Functional Characterization of Novel Atrial Fibrillation-Linked GJA5 (Cx40) Mutants

Abstract

Atrial fibrillation (AF) is the most common form of cardiac arrhythmia. Recently, four novel heterozygous Cx40 mutations-K107R, L223M, Q236H, and I257L-were identified in 4 of 310 unrelated AF patients and a followup genetic analysis of the mutant carriers' families showed that the mutants were present in all the affected members. To study possible alterations associated with these Cx40 mutants, including their cellular localization and gap junction (GJ) function, we expressed GFP-tagged and untagged mutants in connexin-deficient model cells. All four Cx40 mutants showed clustered localization at cell-cell junctions similar to that observed of wildtype Cx40. However, cell pairs expressing Cx40 Q236H, but not the other individual mutants, displayed a significantly lower GJ coupling conductance (G_j) than wildtype Cx40. Similarly, co-expression of Cx40 Q236H with Cx43 resulted in a significantly lower G_j. Transjunctional voltage-dependent gating (V_j gating) properties were also altered in the GJs formed by Q236H. Reduced GJ function and altered V_j gating may play a role in promoting the Q236H carriers to AF.

Keywords: Vj gating; atrial fibrillation; connexin40; gap junction channel; patch clamp.

Figure 1

Localization of atrial fibrillation (AF)-linked Cx40 mutants. (A) Fluorescent images of HeLa cell clusters or pairs expressing YFP-tagged Cx40, K107R, L223M, Q236H, or I257L superimposed on their respective differential interference contrast (DIC) images. Cells expressing each of the AF-linked Cx40 mutants were able to form GJ plaque-like structures at the cell–cell interface similar to that of wildtype Cx40 (white arrows). Scale bars = 10 µm; (B) the bar graph summarizes the percentage of cell pairs showing GJ plaque-like structures at the cell–cell interface for each mutant. No statistical difference was observed between any of the mutants and wildtype Cx40. Approximately 100 positively-transfected cell pairs were examined for each transfection. The total number of transfections is indicated on each bar.

Figure 1

Localization of atrial fibrillation (AF)-linked Cx40 mutants. (A) Fluorescent images of HeLa cell clusters or pairs expressing YFP-tagged Cx40, K107R, L223M, Q236H, or I257L superimposed on their respective differential interference contrast (DIC) images. Cells expressing each of the AF-linked Cx40 mutants were able to form GJ plaque-like structures at the cell–cell interface similar to that of wildtype Cx40 (white arrows). Scale bars = 10 µm; (B) the bar graph summarizes the percentage of cell pairs showing GJ plaque-like structures at the cell–cell interface for each mutant. No statistical difference was observed between any of the mutants and wildtype Cx40. Approximately 100 positively-transfected cell pairs were examined for each transfection. The total number of transfections is indicated on each bar.

Figure 2

Coupling percentage and G_j of AF-linked mutants. (A) Dual whole-cell patch clamp technique was used to measure junctional current (I_j) from N2A cell pairs expressing untagged Cx40, K107R, L223M, Q236H, or I257L at 20 mV V_j; (B) bar graph summarizes the coupling percentages of cell pairs expressing the AF-linked Cx40 mutants. No statistical difference was observed between each of the mutants and the wildtype Cx40. The number of transfections is indicated on each bar; (C) bar graph illustrates the coupling conductance (G_j) of coupled cell pairs expressing Cx40, K107R, L223M, Q236H, or I257L. Cell pairs expressing Q236H showed a significantly lower G_j than those of wildtype Cx40 (* p < 0.05). The number of cell pairs is indicated on each bar.

Figure 3

V_j gating of AF-linked mutant GJs. (A) Dual whole-cell patch clamp was used to measure I_js in N2A cell pairs expressing Cx40, K107R, L223M, Q236H, or I257L in response to a series of V_j pulses as indicated. Superimposed I_js for each mutant is shown; (B) normalized steady state junctional conductance, G_j,ss, of the Cx40 mutants (black filled circles) and wildtype Cx40 (grey open circles) were plotted at different V_js. The G_j,ss–V_j plot of each mutant was fitted with a two-state Boltzmann equation at each V_j polarity (smooth black lines). Boltzmann fittings of G_j,ss–V_j plot of wildtype Cx40 (smooth grey dashed lines) were obtained and superimposed on each plot for comparison. The number of cell pairs is indicated.

Figure 4

V_j-gating kinetics of AF-linked Cx40 mutants. (A) I_js induced at different V_js (60 mV light grey, 80 mV medium grey, 100 mV dark grey) were normalized and superimposed for each of the mutant or Cx40 GJs. I_j deactivations under different V_js were all fitted well with a single exponential process (smooth black lines); (B) The time constants (τs) were plotted on a semi logarithmic scale against different V_js. When the V_js increased, the averaged τs of the mutant GJs (black filled circles) decreased similar to those observed for the wildtype Cx40 (grey open circles). No consistent statistical difference was found between most of the mutant τs and the τs of wildtype Cx40, except the τs of Q236H was consistently lower than those of wildtype Cx40 (two-way ANOVA). The number of cell pairs are indicated.

Figure 5

Coupling percentage and G_j of co-expressing AF-linked mutants with wildtype Cx43. (A) Representative I_js are shown from N2A cell pairs co-expressing Cx40, K107R, L223M, Q236H, or I257L (with an untagged reporter GFP) with wildtype Cx43 (with an untagged reporter DsRed); (B) bar graph illustrates coupling percentages of N2A cell pairs expressing each combination. The number of transfections is indicated; (C) bar graph illustrates the G_j of cell pairs co-expressing one of the Cx40 mutants (K107R, L223M, Q236H, or I257L) with Cx43. The G_j of cell pairs co-expressing Q236H:Cx43 was significantly lower than that of wildtype Cx40:Cx43 (* p < 0.05). The number of cell pairs is indicated.

Figure 6

Functional test on heterotypic mutant/Cx40 GJs. (A) I_js were obtained from heterotypic Q236H/Cx40, L223M/Cx40, or Cx40/Cx40 (in all cases with untagged GFP or DsRed, respectively) N2A cell pairs; (B) Bar graph summarizes the coupling percentages of heterotypic cell pairs. No statistical difference was found between the coupling percentage of any of the mutant heterotypic GJs and that of Cx40/Cx40 GJs. The number of transfections is indicated; (C) G_js of cell pairs expressing L223M/Cx40 or Q236H/Cx40 were not statistically different from those of Cx40/Cx40. The number of cell pairs is indicated.

Figure 7

Propidium iodide uptake of AF-linked Cx40 mutants. (A) HeLa cells transfected with Cx40 mutants, empty vector GFP, or Cx40 are shown: column 1 (under DIC), column 2 (GFP fluorescence to show successful expression of respective vector), column 3 (propidium iodide [PI] uptake in red), column 4 (an overlay of images of column2 and 3). Only cells expressing L221I showed PI uptake. The scale bar = 50 μm; (B) bar graph summarizes PI uptake percentage of isolated individual cells expressing Cx40 mutants, Cx40, or GFP. PI uptake percentage for each of the AF-linked mutants was not statistically different from that of wildtype Cx40 or the empty vector (GFP), except L221I (*** p < 0.001). The number transfection is indicated with observations of over 60 isolated cells for each transfection.