AMP is a true physiological regulator of AMP-activated protein kinase by both allosteric activation and enhancing net phosphorylation

Abstract

While allosteric activation of AMPK is triggered only by AMP, binding of both ADP and AMP has been reported to promote phosphorylation and inhibit dephosphorylation at Thr172. Because cellular concentrations of ADP and ATP are higher than AMP, it has been proposed that ADP is the physiological signal that promotes phosphorylation and that allosteric activation is not significant in vivo. However, we report that: AMP is 10-fold more potent than ADP in inhibiting Thr172 dephosphorylation; only AMP enhances LKB1-induced Thr172 phosphorylation; and AMP can cause > 10-fold allosteric activation even at concentrations 1-2 orders of magnitude lower than ATP. We also provide evidence that allosteric activation by AMP can cause increased phosphorylation of acetyl-CoA carboxylase in intact cells under conditions in which there is no change in Thr172 phosphorylation. Thus, AMP is a true physiological regulator of AMPK, and allosteric regulation is an important component of the overall activation mechanism.

Figure 1

Effect of AMP, ADP, and 5′-Nucleotidase on the Inactivation and Thr172 Dephosphorylation of AMPK by PP2Cα Incubations without Mg²⁺ were used as controls. (A) Effects of AMP and ADP on inactivation by phosphatase (PP2Cα) ± 5 mM ATP. Protection against inactivation is defined as the activity difference in assays with or without nucleotide expressed as a percentage of the difference obtained with or without optimal nucleotide (30 μM for AMP and 300 μM for ADP, both in the absence of ATP). Results were fitted to the equation: Y = 100 × X / (EC₅₀ + X), where Y is the percent of protection and X is the concentration of AMP or ADP. Data are mean ± SEM (n = 2), and curves were generated with the equation above, using best-fit values for EC₅₀ quoted in the text. The vertical dotted lines show the ranges over which AMP and ADP concentrations were estimated to change when G361 cells were treated with 100 μM berberine (Table S1 and Figure 5). (B) Samples from incubations ± 5 mM ATP were analyzed by western blotting using anti-pT172 and anti-AMPK-α antibodies. (C) AMPK was incubated at 30°C with PP2Cα ± Mg²⁺ as in (A), with or without AMP (100 μM), ADP (300 μM), or the 5′-ectonucleotidase CD73 as indicated. The nucleotides were preincubated with CD73 for 5 min at 30°C before starting the reaction by the addition of AMPK. Kinase activities (expressed as percentages of activity in control without Mg²⁺, mean ± SEM, n = 3) and anti-pT172 blots are shown. ^∗∗∗Significantly different from controls without AMP/ADP (p < 0.001); ^†††significantly different from control without CD73 (p < 0.001); ns, not significantly different from control without AMP or CD73.

Figure 2

AMP, but Not ADP, Enhances Thr172 Phosphorylation and Activation of AMPK by LKB1, but Not CaMKKβ (A) Effect of AMP and ADP on activation and Thr172 phosphorylation by LKB1 and CaMKKβ. Purified rat liver AMPK was incubated with bacterially expressed human PP2A_C to give ≈95% inactivation. Okadaic acid was then added to inhibit PP2A_C, and the dephosphorylated kinase was incubated for 10 min with MgCl₂ (5 mM) and ATP (200 μM), with or without LKB1 or CaMKKβ, and with or without AMP or ADP (300 μM). Aliquots were taken for kinase assays (top; mean ± SEM, n = 3) or western blotting (bottom). Kinase activities are expressed as percentages of the initial kinase activity prior to dephosphorylation. (B) Concentration dependence of the effect of AMP on AMPK activation by LKB1 (other conditions are as in A; mean ± SEM, n = 3). Data were fitted to the equation Y = basal + ([{activation × basal − basal} × X] / [EC₅₀ + X]), where Y is kinase activity and X is AMP concentration. The curve was generated using the following best-fit parameters: basal, 37% ± 3%; activation, 2.8 ± 0.3-fold; EC₅₀, 160 ± 60 μM. The vertical dotted lines show the range over which AMP concentration was estimated to change when G361 cells were treated with 100 μM berberine (Table S1 and Figure 5). (C) Time course of AMPK activation by LKB1. Incubations contained no additions (open circles), 300 μM AMP (filled circles), 300 μM ADP (squares), or 300 μM ADP plus the 5′-nucleotidase CD73 (triangles). Kinase activities are expressed as percentages of the initial kinase activity prior to dephosphorylation. (D) Rat liver AMPK was incubated with or without LKB1 (amounts as in A), with or without MgCl₂ (5 mM), and with or without PP2Cα, and samples were analyzed by western blotting. The bar chart at the top (mean ± SEM, n = 3) shows quantification by densitometry of the blots at the bottom (ratio of signal with anti-pT172 and anti-AMPK-α, arbitrary units). ^∗∗∗Significantly different (p < 0.001); ns, not significantly different from control without additions by one-way ANOVA with Dunnett’s multiple comparison test.

Figure 3

Allosteric Activation by AMP, and Inhibition at High AMP Concentrations, of Rat Liver AMPK and GST Fusions of the Isolated α1 and α2 Kinase Domains (A) Effect of increasing AMP concentrations on the activity of purified rat liver AMPK. Data points were generated at three different concentrations of ATP (circles, 0.2 mM; squares, 1 mM; triangles, 5 mM) and were fitted to the equation Y = basal + ([{activation × basal − basal} × X] / [EC₅₀ + X]) − ([{activation × basal} × X] / [IC₅₀ + X]), where Y is activity and X is the AMP concentration. The continuous curves shown were derived using this equation and the best-fit parameters quoted in the main text. (B and C) Effect of increasing AMP concentrations on the activity of GST fusions with the kinase domains of human α1 (B) and α2 (C). Data (mean ± SEM, n = 3) were obtained at three different concentrations of ATP as in (A) and were fitted to the equation Y = basal − (basal × X / [IC₅₀ + X]). The continuous curves shown were derived using this equation and the best-fit parameters obtained (±SEM at 0.2, 1, and 5 mM ATP, respectively): α1 basal activity, 136 ± 5, 404 ± 6, and 598 ± 22 nmol/min/mg; IC₅₀ for α1, 2.4 ± 0.4, 3.3 ± 0.3, and 23 ± 68 mM; α2 basal activity, 260 ± 6, 351 ± 7, and 669 ± 8 nmol/min/mg; IC₅₀ for α2, 3.2 ± 0.4, 13 ± 1.4, and 18 ± 1.4 mM. The vertical dotted lines show the range over which AMP concentration was estimated to change when G361 cells were treated with 100 μM berberine (Table S1 and Figure 5).

Figure 4

Effects of AMPK Activators and the CaMKK Inhibitor STO609 on Phosphorylation and Activation of AMPK and Phosphorylation of ACC in G361 Cells (A) Effects of A23187 (10 μM) or berberine (100 and 150 μM) in the presence and absence of STO609 (2.5 μM). (B) Effects of A23187 (10 μM) or A769662 (50 and 100 μM) in the presence and absence of STO609 (2.5 μM). Cells were incubated with the indicated agents for 1 hr, and lysates were analyzed using immunoprecipitate kinase assays (mean ± SD, n = 3) and western blotting. Significantly different from control without STO609: ^∗p < 0.05, ^∗∗p < 0.01, ^∗∗∗p < 0.001; significantly different from control without AMPK activator: ††† p < 0.001.

Figure 5

Effects of Treatment of G361 Cells with AMPK Activators on Phosphorylation of ACC, Phosphorylation and Activity of AMPK, Cellular ADP:ATP Ratios, and Calculated Cellular AMP (A–C) Effects of treatment of G361 cells with AMPK activators on phosphorylation of ACC, phosphorylation and activity of AMPK (A), cellular ADP:ATP ratios (B), and calculated cellular [AMP] (C). Replicate dishes of cells (n = 3) were incubated for 1 hr with A23187 (10 μM), berberine (100 μM), A769662 (100 μM), or an equivalent concentration of vehicle (DMSO) and then lysed in parallel in neutral detergent buffer for measurement of AMPK activity in immunoprecipitates (top) or western blotting (bottom), or in perchloric acid for analysis of ADP:ATP ratios (center). AMP concentrations (see Table S1) were calculated as described in Experimental Procedures. Data are mean ± SD. Significantly different from DMSO control: ^∗∗∗p < 0.001.

Figure 6

Evidence that ACC Phosphorylation in G361 Cells Is Mediated by AMPK, and Effects of A23187 and Berberine in AMPK Knockout MEFs Expressing α1-T172D Mutant (A) FLAG-tagged inactive (D157A) mutant of AMPK-α2 was stably expressed by homologous recombination in G361 cells carrying an Flp recombinase target site (see Experimental Procedures) to generate dominant-negative (DN) cells. The graph shows AMPK activity (mean ± SEM, n = 4) measured in immunoprecipitates from control (WT) and DN cells with and without treatment with 10 μM A23187, while the pictures below show results of western blotting to determine expression and phosphorylation of various proteins. (B) As in (A), except the cells were treated with increasing concentrations of A769662 (30, 100, 300, 500, 1000 μM) or 10 μM A23187. (C) Effects of A23187 and berberine on AMPK activity and ACC phosphorylation in AMPK KO MEFs that were either untransfected or had been transfected with DNAs encoding myc-tagged AMPK-α1 (wild-type or T172D mutant), AMPK-β2, and AMPK-γ1. Data are mean ± SEM (n = 4). Significant differences from control without A23187 or berberine are shown.

Figure 7

Estimation of Extent of Thr172 Phosphorylation in Intact Cells, and Model for Regulation of AMPK by Adenine Nucleotides (A) G361 cells were treated in triplicate dishes for 60 min with A23187 (10 μM) or DMSO. Bacterially expressed AMPK (α1β2γ1 complex, inactive D157A mutant) was treated with increasing amounts of LKB1 (0.4–120 ng) and MgATP. Equivalent amounts of AMPK from G361 cell lysates and the bacterially expressed AMPK were then analyzed by SDS-PAGE and probed by western blotting with anti-pT172 and anti-α antibodies. (B) As in (A), except that HEK293 cells were treated with A23187 (10 μM), berberine (100 μM), or DMSO; in this experiment, the bacterially expressed heterotrimer was also incubated with increasing amounts of CaMKKβ (75–3,600 ng) and ATP, rather than LKB1. (C) G361 cells (left panel) or HEK293 cells (right panel) were treated for 60 min with or without A23187 (10 μM) or berberine (100 μM), and AMPK was immunoprecipitated with anti-α antibodies. AMPK activity (mean ± SD, n = 3) was then measured before and after subsequent phosphorylation using CaMKKβ and MgATP. Statistically significant from DMSO control (before CaMKK treatment) by one-way ANOVA with Dunnett’s multiple comparison test: ^∗p < 0.05, ^∗∗∗p < 0.001. (D) Model for the regulation of AMPK by adenine nucleotides, based on results in this paper.