Functional importance of the oligomer formation of the cyanobacterial H+ pump Gloeobacter rhodopsin

Abstract

Many microbial rhodopsins self-oligomerize, but the functional consequences of oligomerization have not been well clarified. We examined the effects of oligomerization of a H⁺ pump, Gloeobacter rhodopsin (GR), by using nanodisc containing trimeric and monomeric GR. The monomerization did not appear to affect the unphotolyzed GR. However, we found a significant impact on the photoreaction: The monomeric GR showed faint M intermediate formation and negligible H⁺ transfer reactions. These changes reflected the elevated pKa of the Asp121 residue, whose deprotonation is a prerequisite for the functional photoreaction. Here, we focused on His87, which is a neighboring residue of Asp121 and conserved among eubacterial H⁺ pumps but replaced by Met in an archaeal H⁺ pump. We found that the H87M mutation removes the "monomerization effects": Even in the monomeric state, H87M contained the deprotonated Asp121 and showed both M formation and distinct H⁺ transfer reactions. Thus, for wild-type GR, monomerization probably strengthens the Asp121-His87 interaction and thereby elevates the pKa of Asp121 residue. This strong interaction might occur due to the loosened protein structure and/or the disruption of the interprotomer interaction of His87. Thus, the trimeric assembly of GR enables light-induced H⁺ transfer reactions through adjusting the positions of key residues.

Figure 1

The positions of key residues in this study. Here, we showed the structure of XR (PDB ID: 3DDL), where the “H⁺ acceptor” Asp96 residue interacts with the neighboring His62 residue. They correspond to Asp121 and His87 in GR, respectively. The top view from the cytoplasmic (CP) side is shown in the left panel. Enlarged view of the H⁺ acceptor region is shown in the right panel. Here, “EC side” means “extracellular side”. The broken lines represent the proposed hydrogen bonds, and the red sphere represents water molecule.

Figure 2

Comparison of CD (a) and absorption (b) spectra between two nanodiscs. The inset of panel a shows the nanodisc bands isolated by sucrose density gradient centrifugation. In panel b, the spectrum of DDM-solubilized GR is also shown. Here, all three spectra were plotted after subtracting the scattering contribution as shown in the inset, which shows the raw spectrum of the DDM-solubilized state and the estimated scattering artifact (for details, see Materials and Methods section). The buffer solution was 6-mix buffer, pH 7, containing 0.3 M NaCl. For DDM-solubilized GR, the medium was supplemented with 0.05% DDM.

Figure 3

Comparison of photocycles between trimeric and monomeric GR. Flash-induced absorbance changes at typical three wavelengths were plotted for the GR trimer in ND_H (a) and the monomer in ND_L (b). The buffer solution was 6-mix buffer, pH 7, containing 0.3 M NaCl. The transient pH changes were detected by 100 μM pyranine, whose absorbance changes at 457 nm were measured in 0.5 mM MOPS (pH 7) containing 0.3 M NaCl and plotted here at 10-fold magnification. All samples contained 10 μM GR.

Figure 4

HPLC analysis and resonance Raman spectra. Panel a shows the HPLC chromatographs of retinal isomers extracted from the dark-adapted GR in ND_H (solid line) and ND_L (broken line). The nanodiscs were suspended in 6-mix buffer, pH 7, containing 0.3 M NaCl. The ratios of all-trans and 13-cis retinals were determined from the peak areas and are indicated in the panel. Panel b shows the resonance Raman spectra of unphotolyzed GR with 441.6 nm excitation. The nanodiscs were suspended in 20 mM MOPS, pH 7, containing 0.3 M NaCl.

Figure 5

The pH-dependent shifts of absorption λ_max. The λ_max values at various pH values were examined for three nanodiscs containing wild-type trimer, wild-type monomer, and the monomer of the H87M mutant. The smooth lines are the best-fitted results with the linear combinations of Henderson-Hasselbalch functions. The determined pKa values were 4.52 and 9.89 for ND_H, 3.43, 4.95, 7.41 and 9.78 for ND_L, and 3.72, 6.30 and 9.74 for H87M. The medium contained 6-mix buffer and 0.3 M NaCl. The pH was adjusted by adding HCl or NaOH.

Figure 6

Photocycle of monomeric GR at pH 11. The experimental conditions were the same as in Fig. 3b except for the pH.

Figure 7

Photocycle of monomeric H87M mutant in nanodisc. The experimental conditions were the same as in Fig. 3.

Figure 8

Sensitivities to hydroxylamine and heat treatment. The bleaching kinetics due to 50 mM hydroxylamine (a) and thermal denaturation (b) were examined. Both panels show the remaining amounts of GR, which were evaluated from the absorbance values at the respective absorption λ_max. The bleaching rates were determined by fitting with a single exponential function. The determined rates are as follows: For panel a, 6.07 × 10⁻³ min⁻¹ for ND_H, 1.15 × 10⁻² min⁻¹ for ND_L, and 3.85 × 10⁻² min⁻¹ for H87M; for panel b, 3.79 × 10⁻⁴ min⁻¹ for ND_H, 6.29 × 10⁻⁴ min⁻¹ for ND_L, and 4.88 × 10⁻³ min⁻¹ for H87M. Both experiments were performed in the dark. The nanodiscs were incubated in pH 7 buffer (20 mM MOPS, 0.3 M NaCl) at 25 °C for panel a and pH 8.5 buffer (50 mM HEPES, 0.3 M NaCl) at 65 °C for panel b.