18O-Tracer Metabolomics Reveals Protein Turnover and CDP-Choline Cycle Activity in Differentiating 3T3-L1 Pre-Adipocytes

Abstract

The differentiation of precursor cells into mature adipocytes (adipogenesis) has been an area of increased focus, spurred by a rise in obesity rates. Though our understanding of adipogenesis and its regulation at the cellular level is growing, many questions remain, especially regarding the regulation of the metabolome. The 3T3-L1 cell line is the most well characterized cellular model of adipogenesis. Using a time course metabolomics approach, we show that the 3T3-L1 preadipocyte metabolome is greatly altered during the first 48 hours of differentiation, where cells go through about two rounds of cell division, a process known as mitotic clonal expansion. Short-chain peptides were among several small molecules that were increased during mitotic clonal expansion. Additional indicators of protein turnover were also increased, including bilirubin, a degradation product of heme-containing proteins, and 3-methylhistidine, a post-translationally modified amino acid that is not reutilized for protein synthesis. To study the origin of the peptides, we treated differentiating preadipocytes with 18O labeled water and found that 18O was incorporated into the short chain peptides, confirming them, at least in part, as products of hydrolysis. Inhibitors of the proteasome or matrix metalloproteinases affected the peptide levels during differentiation, but inhibitors of autophagy or peptidases did not. 18O was also incorporated into several choline metabolites including cytidine 5'-diphosphocholine (CDP-choline), glycerophosphocholine, and several phosphatidylcholine species, indicative of phosphatidylcholine synthesis/degradation and of flux through the CDP-choline cycle, a hallmark of proliferating cells. 18O-Tracer metabolomics further showed metabolic labeling of glutamate, suggestive of glutaminolysis, also characteristic of proliferating cells. Together, these results highlight the utility of 18O isotope labeling in combination with metabolomics to uncover changes in cellular metabolism that are not detectable by time-resolved metabolomics.

Fig 1. Time course metabolomics of differentiating adipocytes.

PCA-DA scores plot representing metabolomic analysis (positive ion) of differentiating and control (0.1% DMSO) 3T3-L1 fibroblasts during the early phase of differentiation. The times refer to the amount of time passed after the addition of the differentiation cocktail or DMSO. n = 3 biological replicates for all time points except 0 h, where n = 6. Shown are means ± SE.

Fig 2. Temporal changes in polyamine, glutathione, and amino acid metabolism during 3T3-L1 preadipocyte differentiation.

Time course profiles of metabolites involved in glutathione metabolism (A-C), polyamine metabolism (D-G), and amino acid metabolism (H) over the first 48 h of adipocyte differentiation. Control cells had 0.1% DMSO. (I) Hypothetical scheme linking proline degradation to reactive oxygen species (ROS) formation and polyamine biosynthesis in differentiating 3T3-L1 preadipocytes. n = 3 biological replicates for all time points except time 0 h, where n = 6. Shown are means ± SE.

Fig 3. Temporal changes in products of protein degradation during adipocyte differentiation.

Time course profiles of short-chain peptides (A-C), methylhistidine (D), and bilirubin (E) over the first 48 h of adipocyte differentiation. Control cells had only 0.1% DMSO. n = 3 biological replicates for all time points except time 0 h, where n = 6. Shown are means ± SE.

Fig 4. Short-chain peptides are products of peptide hydrolysis.

Representative total ion chromatograms (A, B) and peak areas of peptide M+H+2 peaks (C) of differentiating (for 24 h) 3T3-L1 preadipocytes treated with 6% H₂O or H₂¹⁸O. Shown are means ± SE, n = 3 biological replicates. ND, not detected.

Fig 5. The CDP-choline cycle is active during 3T3-L1 preadipocyte differentiation.

(A) Choline metabolism and the potential for ¹⁸O incorporation from H₂¹⁸O. Adapted from Fagone and Jackowski [41]. (B-F) Peak area ratios (M+H+2 peak over the M+H peak, a measure of ¹⁸O incorporation) of choline metabolites. (G-M) Temporal changes in choline metabolites during 3T3-L1 preadipocyte differentiation. Shown are means ± SE, n = 3 biological replicates except time 0 h, where n = 6. *** p < 0.0001 and ** p < 0.001 from a two-tailed t-test. ns, not significant where p > 0.05.

Fig 6. Glutaminolysis is active during 3T3-L1 preadipocyte differentiation.

(A) Peak area ratio (M+H+2 peak over the M+H peak, a measure of ¹⁸O incorporation) of glutamate. (B) Scheme of glutamine hydrolysis for production of the anaplerotic amino acid glutamate. Shown are means ± SE, n = 3 biological replicates.

Fig 7. Short-chain peptide levels are reflective of proteasome activity.

(A-D) Relative levels of short-chain peptides in the presence of various concentrations of inhibitors of proteasome activity (epoxomicin; Epox), autophagosome-lysosome fusion (bafilomycin A1; Baf), and aminopeptidase activity (bestatin; Best). 0.1% DMSO served as a vehicle control. Shown are means ± SE, n = 3 biological replicates. ND, not detected.

Fig 8. Short-chain peptide levels are reflective of matrix metalloproteinase activity.

(A-C) Relative levels of short chain peptides in the presence of batimastat (10 μM), a broad spectrum matrix metalloproteinase inhibitor. 0.1% DMSO served as a vehicle control. Shown are means ± SE, n = 3 biological replicates. *** p < 0.0001 and ** p < 0.001 and * p > 0.05 from a two-tailed t-test.

Fig 9. Metalloporphyrin complex antioxidants alter the levels of short-chain peptides and bilirubin.

Relative levels of short chain peptides (A-C), methylhistidine (D), and bilirubin (E) in control undifferentiating 3T3-L1 preadipocytes (Undiff) and differentiating 3T3-L1 readipocytes (Diff) in the presence or not of the metalloporphyrin complex antioxidants EUK134 or nTMPyP. Plain media served as a vehicle control. Shown are means ± SE, n = 3 biological replicates. * p < 0.05 from a Tukey post-hoc test following a one-way ANOVA. ND, not detected.