Phosphatidylserine save-me signals drive functional recovery of severed axons in Caenorhabditis elegans

Abstract

Functional regeneration after axonal injury requires transected axons to regrow and reestablish connection with their original target tissue. The spontaneous regenerative mechanism known as axonal fusion provides a highly efficient means of achieving targeted reconnection, as a regrowing axon is able to recognize and fuse with its own detached axon segment, thereby rapidly reestablishing the original axonal tract. Here, we use behavioral assays and fluorescent reporters to show that axonal fusion enables full recovery of function after axotomy of Caenorhabditis elegans mechanosensory neurons. Furthermore, we reveal that the phospholipid phosphatidylserine, which becomes exposed on the damaged axon to function as a "save-me" signal, defines the level of axonal fusion. We also show that successful axonal fusion correlates with the regrowth potential and branching of the proximal fragment and with the retraction length and degeneration of the separated segment. Finally, we identify discrete axonal domains that vary in their propensity to regrow through fusion and show that the level of axonal fusion can be genetically modulated. Taken together, our results reveal that axonal fusion restores full function to injured neurons, is dependent on exposure of phospholipid signals, and is achieved through the balance between regenerative potential and level of degeneration.

Keywords: Caenorhabditis elegans; axonal fusion; axonal regeneration; nervous system repair; phosphatidylserine.

Fig. 1.

Axonal fusion restores complete function to transected PLM neurons. (A) Image and schematic of regenerative axonal fusion 24 h postaxotomy in a PLM neuron. The closed arrowhead designates the cut site, and the open arrowhead designates the fusion site. Anterior is left and ventral is down for this and all following images. The posterior ventral microtubule (PVM) neuron is also visible in this image. (Scale bar: 25 μm.) (B) Schematic representation of a dorsal view to show how PLM function was assessed postaxotomy. A UV laser was used to ablate one PLM neuron 20 h posthatching and to transect the axon of the contralateral PLM neuron 24 h later. (C and D) A light touch assay was performed on these animals 24 (C) and 48 h (D) postaxotomy to assess the function of the remaining PLM neuron. Animals with only one PLM ablated and no axotomy performed on the second PLM neuron were used as controls (mock axotomy). Bars represent mean ± SE. Symbols represent individual animals; n ≥ 13. P values are from Tukey’s multiple comparisons test. ns, not significant. *P < 0.05. ***P < 0.001. Comparison of light touch response at 24 and 48 h postaxotomy (E) in animals in which axonal fusion was not observed, and (F) in animals in which fusion was observed. Data shown in E and F are replotted from C and D. Symbols represent individual animals, and lines connect the responses of the same animals. P values are from paired t tests. **P < 0.01. (G and H) Forward response induced by posterior mechanical touch stimulation at 24 (G) and 48 h (H) postablation in control animals in which no PLM neurons were ablated (mock ablation), one PLM was ablated, or both PLM neurons were ablated. Bars represent mean ± SE; symbols represent individual animals. P values are from Tukey’s multiple comparisons test. *P < 0.05; **P < 0.01; ***P < 0.001. (I and J) Backward response to anterior light touch (mediated by the ALM and AVM neurons) at 24 (I) and 48 h (J) postaxotomy for animals in which one PLM neuron was ablated and the axon of the second PLM was either transected or left intact (mock axotomy); disruption of the posterior mechanosensory neurons did not affect the function of the anterior mechanosensory neurons.

Fig. S1.

Regeneration without fusion and behavioral response 6 h postaxotomy. (A) Image and schematic of a PLM neuron 24 h postaxotomy displaying regenerative growth without axonal fusion. Arrowheads designate cut site; asterisks highlight the end of the regrowing axon. The posterior lateral microtubule right (PLMR) and posterior ventral microtubule (PVM) neurons are also visible in this image. (Scale bar: 25 μm.) (B and C) Forward response after mechanical stimulation (light touch) on the posterior section of the body. (B) Six hours postaxotomy of animals in which one PLM neuron was ablated and the axon of the second PLM was either transected or left intact (mock axotomy). PLM function is significantly reduced 6 h postaxotomy; (C) behavioral response in animals 6 h postaxotomy compared with those at 24 h postaxotomy without fusion. Data in C are replotted from B and Fig. 1C. (D) Backward response after mechanical stimulation (light touch) on the anterior section of the body; axotomy of PLM did not affect the function of the anterior mechanosensory neurons. Bars represent mean ± SE; symbols represent individual animals. P values are from paired t test. **P < 0.01.

Fig. 2.

Axonal transport is restored after axonal fusion. (A) Images and schematic 6 h after axotomy of PLM expressing diffusible tagRFP and UNC-104::GFP. Transection of the PLM axon prevents the normal anterograde transport, leading to pooling of UNC-104::GFP fluorescence on the proximal side of the cut site. Closed arrowheads designate cut sites. (Scale bars: 25 μm.) (B) By 24 h postaxotomy, axonal fusion has occurred in the same animal as shown in A, restoring axonal transport and releasing the pool of UNC-104::GFP. Open arrowheads designate fusion sites; dashed boxes in A and B highlight the regions used for quantification of relative GFP pooling in C–F. (C and D) Quantification of GFP pooling at 6 (C) and 24 h (D) postaxotomy in animals that regrew without axonal fusion (no fusion) (Fig. S2 B and C), those that displayed fusion, and those in which no axotomy was performed (no cut). Bars represent mean ± SE. Symbols represent individual animals; n ≥ 8. P values are from Tukey’s multiple comparisons test. ***P < 0.001. Comparison of relative GFP pooling levels at 6 and 24 h postaxotomy (E) in animals where axonal fusion was not observed and (F) in animals where fusion was observed. Data shown in E and F are replotted from C and D. Symbols represent individual animals, and lines connect the responses of the same animals; P values are from paired t tests. ns, not significant. *P < 0.05.

Fig. S2.

Analysis of UNC-104::GFP in PLM neurons. (A) Image and schematic of a PLM neuron expressing UNC-104::GFP. Asterisks highlight the pooling of GFP that occurs at the distal end of the axon. Autofluorescence from the intestinal cells is visible in this image. The posterior ventral microtubule (PVM) neuron is also visible in this image. (Scale bars: 25 μm.) (B) Images and schematic showing the localization of tagRFP (Top) and UNC-104::GFP (Middle) in PLM 6 h after axotomy. Pooling of UNC-104::GFP is apparent at the end of the proximal axon fragment. (C) Twenty-four hours postaxotomy, the same axon as shown in B has regrown without axonal fusion, and pooling of GFP is still evident toward the end of the regrowing segment. Closed arrowheads designate cut sites; dashed boxes highlight the regions used for quantification of relative GFP pooling levels shown in Fig. 2 C–E. Note the accumulation of both red and green fluorophores at the site of axotomy at both time points (B and C), likely the result of collateral tissue damage caused by the UV laser. (Scale bars: 25 μm.)

Fig. 3.

Axonal fusion facilitates regrowth from a second site of axotomy. (A) Schematic representation of a lateral view of the PLM neuron showing where the two cuts were performed; Upper shows the first axotomy site ≈50 μm from the PLM cell body, and Lower shows the second site ≈10 μm from the PLM synaptic branch. The second axotomy was performed immediately after the first. (B) Average length of regrowth at 24 h (white bars) and 48 h (black bars) postaxotomy quantified for animals that displayed no fusion at the first site of axotomy and those in which fusion was observed at the first axotomy site. Bars represent mean ± SE; n values are within each bar. P value is from Tukey’s multiple comparisons test. **P < 0.01. Images and schematic of an animal 24 h postaxotomy (C) in which reconnection and fusion have failed to occur at either cut site and (D) in which fusion has occurred only at the first cut site. (E) Images and schematic of an animal 48 h postaxotomy with fusion occurring at both cut sites. Dashed boxes highlight regions magnified in Right, which shows the two fusion sites after transection 50 μm anterior from the cell body (i) and 10 μm posterior from the synaptic branch (ii). This was the only animal in which double fusion was observed; one other animal displayed reconnection at the second site but not successful fusion. No reconnection events were observed at the second site in animals without fusion at the first site. Closed arrowheads designate the cut sites, and open arrowheads designate the fusion sites. Autofluorescence from the intestinal cells is visible in some images. (Scale bars: C–E, 25 μm; E, i and ii, 10 μm.) (F) Table displays the number of animals presenting regrowth, reconnection, and successful fusion at the first and second cut sites.

Fig. 4.

Axonal reconnection and fusion increase with age and are related to regrowth, degeneration, and branching. (A) The percentage of proximal–distal reconnection in PLM neurons 24 h postaxotomy in animals of different ages; n values are within each bar. Black bar designates L4 animals that were used for analyses in other figures. P values are from t test. *P < 0.05 compared with L1; **P < 0.01 compared with L1; ^#P < 0.05 compared with L3 and L4. (B) The percentage of successful axonal fusion in PLM neurons in animals that underwent axotomy at different ages. Data in B are derived from the animals displaying reconnection in A. P values are from t test. *P < 0.05 compared with L1; ^#P < 0.05 compared with L2; ^##P < 0.01 compared with L2; ^‡P < 0.05 compared with L3; ^‡‡‡P < 0.001 compared with L3. (C) The average length of regrowth calculated 24 h postaxotomy across different ages relative to the length of the original PLM axon. P values are from Tukey’s multiple comparisons test. *P < 0.05 compared with L1; ***P < 0.001 compared with L1; ^###P < 0.001 compared with L2 and L3; ^‡‡P < 0.01 compared with L4. (D) The average length of retraction between the proximal and distal axons 24 h postaxotomy across animals of varying ages. P values are from Tukey’s multiple comparisons test. Bars represent mean ± SE of proportion (A and B) or ±SE (C and D). ***P < 0.001 compared with L1; ^###P < 0.001 compared with L2, L3, and L4. (E) Quantification of axonal degeneration in the separate distal axon segment 24 h postaxotomy using the axonal integrity scoring system (23), where a score of five represents no degeneration, and one represents complete clearance of the separated axon. The area of each circle represents the proportion of data within each category; n values are shown below each bubble plot. P values are from Kruskal–Wallis test. *P < 0.05 compared with L1; ***P < 0.001 compared with L1; ^#P < 0.05 compared with L2; ^##P < 0.01 compared with L2; ^###P < 0.001 compared with L2. (F) Quantification of the average number of regenerative branches across different-aged animals 24 h postaxotomy. Bars represent mean ± SE; n values are within or above each bar. P values are from Tukey’s multiple comparisons test. A, adult stage. ***P < 0.001 compared with L1, L2, and L3; ^##P < 0.01 compared with L4; ^###P < 0.001 compared with L4.

Fig. S3.

Correlation analyses. (A) Correlation between the percentage of reconnection (x axis) and the average length of regrowth (scaled to the original length of the PLM axon; y axis) 24 h postaxotomy. (B) Correlation between the percentage of reconnection (x axis) and the average length of proximal–distal retraction (y axis) 24 h postaxotomy. (C) Correlation between the percentage of reconnection (x axis) and the extent of axonal degeneration in the separated PLM distal segment (axonal integrity score; y axis) 24 h postaxotomy. (D) Correlation between the percentage of reconnection (x axis) and the average number of branches on the regrowing axon (y axis) 24 h postaxotomy; r and P values from Pearson correlation coefficients are displayed in red within each graph. A, adult stage.

Fig. 5.

PS exposure strongly correlates with the level of axonal fusion. (A) Images of PLM in a 1-d-old adult animal before (Left) and 1 h after (Right) axotomy. The Pmec-4::GFP transgene was used to visualize the PLM neuron, and Phsp::sAnxV::mRFP was used to visualize exposed PS. Overlay images are shown in Bottom; arrowheads designate the cut site. (Scale bars: 25 μm.) (B) Quantification of the change in sAnxV binding to the distal PLM axon segment from before axotomy to 1 h postaxotomy. Bars represent mean ± SE. Dotted line signifies a value of one (no change); n values are within each bar. P values are from Tukey’s multiple comparisons test. ***P < 0.001 compared with L1, L3, and L4; ^#P < 0.05 compared with L2; ^##P < 0.01 compared with L2. (C) Correlation between the percentage of reconnection (x axis) and the fold change in sAnxV::mRFP binding to the distal PLM axon (y axis) 24 h postaxotomy. Data shown in C are replotted from B; r and P values from Pearson correlation coefficients are displayed in the graph. (D) Quantification of the change in sAnxV binding to the distal PLM axon segment 1 h postaxotomy in WT as well as mutant backgrounds that disrupt proximal–distal reconnection (dark blue bars), fusion (light blue bar), or regrowth (white bar). Bars represent mean ± SE. Dotted line signifies a value of one (no change); n values are within each bar. No significant differences were observed from one-way ANOVA. (E) Quantification of regrowth length 24 h postaxotomy in WT and dlk-1(ju476) mutant strains; dlk-1 mutants were also defective in the initiation of regrowth, with 12 of 41 (29.3%) displaying no regrowth compared with 0 of 42 (0%) WT animals: P < 0.001 from t test. Bars represent mean ± SE; symbols represent individual animals. P values are from t test. A, adult stage.***P < 0.001.

Fig. S4.

PS exposure on the PLM axon after axotomy in animals of advancing age and in those defective for reconnection, fusion, and regrowth. (A) Quantification of sAnxV::mRFP binding to the proximal (white bars) or distal (gray bars) PLM axon segments 1 h postaxotomy relative to preaxotomy levels. Red dashed line designates a value of one (no change). Bars represent mean ± SE; n ≥ 15. A, adult stage. (B) Quantification at 1 h postaxotomy relative to preaxotomy levels of sAnxV::mRFP binding to the proximal (white bars) or distal (gray bars) PLM axon segments of the WT and animals carrying mutations in the listed genes. Bars represent mean ± SE; n ≥ 24. Red dashed line designates a value of one (no change).

Fig. 6.

Axonal fusion is modulated by genetic background. (A) Quantification of reconnection and successful axonal fusion in different genetic backgrounds: zdIs5(Pmec-4::GFP), zdIs4(Pmec-4::GFP), jsIs973(Pmec-7::mRFP), and uIs115(Pmec-17::tagRFP). Bars represent mean ± SE of proportion; n values are within each bar. P values are from t tests. *P < 0.05. (B and C) Behavioral response of four different transgenic backgrounds to mechanical stimulation (two-trial light touch assays) performed either on the anterior (B) or posterior (C) section of the animals. Bars represent proportions of animals with each response (full, partial, or none); n ≥ 100. P values are from Fisher’s exact test. ***P < 0.001. (D and E) A light touch assay was performed on zdIs4 animals with one PLM neuron ablated and the second transected as per Fig. 1. Responses were recorded at 24 h (D) and 48 h (E) postaxotomy. Animals with one PLM ablated and no axotomy performed on the second PLM neuron were used as controls (mock axotomy). Bars represent mean ± SE; symbols represent individual animals. P values are from Tukey’s multiple comparisons test. ns, not significant. *P < 0.05; **P < 0.01. (F and G) Backward response to anterior light touch at 24 h (F) and 48 h (G) postaxotomy for animals in which one PLM neuron was ablated and the axon of the second PLM was either transected or left intact (mock axotomy); disruption of the posterior mechanosensory neurons did not affect the function of the anterior mechanosensory neurons.

Fig. S5.

Analysis of axonal dynamics in axotomized PLM neurons in different transgenic backgrounds. (A) Length of regrowth from the cut site quantified 24 h postaxotomy of PLM performed in different transgenic backgrounds [zdIs5(Pmec-4::GFP), zdIs4(Pmec-4::GFP), jsIs973(Pmec-7::mRFP), uIs115(Pmec-17::tagRFP)]. Bars represent mean ± SE; symbols represent individual animals. P values are from Tukey’s multiple comparisons test. ***P < 0.001 compared with zdIs5. (B) Length of retraction quantified for the same animals shown in A. (C) Quantification of axonal degeneration in the separate axon segment 24 h postaxotomy using the axonal integrity scoring system. The area of each circle represents the proportion of data within each category; n values are shown below each bubble plot. P values are from Kruskal–Wallis test. *P < 0.05 compared with zdIs5; ^#P < 0.05 compared with zdIs4; ^###P < 0.001 compared with zdIs4. (D) Average number of branches on the regrowing axon quantified for the same animals shown in A. Bars represent mean ± SE; symbols represent individual animals. P values are from Tukey’s multiple comparisons test. *P < 0.05 compared with zdIs5; ***P < 0.001 compared with zdIs5; ^###P < 0.001 compared with zdIs4.

Fig. 7.

Axonal fusion is modulated by the site of axotomy and regrowth potential. (A) Quantification of reconnection between the regrowing proximal axon and the separated distal segment after transections performed at increasing distances from the PLM cell body. Bars represent mean ± SE of proportion; n values are within each bar. P values are from t test. **P < 0.01 compared with 50 μm; ^##P < 0.01 compared with 100 μm. (B) Quantification of successful axonal fusion in animals displaying reconnection after transections performed at varying distances from the PLM cell body. Data in B are derived from the animals displaying reconnection in A. P values are from t test. *P < 0.05 compared with 50 μm. (C) Quantification of sAnxV::mRFP binding to the proximal (white bars) and distal (gray bars) segments of PLM 1 h postaxotomy performed at either 50 or 200 μm from the cell body. Bars represent mean ± SE. Dotted line signifies a value of one (no change); n values are within each bar. (D) Comparison of reconnection and successful axonal fusion in zdIs5(Pmec-4::GFP) hermaphrodites (black bars) and males (white bars). Bars represent mean ± SE of proportion; n values are within each bar. (E) Average length of regrowth in the WT and rpm-1(ju41) mutants. Bars represent mean ± SE; symbols represent individual animals. P values are from t test. **P < 0.01. (F) Quantification of reconnection and successful axonal fusion in WT (black bars) and rpm-1(ju41) (white bars) animals. Bars represent mean ± SE of proportion; n values within each bar. P values are from t test. *P < 0.05.

Fig. S6.

Analysis of axonal dynamics after axotomy of the PLM neurons at varying distances from the cell body, in different sexes, and in rpm-1 mutants. (A–D) Length of regrowth (A), retraction (B), level of axonal degeneration (C), and regenerative branching (D) quantified 24 h postaxotomy of PLM performed at different distances from the cell body. (E–H) Length of regrowth (E), retraction (F), level of axonal degeneration (G), and regenerative branching (H) quantified 24 h postaxotomy of PLM performed in hermaphrodites or males. (I–K) Length of retraction (I), level of axonal degeneration (J), and regenerative branching (K) quantified 24 h postaxotomy of PLM performed in the WT and rpm-1(ju41) mutants. Bars represent mean ± SE; symbols represent individual animals. Axonal degeneration was quantified using the axonal integrity scoring system (23). Area of each circle represents the proportion of data within each category; n values are shown below each bubble plot. P values are from Tukey’s multiple comparisons test in A, B, and D. P values in C are from Kruskal–Wallis test. P values are from t test in F. *P < 0.05 compared with 50 μm in A, B, and D; **P < 0.01 compared with 50 μm in A, B, and D; ***P < 0.001 compared with 50 μm in A, B, and D; *P < 0.05 compared with 50 μm in C; **P < 0.01 in F.