In Drosophila melanogaster the COM locus directs the somatic silencing of two retrotransposons through both Piwi-dependent and -independent pathways

Abstract

Background: In the Drosophila germ line, repeat-associated small interfering RNAs (rasiRNAs) ensure genomic stability by silencing endogenous transposable elements. This RNA silencing involves small RNAs of 26-30 nucleotides that are mainly produced from the antisense strand and function through the Piwi protein. Piwi belongs to the subclass of the Argonaute family of RNA interference effector proteins, which are expressed in the germline and in surrounding somatic tissues of the reproductive apparatus. In addition to this germ-line expression, Piwi has also been implicated in diverse functions in somatic cells.

Principal findings: Here, we show that two LTR retrotransposons from Drosophila melanogaster, ZAM and Idefix, are silenced by an RNA silencing pathway that has characteristics of the rasiRNA pathway and that specifically recognizes and destroys the sense-strand RNAs of the retrotransposons. This silencing depends on Piwi in the follicle cells surrounding the oocyte. Interestingly, this silencing is active in all the somatic tissues examined from embryos to adult flies. In these somatic cells, while the silencing still involves the strict recognition of sense-strand transcripts, it displays the marked difference of being independent of the Piwi protein. Finally, we present evidence that in all the tissues examined, the repression is controlled by the heterochromatic COM locus.

Conclusion: Our data shed further light on the silencing mechanism that acts to target Drosophila LTR retrotransposons in somatic cells throughout fly development. They demonstrate that different RNA silencing pathways are involved in ovarian versus other somatic tissues, since Piwi is necessary for silencing in the former tissues but is dispensable in the latter. They further demonstrate that these pathways are controlled by the heterochromatic COM locus which ensures the overall protection of Drosophila against the detrimental effects of random retrotransposon mobilization.

Figure 1. The U5, but not U3, region of the ZAM LTR is required for repression.

The genomic structure of the ZAM retrotransposon is depicted at the top. Structures of the lacZ reporter trangenes used in this study are shown below on the left, and their expression in follicle cells from the S or U background are indicated at right. Transcripts initiated from the endogenous transcription initiation site of ZAM (black arrow) in transgenes pZ499 and pZ475 are homologous to ZAM over 173 and 149 bp, respectively. These transgenes are sensitive to the S or U status of the line as illustrated by the histochemical detection of β-galactosidase activity in the ovarioles. pZ310 contains the U3 sequence of the element and is expressed from a minimal heat shock promoter (white arrow) so that no sequence homologous to ZAM is present within the p310 transcript. Its expression is not under the control of the S or U status of the lines and is thus observed in the ovarioles from both the S and U backgrounds, as illustrated on the right.

Figure 2. Transgenes with a GFP reporter gene fused to a ZAM sequence act as sensors of the repression.

The genomic structures of the transgenes pGFP-Zenv and pGFP-Idgag used in this study are presented at the tops of both panels: The grey boxes correspond to the UASt promoter, the dotted boxes to the GFP gene, and the white box to the env fragment of ZAM or the gag fragment of Idefix. Triangles indicate the FRT sites. Focal plane of the follicles dissected from a line in which the pGFP-Zenv transgene is driven by the ubiquitous Actin-Gal4 driver. Expression of the pGFP-Zenv transgene in an S genetic background before (A) or after (B) flp-recombinase action, or in a U genetic background before the flp treatment (C). GFP expression in the ovarioles of a transgenic line bearing the pGFP-Idgag transgene driven by the ubiquitous Actin-Gal4 driver. Expression of the pGFP-Idgag transgene in an S genetic background before (D) or after (E) flp-recombinase action, or in a U genetic background before the flp treatment (F). No GFP is detected in ovaries of the S lines. Its expression is recovered after the flp treatment or when the COM locus is mutated, as in the U genetic background.

Figure 3. Transgenes bearing ZAM or Idefix sequences placed in an antisense orientation are not targeted by the repression.

Expression of sensor transgenes carrying ZAM or Idefix fragments inserted in a sense and an antisense orientation. The genomic structure of the so-called pGFP-Zenv, pGFP-ZenvAS, pGFP-IdU, pGFP-IdUAS transgenes are depicted on the left. The orientation of the fragment is indicated by an arrow. The repression mechanism is able to discriminate between sense and antisense targeted sequences. In an S/S genetic background, only transgenes with ZAM and Idefix in an antisense orientation are correctly expressed. Clear fluorescence due to GFP expression is detected in the ovarian follicles of pGFP-ZenvAS and pGFP-IdUAS transgenes, as illustrated on the right.

Figure 4. The repression machinery controlling ZAM and Idefix acts post-transcriptionally, before translation.

A: Transcripts from the pGFP-ZU transgene were examined in northern blot experiments. A typical result is shown in A. GFP transcripts revealed by a riboprobe complementary to GFP mRNAs are detected in the U line and not in the S line. Actin is used as a loading control. B: Northern blots and quantification based on three northern blot experiments performed on flies containing pGFP-IdU and pGFP-IdUAS transgenes. Their structures are presented above the graph. No GFP transcripts synthesized from the pGFP-IdU transgene are detected by the GFP riboprobe in an S background, whereas their amount is high in a U background. An even higher amount of GFP transcripts is observed in an S or U background when the Idefix fragment is inserted in the opposite orientation (pGFP-IdUAS transgenes). C and D- RNase protection assays reveal the presence of small RNAs (20 to 30 nt long) that are homologous to ZAM and Idefix. These RNAs are detected in S lines and, at a much lower level, in the U line. Small RNAs homologous to the antisense strand of the 5′UTR of ZAM are presented in C. 20 to 30 nt long antisense strand RNAs (−) homologous to the 5′UTR or the gag gene of Idefix are detected. Sense strands (+) are absent or present in very small amounts. A typical experiment is presented in D. Signs (+) and (−) indicate respectively sense-strand and anti-sense strand RNAs of ZAM or Idefix revealed by the riboprobes.

Figure 5. ZAM and Idefix are regulated by a PIWI-dependent pathway in the reproductive apparatus.

In situ hybridization experiments reveal ZAM and Idefix expression in female gonads from third instar larvae. ZAM and Idefix transcripts are not detected in S flies with a wild-type piwi gene (left). As shown by the black staining, ZAM and Idefix mRNAs are detected in U flies with a wild-type piwi gene (middle). In S lines homozygous for the piwi ³ allele, ZAM or Idefix transcripts are no longer repressed, and their transcription is visualised in gonads (right). Probes used in these experiments are indicated on the left.

Figure 6. The silencing mechanism targeting ZAM and Idefix is active in somatic tissues throughout fly development.

A) In an S/S genetic background, the pGFP-IdU sensor transgene driven by 24B-Gal4 is not expressed in embryos, larvae, or adults (top, middle and bottom panels, respectively). Only a very faint level of fluorescence, corresponding to the background expression of GFP, is detected. B) In a U/U genetic background, the GFP-IdU transgene silencing is released and GFP fluorescence is clearly observed in the three stages analyzed. The fluorescence pattern recapitulates the expression of the HOW gene in muscle and tendon cells, as expected for the 24B-Gal4 driver . C) In an S/S genetic background, the pGFP-IdUAS sensor transgene carrying the 5′UTR of Idefix in the opposite orientation is not subjected to the silencing exerted on the Idefix sequences. pGFP-IdUAS is correctly expressed and GFP is detected in embryos, larvae, and adult flies.

Figure 7. ZAM and Idefix are regulated by a PIWI-independent pathway outside of the reproductive apparatus.

The pGFP-ZU sensor transgene driven by 24B-Gal4 is not expressed in larvae, pupae, or adult stages in a [S/S; piwi+/+] genetic background (right panel). Only a very faint level of fluorescence, corresponding to the background, is detected. A clear GFP expression is observed in these stages of development in a [U/U; piwi+/+] line (middle panel). In piwi mutant backgrounds, in homozygous [S/S; piwi3/3] lines, the silencing of the sensor transgene is not released. A very faint fluorescence level similar to that observed in homozygous [S/S; piwi+/+] lines is observed (left panel).