Spatial reorganization of the endoplasmic reticulum during mitosis relies on mitotic kinase cyclin A in the early Drosophila embryo

Abstract

Mitotic cyclin-dependent kinase with their cyclin partners (cyclin:Cdks) are the master regulators of cell cycle progression responsible for regulating a host of activities during mitosis. Nuclear mitotic events, including chromosome condensation and segregation have been directly linked to Cdk activity. However, the regulation and timing of cytoplasmic mitotic events by cyclin:Cdks is poorly understood. In order to examine these mitotic cytoplasmic events, we looked at the dramatic changes in the endoplasmic reticulum (ER) during mitosis in the early Drosophila embryo. The dynamic changes of the ER can be arrested in an interphase state by inhibition of either DNA or protein synthesis. Here we show that this block can be alleviated by micro-injection of Cyclin A (CycA) in which defined mitotic ER clusters gathered at the spindle poles. Conversely, micro-injection of Cyclin B (CycB) did not affect spatial reorganization of the ER, suggesting CycA possesses the ability to initiate mitotic ER events in the cytoplasm. Additionally, RNAi-mediated simultaneous inhibition of all 3 mitotic cyclins (A, B and B3) blocked spatial reorganization of the ER. Our results suggest that mitotic ER reorganization events rely on CycA and that control and timing of nuclear and cytoplasmic events during mitosis may be defined by release of CycA from the nucleus as a consequence of breakdown of the nuclear envelope.

Fig 1. The ER displays dramatic structural and localization changes during mitosis in the early Drosophila embryo.

(A) Mitotic ER dynamics were examined in cycle 11 transgenic Drosophila embryos expressing the ER marker Pdi-GFP and the DNA marker H2-RFP using time-lapse confocal microscopy. Phases of mitosis are listed at the top with relative time (min:sec) listed in the merge panels. During interphase, ER (green) was initially spread loosely around the nucleus. Upon entry into mitosis, ER accumulates around the nucleus and was rapidly converted to thick, perinuclear cisternae upon chromosome condensation (red) and prophase onset. in prometaphase, the ER membrane reorganizes with the developing mitotic spindle and begins to accumulate at the spindle poles. At metaphase and anaphase the ER is aligned with the mitotic spindle and displays movement towards the spindle poles (arrow). During late anaphase and telophase, the ER sees a rapid localization around the segregated, decondensing chromosomes and a localization at the central spindle / midbody (arrowhead). Scale bar is 10 μm. (B) High magnification of mitotic ER changes following a single nucleus used for quantification of ER movements shown in C (asterisk in A). Yellow line denotes fluorescence trace shown in C. Scale bar is 5 μm. (C) Fluorescence intensity trace of ER (green line) and chromosomes (red line) along 20 μm of the developing embryo. ER fluorescence is maximal just adjacent to the nuclear space, but is excluded from the nucleus. During interphase, the ER is evenly distributed throughout the cytoplasm. Intensity around the nucleus increases during mitosis and follows the extension of the spindle. Pdi-GFP signal intensity reached maximum during metaphase (arrows). Condensation and alignment of chromosomes at the metaphase plate are marked by the arrowhead. At telophase, two new nuclear envelopes are formed with a large peak at the remaining midbody.

Fig 2. Mitotic ER rearrangements do not occur until after NEB.

(A) An embryo expressing Rtnl1-GFP and mCh-Tub was observed during cycle 11. Tubulin entered the nuclear space at the 20 second time-point, signaling nuclear envelope breakdown prior to accumulation of ER at the centrosome. At the 40 second time point ER began its rearrangement at the centrosome (arrow). Yellow dotted line denotes fluorescence trace shown in B. Scale bar is 5 μm. (B) Fluorescence intensity traces of Rtnl1 (green line) and mCh-Tub (red line). mCh-Tub displays an intensity peak at 5 μm and 10 μm before NEB (arrowheads). At 20 seconds, mCh-Tub intensity becomes flat indicating NEB, while Rtnl1 intensity begins to form peaks at 5 μm and 10 μm (arrows). Rtnl1 intensity continues to rise and mCh-Tub intensity also rises between 5 μm and 10 μm indicating mitotic spindle formation. Time is in min:sec.

Fig 3. 3D reconstruction of ER structural changes display a clustering of extended cisternae at the spindle poles during metaphase.

Embryos expressing Pdi-GFP (green) and H2-RFP (red) were fixed and imaged using confocal microscopy. (A) Upper panels (view 1) represent a top view of the nucleus and surrounding ER along the xy-plane and bottom panels (view 2) show the nucleus and ER ~45° -75° tilt along the in the y-plane. Embryos were imaged in the z-direction with a step size of 0.1 μm and subject to 3D reconstruction software. (B) At telophase of cycle 11, the ER is globular and spread along the reforming nuclear envelope and at the midbody (view 1, arrowhead). Exiting mitosis, at interphase, the ER is spread loosely through the cytoplasm outline the nuclear envelope. At prophase, the ER becomes defined and begins to cluster and propagate apically at the spindle poles. These clusters are not uniform in size and appear to be sheet-like structures (view 2, arrows). At metaphase, the clusters are found at the spindle poles and appear to be connected along the spindle area forming a sheath (view 1, arrow). In anaphase, ER cisternal clusters appear with the segregating chromosomes and at the midbody (view 2, arrow). Scale bar is 5 μm.

Fig 4. Arresting the Drosophila embryo in interphase maintains the ER in an interphase-like state.

(A) Time-lapse confocal images of a Pdi-GFP (green) / H2-RFP (red) transgenic embryo injected at metaphase cycle 10 with the DNA replication inhibitor, aphidicolin (APH) and viewed during cycle 11. APH, arrests the embryo in S-phase of cycle 11. In the presence of APH, the ER displayed a loose uniform distribution around the nuclei denoting an interphase-like state. This interphase-like state of the ER persists for greater than 30 minutes without any changes to either localization or structure. This is quantified in the fluorescence intensity traces below (see yellow dotted-lines in merged images). H2-RFP signal inside the nucleus does not increase over this time period as well (arrowheads). (B) Time-lapse confocal images of a Pdi-GFP (green) / H2-RFP (red) embryo injected with the protein synthesis inhibitor cycloheximide (CHX) at metaphase of cycle 10 and viewed during interphase of the following cycle. Similar to APH, CHX induced arrest which maintained the ER in an interphase-like state. This is quantified below, as in A. (C) Similar background and approach as A and B. Embryos were injected with an APH+CHX cocktail. ER membrane maintained an interphase-like organization as seen in APH injections alone. Scale bar is 10 μm. Time is in min:sec.

Fig 5. Inhibition of the APC/C maintains the ER in a mitotic state.

(A) Time-lapse confocal images of a cycle 10 Pdi-GFP / H2-RFP transgenic embryo following micro-injection of a dominant-negative form of UbcH10 just prior to entry into mitosis, eventually arresting the embryo in metaphase. The ER displayed normal structural organization and localization changes early in mitosis and relocated to the mitotic spindle upon nuclear envelope breakdown. The embryo then arrested at metaphase and the ER remained along the mitotic spindle. Flares of membrane began to protrude from the perispindle area. ER membrane was steadily lost from the area adjacent to the spindle pole over time (~20 minutes). Yellow trace line indicates plots for B, orange line for C. Scale bar is 5 μm. Time is in min:sec. (B) Fluorescence intensity trace plots of the longitudinal section of a nucleus. The plots are similar to wildtype through metaphase (see Fig. 1C). The later time points show a lack of intense ER at the poles, as seen in wildtype. (C) A plot of fluorescence intensity through a latitudinal section of the spindle highlights the increase in fluorescence around the spindle normally seen during mitosis. At the arrest, multiple peaks are seen where flares of ER expand from the perispindle region (arrows).

Fig 6. Mitotic ER Spatial Organization is Independent of Individual Cdk1 Activity.

(A) Time-lapse confocal imaging of a Pdi-GFP (green) / H2-RFP (red) embryo injected with dsRNA corresponding to individual mitotic cyclins (cycle 7–9) and viewed during mitosis at cycle 12. When CycA was knocked-down, improper clustering of ER at the mitotic spindle was observed at metaphase (arrow), and nuclear envelope closure was uncoupled from telophase onset and ER invagination at the central spindle (arrowhead). (B) Knock-down of CycB caused irregular chromosome alignment at the metaphase plate (arrowhead). During telophase, the midbody of the ER was absent. (C) Pairwise knockdown of mitotic cyclins produced disparate ER phenotypes in mitosis. Knock-down of CycB and B3, leaving only CycA, did not arrest the cell cycle, but produced lagging chromosomes (arrows). (D) Double knockdown of CycA and CycB3 leaving only CycB during mitosis at cycle 11, saw uneven accumulation of ER around the spindle at prophase and metaphase. Scale bar is 10 μm.

Fig 7. Mitotic Cyc:CDK1 Activity is Necessary for Mitotic ER Dynamics

(A) Cycle 11 transgenic embryo expressing Pdi-GFP / H2-RFP following simultaneous dsRNA-mediated knockdown of Cyclins A,B, and B3. When all three mitotic cyclins were knocked-down, there was a general arrest of the embryo prior to entry into mitosis and a block in ER spatial reorganization events. ER tubules persisted between adjacent nuclei. Chromosomes incompletely condensed (arrowhead) and the ER occasionally invaded the nuclear space (arrow). (B) Quantification of the induced arrest from injection of dsRNA directed at all three mitotic cylins shown in A. Intensities of Pdi-GFP and H2-RFP fluorescence are represented by green and red, respectively. (C) Arrest of ER membrane dynamics was further confirmed by examination of the ER shaping protein, Rtnl1. Injection of dsRNA directed at all three mitotic cyclins into a Rtnl1-GFP / H2-RFP embryo produced an arrest prior to mitotic entry, indicating that Rtnl1 is able to change localization independent of mitotic cyclin/CDK activity. (D) Quantification of arrest seen in C with Rtnl1-GFP in green and H2-RFP in red. Scale bars are 10 μm. Time is in min:sec.

Fig 8. Cyclin A is sufficient to drive mitotic ER reorganization events.

(A) Schematic of injection strategy and imaging of Drosophila embryo experiment. Pdi-GFP / H2-RFP transgenic embryos were injected with a mixture of APH and CHX, inducing a cycle 11 interphase arrest. Following this arrest, embryos were injected with an affinity-purified recombinant form of cyclin and observed for changes in ER localization. (B) After injection of GST-CycA, ER (green) gathered near the spindle (yellow arrowhead). Pdi-GFP intensity increases much like WT embryos (arrow). Chromosomes (red) eventually condensed and aligned at the metaphase plate (black arrowhead). The spindle region extended into a fusiform structure, but did not progress beyond this point. There was a lack of ER gathering at spindle poles, as well. (C) Following injection of GST-CycB, embryos remained in an interphase-like state without rearrangement of ER (green) or chromosome (red) condensation. Scale bars are 5 μm. Time is in min:sec.