Parallel chemical genetic and genome-wide RNAi screens identify cytokinesis inhibitors and targets

Abstract

Cytokinesis involves temporally and spatially coordinated action of the cell cycle and cytoskeletal and membrane systems to achieve separation of daughter cells. To dissect cytokinesis mechanisms it would be useful to have a complete catalog of the proteins involved, and small molecule tools for specifically inhibiting them with tight temporal control. Finding active small molecules by cell-based screening entails the difficult step of identifying their targets. We performed parallel chemical genetic and genome-wide RNA interference screens in Drosophila cells, identifying 50 small molecule inhibitors of cytokinesis and 214 genes important for cytokinesis, including a new protein in the Aurora B pathway (Borr). By comparing small molecule and RNAi phenotypes, we identified a small molecule that inhibits the Aurora B kinase pathway. Our protein list provides a starting point for systematic dissection of cytokinesis, a direction that will be greatly facilitated by also having diverse small molecule inhibitors, which we have identified. Dissection of the Aurora B pathway, where we found a new gene and a specific small molecule inhibitor, should benefit particularly. Our study shows that parallel RNA interference and small molecule screening is a generally useful approach to identifying active small molecules and their target pathways.

Figure 1. Distribution of Active Small Molecules and Genes Targeted by RNAi Identified by Penetrance of Binucleate Phenotype and by Phenotypic Classes

(A and B) Penetrance of binucleate phenotype for small molecules (A) and RNAi hits (B). (A) For the small molecules, 24% (6/25) were strong (s), 44% (11/25) medium (m), and 32% (8/25) weak (w). (B) For the RNAi hits 6% (13/2114) were strong (s), 20% (43/214) medium (m), and 74% (158/214) weak (w). In a weakly penetrant phenotype, the binucleate level was increased by more than 1.25-fold relative to the two neighboring wells in at least two experiments. In a medium penetrance phenotype, the binucleate level was above 4%, or four times as high as the neighboring wells. In a strongly penetrant phenotype, the binucleate level was above 15%. The average binucleate level in controls was approximately 1%. (C and D) Phenotypic classes for small molecules (C) and genes targeted by dsRNAs (D). (C) For the small molecules, 40% (10/25) were binucleate (b; Figure 2A), 8% (2/25) binucleate with large, diffuse DNA (d; Figure 2B), 28% (7/25) binucleate with low cell count (lc; Figure 2C), and 24% (6/25) binucleate with microtubule extensions (MT; Figure 2D). (D) For the RNAi hits, 51% (109/214) were binucleate (b; Figure 2A), 2% (5/214) binucleate with large, diffuse DNA (d; Figure 2B), 29% (62/214) binucleate with low cell count (lc; Figure 2C), and 12% (25/214) binucleate with microtubule extensions (MT; Figure 2D). In addition, 5% (10/214) were binucleate with low cell count and microtubule extensions, and 1% (3/214) were binucleate with low cell count and large, diffuse DNA.

Figure 2. Predicted Functional Annotations of 214 Genes Associated with RNAi Binucleate Phenotypes

Functional groups were assigned using Gene Ontology information presented in FlyBase or the literature (see Table S4). Genes involved in processes associated with cytokinesis are shown in shades of yellow, nucleic acid and protein synthesis and degradation in shades of red, and uncharacterized genes in shades of blue. The uncharacterized genes encode protein sequences that predict recognizable domains (“putative domain”), no recognizable domains (“no recognized domain”), or new gene predictions from the reannotation of the Drosophila genome used as the basis of the dsRNA library (“new annotation”).

Figure 3. Phenotypic Classes

The phenotypic classes are (A) binucleate (CG10522 RNAi) and binucleate with (B) large, diffuse DNA (aurora B RNAi), (C) low cell count (RpS18 RNAi), or (D) microtubule extensions (Act5C RNAi). In (A), (B), and (C), the cytoplasm (tetramethylrhodamine stain) of Kc₁₆₇ cells is shown in red and DNA in green. In (D), tubulin is shown in red and DNA in green. See Table S2 for full classification.

Figure 4. Kc₁₆₇ Cells Exposed to dsRNA Targeting Act5C or to Cytochalasin D

The cells were exposed to dsRNA targeting Act5C for 4 d (A) or to cytochalasin D at 5 μM for 48 h (B). Tubulin is shown in red, DNA in green.

Figure 5. Kc₁₆₇ Cells Untreated or Exposed to aurora B dsRNA, borr (CG4454) dsRNA, or Binucleine 2

TMR-stained cells were untreated, or treated with dsRNA for 4 d or binucleine 2 (50 μM) for 2 d. TMR is shown in red, DNA in green. The chemical structure of binucleine 2 is also shown.

Figure 6. Kc₁₆₇ Cells Transfected with Borr-GFP

In the top row, cells in metaphase, anaphase, and cytokinesis are shown. Borr-GFP is shown in green, tubulin in red, and DNA in blue. The bottom row shows cells in metaphase and cytokinesis. Borr-GFP is shown in green, Aurora B in red, and DNA in blue.

Figure 7. Kc₁₆₇ Cells Untreated or Exposed to aurora B dsRNA, borr (CG4454) dsRNA, or Binucleine 2

INCENP-stained cells in the top row were untreated or treated with aurora B dsRNA for 5 d, borr (CG4454) dsRNA for 3 d, or binucleine 2 (20 μM) for 4 h. Phospho-Histone H3 stained cells in the bottom row were untreated or treated with dsRNA for 4 d or binucleine 2 (20 μM) for 4 h. White arrows indicate absence of phospho-Histone H3 staining in the failed mitotic figures.

Figure 8. Time- and Concentration-Dependence of Binucleine 2

Kc₁₆₇ cells were treated with 1 μM, 5 μM, 25 μM, or 100 μM binucleine 2. Phospho-Histone H3 staining was assessed at different time points. Binucleine 2 at 100 nM and 300 nM was also tested and showed no effect (data not shown).