Fasting prevents hypoxia-induced defects of proteostasis in C. elegans

Abstract

Low oxygen conditions (hypoxia) can impair essential physiological processes and cause cellular damage and death. We have shown that specific hypoxic conditions disrupt protein homeostasis in C. elegans, leading to protein aggregation and proteotoxicity. Here, we show that nutritional cues regulate this effect of hypoxia on proteostasis. Animals fasted prior to hypoxic exposure develop dramatically fewer polyglutamine protein aggregates compared to their fed counterparts, indicating that the effect of hypoxia is abrogated. Fasting also reduced the hypoxia-induced exaggeration of proteostasis defects in animals that express Aβ1-42 and in animals with a temperature-sensitive mutation in dyn-1, suggesting that this effect was not specific to polyglutamine proteins. Our data also demonstrate that the nutritional environment experienced at the onset of hypoxia dictates at least some aspects of the physiological response to hypoxia. We further demonstrate that the insulin/IGF-like signaling pathway plays a role in mediating the protective effects of fasting in hypoxia. Animals with mutations in daf-2, the C. elegans insulin-like receptor, display wild-type levels of hypoxia-induced protein aggregation upon exposure to hypoxia when fed, but are not protected by fasting. DAF-2 acts independently of the FOXO transcription factor, DAF-16, to mediate the protective effects of fasting. These results suggest a non-canonical role for the insulin/IGF-like signaling pathway in coordinating the effects of hypoxia and nutritional state on proteostasis.

Fig 1. Fasting protects against hypoxia-induced protein aggregation.

A. Experimental Schematic. Cohorts of age-synchronized animals were split into three groups: the first was maintained on food in room air, the second was maintained on food before and during exposure to hypoxia, and the third was removed from food before exposure to hypoxia. Fasting is indicated by white plates, yellow plates indicate animals on food. F = the duration of fasting (h) before hypoxia; H = duration of hypoxia (h). Unless otherwise noted, aggregates were counted immediately upon removal from hypoxia. B. Representative images of Q40::YFP animals from cohorts of animals maintained in room air, exposed to hypoxia on food (hypoxia fed), or exposed to hypoxia while fasted (hypoxia fasted). Note that exposures were not normalized, so protein abundance cannot be estimated from these images. F = 6h, H = 24h. Scale bars = 100μm. C-D. Aggregation measurements for L4 Q35::YFP (C) and L1 Q40::YFP (D) animals exposed to hypoxia on food (fed, magenta) or after removal from food (fasted, blue). Controls remained in room air (green). Data from one representative experiment is shown. Each experiment was repeated at least 3 times, and summary statistics from replicates are in S1 Table. Each circle is the number of YFP foci in a single animal, the mean is indicated by the line, and error bars are the standard deviation. Statistical comparisons were made between animals exposed to hypoxia and controls maintained in room air. Significance: *** p < 0.001; ns, not significant.

Fig 2. Fasting protection against HIPA is quickly induced and reversed.

A. Effect of fasting occurs rapidly in hypoxic conditions. Cohorts of L1 Q40::YFP animals were removed from food before exposure to hypoxia (F = 0, 2, or 4 h; H = 24 h). All animals were off of food when exposed to hypoxia and the number of foci was scored immediately upon removal from hypoxia (cyan). Controls remained in room air (green), were continuously on food (fed, magenta), or were fasted for a full 6 h before hypoxia (fasted, blue). Data from one representative experiment is shown. Each circle is the number of YFP foci in a single animal, the mean is indicated by the line, error bars are the standard deviation. Significance was calculated using a Kruskal-Wallis test and Dunn’s multiple comparisons post hoc analysis. Significant differences (p < 0.05) in aggregation between conditions are indicated by letters above each group as follows: a—significantly different from room air controls; b—significantly different from fed hypoxic controls; c—significantly different from fasted hypoxic controls. B. The protective effects of fasting are rapidly reversed. As shown in the schematic above the graph, cohorts of L1 Q40::YFP animals were removed from food 6h before exposure to hypoxia, and fasted for 2, 4, or 6 h before being returned to food. All cohorts were on food when exposed to hypoxia (H = 24 h). The number of foci was scored immediately upon return to room air (gray). Controls remained in room air (green), were continuously on food and exposed to hypoxia (fed, magenta), or were not returned to food before hypoxia (fasted, blue). Data from one representative experiment is shown. Each circle is the number of YFP foci in a single animal, the mean is indicated by the line, error bars are the standard deviation. Statistical comparisons were made between animals fasted for the indicated amount of time and controls maintained in room air, fed controls exposed to hypoxia after being continuously on food, and fasted controls that were not returned to food before hypoxia. Significance was calculated using a Kruskal-Wallis test and Dunn’s multiple comparisons post hoc analysis. Significant differences (p < 0.05) in aggregation between conditions are indicated by letters above each group as follows: a—significantly different from room air controls; b—significantly different from fed hypoxic controls; c—significantly different from fasted hypoxic controls. For all panels, each experiment was repeated at least 3 times, and summary data from replicates are in S2 Table.

Fig 3. Fasting protects against long-term effects of hypoxia on proteostasis.

Cohorts of L4 Q35::YFP animals were exposed to hypoxia (H = 10 h) on food (magenta) or fasted (blue, F = 6h). Controls remained in room air on food (green). The number of YFP foci was scored after return to room air as indicated. Data from one representative experiment is shown. The experiment was repeated at least 3 times. Each cohort included at least 20 animals per time point. Summary statistics from independent replicates are in S10 Table.

Fig 4. Fasting has general protective effects against hypoxia-induced defects in proteostasis.

A. Fasting protects against toxicity of Q40::YFP. Cohorts of L1 animals expressing Q40::YFP were exposed to hypoxia on food (magenta), or fasted (blue) before exposure to hypoxia (F = 6h, H = 24 h). Paralysis was scored after return to room air, beginning the first day of adulthood. Controls remained on food in room air (green). Data from one representative experiment is shown, each cohort included at least 70 animals. Each experiment was repeated at least 3 times. Significance was calculated using a Log-rank (Mantel-Cox) test with a Bonferroni correction for multiple comparisons. Statistical comparisons were made between animals exposed to hypoxia and animals maintained in room air. **** p < 0.0001; ** p < 0.01. B. Fasting protects against toxicity of Aβ_1–42. Cohorts of L4 animals expressing Aβ_1–42 were exposed to hypoxia on food (magenta) or fasted (blue) before exposure to hypoxia (F = 6h, H = 24h). Paralysis was scored after return to room air, beginning at the first day of adulthood. Controls remained on food in room air (green). Data from one representative experiment is shown, each cohort included at least 70 animals. Each experiment was repeated at least 3 times. Significance was calculated using a Log-rank (Mantel-Cox) test with a Bonferroni correction for multiple comparisons. Statistical comparisons were made between animals exposed to hypoxia and animals maintained in room air. *** p < 0.001. C. Fasting protects against hypoxia effects on metastable DYN-1. Temperature-sensitive dyn-1(ky51) mutant animals were exposed to hypoxia at the permissive temperature on food (magenta), or after fasting (blue). Controls remained on food in room air at the permissive temperature (green) or on food at the non-permissive temperature (28°C, gray). Paralysis was scored 1h after return to room air. Average data from 3 independent experiments is shown, each cohort included 10 animals. Significance was calculated using a repeated measures two-way ANOVA and Dunnett’s multiple comparisons test. Statistical comparisons were made between animals exposed to hypoxia or animals maintained at the restricted temperature and animals maintained in room air. Significance: *** p < 0.001; ** p < 0.01. Summary statistics for replicates from all experiments are in S4 Table.

Fig 5. The insulin-like signaling pathway is required for fasting protection.

A. Schematic of key insulin-signaling pathway members in C. elegans. Under nutrient-rich conditions, insulin-like peptides bind to the insulin receptor DAF-2, initiating a phosphorylation cascades that ultimately leads to the phosphorylation of the FoxO transcription factor DAF-16, excluding it from the nucleus. Conversely, when nutrients are scarce, DAF-16 remains unphosphorylated and is able to enter the nucleus and bind to its target genes. B. DAF-16 is not localized to the nucleus in fasted animals exposed to hypoxia. Cohorts of 20 DAF-16::GFP animals were maintained in room air on food for 24 hrs (fed + room air), fasted in room air for 24 hrs (fasted + room air), exposed to hypoxia for 24 hrs on food (fed + hypoxia), or exposed to hypoxia after fasting (fasted + hypoxia; F = 6h, H = 24hr). Scale bars = 100μm. C. Quantification of DAF-16::GFP nuclear accumulation. The percent of animals with nuclear GFP was scored immediately post hypoxia. Average data from 3 independent experiments is shown. The bar height indicates the mean. Error bars are the standard deviation. D. Fasting does not protect daf-2 mutants against HIPA. Aggregation measurements (F = 6h, H = 24h) for L4 Q35::YFP animals with mutations in daf-2(e1370), daf-16(mu86), and the daf-2(e1370); daf-16(mu86) double mutant. Animals were maintained on food in room air (room air, green), were exposed to hypoxia on food (fed, magenta), or were exposed to hypoxia after removal from food (hypoxia fasted, blue). Each circle is the number of YFP foci in a single animal, the mean is indicated by the line, error bars are the standard deviation. Data from one representative experiment is shown. Each cohort included at least 20 animals, and each experiment was repeated at least 3 times. Significance was calculated using a Kruskal-Wallis test and Dunn’s multiple comparisons post hoc analysis. Significant differences (p < 0.05) in aggregation for a given strain between conditions are indicated by letters above each group as follows: a—significantly different from room air controls; b—significantly different from fed hypoxic controls; c—significantly different from fasted hypoxic controls. Summary statistics from replicate experiments is in S5 Table.