Profiling the anaerobic response of C. elegans using GC-MS

Abstract

The nematode Caenorhabditis elegans is a model organism that has seen extensive use over the last four decades in multiple areas of investigation. In this study we explore the response of the nematode Caenorhabditis elegans to acute anoxia using gas-chromatography mass-spectrometry (GC-MS). We focus on the readily-accessible worm exometabolome to show that C. elegans are mixed acid fermenters that utilize several metabolic pathways in unconventional ways to remove reducing equivalents - including partial reversal of branched-chain amino acid catabolism and a potentially novel use of the glyoxylate pathway. In doing so, we provide detailed methods for the collection and analysis of excreted metabolites that, with minimal adjustment, should be applicable to many other species. We also describe a procedure for collecting highly volatile compounds from C. elegans. We are distributing our mass spectral library in an effort to facilitate wider use of metabolomics.

Figure 1. GC-MS reveals marked differences in the exometabolome of C. elegans cultured under anaerobic versus normoxic conditions.

(a) Extracted peak areas for all metabolites were log transformed after normalization to an internal standard and total protein. Metabolites that differed significantly between conditions were identified using a mixed-modeling approach. A false discovery rate (FDR) of 5% was used to set the significance cutoffs. Shown are spaghetti plots for metabolites analyzed by the two different GC procedures described in Methods. Lines correspond to individual metabolites: red lines, significant increases under anoxia; blue lines, significant decreases; and gray lines, no significant change. To aid visual interpretation, the values plotted in this panel were scaled by being converted to z-scores. (b and c) Hierarchical clustering (based on Pearson's correlation coefficient) was used to segregate metabolites that were synchronously up- or down-regulated following oxygen removal (only significantly altered metabolites are plotted). A low-abundance cut-off filter was applied. Heat maps are colored according to: (i) individual metabolite variation across the sample set (blue-yellow); and (ii) global variation among metabolites over the entire exometabolome data set (blue-red). The latter method only approximates relative metabolite abundance (compare to Figure S1). Exometabolites are plotted in two groups based on analytical separation technique, with volatile metabolites shown in (b) and remaining components in (c).

Figure 2. Metabolic map illustrating intracellular changes predicted to occur based on the exometabolome of wild-type worms following exposure to 18 hours of anoxia.

Major metabolic alterations characterize the C. elegans response to anoxia. Exometabolites that were identified by GC-MS, and which were used to drive map construction, are accompanied by bar graphs. In each graph, the incubation condition that resulted in the highest level of expression of a particular metabolite was assigned an expression value of one then the value in the other condition was scaled accordingly (grey: normoxic, black: anaerobic). Shown are the averages of five measurements, with error bars representing ± one standard deviation. Major flux pathways are color-coded as follows: green, glycolysis/malate dismutation/volatile fatty acid synthesis; blue, glyoxylate cycle; pink, acetate/ethanol fermentation; yellow, lactate fermentation/2-hydroxybutyrate fermentation. *, less than 10% false discovery rate; **, less than 5% false discovery rate; NADH, nicotinamide adenine dinucleotide-producing reactions; RQ, reduced rhodoquinone; O₂, oxygen consuming reactions; ^‡, methylacrylic acid was detected but resided on a shoulder of a background peak that we could not deconvolve fully. Circled numbers represent the following glycolysis by-pass enzymes of gluconeogenesis: 1, pyruvate carboxylase; 2, phosphoenolpyruvate carboxykinase; 3, fructose 1,6-bisphosphatase; 4, glucose-6-phosphatase. (Although not shown in the map, pyruvate is the source of acetyl CoA in the coupled conversion of succinate to succinyl CoA on the path to volatile fatty acid synthesis.)

Figure 3. Assessment of technical and biological variability in samples.

Replicate technical analyses were performed on each of two exometabolome samples collected from independent, normoxically-cultured, N2 worm preparations. For all four datasets, integrated metabolite peak areas were normalized to internal standard and total worm protein. Data were plotted after log₁₀ transformation. (a) Combined scatterplot showing technical variation for both biological samples (A1 versus A2, B1 versus B2). (b) Bland-Altman plot highlighting differences between the integrated intensities of metabolites in A1 and A2. The bold horizontal line represents the average difference across all metabolites. The solid horizontal lines correspond to the mean difference ± two standard deviations. The dashed vertical line is the experimentally-determined noise threshold. Data below this threshold were removed from Figure 3 by applying a low-abundance cutoff.