Perturbing Dynamin Reveals Potent Effects on the Drosophila Circadian Clock

shibire^ts1 Potently and Selectively Affects Circadian Period

To test the role of intercellular communication in the Drosophila circadian pacemaker, we expressed shi^ts1 throughout the pacemaker neuron system. Initial experiments utilized GAL4 lines, crypGAL4-16 (cry16) and crypGAL4-24 (cry24), that drive expression throughout the key circadian neuronal groups (LN and DN, [14], [47]) and assayed behavior near the restrictive temperature at 29°C [45]. Under these conditions, most flies died or were arrhythmic consistent with the purported dominant negative function of this transgene (data not shown). As a result, we examined a range of semi-restrictive temperatures (21–27°C). Rather than weak, 24-hour rhythms, we found that flies exhibit robust circadian rhythms and their periods were strikingly long (Fig. 1A, 1B, Table 1, Table S1). In cry16/UASshi^ts1 flies, they were more than 4 hours longer than their GAL4 controls at 27°C (Figure 1B, Table S1). Rhythmicity was not compromised at these temperatures.

To map the neurons involved in this regulation, we expressed shi^ts1 only in the PDF+ pacemaker LNv. With expression driven by pdfGAL4, the period was nearly 2 hours longer than control, again with equivalent rhythmicity, at 25°C (Figure 1B, 1C, Table 1), indicating that shi^ts1 expression in PDF neurons is sufficient for robust period effects. Nonetheless, some of the shi^ts1 period effects may be derived from its expression in non-PDF neurons, since the period effects of pdfGAL4-driven shi^ts1 were less than those driven by cry24 and cry16. We then expressed shi^ts1 broadly in all pacemaker neurons but blocked expression in the LNv using the GAL4 repressor GAL80 (Table 1, cry24; pdfGAL80/+; UASshi^ts1/+, [24]). Period was not different from the GAL4 control, indicating that expression in PDF neurons is necessary and sufficient for period lengthening effects.

shi^ts1 Lengthens Period by Disruption of an Endocytic Process

We found that shi^ts1 expression at 25°C induced strong period effects without affecting rhythmicity. These results do not appear to be due merely to shi overexpression as induction of different wild-type isoforms, singly and in combinations (long Δ0 with short Δ0, 2 independent short Δ2 isoforms, [48]), failed to cause significant period lengthening (data not shown). We also found that period difference was minimal when tested at 18°C, the nominally permissive temperature for this allele (Fig. 1B, Table 1). In contrast period differences from control when tested at 25°C were nearly equivalent whether flies were raised at 18°C or 21°C (data not shown). These results suggest that shi^ts1 functions primarily in adulthood to modulate period.

To determine whether the effects of shi^ts1 were through its role in endocytosis, we asked whether shi^ts1 period effects depend on the expression or activity of other known endocytic components. We first examined clathrin light chain, a principal component of the clathrin cage that surrounds certain endocytic vesicles [49]. Using the broad circadian driver cry24, expression of a clathrin light chain-GFP fusion alone did not affect period. However coexpression of shi^ts1 and clc^GFP [50] resulted in significant period lengthening of almost an hour relative to cry24; UASshi^ts1/+ (Figure 1D). The fact that clc^GFP enhances the long period of cry24; UASshi^ts1/+ suggests shi^ts1's specific effect on a clathrin-mediated endocytic process is responsible for its effect on period.

To assess the functional role of more downstream steps in the endocytic process, we expressed a dominant negative form of Rab5 (Rab5S43N; [51]), a GTPase that regulates vesicle traffic from the cell membrane into early endosomes [52]. Broad expression of Rab5S43N using the cry24 driver failed to alter period or rhythmicity (Figure 1D; Table 1). In combination with shi^ts1 however (cry24; UASshi^ts1/UASRab5S43N), period was significantly longer relative to cry24; UASshi^ts1/+ (Figure 1D; Table 1). These data indicate that perturbing vesicles trafficked into early endosomes regulates circadian period.

We then manipulated arrestins, a clathrin-interacting protein involved in the downregulation, endosomal sorting, and signaling of a variety of G-protein coupled and growth factor receptor-initiated pathways [53]–[55]. We assayed flies carrying an extra genomic copy of arrestin2 or arr2 (p[w+; arr2]; gift of L. Zweibel), one of the fly “sensory” arrestins. Though it had no significant effects on circadian behavior by itself, p[w+; arr2] completely blocked period lengthening by pdfGAL4/+; Ushi^ts1/+ (Table 1). This suggests overexpression of arr2 can compensate for or prevent shi^ts1's effect. Taken together these data suggest the possibility that shi^ts1 affects rhythms by perturbing cell-surface initiated intracellular signaling pathways in the sLNv.

PKA blocks period lengthening by shi^ts1

Endocytosis and arrestin can modulate a variety of intracellular signals. Protein kinase A (PKA) regulates circadian behavior in flies [41] and has been shown to regulate clock output downstream of the clock [40]. To test if PKA played a role in shi^ts1's effects on period, we coexpressed PKA-C1, the catalytic subunit of PKA, with shi^ts1. PKA alone in the LNv (pdfGAL4/UASPKA) did not appreciably alter period relative to control and slightly reduced rhythmicity (Table 1). In contrast, period in flies coexpressing PKA and shi^ts1 (pdfGAL4/UASPKA; Ushi^ts1/+) was one hour shorter than in pdfGAL4/+; Ushi^ts1/+ (Table 1; p<0.01). These data suggest that shi^ts1 may lengthen period by a mechanism that downregulates PKA.

shi^ts1 Expression Delays PERIOD Rhythm Phase and Suppresses Rhythmic Amplitude

Because LNv expression of shi^ts1 is necessary and sufficient for behavioral period changes, we next focused on the cellular effects of pdfGAL4-driven shi^ts1 in the sLNv, crucial for setting period in DD conditions [25], [56]. We set out to examine sLNv PER cycling on the third day of constant dark conditions (DD3) following two days of LD entrainment at 25°C. We reasoned that this would allow us to more easily detect changes in PER cycling resulting from a 2-hour daily period change. To verify the magnitude of changes on DD3 we plotted the behavior of shi^ts1 expressing flies and their GAL4 controls on this day (Fig. 2A). Interestingly, both sets of flies show similar slow increases in activity but control activity then drops relatively abruptly. In the pdfGAL4/+ controls, activity level peaked at about CT13 followed by a rapid decline to a trough around CT17. The activity peak is broader in shi^ts1 expressing flies and the activity reduction is delayed several hours consistent with the observed behavioral period change. These results indicate that the PDF neuron output is intact as PDF neurons can still influence evening activity. Moreover, they suggest that shi^ts1 expressed in PDF neurons may specifically block termination rather than onset of evening activity.

Under the same conditions, (DD3, 25°C) PER staining in the sLNv cycles robustly in control flies (Figure 2B). In the shi^ts1-expressing flies PER rhythms are phase-shifted relative to the control (both peak and trough occur later) and are apparently undamped, consistent with the behavior and with published reports of the critical role of the sLNv in setting DD period [25], [56]. Thus, not only does shi^ts1 alter behavioral period but also alters in a parallel manner the rhythms of the core molecular oscillator in the master pacemaker sLNv.

UASshi^ts1 is temperature-sensitive and has been used to disrupt synaptic transmission in specific neurons at 29°C [45]. Though the average behavioral period of pdfGAL4/+; Ushi^ts1/+ flies at 29°C was not longer than at 25°C (Fig. 1B, Table 1, Table S1), the standard error was high (Table S1); some shi^ts1-driven periods were so short as to be outside the range of controls. When we examined PER cycling at 29°C, the sLNv on DD3 were delayed relative to controls, similar to the case at 25°C (Fig. 2C). However in addition peak PER levels were substantially reduced. Increases in shi^ts1 dose resulted in further peak PER reductions (Figure 2C, pdfGAL4/+; Ushi^ts1/ Ushi^ts1). Peak reductions at 29°C are likely due to reduced cycling amplitude rather than desynchrony among cells as we observed no evidence of desynchronized nuclear entry among the sLNv, and standard error for PER staining intensity was comparable to (pdfGAL4/+; Ushi^ts1/+, p = 0.29) or lower than (pdfGAL4/+; Ushi^ts1/ Ushi^ts1, p<0.05) control. In addition though the strength of the behavioral rhythm was reduced (Table S1), we saw no evidence of complex rhythms. Thus shi^ts1 appears to lengthen period by perturbing the core clock without appreciably affecting molecular synchrony among the sLNv, suggesting that PDF neuron outputs are intact.

PDF is Required for Behavioral Output, not for Delay of the sLNv Molecular Clock

PDF is the only known neurotransmitter output of the core LNv pacemaker cells and is thought to mediate synchrony among the sLNv and between pacemaker groups [16], [21]. We hypothesized that shi^ts1 may modulate PDF signaling and in turn, affect PDF feedback, thus affecting circadian period. To test this model, we assayed the effects of expressing shi^ts1 in a pdf⁰¹ mutant background. Both cry24; UASshi^ts1-pdf⁰¹/pdf⁰¹ and pdfGAL4/+; UASshi^ts1-pdf⁰¹/pdf⁰¹ flies exhibited weak short period (∼23 hour) rhythms, comparable to y w; pdf⁰¹ mutants and completely distinct from the longer periods observed in shi^ts1 expressing PDF-positive flies (Table 1). These results indicate that the behavioral effects of shi^ts1 require PDF.

Some studies show that PDF levels in the dorsal brain terminals of the sLNv cycle in a circadian fashion [57] (but see also [58]) and are altered by chronic manipulations of electrical activity in the circuit [17], [35], [59]–[61]. These findings suggest changes in neuronal activity may affect PDF levels in the dorsal terminals, perhaps by regulating PDF release. We measured PDF levels in the sLNv terminals as a crude measure of potential changes in PDF signaling and release. PDF levels in pdfGAL4/+; Ushi^ts1/+ flies were consistently lower than in pdfGAL4/+ (Fig. 3A, see methods). The combined data show a significant reduction in the level of PDF in the sLNv terminals.

We then asked if PDF is required for shi^ts1 effects on the molecular clock in the sLNv. To assay the state of the molecular clock, flies lacking PDF were collected at six timepoints on DD3 as before. To our surprise, sLNv PER cycling in pdfGAL4; UASshi^ts1-pdf⁰¹/pdf⁰¹ was delayed relative to y w; pdf⁰¹ (Figure 3B), an effect similar to the delay of pdfGAL4/+; UASshi^ts1/+ relative to pdfGAL4/+ (Figure 2B). Peak and trough were both delayed. They results show that PDF is required to convey the altered molecular oscillations to behavioral outputs. More significantly, these results unambiguously demonstrate that PDF is dispensable for shi^ts1 effects on the core molecular oscillator of the sLNv.

Peripheral Clocks are Also Strongly Affected by shi^ts1 Expression

Though PDF signaling does not contribute to the molecular effect of shi^ts1, period lengthening may occur through perturbation of other intercellular signals specific to core pacemakers. To determine if shi^ts1's effects are specific to the network of circadian neurons that drive locomotor rhythms, we expressed shi^ts1 instead in the eye. The majority of PER in the head is derived from peripheral clocks in the eye that cycle coherently in LD cycles but damp gradually in DD [62]. We expressed shi^ts1 in all photoreceptors using GMRGAL4. Flies raised at 18°C were shifted to 29°C at the beginning of a two-day LD entrainment period. We examined whole-head PER levels throughout DD1 as peripheral cycling remains appreciable at this point. Cycling in the control GMRGAL4/+ flies was robust, peaking at CT5 and showing roughly 3-fold amplitude (Fig. 4A, 4B). In contrast, PER in GMRGAL4/+; UASshi^ts1/+ heads was lower at the beginning of DD and quickly fell to low baseline levels, remaining relatively stable throughout DD1. This dramatic effect on PER levels was similar to that seen in the sLNv of pdfGAL4/+; Ushi^ts1/ Ushi^ts1 flies at 29°C (Fig. 2C), indicating that shi^ts1's effects are not specific to networked pacemaker clocks.

Reduced PER could be due to increased turnover or reduced synthesis. We asked if reduced PER levels were a reflection of reduced mRNA levels. Fly heads expressing shi^ts1 in the eye were collected as before on DD1 and analyzed for per mRNA levels. per in controls cycled robustly, peaking at CT9 with roughly 2.5-fold amplitude. By contrast per in GMRGAL4/+; UASshi^ts1/+ was low and stable throughout the day (Fig. 4C). These effects were not specific to per, as vri levels from the same flies were also substantially reduced (Fig. 4D). These results favor the interpretation that shi^ts1 perturbs the clock by reducing transcription of at least two CLK-activated core clock components, per and vri, and that this leads to reductions in PER levels.

CLK is Reduced in shi^ts1-expressing Pacemaker sLNv

It is notable that per and vri are both direct targets of the transcriptional activator CLK [2], [63], [64]. One mechanism by which both mRNAs could be reduced coordinately is through reductions of CLK-mediated transcription. To assess whether shi^ts1 might affect CLK, we quantified CLK levels in the sLNv of flies expressing high doses of shi^ts1 (pdfGAL4/+; Ushi^ts1/ Ushi^ts1) at 29°C, conditions under which PER was stably reduced 5-fold from the control peak (Fig. 2C). Under the same conditions, we found nuclear CLK in the sLNv is also reduced to approximately 60% of the control level (Fig. 5). Thus it is plausible that CLK transcription is reduced by shi^ts1, leading to reductions in per and other clock transcripts. If so, we might expect that artificially increasing CLK levels could mitigate period lengthening in shi^ts1-expressing flies. We coexpressed Clk with shi^ts1 and assayed behavioral rhythms. Flies expressing Clk in the PDF+ LNv show behavioral rhythms approximately one hour shorter than the GAL4 control but of equivalent rhythmicity (Table 1). Coexpression of Clk and shi^ts1 resulted in nearly identical behavior to expression of Clk alone; i.e. about one hour short. Thus Clk expression in the LNv either compensated for or completely blocked the effect of shi^ts1 on behavioral rhythms. Interestingly, coexpression of the CLK targets per or tim with shi^ts1 was also able to return period to control levels (Table 1), supporting the interpretation that shi^ts1 modulates period through Clk's transcriptional activation of per and tim.

Taken together these data suggest that shi^ts1 may affect clocks by reducing CLK levels and/or transcriptional activity and slowing feedback in the molecular clock. As our work indicates that shi^ts1's effects operate by compromising endocytic pathways, we suggest that membrane events leading to PKA signaling may modulate the clock by regulating expression, turnover, and/or activity of CLK.

Behavior

Crosses were maintained at 21°C until behavior. Male flies were then entrained at 25°C (unless otherwise indicated) for 2 or 5 days in 12-hour light∶12 hour dark conditions before release into constant darkness. Activity was monitored with the Trikinetics DAM system. LD activity averages were compiled with in-house DCM software. DD behavior was analyzed using Clocklab software (Actimetrics). Period differences were evaluated with t-test.

Immunostaining

Flies were entrained for 2–3 days in LD before release into DD. On the third day of DD flies were collected and 6–8 were dissected at the indicated timepoints. Brain tissue was fixed 40 minutes in 4% formalin in phosphate buffer (PB). Primary rabbit anti-PER (sometimes embryo pre-absorbed) at 1∶4000 diluted in PBT (PB with 0.3% Triton) with 10% normal serum was applied overnight. A secondary goat anti-rabbit Alexa 594 antibody (Molecular Probes) was applied at 1∶600 overnight. Final washes in PBT and PB were followed by mounting in 80% glycerol/PB. For experiments with PDF-positive genotypes, tissue was double-labeled for PER and PDF to aid cell identification. Mouse anti-PDF (1∶800, DSHB #C7) and 1∶500 goat anti-mouse Alexa 488 (Molecular Probes) were applied with the PER primary and secondary, respectively. For CLK staining, guinea pig anti-CLK [78] at 1∶10000 was applied with mouse anti-PDF as above. Secondary detection used goat anti-guinea pig Alexa 647 and goat anti-mouse 488 (1∶600).

Quantitation

Slides were coded to allow blind imaging, data collection, and analysis. Experiments were run at least twice and in each experiment staining from 4–8 hemispheres/condition was imaged on a Nikon C1 confocal (PER and PDF, 60× oil objective, PDF terminals 20×, 1 µm steps). PER, CLK quantitation: Cells were identified by position, size, and PDF double-labeling when applicable. The entire soma (nucleus only for CLK) was manually circled in the single confocal section of maximum diameter and digitally quantified using ImageJ (NIH). A nearby non-stained region was quantified for background subtraction. Average intensity for each cell was used to compute a mean for the group. Experiments were repeated at least twice and results were consistent. Subsequently data from individual cells was scaled to the typical peak control average for each experiment (CT1 of pdfG4/+ in figure 2; in figure 3 CT9 of pdfGAL4/+; Ushi-pdf⁰¹/pdf⁰¹. PDF quantitation: The terminal segment of sLNv neurites in the dorsal brain was quantified as a single number representing the mean intensity of pixels on a hand-drawn line in ImageJ. Measurements were averaged across genotype within four timepoints for each replication. PDF levels in were lower in UASshi^ts1-expressing flies at nearly all timepoints. However as two replications of the experiment a) gave inconsistent fluctuations and b) did not reflect control PDF oscillations reported in the literature, we combined data across timepoints within genotype for final means+/−SEM seen in graphs. Averaged data were compared using t-test.

Flies

Fly stocks were obtained from the following sources: M. Rosbash (cry16, cry24, pdfGAL4, pdfGAL80, pdf⁰¹); T. Kitamoto (UASshi^ts1); I. Mellman (UASclc); M. Gonzalez-Gaitan (UASRab5S43N); L. Zweibel (p[arr2]); M. Ramaswami (UASTf82-1; UASTf27-25 and UASTf114-5 and UASTf114-2); D. Kalderon (UAS-PKAC1). All other fly stocks were obtained from Bloomington Stock Center.

Westerns

Crosses were raised at 18°C. Western blotting was performed as reported elsewhere [79]. After two days of entrainment at 29°C, heads from entrained flies were collected on dry ice at four-hour interval timepoints throughout DD1. Protein extracts were made from 20–30 heads (same within experiment) and run on a 6% SDS-PAGE gel. After Ponceau staining confirmed equal loading, nitrocellulose blots were probed with 1∶10000 rabbit anti-PER followed by 1∶2000 HRP anti-rabbit. Signal was detected with ECL following kit directions (Amersham). Autoradiographs were scanned and quantified using NIH ImageJ.