Protein kinase B controls transcriptional programs that direct cytotoxic T cell fate but is dispensable for T cell metabolism

Abstract

In cytotoxic T cells (CTL), Akt, also known as protein kinase B, is activated by the T cell antigen receptor (TCR) and the cytokine interleukin 2 (IL-2). Akt can control cell metabolism in many cell types but whether this role is important for CTL function has not been determined. Here we have shown that Akt does not mediate IL-2- or TCR-induced cell metabolic responses; rather, this role is assumed by other Akt-related kinases. There is, however, a nonredundant role for sustained and strong activation of Akt in CTL to coordinate the TCR- and IL-2-induced transcriptional programs that control expression of key cytolytic effector molecules, adhesion molecules, and cytokine and chemokine receptors that distinguish effector versus memory and naive T cells. Akt is thus dispensable for metabolism, but the strength and duration of Akt activity dictates the CTL transcriptional program and determines CTL fate.

Figure 1

Akt Is Not Necessary for IL-2-Driven Survival or Proliferation in CTL (A) Immunoblot analysis of Akt T308 and Foxo1 T24, Foxo3a T32 phosphorylation in wild-type (C57/BL6) and p110δ^D910A-expressing (Pik3cd^D910A) splenic T cells activated with 2C11 for 48 hr then cultured in IL-2 for 3 days. (B) Wild-type splenic T cells were activated with 2C11 for 48 hr then cultured in IL-2 for 5 days, with some cells being deprived of IL-2 for the last 24 hr of culture. Data show fold change in cell number over the last 24 hr of culture and the cell FSC and SSC profiles at the end of the experiment. Gates indicate dead (left) and viable (right) cell populations. (C) Splenic T cells from wild-type and p110δ^D910A-expressing mice (Pik3cd^D910A) were cultured as in (A). Data show fold change in cell number over the last 48 hr of culture. (D) Western blot analysis of Akt T308 phosphorylation in P14 T cells activated with gp33 for 48 hr then cultured in IL-2 for 5 days, with IC87114 or LY294002 being added for the last 48 hr of culture. (E) P14 T cells were activated with gp33 for 48 hr then cultured in IL-2 for 5 days, with IC87114 added for the last 48 hr of culture. Alternatively, IL-2 was removed from the culture for the last 48 hr. Data show fold change in cell number over last 48 hr of culture. (F and G) Wild-type splenic T cells activated with 2C11 for 48 hr cultured in IL-2 for 5 days, with AktI being added for the last 48 hr of culture. Data show (F) immunoblot of Akt T308 and Foxo1 T24, Foxo3a T32 phosphorylations and (G) FSC and SSC profiles of cells at the end of the culture plus fold change in cell number during the last 48 hr of culture. Data are representative of 3 (A, C–F), 7 (B), or 11 (G) experiments; mean ± SEM of biological replicates.

Figure 2

PDK1 Maintains IL-2-Driven Proliferation (A and B) Immunoblot analysis of (A) PDK1 expression and (B) phosphorylation of Akt, Foxo1 and Foxo3a, RSK, and small ribosomal subunit S6 in Pdpk11^{fl/fl /tm9(creEsr1)Arte} (Pdpk1^fl/fl TamoxCre) and Pdpk1^{+/+/ tm9(creEsr1)Arte} (Pdpk1^WT/WT TamoxCre) T cells activated with 2C11 for 2 days and then cultured in IL-2 for 5 days, supplemented as indicated with 4OHT for the final 72 hr of culture. (C and D) Fold change in cell number over the last 48 hr of culture (C) and FSC and SSC profiles (D) of 4OHT-treated cells from (A), gates indicate dead (left) and viable (right) cell populations. Data are representative of three (A, B) or five (C, D) experiments; mean ± SEM of biological replicates.

Figure 3

IL-2 and PDK1 but Not Akt Sustain Glucose Uptake in CTL (A) 2-deoxyglucose (2DOG) uptake by wild-type splenic T cells activated with 2C11 for 48 hr and then cultured in IL-2 for 5 days, with some cells being deprived of IL-2 for the last 24 hr of culture. (B) Wild-type splenocytes were activated with 2C11 and IL-2 for 2 days and then cultured in IL-2 in standard media for 72 hr. For the final 48 hr of culture, cells were placed in media containing indicated glucose concentrations and the fold change in cell number assessed. (C) Relative 2DOG uptake in wild-type splenic T cells activated with 2C11 for 48 hr then cultured in IL-2 for an additional 5 days, with 1 μM AktI being added for the last 48 hr of culture. (D and E) Relative 2DOG uptake (D) and phenylalanine uptake (E) by Cre control (Pdpk1^{+/+/ tm9(creEsr1)Arte} +4OHT) and Pdpk1-null (Pdpk1^{fl/fl/ tm9(creEsr1)Arte} +4OHT) CTL. (F) Naive P14 T cells were maintained in IL-7 or stimulated for 18 hr with gp33 in the presence or absence of AktI or IC87114 and then their ability to take up 2DOG was assayed. Data are representative of 3 (B, D, F), 5 (A), or 11 (C) experiments; mean ± SEM of biological replicates, except (F), representative data from 2 experiments; mean ± SD of technical replicates.

Figure 4

PDK1 and Akt Regulation of the CTL Transcriptional Program Pdpk1-null (Pdpk1^{fl/fl/ tm9(creEsr1)Arte} +4OHT) and Cre control (Pdpk1^{+/+/ tm9(creEsr1)Arte} +4OHT) CTL were generated and their transcriptional profiles compared via microarray. Analysis was performed with cells from three age- and sex-matched mice for each genotype. In a separate experiment, three wild-type (C57/BL6) age- and sex-matched mice were used to generate CTL by activating wild-type splenocytes with 2C11 for 48 hr with IL-2 then culturing the cells in IL-2 for a further 5 days, with 1 μM AktI being added to half of each culture for the last 48 hr. Comparison of the transcriptional profile in control versus AktI-treated cells was then performed by microarray. (A) Heat map showing the relative normalized expression of selected genes changing in expression after Pdpk1 loss but not Akt inhibition. (B) Gene ontology analysis of genes changing in expression after Pdpk1 loss but not Akt inhibition. (C) Heat maps showing the relative normalized expression of Foxo-regulated genes that are significantly different in expression between untreated and AktI-treated CTL and between Cre control and Pdpk1-null CTL. (D–G) Real-time PCR measurements of relative gene expression levels in (D) Cre control versus Pdpk1-null CTL, (E) untreated versus 48 hr AktI-treated wild-type CTL, (F) wild-type versus PI3K p110δ^D910A-expressing CTL (Pik3cd^D910A), and (G) untreated versus 48 hr IC87114-treated CTL. Data representative of a minimum of three experiments; mean ± SEM of biological replicates.

Figure 5

Suppression of PI3K p110δ and Akt Reprograms Lymph Node Homing of CTL (A) Heat map showing the relative normalized expression of selected genes that are significantly different in expression between untreated and AktI-treated CTL, as determined by microarray. (B) Lymph node P14 T cells were activated for 2 days with cognate peptide and then cultured for 5 days in IL-2, with IC87114 being added to half of each culture for the last 48 hr. Cells were then labeled with carboxyfluorescein succinimidyl ester (CFSE) or 5-(and-6) (((4chloromethyl)benzoyl) amino) tetramethylrhodamine (CMTMR) and mixed at a ratio of 1:1 before being injected into C57/BL6 host mice. Values indicate recovery of inhibitor-treated or untreated cells as a percentage of the total recovered transferred cells from the blood and lymph nodes 18 hr after transfer. Each dot indicates a mouse; horizontal bars indicate mean. (C) As for (B) with cells being treated with AktI rather than IC87114 for the last 48 hr of culture. (D–F) CD8⁺ T cells expressing Vα2Vβ5 TCR were purified from Pdpk1^WT/WT OT1 (CD45.1^+/+) and Pdpk1^K465E/K465E OT1 (CD45.1⁺ CD45.2⁺) mice, mixed at a 1:1 ratio, and stained with CFSE. 5 × 10⁶ mixed T cells were injected into the tail vein of C57/BL6 mice (CD45.2^+/+). 24 hr later the host mice were injected intraperitoneally with either 25 mg LPS or LPS plus 40 mg of SIINFEKL peptide. The ratio of Pdpk1^WT/WT OT1 and Pdpk1^K465E/K465E OT1 donor cells in lymph nodes and proliferation (CFSE dilution) was analyzed after 6 days, with CD62L expression assayed after 2, 4, and 6 days.

Figure 6

Suppression of PI3K p110δ and Akt Alters the Expression of Key CTL Effector Molecules (A and B) Heat maps showing the relative normalized expression of selected genes that are significantly different in expression between untreated and AktI-treated CTL, as determined by microarray. (C) Wild-type splenocytes were activated with 2C11 for 48 hr with IL-2 and then cultured in IL-2 for a further 5 days, with half the cells being placed in AktI for the last 48 hr of culture. Shown is IFN-γ release by 1 million cells in 6 hr, relative IFN-γ mRNA content, immunoblot analysis of total perforin protein content, and perforin mRNA content of cells cultured with and without AktI. (D) Pdpk1-null (Pdpk1^{fl/fl/ tm9(creEsr1)Arte} +4OHT) and Cre control (Pdpk1^{+/+/ tm9(creEsr1)Arte} +4OHT) CTL were generated. Shown are IFN-γ release by 1 million cells in 6 hr, relative IFN-γ mRNA content, immunoblot analysis of total perforin protein content, and perforin mRNA content of Cre control versus Pdpk1-null CTL. Data representative of a minimum of three experiments; mean ± SEM of biological replicates.

Figure 7

PDK1 Controls Antigen Receptor-Driven IFN-γ Expression via a Foxo-Mediated Mechanism (A) Naive P14 lymph node T cells were stimulated for 4 hr with LCMV peptide gp33 in the presence or absence of AktI and the IFN-γ produced assayed by ELISA. (B) P14 T cells were activated for 48 hr with gp33 and then cultured for 3 days in IL-2. Left: Cells were then stimulated for 4 hr with 100 ng/ml gp33 in the presence of AktI or IC87114 and IFN-γ production assayed by flow cytometry. Right: Alternatively, cells were stimulated for 4 hr with 125 ng/ml gp33 in the presence of AktI and IFN-γ production assayed by ELISA. (C) P14 T cells were activated for 48 hr with gp33 and then cultured for 3 days in IL-2. Cells were stimulated for 3 hr with 62.5 ng/ml gp33 in the presence or absence of AktI. ChIP was performed with anti-PolII, and the changes in PolII binding to (left) the IFN-γ-proximal promoter region and (right) the IFN-γ fourth exon were quantified by real-time PCR. Data are normalized to input DNA amounts and plotted as fold over the values for PolII binding to the HPRT-proximal promoter. (D) P14 TCR transgenic T cells from lymph nodes of Pdpk1^WT/WT and Pdpk1^K465E/K465E P14 transgenic mice were activated for 48 hr with gp33 and then cultured for 3 days in IL-2. Cells were then stimulated for 4 hr with gp33 and IFN-γ produced assayed by ELISA. (E and F) P14 T cells were activated for 24 hr with gp33 and then spinfected with retrovirus encoding either GFP or GFP-tagged Foxo3a T32A S252A S314A (FoxAAA). Three days after infection, cells were (E) stimulated for 4 hr with 100 ng/ml gp33 in the presence or absence of AktI or IC87114 and then stained for intracellular IFN-γ or (F) sorted into GFP^+/− populations, cultured for a further 24 hr, and then stimulated for 4 hr with 100 ng/ml gp33 and IFN-γ production assayed by ELISA. Data are representative of a minimum of two (E, F) or three (A–C, D) experiments; mean ± SEM of biological replicates.