Identification of a redox-sensitive switch within the JAK2 catalytic domain

Abstract

Four cysteine residues (Cys866, Cys917, Cys1094, and Cys1105) have direct roles in cooperatively regulating Janus kinase 2 (JAK2) catalytic activity. Additional site-directed mutagenesis experiments now provide evidence that two of these residues (Cys866 and Cys917) act together as a redox-sensitive switch, allowing JAK2's catalytic activity to be directly regulated by the redox state of the cell. We created several variants of the truncated JAK2 (GST/(NΔ661)rJAK2), which incorporated cysteine-to-serine or cysteine-to-alanine mutations. The catalytic activities of these mutant enzymes were evaluated by in vitro autokinase assays and by in situ autophosphorylation and transphosphorylation assays. Cysteine-to-alanine mutagenesis revealed that the mechanistic role of Cys866 and Cys917 is functionally distinct from that of Cys1094 and Cys1105. Most notable is the observation that the robust activity of the CC866,917AA mutant is unaltered by pretreatment with dithiothreitol or o-iodosobenzoate, unlike all other JAK2 variants previously examined. This work provides the first direct evidence for a cysteine-based redox-sensitive switch that regulates JAK2 catalytic activity. The presence of this redox-sensitive switch predicts that reactive oxygen species can impair the cell's response to JAK-coupled cytokines under conditions of oxidative stress, which we confirm in a murine pancreatic β-islet cell line.

Fig. 1

In vitro autokinase activities of four cysteine-to-alanine mutants expressed as a normalized percentage of GST/(NΔ661)rJAK2 activity. Sf21 cells were infected separately with baculoviruses expressing recombinant enzyme variants. Each JAK2-immunoprecipitated sample was divided into two aliquots. One aliquot was analyzed via anti-JAK2 immunoblot. The other aliquot was treated with 10 mM DTT and then assayed for radiolabeling autokinase activity. The intensity of each of the autokinase signals was calculated as a percentage of the nonmutated GST/(NΔ661)r]AK2 autokinase signal and then normalized for the anti-JAK2 signal intensity relative to the nonmutated GST/(NA661)rJAK2. The normalized autokinase activities of nonmutated GST/ (NΔ661)rJAK2, kinase-inactive K882E, and C866A, C917A C1094A and C1105A mutants are plotted left to right (n = 3; bars indicate mean±standard error). *P from <0.001 to 0.018; #P = 0.024.

Fig. 2

In situ exokinase activities of GST/(NA661)rJAK2 mutants containing serine or alanine substitutions at four critical cysteine residues. Sf21 cells were co-infected with the inactive GST/rJAK2(K882E) substrate and GST/(NA661 )rJAK2, K882E, C866S, C917S, C1094S, C1105S, C866A, C917A C1094A or C1105A mutants (lanes 1–10, respectively). (A) Immunoprecipitated proteins were analyzed via Western immunoblot with anti-JAK2, then (B) the PVDF membranes were “stripped” and reprobed with anti-phosphotyrosine antibodies. The upper arrows indicate the 140-kDa GST/ rJAK2(K882E) substrate and the lower arrows indicate the various 84-kDa GST/ (NΔ661)rJAK2 variants.

Fig. 3

Redox-reversible in vitro radiolabeling autokinase activity of GST/(NΔ661)rJAK2 mutants containing serine or alanine substitutions at the critical cysteine residues. Using immunoprecipitated recombinant GST/(NA661)rJAI<2 variants produced in Sf21 cells, the reversible effects of redox pretreatments on in vitro radiolabeling activities were assessed on mutants in which cysteines at residues (A) 866, (B) 917, (C) 1094, and (D) 1105 were mutated to serines (lanes 1–4) or alanines (lanes 5–8). Before assay, proteins were treated with DTT (lanes 1 and 5), o-IBZ (lanes 2 and 6), DTT and then o-IBZ (lanes 3 and 7), or o-IBZ and then DTT (lanes 4 and 8). Autokinase activities are shown above, and Western immunoblots with anti-JAK2 are shown below.

Fig. 4

In vitro radiolabeling autokinase activities of GST/(NΔ661)rJAK2 containing combinatorial cysteine-to-serine and cysteine-to-alanine mutations. Using immunoprecipitated recombinant GST/(NA661)rJAK2 variants produced in Sf21 cells, the autokinase activities of DTT-pretreated GST/(NA661)rJAK2, K882E, CC866,917SS, CC1094,1105SS, 4C:4S, CC866,917AA CC1094,1105AA and 4C:4A are shown in (A) lanes 1–8, respectively, and corresponding Western immunoblots probed with anti-JAK2 are shown in (B).

Fig. 5

In situ exokinase activities of GST/(NΔ661)rJAK2 containing combinatorial cysteine-to-serine and cysteine-to-alanine mutations. Immunoprecipitated proteins were recovered from Sf21 cells co-infected with GST/rJAK2(K882E) and GST/(NΔ661) rJAK2, K882E, CC866,917SS, CC1094,1105SS, 4C:4S, CC866,917AA, CC1094,1105AA, or 4C:4A (in lanes 1–8, respectively). (A) Proteins were analyzed via Western immuno-blot with anti-JAK2 and then (B) the PVDF membrane was “stripped” and reprobed with anti-phosphotyrosine. The upper arrows indicate the 140-kDa GST/rJAK2(K882E) substrate and the lower arrows indicate the various 84-kDa GST/(NΔ661)rJAK2 mutants.

Fig. 6

Redox-reversible in vitro radiolabeling autokinase activity of CC866,917AA and CC1094,1105AA. (A) The CC1094,1105AA mutant or (B) the CC866,917AA mutant was recovered from Sf21 cells via immunoprecipitation. Before assay, proteins were treated with DTT (lane 1), o-IBZ (lane 2), DTT and then o-IBZ (lane 3), or o-IBZ and then DTT (lane 4). Autokinase activities are shown above, and Western immunoblots with anti-JAK2 are shown below.

Fig. 7

Simplified representation of the redox sensor switch in JAK2 and JAK1. The kinase domains of (A) JAK2 and (B) JAK1 are shown as ribbon diagrams in which the N lobe is positioned above the C lobe. Gold space-filling elements indicate the locations of Cys866 (A) and Cys892 (B) on the left and Cys917 (A) and Cys944 (B) on the right. The location of the essential lysine, Lys882 in (A) and Lys908 in (B), is indicated by a Deep Purple space-filling element.

Fig. 8

Effects of hydrogen peroxide, hyperglycemia, and AG-490 on prolactin-stimulated STAT5 tyrosine phosphorylation in βTC-6 cells. βTC-6 cells were incubated 21–22 h in quiescence medium, hyperglycemia medium, or AG490 medium; a set of quiescent cells was then incubated with 500 μM hydrogen peroxide for 30 min before cytokine stimulation. Cells were then stimulated for 15 min without or with 15 nM recombinant mouse prolactin (mPRL). The cells were then lysed, and STAT5 was immunoprecipitated from the PAS-precleared lysate and analyzed via SDS–PAGE and Western immunoblot as described under Material and methods to measure the ratio of phosphorylated STAT5 to total STAT5; these ratios were expressed as the mean (n = 3) ± standard deviation. *P<0.001 relative to mPRL-stimulated, nonoxidized quiescent cells; #P<0.05 relative to mPRL-stimulated cells grown under hyperglycemic conditions.

Fig. 9

Effect of hydrogen peroxide on growth hormone-stimulated STAT5 tyrosine phosphorylation in βTC-6 cells. βTC-6 cells were incubated 21–22 h in quiescence medium and then incubated with 0, 25, 50, or 100 μM hydrogen peroxide for 30 min before cytokine stimulation. Cells were then stimulated for 15 min without or with 15 nM recombinant mouse growth hormone (mGH). The cells were then lysed, and STAT5 was immunoprecipitated from the PAS-precleared lysate and analyzed via SDS–PAGE and Western immunoblot as described under Material and methods to measure the ratio of phosphorylated STAT5 to total STAT5; these ratios were expressed as the mean (n = 3) ± standard deviation. #P<0.05 relative to mGH-stimulated, nonoxidized quiescent cells.