reads were identified using an updated version of TEChim. Paired-end reads were merged with FLASH (<xref ref-type="bibr" rid="bib17">Magoč and Salzberg, 2011</xref>) into contigs and separated again in silico to generate new paired-end reads, which were mapped to a repeat-masked reference genome that also contained a single copy of each consensus transposon sequence (and a separate, single section of the LTR, where relevant), using STAR (<xref ref-type="bibr" rid="bib11">Dobin et al., 2013</xref>). Breakpoint-spanning reads were identified using samtools flag filtering (<xref ref-type="bibr" rid="bib16">Li et al., 2009</xref>), and precise breakpoints were resolved from the corresponding contig using BLAST (<xref ref-type="bibr" rid="bib3">Altschul et al., 1990</xref>). For mRNA data, candidate breakpoints were then intersected with annotated exon/intron sections and canonical splice sites. The background rate of spurious chimeric reads was estimated using expression-matched IGEs that cannot mobilise in the genome, and used to define a cutoff for a given FDR. The full pipeline, and detailed documentation are available at <ext-link ext-link-type="uri" xlink:href="https://github.com/charliefornia/TEchim">https://github.com/charliefornia/TEchim</ext-link> (copy archived at <xref ref-type="bibr" rid="bib9">charliefornia, 2026</xref>).</p></sec><sec id="s4-2"><title>Fly stocks</title><p>Wild-type Canton-S flies (Bloomington stock # 64349) were raised on standard brown cornmeal agar food at room temperature and collected at 3–5 days post-eclosion.</p></sec><sec id="s4-3"><title>RNA extraction</title><p>RNA was extracted using a Promega ReliaPrep RNA Tissue Miniprep kit. Midbrains of 20 male and 20 female flies per biological replicate (<italic>n</italic> = 3 independent biological replicates) were dissected directly into lysis buffer, and tissue was lysed using a Kinematica AG PT1200 Polytron homogenizer. Samples were processed following the standard protocol, including DNAse1 incubation to reduce gDNA contamination. Samples were eluted in 22 µl nuclease-free water.</p></sec><sec id="s4-4"><title>cDNA library preparation</title><p>First-strand cDNA synthesis was performed using a Promega GoScript Reverse Transcription Mix Oligo(dT) primer. For each biological replicate, the RNA eluate was split into two 10 µl aliquots – one was incubated together with GoScript Reverse Transcriptase (‘+RT’), and one processed identically, with the same buffers, but without enzyme (‘−RT’, the enzyme volume was instead substituted by nuclease-free water).</p></sec><sec id="s4-5"><title>Primer design for RT-PCR</title><p>Candidate splicing events were first identified using TEChim (see above) and the mRNA and gDNA data were used to reproduce the precise genomic locus, including up- and downstream exons, in ApE (<xref ref-type="bibr" rid="bib10">Davis and Jorgensen, 2022</xref>). For RT-PCR validation, we designed a gene-specific forward primer upstream of the exon–intron junction in <italic>Bx</italic>, and a TE-specific reverse primer in the region downstream of the cryptic splice acceptor site in <italic>opus</italic> (see <xref ref-type="fig" rid="fig3">Figure 3A</xref>), so that the product is only generated across the splice junction, and not from unspliced gDNA. Primer design was complicated because <italic>opus</italic>, like most TE sequences, occurs in multiple copies along the <italic>Drosophila</italic> genome. It was therefore necessary to test two to three different primer combinations at varying distances from the predicted junction. Every resulting product was Sanger sequenced to confirm it matched the predicted spliced mRNA fragment.</p></sec><sec id="s4-6"><title>RT-PCR</title><p>cDNA libraries (+RT) and matched −RT controls were analysed in parallel. We followed a standard PCR protocol with APExBT 2X Taq PCR Master Mix, a 1:10 dilution of the stock cDNA libraries, the forward primer: <named-content content-type="sequence">CCTGATCTCACGGTCTCTGT</named-content> and the reverse primer: <named-content content-type="sequence">CCTTAATGCCTGTCACCACG</named-content>, with the following conditions: initial denaturation at 94°C for 2 min, followed by 40 cycles of 94°C for 15 s, 56°C for 15 s, and 72°C for 30 s, with a final hold at 4°C. In parallel, a no-template control, with nuclease-free water substituted for cDNA, was included to confirm the absence of contaminating amplification.</p></sec><sec id="s4-7"><title>gDNA extraction and PCR</title><p>gDNA was extracted from individual Canton-S flies using a rapid single-fly squish preparation. Single flies were homogenised in 50 µl squishing buffer (10 mM Tris-HCl pH 8.0, 1 mM EDTA, 25 mM NaCl) containing 200 µg/ml Proteinase K, added from stock. Homogenates were incubated at 37°C for 30 min, then heat-inactivated at 95°C for 5 min. Debris were pelleted by brief centrifugation, and the supernatant was decanted into a fresh Eppendorf tube. 1 µl of a 1:10 dilution of this supernatant was used directly as template for each gDNA PCR reaction. The opus insertion within the Bx gene was confirmed by a junction spanning PCR on each end. For the upstream end, we used a forward primer in the intron of Bx (<named-content content-type="sequence">GGGTTGCGGCTAAACAGATC</named-content>) and a reverse primer within the LTR of opus (<named-content content-type="sequence">TGACAACCAACATGCTGTGG</named-content>), with a predicted fragment size of 888 bp if the insertion is present, and no band if it is not. For the downstream end, we used a forward primer <named-content content-type="sequence">GGATATAAAAGCAGCGGGGC</named-content> and reverse primer <named-content content-type="sequence">GCGTTTTGTGGCGTGTTAAT</named-content>, with an expected fragment size of 540 bp. PCR produced bands of the expected size in Canton-S, confirmed by Sanger sequencing.</p></sec><sec id="s4-8"><title>Sanger sequencing</title><p>PCR products (both from cDNA and gDNA) were loaded on a 1% agarose gel supplemented with SYBRsafe alongside a Quick-Load 100 bp DNA Ladder (New England Biolabs), and size separated using standard gel electrophoresis. Bands were excised and purified using a QIAquick Gel Extraction Kit (QIAGEN) following the manufacturer’s protocol, with an elution volume of 30 µl. Sanger sequencing was performed by Source Bioscience (Nottingham, UK).</p></sec><sec id="s4-9"><title>Declaration of generative AI and AI-assisted technologies in the writing process</title><p>Generative AI (ChatGPT, OpenAI and Claude, Anthropic) was used during the drafting process to help refine sentence structure, improve clarity, and explore alternative phrasings. All content, data interpretation, and scientific arguments were conceived, written, and verified by the authors.</p></sec></sec></body><back><sec sec-type="additional-information" id="s5"><title>Additional information</title><fn-group content-type="competing-interest"><title>Competing interests</title><fn fn-type="COI-statement" id="conf1"><p>No competing interests declared</p></fn></fn-group><fn-group content-type="author-contribution"><title>Author contributions</title><fn fn-type="con" id="con1"><p>Formal analysis, Validation, Investigation, Visualization, Writing – review and editing</p></fn><fn fn-type="con" id="con2"><p>Formal analysis, Validation, Investigation, Visualization, Writing – review and editing</p></fn><fn fn-type="con" id="con3"><p>Conceptualization, Data curation, Software, Formal analysis, Funding acquisition, Investigation, Visualization, Writing – original draft</p></fn></fn-group></sec><sec sec-type="supplementary-material" id="s6"><title>Additional files</title><supplementary-material id="supp1"><label>Supplementary file 1.</label><caption><title>TE–gene chimeric breakpoints and splice ratios identified by TEChim Full list of TE–gene chimeric breakpoints identified by TEChim in high-coverage RNA sequencing data from abCherry <italic>Drosophila</italic> midbrains, corresponding to the analysis in <xref ref-type="fig" rid="fig1">Figure 1</xref>.</title><p>Each row is one TE–gene breakpoint along the genome. The ‘te_gene_pair_IDs’ were curated manually and are shared across rows where a TE–gene pair contains more than one breakpoint. ‘gene_ID’, ‘gene_name’, ‘gene_chr’, ‘gene_strand’, and ‘gene_breakpoint’ identify the precise genomic location of the detected breakpoint. ‘te_name’ is the inserted TE, ‘breakpoint_type’ indicates whether the contiguous fragment starts with the TE- or gene sequence (relative to the coding strand direction), and ‘te_orientation’ is the strand of the TE at that breakpoint. ‘samples’ and ‘reads’ give the number of samples and the total number of distinct breakpoint-spanning reads supporting the call, and ‘assay’ indicates whether the call was based on stranded (mRNA) or unstranded sequencing data. ‘te_concatenated’ lists all TE names contributing to a merged call. Where a breakpoint coincides with an annotated splice donor or acceptor site, ‘splice_site’ gives its genomic coordinates. ‘gene_features’ lists all annotated gene, transcript and feature (exon, intron, UTR, and CDS) combinations overlapping with the genomic breakpoint. ‘te_breakpoints’ gives the precise breakpoint position on the TE consensus sequence, with the number of supporting reads at each locus. Note that coordinates either refer to the LTR of a TE, or the core segment only. ‘supporting_reads_per_sample’ and ‘gene_to_gene_reads_per_sample’ give, for each sample, the number of reads supporting a splicing event into or out of a TE, and the number supporting the canonical (non-TE) splicing event at the same junction, respectively. The latter is taken from the corresponding STAR aligner splice-junction file (see TEChim manual on GitHub for details). ‘te_ratio_per_sample’, ‘mean_ratio’, and ‘SEM_of_ratios’ were added during post-processing, and represent the proportion of reads at that junction supporting TE inclusion, relative to the total number of reads supporting either splicing outcome. Splice ratios are only calculated for breakpoints coinciding with an annotated splice site.</p></caption><media xlink:href="elife-110625-supp1-v1.csv" mimetype="application/octet-stream"/></supplementary-material><supplementary-material id="mdar"><label>MDAR checklist</label><media xlink:href="elife-110625-mdarchecklist1-v1.pdf" mimetype="application/pdf"/></supplementary-material></sec><sec sec-type="data-availability" id="s7"><title>Data availability</title><p>Data has been made publicly available as part of a previous study (<xref ref-type="bibr" rid="bib21">Treiber and Waddell, 2020a</xref>, <xref ref-type="bibr" rid="bib22">Treiber and Waddell, 2020b</xref>).</p></sec><ref-list><title>References</title><ref id="bib1"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Adami</surname><given-names>A</given-names></name><name><surname>Garza</surname><given-names>R</given-names></name><name><surname>Gerdes</surname><given-names>P</given-names></name><name><surname>Johansson</surname><given-names>PA</given-names></name><name><surname>Dorazehi</surname><given-names>F</given-names></name><name><surname>Koutounidou</surname><given-names>S</given-names></name><name><surname>Castilla-Vallmanya</surname><given-names>L</given-names></name><name><surname>Atacho</surname><given-names>DAM</given-names></name><name><surname>Sharma</surname><given-names>Y</given-names></name><name><surname>Johansson</surname><given-names>JG</given-names></name><name><surname>Tam</surname><given-names>O</given-names></name><name><surname>Kirkeby</surname><given-names>A</given-names></name><name><surname>Barker</surname><given-names>RA</given-names></name><name><surname>Hammell</surname><given-names>MG</given-names></name><name><surname>Douse</surname><given-names>CH</given-names></name><name><surname>Jakobsson</surname><given-names>J</given-names></name></person-group><year iso-8601-date="2025">2025</year><article-title>LINE-1 retrotransposons mediate cis-acting transcriptional control in human pluripotent stem cells and regulate early brain development</article-title><source>Cell Genomics</source><volume>5</volume><elocation-id>100979</elocation-id><pub-id pub-id-type="doi">10.1016/j.xgen.2025.100979</pub-id><pub-id pub-id-type="pmid">40848716</pub-id></element-citation></ref><ref id="bib2"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Akagi</surname><given-names>K</given-names></name><name><surname>Li</surname><given-names>J</given-names></name><name><surname>Stephens</surname><given-names>RM</given-names></name><name><surname>Volfovsky</surname><given-names>N</given-names></name><name><surname>Symer</surname><given-names>DE</given-names></name></person-group><year iso-8601-date="2008">2008</year><article-title>Extensive variation between inbred mouse strains due to endogenous L1 retrotransposition</article-title><source>Genome Research</source><volume>18</volume><fpage>869</fpage><lpage>880</lpage><pub-id pub-id-type="doi">10.1101/gr.075770.107</pub-id><pub-id pub-id-type="pmid">18381897</pub-id></element-citation></ref><ref id="bib3"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Altschul</surname><given-names>SF</given-names></name><name><surname>Gish</surname><given-names>W</given-names></name><name><surname>Miller</surname><given-names>W</given-names></name><name><surname>Myers</surname><given-names>EW</given-names></name><name><surname>Lipman</surname><given-names>DJ</given-names></name></person-group><year iso-8601-date="1990">1990</year><article-title>Basic local alignment search tool</article-title><source>Journal of Molecular Biology</source><volume>215</volume><fpage>403</fpage><lpage>410</lpage><pub-id pub-id-type="doi">10.1016/S0022-2836(05)80360-2</pub-id><pub-id pub-id-type="pmid">2231712</pub-id></element-citation></ref><ref id="bib4"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Arribas</surname><given-names>YA</given-names></name><name><surname>Baudon</surname><given-names>B</given-names></name><name><surname>Rotival</surname><given-names>M</given-names></name><name><surname>Suárez</surname><given-names>G</given-names></name><name><surname>Bonté</surname><given-names>PE</given-names></name><name><surname>Casas</surname><given-names>V</given-names></name><name><surname>Roubert</surname><given-names>A</given-names></name><name><surname>Klein</surname><given-names>P</given-names></name><name><surname>Bonnin</surname><given-names>E</given-names></name><name><surname>Mchich</surname><given-names>B</given-names></name><name><surname>Legoix</surname><given-names>P</given-names></name><name><surname>Baulande</surname><given-names>S</given-names></name><name><surname>Sadacca</surname><given-names>B</given-names></name><name><surname>Diharce</surname><given-names>J</given-names></name><name><surname>Waterfall</surname><given-names>JJ</given-names></name><name><surname>Etchebest</surname><given-names>C</given-names></name><name><surname>Carrascal</surname><given-names>M</given-names></name><name><surname>Goudot</surname><given-names>C</given-names></name><name><surname>Quintana-Murci</surname><given-names>L</given-names></name><name><surname>Burbage</surname><given-names>M</given-names></name><name><surname>Merlotti</surname><given-names>A</given-names></name><name><surname>Amigorena</surname><given-names>S</given-names></name></person-group><year iso-8601-date="2024">2024</year><article-title>Transposable element exonization generates a reservoir of evolving and functional protein isoforms</article-title><source>Cell</source><volume>187</volume><fpage>7603</fpage><lpage>7620</lpage><pub-id pub-id-type="doi">10.1016/j.cell.2024.11.011</pub-id><pub-id pub-id-type="pmid">39667937</pub-id></element-citation></ref><ref id="bib5"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Azad</surname><given-names>MF</given-names></name><name><surname>Tong</surname><given-names>T</given-names></name><name><surname>Lau</surname><given-names>NC</given-names></name></person-group><year iso-8601-date="2024">2024</year><article-title>Transposable Element (TE) insertion predictions from RNAseq inputs and TE impact on RNA splicing and gene expression in Drosophila brain transcriptomes</article-title><source>Mobile DNA</source><volume>15</volume><elocation-id>20</elocation-id><pub-id pub-id-type="doi">10.1186/s13100-024-00330-z</pub-id><pub-id pub-id-type="pmid">39385293</pub-id></element-citation></ref><ref id="bib6"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Bennett</surname><given-names>EA</given-names></name><name><surname>Coleman</surname><given-names>LE</given-names></name><name><surname>Tsui</surname><given-names>C</given-names></name><name><surname>Pittard</surname><given-names>WS</given-names></name><name><surname>Devine</surname><given-names>SE</given-names></name></person-group><year iso-8601-date="2004">2004</year><article-title>Natural genetic variation caused by transposable elements in humans</article-title><source>Genetics</source><volume>168</volume><fpage>933</fpage><lpage>951</lpage><pub-id pub-id-type="doi">10.1534/genetics.104.031757</pub-id><pub-id pub-id-type="pmid">15514065</pub-id></element-citation></ref><ref id="bib7"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Brown</surname><given-names>JB</given-names></name><name><surname>Boley</surname><given-names>N</given-names></name><name><surname>Eisman</surname><given-names>R</given-names></name><name><surname>May</surname><given-names>GE</given-names></name><name><surname>Stoiber</surname><given-names>MH</given-names></name><name><surname>Duff</surname><given-names>MO</given-names></name><name><surname>Booth</surname><given-names>BW</given-names></name><name><surname>Wen</surname><given-names>J</given-names></name><name><surname>Park</surname><given-names>S</given-names></name><name><surname>Suzuki</surname><given-names>AM</given-names></name><name><surname>Wan</surname><given-names>KH</given-names></name><name><surname>Yu</surname><given-names>C</given-names></name><name><surname>Zhang</surname><given-names>D</given-names></name><name><surname>Carlson</surname><given-names>JW</given-names></name><name><surname>Cherbas</surname><given-names>L</given-names></name><name><surname>Eads</surname><given-names>BD</given-names></name><name><surname>Miller</surname><given-names>D</given-names></name><name><surname>Mockaitis</surname><given-names>K</given-names></name><name><surname>Roberts</surname><given-names>J</given-names></name><name><surname>Davis</surname><given-names>CA</given-names></name><name><surname>Frise</surname><given-names>E</given-names></name><name><surname>Hammonds</surname><given-names>AS</given-names></name><name><surname>Olson</surname><given-names>S</given-names></name><name><surname>Shenker</surname><given-names>S</given-names></name><name><surname>Sturgill</surname><given-names>D</given-names></name><name><surname>Samsonova</surname><given-names>AA</given-names></name><name><surname>Weiszmann</surname><given-names>R</given-names></name><name><surname>Robinson</surname><given-names>G</given-names></name><name><surname>Hernandez</surname><given-names>J</given-names></name><name><surname>Andrews</surname><given-names>J</given-names></name><name><surname>Bickel</surname><given-names>PJ</given-names></name><name><surname>Carninci</surname><given-names>P</given-names></name><name><surname>Cherbas</surname><given-names>P</given-names></name><name><surname>Gingeras</surname><given-names>TR</given-names></name><name><surname>Hoskins</surname><given-names>RA</given-names></name><name><surname>Kaufman</surname><given-names>TC</given-names></name><name><surname>Lai</surname><given-names>EC</given-names></name><name><surname>Oliver</surname><given-names>B</given-names></name><name><surname>Perrimon</surname><given-names>N</given-names></name><name><surname>Graveley</surname><given-names>BR</given-names></name><name><surname>Celniker</surname><given-names>SE</given-names></name></person-group><year iso-8601-date="2014">2014</year><article-title>Diversity and dynamics of the Drosophila transcriptome</article-title><source>Nature</source><volume>512</volume><fpage>393</fpage><lpage>399</lpage><pub-id pub-id-type="doi">10.1038/nature12962</pub-id><pub-id pub-id-type="pmid">24670639</pub-id></element-citation></ref><ref id="bib8"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Bustin</surname><given-names>SA</given-names></name><name><surname>Benes</surname><given-names>V</given-names></name><name><surname>Garson</surname><given-names>JA</given-names></name><name><surname>Hellemans</surname><given-names>J</given-names></name><name><surname>Huggett</surname><given-names>J</given-names></name><name><surname>Kubista</surname><given-names>M</given-names></name><name><surname>Mueller</surname><given-names>R</given-names></name><name><surname>Nolan</surname><given-names>T</given-names></name><name><surname>Pfaffl</surname><given-names>MW</given-names></name><name><surname>Shipley</surname><given-names>GL</given-names></name><name><surname>Vandesompele</surname><given-names>J</given-names></name><name><surname>Wittwer</surname><given-names>CT</given-names></name></person-group><year iso-8601-date="2009">2009</year><article-title>The MIQE guidelines: minimum information for publication of quantitative real-time PCR experiments</article-title><source>Clinical Chemistry</source><volume>55</volume><fpage>611</fpage><lpage>622</lpage><pub-id pub-id-type="doi">10.1373/clinchem.2008.112797</pub-id><pub-id pub-id-type="pmid">19246619</pub-id></element-citation></ref><ref id="bib9"><element-citation publication-type="software"><person-group person-group-type="author"><collab-name>charliefornia</collab-name></person-group><year iso-8601-date="2026">2026</year><data-title>TEchim</data-title><version designator="swh:1:rev:237d56ce295f4b9fe9e56b5b556e2de1562ce180">swh:1:rev:237d56ce295f4b9fe9e56b5b556e2de1562ce180</version><source>Software Heritage</source><ext-link ext-link-type="uri" xlink:href="https://archive.softwareheritage.org/swh:1:dir:22125d7ddabad7cb42f1212c8534956ada96b64c;origin=https://github.com/charliefornia/TEchim;visit=swh:1:snp:b67f224e34e81c18581b87684d427b24b93b61ab;anchor=swh:1:rev:237d56ce295f4b9fe9e56b5b556e2de1562ce180">https://archive.softwareheritage.org/swh:1:dir:22125d7ddabad7cb42f1212c8534956ada96b64c;origin=https://github.com/charliefornia/TEchim;visit=swh:1:snp:b67f224e34e81c18581b87684d427b24b93b61ab;anchor=swh:1:rev:237d56ce295f4b9fe9e56b5b556e2de1562ce180</ext-link></element-citation></ref><ref id="bib10"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Davis</surname><given-names>MW</given-names></name><name><surname>Jorgensen</surname><given-names>EM</given-names></name></person-group><year iso-8601-date="2022">2022</year><article-title>ApE, A Plasmid Editor: A freely available DNA manipulation and visualization program</article-title><source>Frontiers in Bioinformatics</source><volume>2</volume><elocation-id>818619</elocation-id><pub-id pub-id-type="doi">10.3389/fbinf.2022.818619</pub-id><pub-id pub-id-type="pmid">36304290</pub-id></element-citation></ref><ref id="bib11"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Dobin</surname><given-names>A</given-names></name><name><surname>Davis</surname><given-names>CA</given-names></name><name><surname>Schlesinger</surname><given-names>F</given-names></name><name><surname>Drenkow</surname><given-names>J</given-names></name><name><surname>Zaleski</surname><given-names>C</given-names></name><name><surname>Jha</surname><given-names>S</given-names></name><name><surname>Batut</surname><given-names>P</given-names></name><name><surname>Chaisson</surname><given-names>M</given-names></name><name><surname>Gingeras</surname><given-names>TR</given-names></name></person-group><year iso-8601-date="2013">2013</year><article-title>STAR: ultrafast universal RNA-seq aligner</article-title><source>Bioinformatics</source><volume>29</volume><fpage>15</fpage><lpage>21</lpage><pub-id pub-id-type="doi">10.1093/bioinformatics/bts635</pub-id><pub-id pub-id-type="pmid">23104886</pub-id></element-citation></ref><ref id="bib12"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Domínguez</surname><given-names>A</given-names></name></person-group><year iso-8601-date="2021">2021</year><article-title>Interrogating the 5’UTR tandem repeats of retrotransposon roo of Drosophila about horizontal transfer</article-title><source>Genetica</source><volume>149</volume><fpage>171</fpage><lpage>177</lpage><pub-id pub-id-type="doi">10.1007/s10709-021-00120-y</pub-id><pub-id pub-id-type="pmid">33900494</pub-id></element-citation></ref><ref id="bib13"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Ewing</surname><given-names>AD</given-names></name><name><surname>Kazazian</surname><given-names>HH</given-names></name></person-group><year iso-8601-date="2011">2011</year><article-title>Whole-genome resequencing allows detection of many rare LINE-1 insertion alleles in humans</article-title><source>Genome Research</source><volume>21</volume><fpage>985</fpage><lpage>990</lpage><pub-id pub-id-type="doi">10.1101/gr.114777.110</pub-id><pub-id pub-id-type="pmid">20980553</pub-id></element-citation></ref><ref id="bib14"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Garza</surname><given-names>R</given-names></name><name><surname>Atacho</surname><given-names>DAM</given-names></name><name><surname>Adami</surname><given-names>A</given-names></name><name><surname>Gerdes</surname><given-names>P</given-names></name><name><surname>Vinod</surname><given-names>M</given-names></name><name><surname>Hsieh</surname><given-names>P</given-names></name><name><surname>Karlsson</surname><given-names>O</given-names></name><name><surname>Horvath</surname><given-names>V</given-names></name><name><surname>Johansson</surname><given-names>PA</given-names></name><name><surname>Pandiloski</surname><given-names>N</given-names></name><name><surname>Matas-Fuentes</surname><given-names>J</given-names></name><name><surname>Quaegebeur</surname><given-names>A</given-names></name><name><surname>Kouli</surname><given-names>A</given-names></name><name><surname>Sharma</surname><given-names>Y</given-names></name><name><surname>Jönsson</surname><given-names>ME</given-names></name><name><surname>Monni</surname><given-names>E</given-names></name><name><surname>Englund</surname><given-names>E</given-names></name><name><surname>Eichler</surname><given-names>EE</given-names></name><name><surname>Gale Hammell</surname><given-names>M</given-names></name><name><surname>Barker</surname><given-names>RA</given-names></name><name><surname>Kokaia</surname><given-names>Z</given-names></name><name><surname>Douse</surname><given-names>CH</given-names></name><name><surname>Jakobsson</surname><given-names>J</given-names></name></person-group><year iso-8601-date="2023">2023</year><article-title>LINE-1 retrotransposons drive human neuronal transcriptome complexity and functional diversification</article-title><source>Science Advances</source><volume>9</volume><elocation-id>37910626</elocation-id><pub-id pub-id-type="doi">10.1126/sciadv.adh9543</pub-id></element-citation></ref><ref id="bib15"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Lev-Maor</surname><given-names>G</given-names></name><name><surname>Sorek</surname><given-names>R</given-names></name><name><surname>Shomron</surname><given-names>N</given-names></name><name><surname>Ast</surname><given-names>G</given-names></name></person-group><year iso-8601-date="2003">2003</year><article-title>The birth of an alternatively spliced exon: 3’ splice-site selection in Alu exons</article-title><source>Science</source><volume>300</volume><fpage>1288</fpage><lpage>1291</lpage><pub-id pub-id-type="doi">10.1126/science.1082588</pub-id><pub-id pub-id-type="pmid">12764196</pub-id></element-citation></ref><ref id="bib16"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Li</surname><given-names>H</given-names></name><name><surname>Handsaker</surname><given-names>B</given-names></name><name><surname>Wysoker</surname><given-names>A</given-names></name><name><surname>Fennell</surname><given-names>T</given-names></name><name><surname>Ruan</surname><given-names>J</given-names></name><name><surname>Homer</surname><given-names>N</given-names></name><name><surname>Marth</surname><given-names>G</given-names></name><name><surname>Abecasis</surname><given-names>G</given-names></name><name><surname>Durbin</surname><given-names>R</given-names></name><collab-name>1000 Genome Project Data Processing Subgroup</collab-name></person-group><year iso-8601-date="2009">2009</year><article-title>The sequence alignment/map format and SAMtools</article-title><source>Bioinformatics</source><volume>25</volume><fpage>2078</fpage><lpage>2079</lpage><pub-id pub-id-type="doi">10.1093/bioinformatics/btp352</pub-id><pub-id pub-id-type="pmid">19505943</pub-id></element-citation></ref><ref id="bib17"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Magoč</surname><given-names>T</given-names></name><name><surname>Salzberg</surname><given-names>SL</given-names></name></person-group><year iso-8601-date="2011">2011</year><article-title>FLASH: fast length adjustment of short reads to improve genome assemblies</article-title><source>Bioinformatics</source><volume>27</volume><fpage>2957</fpage><lpage>2963</lpage><pub-id pub-id-type="doi">10.1093/bioinformatics/btr507</pub-id><pub-id pub-id-type="pmid">21903629</pub-id></element-citation></ref><ref id="bib18"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Rahman</surname><given-names>R</given-names></name><name><surname>Chirn</surname><given-names>G</given-names></name><name><surname>Kanodia</surname><given-names>A</given-names></name><name><surname>Sytnikova</surname><given-names>YA</given-names></name><name><surname>Brembs</surname><given-names>B</given-names></name><name><surname>Bergman</surname><given-names>CM</given-names></name><name><surname>Lau</surname><given-names>NC</given-names></name></person-group><year iso-8601-date="2015">2015</year><article-title>Unique transposon landscapes are pervasive across <italic>Drosophila melanogaster</italic> genomes</article-title><source>Nucleic Acids Research</source><volume>43</volume><fpage>10655</fpage><lpage>10672</lpage><pub-id pub-id-type="doi">10.1093/nar/gkv1193</pub-id><pub-id pub-id-type="pmid">26578579</pub-id></element-citation></ref><ref id="bib19"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Torres-Méndez</surname><given-names>A</given-names></name><name><surname>Pop</surname><given-names>S</given-names></name><name><surname>Bonnal</surname><given-names>S</given-names></name><name><surname>Almudi</surname><given-names>I</given-names></name><name><surname>Avola</surname><given-names>A</given-names></name><name><surname>Roberts</surname><given-names>RJV</given-names></name><name><surname>Paolantoni</surname><given-names>C</given-names></name><name><surname>Alcaina-Caro</surname><given-names>A</given-names></name><name><surname>Martín-Anduaga</surname><given-names>A</given-names></name><name><surname>Haussmann</surname><given-names>IU</given-names></name><name><surname>Morin</surname><given-names>V</given-names></name><name><surname>Casares</surname><given-names>F</given-names></name><name><surname>Soller</surname><given-names>M</given-names></name><name><surname>Kadener</surname><given-names>S</given-names></name><name><surname>Roignant</surname><given-names>J-Y</given-names></name><name><surname>Prieto-Godino</surname><given-names>L</given-names></name><name><surname>Irimia</surname><given-names>M</given-names></name></person-group><year iso-8601-date="2022">2022</year><article-title>Parallel evolution of a splicing program controlling neuronal excitability in flies and mammals</article-title><source>Science Advances</source><volume>8</volume><elocation-id>35089784</elocation-id><pub-id pub-id-type="doi">10.1126/sciadv.abk0445</pub-id></element-citation></ref><ref id="bib20"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Treiber</surname><given-names>CD</given-names></name><name><surname>Waddell</surname><given-names>S</given-names></name></person-group><year iso-8601-date="2017">2017</year><article-title>Resolving the prevalence of somatic transposition in Drosophila</article-title><source>eLife</source><volume>6</volume><elocation-id>e28297</elocation-id><pub-id pub-id-type="doi">10.7554/eLife.28297</pub-id><pub-id pub-id-type="pmid">28742021</pub-id></element-citation></ref><ref id="bib21"><element-citation publication-type="journal"><person-group person-group-type="author"><name><surname>Treiber</surname><given-names>CD</given-names></name><name><surname>Waddell</surname><given-names>S</given-names></name></person-group><year iso-8601-date="2020">2020a</year><article-title>Transposon expression in the <italic>Drosophila</italic> brain is driven by neighboring genes and diversifies the neural transcriptome</article-title><source>Genome Research</source><volume>30</volume><fpage>1559</fpage><lpage>1569</lpage><pub-id pub-id-type="doi">10.1101/gr.259200.119</pub-id><pub-id pub-id-type="pmid">32973040</pub-id></element-citation></ref><ref id="bib22"><element-citation publication-type="data" specific-use="analyzed"><person-group person-group-type="author"><name><surname>Treiber</surname><given-names>CD</given-names></name><name><surname>Waddell</surname><given-names>S</given-names></name></person-group><year iso-8601-date="2020">2020b</year><data-title>Data from: Transposon expression in the Drosophila brain is driven by neighbouring genes and diversifies the neural transcriptome</data-title><source>NCBI Sequence Read Archive</source><ext-link ext-link-type="uri" xlink:href="https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA588978">https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA588978</ext-link></element-citation></ref><ref id="bib23"><element-citation publication-type="software"><person-group person-group-type="author"><name><surname>Treiber</surname><given-names>C</given-names></name></person-group><year iso-8601-date="2026">2026</year><data-title>TEchim: a pipeline for detecting transposable element–gene chimeric sequences</data-title><version designator="version 1.0.0">version 1.0.0</version><source>GitHub</source><ext-link ext-link-type="uri" xlink:href="https://github.com/charliefornia/TEchim/releases/tag/v1.0.0">https://github.com/charliefornia/TEchim/releases/tag/v1.0.0</ext-link></element-citation></ref></ref-list></back><sub-article article-type="editor-report" id="sa0"><front-stub><article-id pub-id-type="doi">10.7554/eLife.110625.3.sa0</article-id><title-group><article-title>eLife Assessment</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Karimi</surname><given-names>Mohammad M</given-names></name><role specific-use="editor">Reviewing Editor</role><aff><institution>King's College London</institution><country>United Kingdom</country></aff></contrib></contrib-group><kwd-group kwd-group-type="evidence-strength"><kwd>Convincing</kwd></kwd-group><kwd-group kwd-group-type="claim-importance"><kwd>Important</kwd></kwd-group></front-stub><body><p>This <bold>important</bold> study provides <bold>convincing</bold> evidence supporting the existence of transposable element (TE)-gene chimeric transcripts in the Drosophila brain and helps reconcile previously conflicting findings. The authors demonstrate that differences in computational approaches, experimental design, and Drosophila lines can substantially influence the detection of these transcripts. The work highlights the importance of standardized approaches for studying TE-derived transcripts, although their broader biological significance remains to be established.</p></body></sub-article><sub-article article-type="referee-report" id="sa1"><front-stub><article-id pub-id-type="doi">10.7554/eLife.110625.3.sa1</article-id><title-group><article-title>Reviewer #1 (Public review):</article-title></title-group><contrib-group><contrib contrib-type="author"><anonymous/><role specific-use="referee">Reviewer</role></contrib></contrib-group></front-stub><body><p>Summary:</p><p>Choucri and Treiber have reassessed their previous study on TE-gene chimeric transcripts in neural genes in response to Azad et al (2024). Azad and colleagues argued that contrary to Choucri and Treiber's findings, chimeric TE-mRNAs are relatively infrequent, and they cautioned that further optimization of bioinformatics pipelines is needed to accurately detect TE insertions from RNA-seq. In this short response, Choucri and Treiber clearly show that differences in the tools used between their study and that of Azad et al. likely explain the contrasting results, along with RT-PCR failure to design primers that match the chimeric transcript and the use of different Drosophila lines. The authors emphasize the need for uniform, standardized criteria in such analysis, which would ultimately strengthen and advance the field.</p><p>Strengths:</p><p>The addition of a ratio to compute the number of splice reads specific to the chimeric transcript and to compare to the exon-exon splice reads is really interesting because it opens the door to finally quantify the contribution of chimeric TEs to the overall gene expression, although this is not the scope of the present article. The clear dissection of chimeric transcripts, along with the results from Azad et al, allows us to understand the differences between the two studies confidently. The methods are clear and thorough. The discussion on Drosophila lines is indeed essential, given that the lines and even individuals have high TE polymorphism.</p><p>The biological function, if any, of such chimeric transcripts remains to be determined by further analysis, including chimeric transcripts with low to high overall contribution to gene expression (Figure 1B).</p></body></sub-article><sub-article article-type="referee-report" id="sa2"><front-stub><article-id pub-id-type="doi">10.7554/eLife.110625.3.sa2</article-id><title-group><article-title>Reviewer #3 (Public review):</article-title></title-group><contrib-group><contrib contrib-type="author"><anonymous/><role specific-use="referee">Reviewer</role></contrib></contrib-group></front-stub><body><p>Summary:</p><p>This manuscript by Choucri and Treiber responds to a recent paper by Azad et al., which responds to a paper by Treiber and Wadell (Genome Research, 2020). The controversy relates to the detection of transcripts with transposable elements (TEs) spliced into them in the Drosophila brain.</p><p>Strengths:</p><p>The authors now argue convincingly that these transcripts exist using an improved, updated version of their pipeline. They also validate some of their findings using RT-PCR and explain why Azad et al. failed to detect these transcripts due to methodological errors. Overall, I am convinced that these transcripts exist and that the TE-derived transcripts described by Choucri and Treiber are real.</p><p>Weaknesses:</p><p>The authors should mention that combining PCR-amplified cDNA generation with short-read sequencing is suboptimal for detecting TE-fusion transcripts. Recently, direct long-read ONT RNA sequencing, which does not require amplification and spans the entire transcript, has been used to detect similar transcripts in human stem cells and the human brain (PMID: 40848716 &amp; Garza et al, BioRxiv) . Had the authors used this technology to validate their findings, there would be no question about these transcripts. If not doing such experiments, then they should at least discuss the possibility and the advantage of the approach.</p></body></sub-article><sub-article article-type="author-comment" id="sa3"><front-stub><article-id pub-id-type="doi">10.7554/eLife.110625.3.sa3</article-id><title-group><article-title>Author response</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Choucri</surname><given-names>Malak</given-names></name><role specific-use="author">Author</role><aff><institution>University of Oxford</institution><addr-line><named-content content-type="city">Oxford</named-content></addr-line><country>United Kingdom</country></aff></contrib><contrib contrib-type="author"><name><surname>Rainey</surname><given-names>Tina</given-names></name><role specific-use="author">Author</role><aff><institution>University of Oxford</institution><addr-line><named-content content-type="city">Oxford</named-content></addr-line><country>United Kingdom</country></aff></contrib><contrib contrib-type="author"><name><surname>Treiber</surname><given-names>Christoph Daniel</given-names></name><role specific-use="author">Author</role><aff><institution>University of Oxford</institution><addr-line><named-content content-type="city">Oxford</named-content></addr-line><country>United Kingdom</country></aff></contrib></contrib-group></front-stub><body><p>The following is the authors’ response to the original reviews.</p><disp-quote content-type="editor-comment"><p><bold>Public Reviews:</bold></p><p><bold>Reviewer #1 (Public review):</bold></p><p>Summary:</p><p>Choucri and Treiber have reassessed their previous study on TE-gene chimeric transcripts in neural genes in response to Azad et al (2024). Azad and colleagues argued that, contrary to Choucri and Treiber's findings, chimeric TE-mRNAs are relatively infrequent, and they cautioned that further optimization of bioinformatics pipelines is needed to detect TE insertions from RNAseq accurately. In this short response, Choucri and Treiber clearly demonstrate that differences in the tools used between their study and that of Azad et al. likely account for the contrasting results, along with RT-PCR failure in designing primers that would match the chimeric transcript, and the use of different Drosophila lines. The authors emphasize the need for uniform, standardized criteria in such analysis, which would ultimately strengthen and advance the field.</p><p>Strengths:</p><p>The addition of a ratio to compute the number of splice reads specific to the chimeric transcript and compare to the exon-exon splice reads is really interesting because it opens the door to finally quantify the contribution of chimeric TEs to the overall gene expression, although this is not the scope of the present article. The clear dissection of chimeric transcripts, along with the results from Azad et al, allows us to understand the differences between the two studies confidently. Finally, the discussion on Drosophila lines is indeed essential, given that the lines and even individuals have high TE polymorphism.</p><p>Weaknesses:</p><p>I think it is necessary to add more detail to this article, for instance, the differences between TEchim and Tidal could be laid out more precisely.</p></disp-quote><p>We thank the reviewer for this helpful suggestion and agree that a more explicit comparison improves the clarity of the manuscript. Briefly, TIDAL and TEChim are designed to answer different questions. TIDAL is an insertion/deletion caller that was primarily built to determine whether a TE insertion exists at a genomic locus and how it is distributed across strains or populations. It was not designed to resolve splice junctions between exons and TEs. TEChim, by contrast, is purpose-built to detect breakpoint-spanning reads that span exon junctions and putative splice sites within a TE. This difference in design has several concrete consequences in the algorithms used:</p><p>(1) TIDAL clusters reads that support a candidate breakpoint within a window of twice the sequencing read length (e.g. 300nt for 150nt reads). This works well for calling genomic insertions, but it can be too restrictive for a splice junction, which may fall at a variable position within the gene and TE. TEChim does not rely on fixed-window clustering, but instead maps all reads, groups them to individual nt positions within the genome, and then filters for events that were detected in more than one biological replicate.</p><p>(2) TEChim reconstructs long <italic>in-silico</italic> reads from overlapping paired-end reads, using FLASH, prior to alignment. <italic>In-silico</italic> paired-end reads are analysed, and full-read merged fragments provide single-nucleotide resolution for a breakpoint. This increases accuracy and confidence in split reads.</p><p>(3) TEChim explicitly intersects candidate breakpoints with annotated exon/intron/UTR. Structures and canonical splice donor- and acceptor sites.</p><p>We have now added a concise summary of the underlying principles of TEChim in the Methods section, and added details to the comparison of TIDAL with TEChim in the discussion. We hope that this addition makes it clearer why the two pipelines produce different results from the same input data.</p><disp-quote content-type="editor-comment"><p>Regarding the roo example, one of the caveats of this family, along with others, is the presence of simple repeats. It would be important to show that the simple repeats are not interfering with the read mapping.</p></disp-quote><p>We thank the reviewer for raising this important point. We agree that simple repeats can complicate read mapping and that this requires careful consideration. We have now added to the results the exact locations and lengths of the three known and annotated repeat regions within roo (Domínguez, 2021) and show that the breakpoints we report map more than 4kb away from these regions. In addition, the splice junctions we identify (at positions 5190 and 5462) recur at the same position relative to the roo consensus sequence across multiple genomic insertions, and biological replicates. If these calls were artifacts of copyspecific simple repeats that interfered with read mapping, then we would expect breakpoints to vary between with each insertions local sequence, rather than converge on the same breakpoint. We therefore consider it unlikely that simple repeats account for the observed splice junctions. We have expanded our discussion to make this reasoning clearer.</p><disp-quote content-type="editor-comment"><p>Regarding the experiments, if we are looking for a standardized protocol, then we should have a detailed material and methods section, with every experiment, replicate, and PCR temperature clearly defined.</p></disp-quote><p>We thank the reviewer for this suggestion and agree that a more detailed description of the experimental procedures will improve the reproducibility of the study. We have substantially expanded the Materials and Methods section, including the number of biological replicates, primer information, PCR conditions and other methodological details relevant for reproducing the experiments. In addition, we have written a detailed manual for the updated version of TEChim that we used here.</p><disp-quote content-type="editor-comment"><p>Finally, and in my opinion, more importantly, the use of RT negative controls on the RT PCRs, along with DNA PCRs to show insertion presence, is mandatory for testing the presence of chimeric genes. Of course, water negative PCR controls are also needed, and unfortunately, absent from Figure 3.</p></disp-quote><p>We thank the reviewer for this helpful suggestion. We have repeated the RNA extraction on 3 new samples, and this time also included minus-RT aliquots for each of the three biological replicates. We have run our PCR for the chimeric transcript between Beadex and opus on all these samples, and in addition on a water control. All these new results are now shown in Figure 3, and confirm our previous conclusions.</p><p>We now also provide results from our DNA testing for the opus insertion in Beadex. We conduct these at regular intervals in our lab to ensure the insertion remains stable in our stock, and mentioned the results in the original version of this manuscript, but we agree that it is important to also show the raw data of this in this study. We use primers at the up- and downstream end of the opus insertion. The downstream pair gave a single band at the predicted size, which we confirmed by Sanger sequencing. This data is now presented in Figure 3 – Figure supplement 1. The PCR around the upstream end resulted in the expected band of 888bp, and two additional bands. Sanger sequencing of the 888bp band produced signals for both Beadex and opus, but we did not get a reliable signal across the precise breakpoint (see Author response image 1). We think this might partly be due to a tandem repeat at the beginning of the opus LTR, which may interfere with Sanger sequencing. Taken together, our data provides strong evidence that the opus insertion is present in our flies.</p><fig id="sa3fig1" position="float"><label>Author response image 1.</label><caption><title>Sanger sequencing results of the 888bp band: Two segments of the raw Sanger sequencing trace are shown; the intervening, unmapped section is omitted.</title><p>The left segment (grey) shows clean, high-confidence signal matching the Bx locus. The right segment (pink) shows the signal falling to near baseline within the opus LTR, so base calls in this region are log-confidence, and the trace does not resolve the breakpoint. Numbers above the sequence indicate position within the raw sequencing read.</p></caption><graphic mimetype="image/tiff" xlink:href="elife-110625-sa3-fig1-v1.tif"/></fig><disp-quote content-type="editor-comment"><p><bold>Reviewer #2 (Public review):</bold></p><p>Summary:</p><p>This study by Choucri and Treiber aims to directly address a recent critique regarding the role of transposable elements (TEs) in diversifying the neural transcriptome of Drosophila. The authors seek to demonstrate that TEs are not merely genomic &quot;noise&quot; but are frequently and reliably &quot;exonized&quot; into brain-specific mRNA. By introducing an upgraded computational pipeline, TEChim, and conducting precise experimental validations, the authors set out to show that TE-mediated splicing represents a genuine biological phenomenon that expands the molecular repertoire of the nervous system.</p><p>Strengths:</p><p>The study's primary strength lies in its rigorous technical &quot;forensic&quot; analysis of previous failed replication attempts. The authors convincingly demonstrate that the lack of signal in the opposing study stemmed from a fundamental methodological mismatch: the software used by the critics (TIDAL) is logically incapable of detecting splice sites located within TE sequences. Importantly, the authors complement this computational clarification with definitive experimental evidence through an effective &quot;experimental rescue.&quot; By employing correctly designed primers and matching the genetic backgrounds of the fly strains, thereby accounting for genomic polymorphisms, they successfully validated all seven loci that were previously reported as undetectable. This dual-pronged strategy, addressing both algorithmic bias and experimental design, establishes a more robust technical benchmark for the detection and validation of TE-derived exons in neural tissues.</p><p>Weaknesses:</p><p>While the technical rebuttal is highly convincing, the scope of the study remains primarily defensive. As a response to a prior critique, the work focuses on establishing the existence and detectability of chimeric TE-derived transcripts rather than exploring their broader functional consequences. As a result, there is limited new insight into how these TEmodified isoforms influence neural circuit function or organismal behavior.</p></disp-quote><p>We agree with the reviewer that the primary focus of this study is to establish a robust protocol for the detection and validation of TE-derived chimeric transcripts, and to resolve discrepancies raised by Azad et al. We believe this provides an important technical and conceptual framework for future studies investigating the functional impact of TE-driven genetic variation.</p><disp-quote content-type="editor-comment"><p>In addition, the detection and validation of these events remain technically demanding, requiring deep sequencing and specialized bioinformatic expertise, which may limit broader adoption by laboratories without dedicated computational resources.</p></disp-quote><p>We agree that the robust detection and validation of TE-derived chimeric transcripts is technically demanding, requiring both high-quality sequencing data and specialised computational analyses. However, we believe that these methodological challenges are justified by the biological insights that can be gained. By providing an updated computational approach together with experimental validation, we hope to facilitate further research into this phenomenon.</p><disp-quote content-type="editor-comment"><p><bold>Reviewer #3 (Public review):</bold></p><p>Summary:</p><p>This manuscript by Choucri and Treiber responds to a recent paper by Azad et al., which responds to a paper by Treiber and Wadell (Genome Research, 2020). The controversy relates to the detection of transcripts with transposable elements (TEs) spliced into them in the Drosophila brain.</p><p>Strengths:</p><p>The authors now argue convincingly that these transcripts exist using an improved, updated version of their pipeline. They also validate some of their findings using RT-PCR and explain why Azad et al. failed to detect these transcripts due to methodological errors. Overall, I am convinced that these transcripts exist and that the TE-derived transcripts described by Choucri and Treiber are real.</p><p>Weaknesses:</p><p>The authors should mention that combining PCR-amplified cDNA generation with shortread sequencing is suboptimal for detecting TE-fusion transcripts. Recently, direct longread ONT RNA sequencing, which does not require amplification and spans the entire transcript, has been used to detect similar transcripts in human stem cells and the human brain (PMID: 40848716 &amp; Garza et al, BioRxiv). Had the authors used this technology to validate their findings, there would be no question about these transcripts. If not doing such experiments, then they should at least discuss the possibility and the advantage of the approach.</p></disp-quote><p>We thank the reviewer for this excellent suggestion and agree that long-read RNA sequencing represents a powerful approach to characterise chimeric transcripts, because it can capture full-length transcripts and reduce ambiguity of mapping short reads onto repetitive sequences. We have now expanded the Discussion to highlight the advantages of these technologies and to cite the suggested studies. At present, long-read RNA sequencing remains challenging for <italic>Drosophila</italic> brain samples, because the total amount of input RNA is limited. As a consequence, amplification is usually required, which itself can introduce artefacts, which we showed previously (Treiber and Waddell, 2017). While we agree that long-read sequencing will be an important approach for future studies, we believe that the combination of computational analysis and targeted experimental validation presented here provides robust evidence for the existence of chimeric TE-gene transcripts.</p><disp-quote content-type="editor-comment"><p><bold>Recommendations for the authors:</bold></p><p><bold>Reviewer #2 (Recommendations for the authors):</bold></p><p>To maximize the impact of the work, the authors should consider adding a technical guide that outlines the implementation of the updated TEChim pipeline and provides a standardized protocol for designing chimeric RT-PCR primers. This section should include a clear software workflow and a precise primer design strategy, emphasizing junction spanning probes and the necessity of genomic confirmation, to establish these methods as the definitive technical standard for studying transposable elements in the nervous system.</p></disp-quote><p>We thank the reviewer for this constructive suggestion and want to be upfront about what can and cannot be standardized here. Because TE sequences are repetitive, the specific primer pair that works best for a given locus cannot necessarily be predicted in advance, and some empirical testing of candidate primer pairs is unavoidable. What we can standardise, and now describe explicitly in the Methods section, is, firstly the use of TEChim to identify candidate splicing events, and secondly, the logic behind how we choose primers. Several candidate primer pairs are tested for a given genomic locus, and all resulting bands are confirmed using Sanger sequencing. Together with an expanded TEChim manual on GitHub, we believe this study gives other research groups a clear and reproducible starting point, while remaining honest that, as with most repeat-adjacent primer design, some locus-specific optimization remains necessary.</p></body></sub-article></article>