Slit-Dependent Endocytic Trafficking of the Robo Receptor Is Required for Son of Sevenless Recruitment and Midline Axon Repulsion

Abstract

Understanding how axon guidance receptors are activated by their extracellular ligands to regulate growth cone motility is critical to learning how proper wiring is established during development. Roundabout (Robo) is one such guidance receptor that mediates repulsion from its ligand Slit in both invertebrates and vertebrates. Here we show that endocytic trafficking of the Robo receptor in response to Slit-binding is necessary for its repulsive signaling output. Dose-dependent genetic interactions and in vitro Robo activation assays support a role for Clathrin-dependent endocytosis, and entry into both the early and late endosomes as positive regulators of Slit-Robo signaling. We identify two conserved motifs in Robo's cytoplasmic domain that are required for its Clathrin-dependent endocytosis and activation in vitro; gain of function and genetic rescue experiments provide strong evidence that these trafficking events are required for Robo repulsive guidance activity in vivo. Our data support a model in which Robo's ligand-dependent internalization from the cell surface to the late endosome is essential for receptor activation and proper repulsive guidance at the midline by allowing recruitment of the downstream effector Son of Sevenless in a spatially constrained endocytic trafficking compartment.

Fig 1. Genetic interactions between Clathrin-dependent endocytosis, and endocytic trafficking genes, and slit and robo.

(A) An ipsilateral subset of axons in the ventral nerve cord of WT stage 16 Drosophila embryos are stained with a monoclonal antibody (mAb) to FasciclinII (FasII), and quantified in the histogram below as having 0% error in the number of embryonic segments with fascicles crossing the midline. (B) Double heterozygous slit, robo embryos have a mild loss-of-repulsion phenotype (induction of ectopic crossing events in 16% of embryonic segments). Inhibiting Clathrin-dependent endocytosis by removing one copy of either α-adaptin or endophilinA in the slit,robo/+ background enhances the number of crossing defects (C, D), as does inhibiting either entry into the early endosome by removing one copy of rab5 (E), or entry into the late endosome by removing one copy of rab7 (F). These genetic enhancements of the slit,robo/+, but not of the +/+, ectopic crossing frequency are statistically significant (*, indicates p<0.0001) by two-way ANOVA, Sidak’s 95% Confidence Interval. Error bars indicate standard error of the mean. (+/+ n (number of segments) = 121, slit ¹,robo ⁵/+: 132; α-ada ¹/+ 121, α-ada ¹/ slit ¹,robo ⁵ 99; α-ada ³/+ 121, α-ada ³/ slit ¹,robo ⁵ 154; endoA¹⁰/+ 121, slit ¹,robo ⁵/+; endoA¹⁰/+ 154; endoA^EP927/+ 121, slit ¹,robo ⁵/+; endoA^EP927/+ 121; rab5 ^k08232/+ 121, slit ¹,robo ⁵/rab5 ^k08232 154; rab5 ²/+ 121, slit ¹,robo ⁵/rab5 ² 121; rab7^EY10675/+ 121, slit ¹,robo ⁵/+; rab7^EY10675/+ 176; rab7^FRT82B/+ 121, slit ¹,robo ⁵/+; rab7^FRT82B/+ 154.)

Fig 2. Genetic interactions between Dominant-Negative Transgenes for Clathrin-dependent endocytosis, and endocytosis through the late endosome, and slit.

A more restricted ipsilateral subset of axons are genetically labeled with Tau-Myc-GFP transgene to highlight their microtubules and therefore axonal projection patterns. (A) In stage 16 WT embryos the two Ap axon fascicles on either side of the midline project ipsilaterally in all embryonic segments (3 shown here, 8 abdominal scored). (B) In animals where one copy of slit has been removed, a partial loss of repulsion phenotype results with 11% of segments exhibiting ectopic crossing events (indicated by *). (C) Inhibiting Clathrin-dependent endocytosis in a WT background by adding in Dominant-Negative (DN) transgenes to Shibire, the fly homolog to Dynamin, causes ectopic crossing errors in the Ap axons. (D) Inhibiting entry into the early endosome by expressing DN-Rab5 Transgene causes ectopic crossing, which enhances the background level present in slit heterozygotes. (E) Inhibiting entry into the late endosome with DN-Rab7 transgene expression also causes loss of repulsion, which enhances the background level of crossing in slit heterozygotes. (F) Histogram: Inhibiting entry into the recycling endosome does not enhance the background crossing in slit heterozygotes. These genetic enhancements are statistically significant (*, indicates p<0.0001)) by two-way ANOVA, Sidak’s 95% Confidence Interval. Error bars indicate standard error of the mean. (+/+ n (number of segments) = 112, slit ²/+: 104; α-ada ¹/+ 320, α-ada ¹/ slit ² 112; α-ada ³/+ 112, α-ada ³/slit ² 80; endoA ^Δ4/+ 88, slit ²/+; endoA ^Δ4/+ 112; endoA¹⁰/+136, slit ²/+; endoA¹⁰/+ 120; UAS-ShiDN/+;UAS-ShiDN/+ 112, slit ²/UAS-ShiDN; UAS-ShiDN/+ 80; rab5 ^k08232/+ 144, slit ²/rab5 ^k08232 110; rab5 ²/+ 232, slit ²/rab5 ² 152; UAS-Rab5DN/+ 168, slit ²/+; UAS-Rab5DN/+ 88; rab7^EY10675/+ 128, slit ²/+; rab7^EY10675/+ 112; UAS-Rab7DN/+ 128, slit ²/+; UAS-Rab7DN/+ 152; UAS-Rab4DN/+;UAS-Rab11DN/+ 128, slit ²/UAS-Rab4DN; UAS-Rab11DN/+ 136.) See also S1 Fig.

Fig 3. Clathrin-dependent endocytosis from the cell surface through the early and late endosome positively regulate Robo signaling in vitro.

Morphological profiles of Drosophila embryonic cells bath treated for 10’ with Conditioned Media (CM) from cells either expressing empty vector (“Control”, A-C, E-G, I-J), or secreting Slit (A-C’, E-G’, I-J’). Cells expressing WT Robo that are treated with Control CM show a baseline level of process generation (A) that are more branched and elaborated if Slit treated, with two representative examples shown in (A’). This change is quantified as an increase in the average process area of multiple cells in the histogram, which is statistically significant by Two-way ANOVA, Sidak’s 95% Confidence Interval (n’s denoted on histogram). Error bars indicate standard error of the mean (D: n’s displayed on each bar). The Sholl analysis profile below reflects process field complexity as a function of the cells’ radii for cells treated with Slit CM (WT n = 13, ∆C n = 5, ∆Ig1 n = 8). (B) Cells that express Robo missing their Slit-binding motif (∆Ig1), do not elaborate processes in response to Slit treatment (B’), and show a smaller total process area, and a drop in the process field maximum radius in the Sholl profile (D). (C) Cells expressing Robo that lacks the ability to signal (∆C-terminus) show short processes that don’t branch or elaborate in response to Slit treatment (C’, D, E, E’). Inhibiting Clathrin-dependent endocytosis directly by cotransfection of WT Robo with DN-Shibire, the fly homolog of Dynamin, causes no change in the average process area of cells treated with Control CM but a defect in process elaboration in response to Slit treatment as compared to WT alone (A’), quantified as a decrease in the total process area in cells treated with Slit CM and a downward shift in the Sholl profile (H: ShiDN n = 13, ∆YQAGL n = 13, ∆YQAGL n = 12, ∆YLQY∆YQAGL n = 10). (F, G) Cells expressing Robo carrying deletions of either of two motifs predicted to be required for binding to AP-2, the Clathrin-adaptor complex expressed on the surface of cells, look similar to cells in (E’). (I, J) Inhibiting entry into the early (I’), or late (J’) endosome by co-expression of DN-Rab5, or DN-Rab7, respectively, with WT Robo causes a decrease in total process area, and a downward shift in the Sholl profile (K: Rab5DN n = 14, Rab7DN n = 13). See also S2 Fig.

Fig 4. Clathrin-dependent Endocytosis is required for removal of Robo from the surface.

An N-terminal pH sensitive tag on Robo (A-F) reveals the pool of Robo expressed on the surface of S2R+ cells after 2’ of conditioned media (CM) bath-treatment. S2R+ cells treated with CM from cells expressing Slit (B) as opposed to empty vector (A) show a decrease in surface levels of Robo, quantified in (G) as a percent decrease in average pixel intensity value of processes in (B) as compared to (A). (C, D) Inhibiting Robo signaling by deleting the entire C-terminus shunts the Slit-dependent reduction in average pixel intensity value of surface Robo, leading to a smaller percentage decrease in (G). (E, F) Deleting both of Robo’s putative AP-2 motifs abrogates the Slit-dependent reduction in surface receptor levels, leading to a smaller % decrease in average pixel intensity in (G), significant (*) according to one-way ANOVA Dunnett’s test (n’s for Control and Slit CM displayed below each bar). (H-M) The ectopic crossing events of a normally ipsilateral subset of axons in the ventral nerve cord of Stage 16 Drosophila embryos are induced by either manipulating entry to the early endosome with expression of DN-Rab5 transgene (H), or by overexpression of an attractive guidance receptor, Frazzled (J, L). Robo transgene is mislocalized to the ectopically crossing segments of axons in embryos defective for endocytic trafficking (I) but not in those with excessive attractive guidance (K), despite the similarity in strength of ectopic crossing phenotype (N). In contrast, Robo transgene defective for AP-2 binding is mislocalized to the ectopically crossing segments of axons (M) in the same gain of attraction background (L). See also S3 Fig.

Fig 5. Slit induces Robo colocalization with Rab5 in cell processes.

S2R+ cells expressing Robo and treated with SlitCM were fixed at an earlier timepoint (2’) and stained for endogenous Rab5, a marker of the early endosome, (A, C, E, F, H, J, K, M, O) and either bound Slit ligand (B, G, L), or Robo’s C-terminal tag (D, I, N). Cells with Slit bound to processes show covariance between ligand and early endosome signal (B, P (n = # cells indicated on histogram bar)). This colocalization is reduced either by reducing Slit-binding (ΔIg1 in P), or by inhibiting Clathrin-dependent endocytosis globally with DN-Shibire (F, G), or the Dynamin inhibitor Dynasore (P), or by deleting Robo’s AP-2-binding motifs (K, L). Treatment with Slit CM induces colocalization between Robo and Rab5 in processes as compared to cells treated with Control CM, quantified as a percent increase of thresholded Mander’s Overlap Coefficient between Slit and Control CM (C-E, Q). Inhibiting Clathrin-dependent endocytosis by coexpression with DN-Shibire (H-J), use of Dynasore, or deleting AP-2 adaptor motifs (M-O), or inhibiting Slit-binding by deleting the first Ig domain, causes a loss of Slit-dependent colocalization between Robo C-terminus and the early endosome in processes, quantified as the percent change in colocalization between Slit and Control CM (Q). The percentage change switches from positive to negative (Q (n’s for Ctrl CM on top, Slit CM on bottom). See also S4 Fig.

Fig 6. Robo Endocytosis is required for Sos recruitment in vitro.

Co-expression of a version of Son of Sevenless dominant-negative for its RacGEF activity (B) inhibits spreading and branching of processes in response to Slit CM as effectively as deleting Robo’s entire C-terminus (A). Feature extraction of the pixel intensity of endogenous Sos in processes reveals recruitment of Sos to processes in Slit (D) versus Control CM (C) treatment. The increase in Sos signal in processes in response to Slit seen in Robo^WT-expressing cells, quantified in the histogram as a statistically significant increase (*) in average signal intensity (I, n’s displayed on histogram), is missing in cells expressing RoboΔIg1 (E, E’). Cells expressing a Robo∆CC2∆CC3 receptor that can’t bind Ena or Dock, required for Sos binding (F, F’) also show impaired recruitment of endogenous Sos to processes, as do conditions inhibiting endocytosis (G-H’), despite comparable number of pixels (process area) analyzed (J). Statistical significance quantified by two-way ANOVA, Sidak’s 95% Confidence Interval. Error bars indicate standard error of the mean.

Fig 7. Endocytosis motifs are required for ectopic repulsion in vivo.

The projection pattern of all axons of the ventral nerve cord of late stage 14 Drosophila embryos are imaged with HRP (A-D) and the fascicles of the Eg commissural subset are imaged with a Tau-myc-GFP transgene (E-H). (A) In wild-type embryos, all segments (3 shown here) have two horizontal commissures, which are quantified as 0% of segments with error in the histogram (L n = 88). (B) Overexpressing wild-type Robo transgene in all neurons causes gain of repulsion from midline Slit, resulting in a loss of commissures in 76% of embryonic segments (L, n = 99). In contrast, overexpressing similar levels of Robo transgene that is missing its AP-2 binding motifs (C, D) can not signal ectopic repulsion from the midline, with all segments projecting in a commissural pattern indistinguishable from embryos without transgene (L ΔYQAGL n = 152, ΔYLQY n = 136, ΔYLQYΔYQAGL n = 88). (E) The Ew commissural subset of axons, schematized on the right, cross the midline in each embryonic segment, quantified as 0% error in (M, n = 88). (F) Expressing wild-type Robo transgene (I) specifically in the Ew commissural subset of axons is sufficient to cause ectopic repulsion, with loss of projection across the midline (schematized in dotted gray) in 96% of embryonic segments (M, n = 99). In contrast, expressing either Robo∆YQAGL (G, J) or Robo∆YLQY (H, K) does not cause ectopic repulsion of the Ew projection pattern, with a 0% error in (M, ΔYQAGL n = 152, ΔYLQY n = 136, ΔYLQYΔYQAGL n = 88). Error bars indicate standard error of the mean. See also S5 Fig.

Fig 8. Robo Endocytosis is required for axon guidance in vivo.

Two ipsilateral subsets of axons are imaged in Stage 17 Drosophila embryos- the FasII+ axons with a monoclonal antibody to FasII (A-E) and the Ap axons (F-J) with a GFP antibody detecting Tau-Myc-GFP transgene. In wild-type embryos these ipsilateral subsets project on either side of the midline, with three fascicles on either side for FasII (A) and one fascicle on either side for Ap (F). In robo mutant embryos, the two medial-most of the FasII+ fascicles (B) and both of the Ap fascicles (G) collapse onto the midline, scored as 100% of embryonic segments having ectopic collapse/circling events. Expressing wild-type Robo transgene is sufficient to restore repulsive signaling and therefore rescue the crossing defects in the FasII+ axons (C, +/+ n = 121, robo ^GA285 /robo ^GA285 n = 121, robo ^GA285 /robo ^GA285;ElavGAL4/UAS-Robo^WT n = 121) and the Ap axons (I +/+ n = 120, robo ^GA285 /Ap, robo ^z1772 n = 120, robo ^GA285 /Ap, robo ^z1772;UAS-RoboWT n = 80). In contrast, expressing Robo∆YQAGL (D, I), Robo∆YLQY, or Robo∆YQAGL ∆YLQY (E, J) is not sufficient to rescue the ectopic crossing events, with a large portion of embryonic segments carrying severe errors (crossing/circling events represented by dark gray) remaining. Dark gray indicates a qualitatively more severe crossing error, light gray indicates a less severe crossing error, with the stacked histogram bar height indicating total % of embryonic segments with loss-of-repulsion errors for each genotype. Error bars indicate standard error of the mean. (robo ^GA285 /robo ^GA285; ElavGAL4/UAS-Robo^∆YQAGL n = 154, robo ^GA285 /robo ^GA285; ElavGAL4/UAS-Robo^∆YLQY n = 99, robo ^GA285 /robo ^GA285; ElavGAL4/UAS-Robo^{∆YLQY∆YQAGL} n = 121. robo ^GA285 /ApGAL4, robo ^z1772;UAS-Robo^∆YQAGL n = 80, robo ^GA285 /ApGAL4, robo ^z1772;UAS-Robo^∆YLQY n = 120, robo ^GA285 /ApGAL4, robo ^z1772;UAS-Robo^{∆YLQY∆YQAGL} n = 136.)