Site-Specific Labeling of Protein Kinase CK2: Combining Surface Display and Click Chemistry for Drug Discovery Applications

Abstract

Human CK2 is a heterotetrameric constitutively active serine/threonine protein kinase and is an emerging target in current anti-cancer drug discovery. The kinase is composed of two catalytic CK2α subunits and two regulatory CK2β subunits. In order to establish an assay to identify protein-protein-interaction inhibitors (PPI) of the CK2α/CK2β interface, a bioorthogonal click reaction was used to modify the protein kinase α-subunit with a fluorophore. By expanding the genetic code, the unnatural amino acid para azidophenylalanine (pAzF) could be incorporated into CK2α. Performing the SPAAC click reaction (Strain-Promoted Azide-Alkyne Cycloaddition) by the use of a dibenzylcyclooctyne-fluorophore (DBCO-fluorophore) led to a specifically labeled human protein kinase CK2α. This site-specific labeling does not impair the phosphorylation activity of CK2, which was evaluated by capillary electrophoresis. Furthermore a dissociation constant (KD) of 631 ± 86.2 nM was determined for the substrate αS1-casein towards CK2α. This labeling strategy was also applied to CK2β subunit on Escherichia coli, indicating the site-specific modifications of proteins on the bacterial cell surface when displayed by Autodisplay.

Keywords: Autodisplay; CK2; bioorthogonal; click chemistry; drug discovery; kinase; labeling; protein-protein interaction; unnatural amino acid.

Figure 1

Comparison of the phosphorylation activity of the heterotetrameric CK2 before and after reaction with FITC. The CE-based assay as described before by Gratz et al. [23] was used to determine the CK2 activity. Electropherogram of the phosphorylation of the substrate peptide RRRDDDSDDD (114 µM) by unlabeled (I, 2.6 µg) and fluorescein-conjugated CK2 (II, 2.6 µg) after an incubation time of 30 min is shown. Substrate (S) and product (P) peaks were detected after 3.7 min and 4.3 min, respectively.

Figure 2

Ribbon diagram illustrating the structure of heterotetrameric human protein kinase CK2. For this purpose CK2 structure (PDB identification number 1JWH) was processed with the UCSF Chimera 1.10.2 software package [26]. The catalytic CK2α subunit binds to the regulatory CK2β subunit. Dimerization of two β-subunits is mediated by a zinc finger. The non-hydrolysable ATP analogue adenosine 5´-[β,γ-imido]triphosphate (AMPPNP) is bound in the ATP binding pocket of one catalytic α-subunit. A tyrosine in position 239 (Y239) was chosen to be replaced by the unnatural amino acid pAzF into CK2α.

Figure 3

SDS-PAGE analysis of gene expression and incorporation of pAzF into CK2α. The addition or the omission of the unnatural amino acid pAzF, the inducers IPTG and arabinose to E. coli BL21(DE3) cells with the plasmids CK2α^Y239Stop and pEVOL-pAzF, expressing the mutated CK2α (IPTG) and the amber suppressor tRNA (constitutive)/aminoacyl-tRNA synthetase (constitutive/arabinose), were proven in a volume of 1 mL minimal medium for each case. Cells were boiled for 20 min at 95 °C and protein lysates were separated on 10% acrylamide. The apparent molecular mass of the marker proteins is shown in lane M. Full-length CK2α (40 kDa) could be synthesized in lane 6 and 8, i.e., when all components were present. Because of the stop codon UAG and the lack of pAzF, the truncated CK2α (28 kDa) appeared in lane 2 and 4.

Figure 4

SPAAC click reaction of CK2α-pAzF with the two dibenzylcyclooctyne-fluorophores DBCO545 and DBCO-Sulfo -Cy5, respectively (R₁ = N-terminal sequence of CK2α-pAzF, R₂ = C-terminal sequence of CK2α-pAzF). For both cases, beside the regioisomer 1,4 as shown in the reaction scheme, the regioisomer 1,5 can be obtained as well.

Figure 5

SDS-PAGE analysis of the SPAAC click reaction between CK2α-pAzF and the fluorophore DBCO545. Protein solutions were separated on 10% acrylamide. In lane M, the apparent molecular mass of the marker proteins is given. Purified and concentrated CK2α-pAzF (11 µg) in presence and absence of DBCO545 in a final concentration of 50 µM are shown in lane 2 and lane 1, respectively. As control purified full length CK2α (2.8 µg) without incorporated pAzF was also incubated with DBCO545 (lane 3). (A) Proteins were stained with Coomassie brilliant blue G250. (B) Visualization of the fluorescent protein band of CK2α-DBCO545 by LED-illuminator (470 nM).

Figure 6

Proof of interaction between CK2β and the CK2α-DBCO-subunit. The activity of CK2α-DBCO545 [□] alone and by addition of purified CK2β [■] was analyzed by CE assay. There were significant differences in activity (n = 3, error bars ± SEM, *** p < 0.0001, unpaired t test).

Figure 7

Phosphorylation activity of the heterotetrameric CK2 with or without coupling to DBCO545. (A) Comparison of the phosphorylated product between the holoenzyme including CK2α-DBCO545 (I, 2.6 µg) and CK2α-pAzF (II, 2.6 µg) is shown in an electropherogram after 30 min incubation with the substrate RRRDDDSDDD. Substrate (S) and product (P) peaks were detected after 3.7 min and 4.3 min, respectively. (B) The activities of the holoenzymes consisting of CK2α-pAzF [□] as well as CK2α-DBCO545 [■] were analyzed after 15, 30 and 45 min for each sample by CE. Mean values ± standard errors of the means (SEM) from three independent experiments are given (not significant, p > 0.05).

Figure 8

Proof of interaction between surface-displayed CK2β and CK2α-DBCO545-subunit. CK2β, which was translocated on the surface of E. coli by Autodisplay, was incubated for 1 h at 37 °C with purified specifically labeled CK2α-DBCO545. The binding affinity of CK2β and CK2α-DBCO545 (red, mF = 3800) was analyzed by flow cytometry. As a non-binding control, surface-displayed sorbitol dehydrogenase [33] was used (grey, mF = 108).

Figure 9

SPAAC reaction of CK2β-AT-pAzF and DBCO545 on the surface of E. coli. Cells (OD₅₇₈ = 1) displaying CK2β-AT-pAzF were incubated with the fluorophore DBCO545 (50 µM) for 1h at RT. After three washing steps, E. coli displaying CK2β-AT-DBCO545 (red, mF = 1495) were analyzed by flow cytometry. As a control, surface translocated CK2β-AT without incorporated unnatural amino acid pAzF was applied and treated identically (grey, mF = 120).

Figure 10

Interaction of CK2α-DBCO-Sulfo-Cy5 and human α_S1-casein. To a constant amount of CK2α (65 nM) α_S1-casein was titrated in different concentrations, ranging from 0.76 nM to 12.50 µM. (A) The normalized fluorescence signals of the thermophoresis of 15 different dilutions of α_S1-casein in presence of the CK2α subunit were recorded. (B) The K_D value of 631 ± 86.2 nM was determined from three independent experiments using NT Analysis 1.5.41 software (NanoTemper Technologies GmbH, München, Germany).