FLN-2 functions in parallel to LINC complexes and Cdc42/actin pathways during P-cell nuclear migration through constricted spaces in Caenorhabditis elegans

Abstract

Nuclear migration through narrow constrictions is important for development, metastasis, and pro-inflammatory responses. Studies performed in tissue culture cells have implicated LINC (linker of nucleoskeleton and cytoskeleton) complexes, microtubule motors, the actin cytoskeleton, and nuclear envelope repair machinery as important mediators of nuclear movements through constricted spaces. However, little is understood about how these mechanisms operate to move nuclei in vivo. In C. elegans larvae, 6 pairs of hypodermal P cells migrate from lateral to ventral positions through a constricted space between the body wall muscles and the cuticle. P-cell nuclear migration is mediated in part by LINC complexes using a microtubule-based pathway and by an independent CDC-42/actin-based pathway. However, when both LINC complex and actin-based pathways are knocked out, many nuclei still migrate, suggesting the existence of additional pathways. Here we show that FLN-2 functions in a third pathway to mediate P-cell nuclear migration. The predicted N-terminal actin binding domain in FLN-2 that is found in canonical filamins is dispensable for FLN-2 function, this and structural predictions suggest that FLN-2 is not a divergent filamin. The immunoglobulin (Ig)-like repeats 4-8 of FLN-2 were necessary for P-cell nuclear migration. Furthermore, in the absence of the LINC complex component unc-84, fln-2 mutants had an increase in P-cell nuclear rupture. We conclude that FLN-2 functions to maintain the integrity of the nuclear envelope in parallel with the LINC complex and CDC-42/actin-based pathways to move P-cell nuclei through constricted spaces.

Figure 1:. fln-2 mutants enhance the P-cell nuclear migration defect observed in unc-84 worms.

(A-C) Representative epifluorescence images of unc-47::gfp-marked GABA neurons in wild type, unc-84(n369), or unc-84(n369); fln-2(tm4687) animals. (D) The numbers of missing GABA neurons are shown from the following genotypes: unc-84(n369) (black), fln-2(tm4687) (magenta), unc-84(n369) fln-2(tm4687) (red), and unc-84(n369) fln-2(RNAi) (pink). **** signifies a P-value < 0.0001 when compared to unc-84(n369) alone. (E) Schematic of four of the more than 25 predicted isoforms of fln-2. The purple diamond indicates the ot611 point mutant producing an early stop codon. The pink box indicates the X-4P01 clone used for RNAi. The magenta box shows the location of the tm4687 deletion allele. The fosmids used in these experiments are marked below the isoforms. (F-G) Missing GABA neuron counts for the unc-84(n369) fln-2(tm4687) mutants with and without the indicated fosmids. *, **, ***, and **** indicates a p-value < 0.02, < 0.003, 0.0007, and < 0.0001, respectively; error bars are 95% confidence intervals.

Figure 2:. Deletion of Ig-like repeats 4–9 enhances the unc-84 P-cell nuclear migration defect.

(A) Schematic of the FLN-2c isoform, which contains 20 predicted Ig-like repeats (maroon boxes). Ig-like repeats 1–3 are only found in the longer isoforms of FLMN-2 with interspersed disordered regions are indicated by the zig-zag lines. The region between repeats 6 and 7 is predicted to be disordered. The deleted portions of FLN-2 in three strains made by CRISPR/Cas9 editing are indicated below the schematic. The scale bar indicates 100 amino acids. (B) Missing GABA neurons at 15°C were scored as a proxy for failed P-cell nuclear migrations. See Table 1 for details on the genotypes of the strains used here. Means with 95% confidence intervals are shown. *** indicates significant differences with a p-value of <0.001 when compared to unc-84 null animals and ns stands for no significant difference from unc-84 null animals. A t-test was done to generate pvalues.

Figure 3:. Actin networks during P-cell nuclear migration.

(A) Representative Airyscan super-resolution images of a wild-type L1 larvae during P-cell nuclear migration. P-cell nuclei are marked by nls::tdTomato (magenta) and actin in P cells is tagged with vab-10::mVenus (cyan). The gold box indicates a P cell mid nuclear migration that is enlarged in the inset below. The orange arrow points out actin perpendicular to the direction of nuclear migration in the lateral compartment and the white arrow indicates actin parallel to the direction of nuclear migration in the constriction. A ventral view is shown and the ventral cord is marked by the dashed line. Anterior is left; scale bar is 10 μm. (B-C) A ventral view (B) and lateral view (C) of P cells during the narrowing (B and C) and migration (B’ and C’) stages. P cells are in cyan, nuclei are in magenta. The dashed line indicates the ventral cord. The pharynx indicates the anterior end of the worm and body wall muscles are represented by the transparent gray bar. (D) Actin (vab10::mVenus; cyan) and P-cell nuclei (nls::tdTomato; magenta) in wild-type, unc-84(n369), fln-2(tm4687), or fln-2(tm4687) unc-84(n369) double mutant animals. Maximum projections of z stacks are shown. The scale bar is 10 μm.

Figure 4:. P-cell nuclei in fln-2 unc-84 mutant animals often rupture during migration.

(A) Representative Airyscan super-resolution images of P cells late in L1 after or during nuclear migration into the ventral cord in wildtype, unc-84(n369), fln-2(tm4687), and fln-2(tm4687) unc-84(n369) animals. Actin is shown to mark the shape of P cells. Arrows point to suspected nuclear rupture events where the nls::tdTomato marker has leaked into the cytoplasm of the P cell. Maximum projections of z stacks are shown. The scale bar is 10 μm. (B) The number of P cells with cytoplasmic nls::tdTomato per worm in late L1. Means and 95% confidence intervals are shown. **** denotes a p-value of <0.00001.

Figure 5:. FLN-2 localization in larval P cells.

A) Representative Airyscan super-resolution image of fln-2c::GFP expressed in a C. elegans L1 larva. A lateral view is shown; ventral is toward the lower right. Scale bar is 10 μm. B) Graph depicting the number of missing GABA neurons in unc-84(n369), unc-84(n369) + Ex[unc-84(+)], fln-2c::spGFP unc-84(n369), and fln-2c::spGFP unc-84(n369) + Ex[unc-84(+)] worms. Error bars are 95% CI, and non-significant P-values > 0.05.

Figure 6:. fln-2 has synthetic interactions with unc-84 and cgef-1.

Graph depicting the number of missing GABA neurons in the designated genotypes. The mean is shown with 95% CI error bars. Data was collected at 15°C. n is at least 15. *** denotes p<0.001 from a paired t-test.

Figure 7:. Alphafold predictions of the structure of FLN-1 and FLN-2.

The highest confidence of five FLN-1a (top) and FLN-2d (bottom) structures predicted by ColabFold version 1.5.2 are shown. On the right, the pLDDT scores (predicted local distance difference test; a per-residue confidence metric) for five different predictions are shown. The protein diagrams are colored by sequence order from blue (N terminus) to red (C terminus).