Glucose feeds the TCA cycle via circulating lactate

Metabolites (n = 39) with reported concentration greater than 30 μM in mouse plasma. Left bar graph shows those >100 μM (n = 17) and right bar graph those between 30 μM and 100 μM (n = 22). Most of the data are from the Mouse Multiple Tissue Metabolome Database (http://mmdb.iab.keio.ac.jp) (n = 2 mice), except for glucose (n = 6 mice), acetate (n = 3 mice), and glycerol (n = 3 mice), whose concentrations were determined in this study. The metabolites shown with red bars (n = 30) are those whose turnover fluxes have been determined (Table 1). Values are mean ± s.d. The concentration cut off of 30 μM was calculated using equation (1) where we used a cardiac output of 0.5 ml g⁻¹ min⁻¹ (see Supplementary Note 1 for references) and a turnover flux equating to 10% of glucose F_circ.

a, Illustration of the mouse infusion experimental setup. b, Relative total ion counts (TICs) of serum glucose and lactate during ¹³C-glucose infusion (individual mouse data are shown for three mice for each condition). c, Relative TICs of serum glucose and lactate during ¹³C-lactate infusion. d, Glucose (n = 16 for 1× and n = 6 for 0.5×; P = 0.61) and lactate (n = 18 for 1× and n = 6 for 0.5×; P = 0.50) turnover fluxes determined using two different infusion rates (mean ± s.d.). P values were determined by a two-tailed unpaired Student’s t-test. The 1× infusion rates are listed in Supplementary Table 1.

Source data

a, The dependence of lactate turnover flux (F_circ) on the exchanging flux (forward (J_f) and reverse (J_r)) between circulating lactate and tissue pyruvate. Rapid exchanging flux does not lead to infinitely fast lactate turnover flux. Instead, it leads to a lactate turnover flux approaching the net production rate of pyruvate (J_g), as illustrated in lower panel. J_t is the pyruvate flux going to the TCA cycle. See Supplementary Note 2 for derivation. b, Spatial dependence of tracer enrichment. Labelling (L(x)) decreases in an exponential manner across a tissue capillary bed (shown schematically in the shading of the cylinder representing tissue) with the extent of arteriovenous difference in tracer labelling depending on the metabolic transformation rate (k) relative to the volumetric blood flow rate (q = Q/V; V is tissue volume) as shown in the equation. L_a and L_v are labelled fraction in the artery and the vein, respectively. See Supplementary Note 1. c, Lactate labelled fraction in arterial (carotid artery; n = 8 mice, mean ± s.d.) and venous (tail vein and vena cava; n = 3 mice, mean ± s.d.) serum samples, and in tail snip serum sample (n = 3 mice, mean ± s.d.). For comparison of tail snip to vena cava only, samples were collected under anaesthesia to allow access to the inferior vena cava. The difference in lactate labelling between the carotid artery and tail snip can be used to calculate lactate F_circ using equation (3). With Q = 0.53 ± 0.11 ml min⁻¹ g⁻¹ and C = 2.5 ± 0.2 mM, together with , we get lactate F_circ as 398 ± 88 nmol min⁻¹ g⁻¹ in the fasted state, which is comparable to the value of 374 ± 112 nmol min⁻¹ g⁻¹ obtained with equation (2). See Supplementary Note 1 for details.

Source data

a, Comparison of normalized labelling of tissue malate after 2.5 h (n = 5 mice; mean ± s.d.) and after 5 h of [U-¹³C]glucose infusion (n = 3 mice; mean ± s.d.). P values were determined by an unpaired Student’s t-test, corrected for multiple comparisons using the Holm–Sidak method. Normalized labelling is the fraction of ¹³C atoms in a metabolite divided by the fraction of ¹³C atoms in serum glucose. None of the differences are significant (P > 0.14 for the brain and liver, and P > 0.98 for other tissues). b, Comparison of normalized labelling of tissue succinate after 2.5 h (n = 5 mice; mean ± s.d.) and after 5 h of [U-¹³C]glucose infusion (n = 3 mice; mean ± s.d.). None of the differences are significant (P > 0.18 for the brain and liver, and P > 0.85 for other tissues).

Source data

a, Normalized labelling by ¹³C-glucose in fasting mice (n = 3 for pyruvate, 2-oxoglutarate, and 3-phosphoglycerate, n = 4 for alanine, and n = 5 for all other metabolites; mean ± s.d.). b, Normalized labelling by ¹³C-lactate in fasting mice (n = 3 for 3-phosphoglycerate and n = 4 for all other metabolites; mean ± s.d.). n indicates the number of mice. For the lactate tracer studies, venous serum and tissue labelling are normalized to the arterial serum lactate labelling. Note that citrate, malate and succinate in tissues turn over sufficiently slowly that labelling is robust to the small (<90 s) delay between euthanizing the mouse and tissue harvesting. This delay may, however, result in erroneous measurements for tissue lactate, pyruvate and glycolytic intermediates. Analyses in the main text are limited to the better validated measurements of serum metabolites and tissue TCA intermediates. With this caveat in mind, it is nevertheless intriguing that lactate labelling varies markedly across tissues. After labelled glucose infusion, lactate labelling is highest in the brain, consistent with its use of glucose as a major substrate. In the kidneys lactate is strongly labelled after glucose infusion, even though TCA intermediates are more labelled after lactate infusion. A potential explanation involves tissue heterogeneity; for example, the presence both of glycolytic cells that make lactate from circulating glucose and of oxidative cells that make TCA intermediates from circulating lactate. In other tissues, such as liver, tissue lactate labelling is far below circulating lactate and very similar to TCA labelling; this may reflect mixing of carbon between lactate and TCA intermediates via gluconeogenesis or pyruvate cycling. Another factor diluting tissue lactate labelling is that, as blood passes through tissue, owing to the rapid exchange between tissue and circulating lactate, the circulating lactate loses its labelling, as is evident from the lactate arteriovenous labelling difference.

Source data

Unlike citrate, succinate and malate have substantially higher concentrations in tissues than in the bloodstream, thus making them a suitable readout for the tissue TCA cycle. Data are from the Mouse Multiple Tissue Metabolome Database (http://mmdb.iab.keio.ac.jp). Values are mean ± s.d. (n = 2 mice). Note that the y-axis is a logarithmic scale.

a, Turnover fluxes of glucose (n = 4 mice, mean ± s.d.) and lactate (n = 3 mice, mean ± s.d.) in anaesthetized mice. b, Normalized labelling of serum glucose, lactate, and glutamine in anaesthetized mice with ¹³C-glucose infusion (n = 4 mice; mean ± s.d.) and ¹³C-lactate infusion (n = 3 mice; mean ± s.d.). c, Steady-state whole-body flux model summarizing glucose and lactate interconversion and their feeding to the TCA (see Supplementary Note 4). Values are mean ± s.e.m.

Source data

a, ¹³C-lactate infusion (n = 5 mice). b ¹³C-glutamine infusion (n = 3 mice). c, ¹³C-glucose infusion (n = 4 mice). Bars are mean ± s.d.

Source data

a, Kras^LSL-G12D/+Trp53^−/− (KP) non-small cell lung cancer (n = 3 for ¹³C-glucose and ¹³C-lactate infusions, and n = 4 for ¹³C-glutamine infusion). b, Kras^LSL-G12D/+Stk11^−/− (KL) lung cancer (n = 3 mice for infusion of each tracer). c, Kras^LSL-G12D/+Trp53^−/−Ptf1a^CRE/+ (KP^f/fC) pancreatic ductal adenocarcinoma (n = 4 for ¹³C-glucose infusion, n = 3 for ¹³C-lactate and ¹³C-glutamine infusions). Values are mean ± s.d. Data are from Fig. 4a–c. The solid line represents the expected labelling by ¹³C-glucose assuming that glucose feeds the TCA cycle solely through circulating lactate. The dashed line indicates the expected labelling by ¹³C-lactate, assuming that lactate feeds the TCA cycle solely through circulating glucose.

Source data