Adaptive Evolution Targets a piRNA Precursor Transcription Network

Abstract

In Drosophila, transposon-silencing piRNAs are derived from heterochromatic clusters and a subset of euchromatic transposon insertions, which are bound by the Rhino-Deadlock-Cutoff complex. The HP1 homolog Rhino binds to Deadlock, which recruits TRF2 to promote non-canonical transcription from both genomic strands. Cuff function is less well understood, but this Rai1 homolog shows hallmarks of adaptive evolution, which can remodel functional interactions within host defense systems. Supporting this hypothesis, Drosophila simulans Cutoff is a dominant-negative allele when expressed in Drosophila melanogaster, in which it traps Deadlock, TRF2, and the conserved transcriptional co-repressor CtBP in stable complexes. Cutoff functions with Rhino and Deadlock to drive non-canonical transcription. In contrast, CtBP suppresses canonical transcription of transposons and promoters flanking the major germline clusters, and canonical transcription interferes with downstream non-canonical transcription and piRNA production. Adaptive evolution thus targets interactions among Cutoff, TRF2, and CtBP that balance canonical and non-canonical piRNA precursor transcription.

Keywords: CtBP; Cutoff; TRF2; adaptive evolution; cross-species complementation; piRNA cluster transcriptional regulation; piRNA pathway; transposon silencing.

Figure 1.. sim-Cuff Does Not Complement D. melanogaster cuff Mutations

(A) Genetic complementation strategy. The sim-cuff or mel-cuff genes were expressed in D. melanogaster cuff mutants using the germline-specific rhi promoter and assayed for phenotypic rescue. (B) Bar graphs showing number of eggs laid per female per day, percentage of eggs with two appendages, and percentage of hatched eggs produced by OrR (wild-type [WT] control), cuff mutants, and cuff mutants expressing either mel-cuff or sim-cuff. Error bars show standard deviation of three biological replicates, with a minimum of 500 embryos scored per replicate, except for cuff mutants and cuff mutants rescued by sim-cuff, for which average of 230 and 23 eggs were scored, respectively. (C–H) Scatterplots showing comparisons of RNA-seq (C and D), CapSeq (E and F), and small RNA-seq signal (G and H) for transposon families in cuff mutant or cuff mutant expressing sim-cuff versus cuff mutant expressing mel-cuff. Each point on the scatterplots shows RPKM (long RNAs) or RPM (small RNAs) for a transposon family in ovaries of the indicated genotype. For transposons, anti-sense piRNA abundance is plotted. Diagonal represents x = y. Points in red show y/x > 3. p value for differences obtained using Wilcoxon test. (I and J) Localization of GFP-tagged Cuff with respect to H3K9me3-marked chromatin in germline nuclei of cuff mutants expressing rhi promoter-driven mel-Cuff or sim-Cuff. Color assignments for merged images shown on top. Arrowheads and arrows denote locations of mel-Cuff and sim-Cuff foci, respectively. Identical imaging conditions were used for all panels. Scale bar, 2 μm. Fluorescence intensities calculated across the white lines in the merged images (I) are shown in (J).

Figure 2.. sim-Cuff Disrupts RDC Localization

(A) Localization of GFP-tagged Cuff with respect to Rhi and Del in the germline nuclei of cuff mutants expressing rhi promoter-driven mel-Cuff or sim-Cuff. Color assignments for merged images shown on top. Arrows and arrowheads denote locations of mel-Cuff and sim-Cuff foci, respectively. Scale bar, 2 μm. (B–E) Scatterplots showing comparisons of RNA-seq signal (B and C) and small RNA-seq signal (D and E) at piRNA clusters in ovaries with genotypes cuff mutant or cuff mutant expressing sim-cuff versus cuff mutant expressing mel-cuff. In (B) and (C), each point on the scatterplots shows RPKM value for a 1 kb piRNA clusters bin. In (D) and (E), each point shows RPM value for an entire cluster. Diagonal represents x = y. p value for differences obtained using Wilcoxon test. (F) Genome Browser view of GFP-Cuff (top) and Rhi (bottom) ChIP-seq profiles at 42AB piRNA cluster in the ovaries of cuff mutants expressing either mel-cuff (blue) or sim-cuff (red). (G and H) Scatterplots showing comparisons of ChIP/Input values for GFP-Cuff (G) and Rhi (H) at piRNA clusters in ovaries with genotypes cuff mutant expressing sim-cuff versus mel-cuff. The clusters with prominent Cuff or Rhi binding (RPKM > 2) in cuff mutant with mel-cuff control were used for analysis. Diagonal represents x = y. p value for differences obtained using Wilcoxon test.

Figure 3.. D. simulans Cuff Traps Transcription Factors and Acts as a Dominant Negative

(A–D) Mass spectrometric analysis of mel-Cuff (A), sim-Cuff (B), Del (C), and Rhi (D) binding proteins. Graphs show ratios of iBAQ value of a bound protein in a RDC protein IP versus tag control IP ranked by ratio values. RDC components are shown in red, TRF2 and CtBP in blue. (E) Bar graphs showing percentages of hatched eggs produced by control (w¹; Sp/CyO) and flies overexpressing either mel-cuff or sim-cuff by either nanos-Gal4 (nG) or Act5C-Gal4 (Act-Gal4) drivers. Error bars show standard deviation of three biological replicates, with a minimum of 200 embryos scored per replicate, except for nanos-Gal4-driven sim-cuff, for which an average of 50 eggs were scored. (F) Localization of overexpressed GFP-tagged Cuff with respect to TRF2 in the germline nuclei of Act-Gal4-driven mel-Cuff or sim-Cuff. Color assignments for merged images shown on top. Arrowheads and arrows denote locations of TRF2 foci. Scale bar, 2 μm. (G) Localization of overexpressed GFP-tagged Cuff with respect to Rhi and Del in the germline nuclei of Act-Gal4-driven mel-Cuff or sim-Cuff. Color assignments for merged images shown on top. Arrows denote locations of RDC complex foci. Scale bar, 2 μm.

Figure 4.. CtBP Suppresses Canonical Transcription at piRNA Clusters

(A and B) Scatterplots showing comparisons of RNA-seq signal for transposons (A) and piRNA clusters (B) in CtBP-kd versus w-kd ovaries. TEs with more than 3-fold overexpression in CtBP-kd versus w-kd as shown in red. (C and D) Scatterplots showing comparisons of small RNA-seq signal for transposons (C) and piRNA clusters (D) in CtBP-kd versus w-kd ovaries. For transposon mapping plots, only anti-sense piRNAs are shown. Red points denote piRNA abundance for TEs that are overexpressed in CtBP-kd (A). Each point on the scatterplots shows RPKM or RPM value for a transposon family or a piRNA cluster. Diagonal represents x = y. p value for differences obtained using Wilcoxon test. (E) Genome Browser view of RNA-seq (top), small RNA-seq (middle), and CapSeq (bottom) profiles at 42AB piRNA cluster from w-kd and CtBP-kd ovaries. Pol II ChIP-seq peak in nanos-Gal4-driven mel-Cuff ovaries marks the cluster promoter (blue). Arrows and arrowheads show the increase in canonical transcripts and decrease in non-canonical transcripts respectively after CtBP-kd. CapSeq profiles are saturated at promoters. The peak heights of CapSeq promoters are denoted by numbers next to the peaks. (F and G) Scatterplots showing comparisons of RPM values for 1 kb bins of piRNA clusters, which have RNA Pol II and TBP promoter peaks, for RNA-seq (F) and small RNA-seq (G) in CtBP-kd versus w-kd. The bins close to promoters are shown by large circles and ones farther away by small circles. p value for differences obtained using Wilcoxon test. (H–K) Genome Browser views of CapSeq or RNA-seq signals at 42AB promoter for CtBP-kd versus w-kd (H) and cuff mutants expressing either mel-cuff or sim-cuff (I–K). (J) and (K) show RNA-seq profiles at different scales.

Figure 5.. CtBP Suppresses Canonical Transcription of Dispersed Transposon Insertions

(A and B) Genome Browser views of Rhi ChIP-seq and small RNA-seq profiles flanking dispersed transposons, Diver (A) and Blood (B), in CtBP-kd and w-kd. The transposon insertion is shown at the top. (C and D) Scatterplots showing comparisons of RPM values of Rhi ChIP-seq (C) and small RNAs (D), 0.5 kb upstream and downstream of new transposons in CtBP-kd versus w-kd. The transposons insertions were identified by genomic sequencing with TEMP (Zhuang et al., 2014), and the graphs show the values for new TEs (not present in the reference genome), which have both flanking piRNAs and Rhi signal. Red points denote expression of TEs overexpressed in CtBP-kd, as shown in Figure 4A. p value for differences obtained using Wilcoxon test. (E) Genome Browser view of CapSeq signal at Diver insertion in CtBP-kd versus w-kd. Arrow shows increased CapSeq signal at Diver 5′ end in CtBP-kd. The signal shows all Diver insertion mapping reads and are not specific to this insertion. (F and G) Scatterplots showing comparisons of CapSeq signal for 1 kb bins mapping to transposons present outside clusters, (bins at 5′ and 3′ ends are excluded, to remove canonical transcription peaks) for CtBP-kd versus w-kd. (F) shows sense strand and (G) shows anti-sense strand initiation. Points in red show x/y > 3. p value for differences obtained using Wilcoxon test.

Figure 6.. Role of Cuff in piRNA Cluster Transcription

(A and B) Genome Browser views at 42AB cluster. (A) Right side of the 42AB cluster, proximal to the flanking canonical promoter, showing Pol II, TBP (TATA binding protein), Rhi, Del, and Cuff ChIP-seq, and RNA-seq and CapSeq signals. Rhi, Del, and Cuff localize throughout the clusters, while Cuff and Del also show peaks that correspond to the flanking canonical promoter, marked by Pol II (arrow). (B) Zoomed-in view of the promoter region for all the tracks in (A). All the ChIP-seq tracks are auto-scaled, except for input track. RNA-seq and CapSeq profiles shown in cuff mutants and cuff mutants expressing mel-cuff.

Figure 7.. Model for a Transcriptional Network Balancing Canonical and Non-canonical piRNA Precursor Transcription

piRNAs are generated from both piRNA clusters and dispersed transposon insertions, which act as “mini-clusters.” At both locations, Rhi binds to H3K9me3 histone marks and recruits Del, TRF2, and Cuff proteins, through direct or indirect interactions, to initiate non-canonical transcription from both strands. Non-canonical transcription (green lines) is inhibited by canonical transcription (red lines), and CtBP represses canonical transcription, regulating non-canonical transcription and piRNA production.