Phosphorylation of CDK9 at Ser175 enhances HIV transcription and is a marker of activated P-TEFb in CD4(+) T lymphocytes

Abstract

The HIV transactivator protein, Tat, enhances HIV transcription by recruiting P-TEFb from the inactive 7SK snRNP complex and directing it to proviral elongation complexes. To test the hypothesis that T-cell receptor (TCR) signaling induces critical post-translational modifications leading to enhanced interactions between P-TEFb and Tat, we employed affinity purification-tandem mass spectrometry to analyze P-TEFb. TCR or phorbal ester (PMA) signaling strongly induced phosphorylation of the CDK9 kinase at Ser175. Molecular modeling studies based on the Tat/P-TEFb X-ray structure suggested that pSer175 strengthens the intermolecular interactions between CDK9 and Tat. Mutations in Ser175 confirm that this residue could mediate critical interactions with Tat and with the bromodomain protein BRD4. The S175A mutation reduced CDK9 interactions with Tat by an average of 1.7-fold, but also completely blocked CDK9 association with BRD4. The phosphomimetic S175D mutation modestly enhanced Tat association with CDK9 while causing a 2-fold disruption in BRD4 association with CDK9. Since BRD4 is unable to compete for binding to CDK9 carrying S175A, expression of CDK9 carrying the S175A mutation in latently infected cells resulted in a robust Tat-dependent reactivation of the provirus. Similarly, the stable knockdown of BRD4 led to a strong enhancement of proviral expression. Immunoprecipitation experiments show that CDK9 phosphorylated at Ser175 is excluded from the 7SK RNP complex. Immunofluorescence and flow cytometry studies carried out using a phospho-Ser175-specific antibody demonstrated that Ser175 phosphorylation occurs during TCR activation of primary resting memory CD4+ T cells together with upregulation of the Cyclin T1 regulatory subunit of P-TEFb, and Thr186 phosphorylation of CDK9. We conclude that the phosphorylation of CDK9 at Ser175 plays a critical role in altering the competitive binding of Tat and BRD4 to P-TEFb and provides an informative molecular marker for the identification of the transcriptionally active form of P-TEFb.

Figure 1. Ser175 phosphorylation of CDK9 is rapidly induced by T-cell activation signals.

(A) Affinity purification of FLAG-CDK9 complexes from Jurkat 2D10 cells and their identification by mass spectrometry. The percent values indicate the sequence coverage of the identified proteins. (B) Manually annotated MS/MS fragmentation spectra of the unmodified (upper) and phosphorylated (lower) CDK9 AFSLAK tryptic precursor peptides. (C) Ratio of phosphorylation of CDK9 at Ser175 and Thr186 in PMA stimulated (50 ng/ml) versus untreated cells with or without pretreatment with 20 µM U0126.

Figure 2. Signal-dependent phosphorylation of CDK9 at Ser175.

(A) Detection of Ser175 phosphorylation by Western blotting after 1 h PMA (50 ng/mL) stimulation for wild type CDK9 and the T186A and T186D mutants. FLAG-CDK9 carrying the wild type sequence, or the S175A, S175D, T186A, or T186D mutations was stably expressed in latently infected Jurkat 2D120 cells using the MSCV retroviral expression system. Top panel: Whole cell extracts used for immunoprecipitation were immunoblotted for total CDK9. Note the slower migration of the ectopically expressed FLAG-CDK9 compared to the endogenous CDK9. Bottom three panels: Anti-FLAG-CDK9 immunoprecipitates were screened by immunoblotting for CDK9, pThr186, and pSer175 using a polyclonal antibody derived using a 19-residue peptide carrying a pSer175 epitope. (B) Validation of the epitope specificity of the pSer175 CDK9 antibody by peptide blocking. Purified antibody was pre-incubated overnight with pSer175 peptide epitope prior to immunoblotting anti-FLAG-CDK9 immunoprecipitates derived from control Jurkat T-cells, or 2D10 cells expressing FLAG-CDK9 before and after stimulation for 1 hr by PMA.

Figure 3. Ser175 is not required for P-TEFb formation and the assembly of the 7SK snRNP complex.

(A) FLAG-CDK9 wildtype, S175A, S175D, T186A, or T186D were stably expressed in Jurkat 2D10 cells using the MSCV retroviral expression system. Western blotting analysis was performed on the whole cell extracts (left panels) and the corresponding anti-FLAG-CDK9 immunoprecipitates (right panels) using antibodies against CycT1, CDK9 and the 7SK RNP protein components HEXIM1 and LARP7. (B) Quantitative analysis of protein levels. Protein concentrations were estimated by densitometry of the Western blots and normalized against total immunoprecipitated CDK9. The data are from five independent experiments. Error bars: ± standard error of the mean.

Figure 4. CDK9 phosphorylated at Ser175 is excluded from the 7SK snRNP complex.

2D10 cells were engineered to stably express FLAG-HEXIM1. Left panels: WCEs were prepared from cells that were unstimulated or treated with PMA for 1 h with or without the inhibitor U0126. Right panels: FLAG-HEXIM1 complexes were isolated by anti-FLAG IP followed by elution with FLAG peptide. Immunoblotting was performed on whole cell extracts (input samples) and anti-FLAG immunoprecipitates using antibodies towards CycT1, CDK9, HEXIM1, LARP7, pT186 CDK9, and pSer175 CDK9. The result shown is representative of two different experiments. Note that HEXIM1- P-TEFb found in the HEXIM-associated complexes is devoid of phosphorylation at Ser175 whereas the modification is readily detected in WCEs and in FLAG-CDK9 immunoprecipates ( Fig. 3 ).

Figure 5. Ser175 mediates the binding of Tat to CDK9 and BRD4.

(A) Induction of Tat expression in latently infected Jurkat 2D10 cells. WCEs were prepared from 2D10 cells and treated for the indicated times with PMA (50 ng/ml), TNF-α (10 ng/ml), or a combination of anti-CD3 (0.125 µg/ml) and anti-CD28 (1 µg/ml) mAbs. The extracts were then subjected to Western blotting using a Tat monoclonal antibody.(B) Relative binding of Tat and BRD4 to P-TEFb. Top: Western blots of WCEs (left panels) or FLAG-CDK9 immunoprecipitates (right panels). Top two panels show an experiment detecting BRD4 association with FLAG-CDK9 while the bottom three panels show a separate experiment detecting CycT1 and Tat association with FLAG-CDK9. Graph shows the relative levels of co-precipitated BRD4, Tat, and CycT1 normalized to corresponding total CDK9 levels. Data are from three different experiments. Error bars: ± standard error of the mean. (C) Tat-dependent and signal-dependent dissociation of P-TEFb from 7SK snRNP. 293T cells stably expressing FLAG-tagged CDK9 were transiently transfected with HA-tagged Tat. Immunoprecipitation was performed using anti-FLAG antibody followed by immunoblotting using antibodies against CycT1, CDK9, HEXIM1, LARP7, and Tat.

Figure 6. CDK9 kinase activity does not require S175.

Radioactive in vitro kinase assays perfomed using FLAG-CDK9 complexes isolated from Jurkat 2D10 cells stimulated for 20 h with 10 ng/mL TNF-α to induce Tat expression. Western blots of these IPs and the corresponding WCEs are shown in the lower panel of Fig. 5B . The kinase assays were performed in the absence (A) or presence (B) of 250 ng of His-tagged full length human pol II CTD repeat substrate. Inhibition of activity by pretreatment with 100 nM flavopiridol confirms the activity in both assays to be CDK9 kinase. Note that the S175A and S175D mutations display wildtype kinase activity in both assays.

Figure 7. Reactivation of latent HIV proviruses by expression of P-TEFb carrying mutations in CDK9 Ser175 or by knockdown of BRD4 expression.

(A) Western blots. Left panels: Stable ectopic expression of FLAG-CDK9 wildtype, S175A, S175D, T186A, or T186D in latently infected E4 (Wildtype Tat), 2D10 (H13L Tat), and 2B2D (C22G Tat) Jurkat T-cells using the MSCV retroviral expression system. Right panels: Stable knockdown of BRD4 expression in E4, 2D10, and 2B2D cells using lentiviral expressing shRNA constructs. (B) Activation of latently infected cells. Left graph: Reactivation of proviral gene expression by S715D CDK9 or S175A CDK9 requires functional Tat. Three weeks post-transduction with FLAG-CDK9 wildtype, S175A, S175D, T186A, or T186D the cells were analyzed by flow cytometry for the spontaneous reactivation of latent proviruses. Right graph: Knockdown of BRD4 reactivates HIV proviral expression in a Tat-dependent manner. Three weeks post-infection with mock or BRD4-specific shRNA lentiviral constructs the cells were analyzed by flow cytometry for the spontaneous reactivation of latent proviruses.

Figure 8. Energy minimized models of the interaction of the N-terminal region of Tat with the activation loop of CDK9.

(A) Phosphorylation of Ser175 at the activation loop of CDK9 favors a hydrogen bonding interaction with Lys12 of wild type Tat. (B) pSer175 interactions with Lys12 are unaffected by the H13L mutation. (C) Impact of Ser175 phosphorylation on preexisting intermolecular interactions between CDK9 and Tat. (D) Modeling of K12N Tat/CDK9 interactions with or without the phosphate moiety at Ser175. (E) Tat interactions with CDK9 S175A in the wildtype and H13L backgrounds. (F) Tat interactions with the CDK9 phosphomimetic mutants S175D and S175E.

Figure 9. Induction of CycT1 expression and CDK9 Ser175 phosphorylation after activation of primary memory CD4⁺ T-cells via the T-cell receptor.

(A) Induction of CDK9 and Cyclin T1. Memory CD4⁺ T cells isolated from a healthy donor were stimulated for 16 hr with α-CD3 and α-CD28 mAbs to activate the TCR, and immunostained with flourophore-conjugated antibodies against CDK9 (red), CycT1 (yellow). Nuclear DNA was stained with DAPI (blue). (B) Cells stained for pSer175 CDK9 (green), nuclear speckles (red), CycT1 (yellow) and nuclear DNA (blue). Images were obtained using a DeltaVision deconvolution microscope.

Figure 10. Activated (CD25⁺ CD69⁺) memory CD4⁺ T-cells have elevated expression of pSer175 CDK9 and CycT1.

(A) Resting memory CD4⁺ T-cells isolated from a healthy donor stained for flourophore-conjugated antibodies against the T-cell activation markers (CD25 and CD69) and P-TEFb components (Cyclin T1 and pSer175 CDK9) components and then analyzed by multicolor flow cytometry. (B) Cells from the same donor activated for 16 hr with α-CD3 and α-CD28 mAbs.

Figure 11. Rapid induction of Ser175 phosphorylation of CDK9 after stimulation of resting memory CD4+ T cells through the TCR.

(A) Flow cytometry. Memory CD4⁺ T-cells isolated from healthy donors were stimulated for 2 hr or 24 hr with α-CD3 and α-CD28 mAbs to activate the TCR, immunostained with the flourophore-conjugated antibodies against total CDK9, pThr186 CDK9, CycT1 and pSer175 CDK9 and analyzed by multicolor flow cytometry. Top panels: Representative data from Experiment 1 (Figs. S5 and S6). Bottom panels: Representative data from Experiment 2 (Figs. S7 and S8). (B) Kinetic analysis. Time course of P-TEFb activation in primary resting memory CD4⁺ T-cells stimulated between 0 and 24 hrs with α-CD3 and α-CD28 mAbs or with PMA. Kinetic data from two TCR and one PMA activation (Figs. S9 and S10) experiments are shown. The fraction of positive cells staining for pThr186 (blue lines), CycT1 (red lines), pSer175 CDK9 (black lines), and total CDK9 (black lines) were measured by flow cytometry as shown in Panel A. Note that during the course of the experiment there is also a 2- to 10-fold increase in the mean fluorescent intensity for the CDK9 and CycT1 proteins that is not represented by the data for % positive cells.

Figure 12. Model for the activation of P-TEFb in memory CD4⁺ T-cells.

In resting memory CD4⁺ T-cells P-TEFb expression is restricted due to low levels of CycT1. T-cell receptor activation of the cells leads to new CycT1 synthesis, phosphorylation of CDK9 at Thr186, and the assembly of the transcriptionally inactive 7SK snRNP complex containing 7SK RNA, HEXIM1 and the RNA binding proteins MePCE and LARP7. TCR signaling disrupts the 7SK RNP complex and leads to phosphorylation of CDK9 on Ser175 (this paper), HEXIM1 on Ser158 , and acetylation of CycT1 on K386 [8181] which shift the binding equilibrium away from the 7SK RNP complex. Tat and BRD4 compete for P-TEFb binding with the equilibrium being shifted in favor of Tat binding when Ser175 is phosphorylated.