Retinal pigment epithelium 65 kDa protein (RPE65): An update

Abstract

Vertebrate vision critically depends on an 11-cis-retinoid renewal system known as the visual cycle. At the heart of this metabolic pathway is an enzyme known as retinal pigment epithelium 65 kDa protein (RPE65), which catalyzes an unusual, possibly biochemically unique, reaction consisting of a coupled all-trans-retinyl ester hydrolysis and alkene geometric isomerization to produce 11-cis-retinol. Early work on this isomerohydrolase demonstrated its membership to the carotenoid cleavage dioxygenase superfamily and its essentiality for 11-cis-retinal production in the vertebrate retina. Three independent studies published in 2005 established RPE65 as the actual isomerohydrolase instead of a retinoid-binding protein as previously believed. Since the last devoted review of RPE65 enzymology appeared in this journal, major advances have been made in a number of areas including our understanding of the mechanistic details of RPE65 isomerohydrolase activity, its phylogenetic origins, the relationship of its membrane binding affinity to its catalytic activity, its role in visual chromophore production for rods and cones, its modulation by macromolecules and small molecules, and the involvement of RPE65 mutations in the development of retinal diseases. In this article, I will review these areas of progress with the goal of integrating results from the varied experimental approaches to provide a comprehensive picture of RPE65 biochemistry. Key outstanding questions that may prove to be fruitful future research pursuits will also be highlighted.

Keywords: Carbocation; Inhibitor; Isomerase; Isomerohydrolase; Non-heme iron enzyme; Photoreceptors; Retinal pigment epithelium; Visual cycle.

Figure 1.. Overview of the classical visual cycle.

A). Anatomic arrangement of the outer retina showing the operation of the visual cycle between photoreceptor outer segments (red and blue for rods and cones, respectively) and the RPE. Also shown are the apical processes of Müller glia cells, which play non-classical roles in the delivery of visual chromophore to photoreceptors, particularly cones. B) Details of the classical visual cycle. Protein components of the pathway are shown in blue with the exception of RPE65 and opsin. Non-standard abbreviations are as follows: CRALBP, cellular retinaldehyde-binding protein; CRBP, cellular retinol-binding protein; IRBP, interphotoreceptor retinoid-binding protein; LRAT, lecithin:retinol acyltransferase; PC, phosphatidylcholine; RDH, retinol dehydrogenase; RPE65, retinal pigment epithelium 65 kDa. Panel B is modified and used with permission from (Kiser et al., 2014).

Figure 2.. Sequence and phylogenetic relationship of RPE65 to carotenoid cleavage dioxygenase.

A) An alignment of RPE65, BCO1, and BCO2 consensus sequences along with the sequence of a metazoan-like archaeal CCD, NdCCD. Residues making up the conserved His/Glu iron coordination motif are marked with blue and red stars, respectively. The green star indicates the location of the residue that occludes one of the potential iron coordination sites. Red arrowheads indicate ‘RPE65-specific’ residues as defined in the main text. Consensus sequences were generated using the program Cons. Consensus residues were assigned based on the default plurality rule. Consensus residues are shown in uppercase if the corresponding column in the alignment consisted of all positively matched residues according to the BLOSUM62 scoring matrix. The alignment was generated using Clustal Omega (Sievers et al., 2011) and displayed using Espript3 (Gouet et al., 2003). With a few exceptions, CCD sequences from the following organisms were used to generate the consensus sequences: Bos taurus (cow), Mus musculus (mouse), Homo sapiens (human), Canis lupus familiaris (dog), Ornithorhynchus anatinus (platypus), Xenopus tropicalis (frog), Sus scrofa (pig), Felis catus (cat), Chelonia mydas (green sea turtle), Petromyzon marinus (Sea lamprey), Latimeria chalumnae (coelacanth), Gallus gallus (chicken), Eptatretus stoutii (hagfish). Hagfish BCO1 and BCO2 sequences were unavailable for use in consensus sequence generation. Additionally, the platypus BCO2 sequence was not used for consensus sequence generation owing to its questionable accuracy. B). Venn diagram comparison of residues identified as being “RPE65-specific” in different studies. C). Phylogeny of metazoan CCDs generated using MrBayes (Ronquist and Huelsenbeck, 2003). NdCCD was used as an outgroup sequence to root the tree. The scale bar indicates the average number of substitutions per site. Numbers along the bipartitions are posterior probabilities estimated by Markov Chain Monte Carlo using the Jones substitution matrix and assuming invgamma among-site rate variation. The majority rule consensus tree is shown.

Figure 3.. Absence of Rpe65 promoter activity in cone photoreceptors.

A) Retinal cryo-section from a Rpe65^CreERT2 mT/mG^+/− mouse treated with tamoxifen to induce Cre activity. Green fluorescence (mG) shows cells where the Rpe65 promoter was active resulting in Cre activity at the mT/mG locus. Red fluorescence (mT) shows cells lacking Cre activity. The sections were co-stained with DAPI (blue) and peanut agglutinin (PNA, magenta) to demarcate nuclei and cones, respectively. The composite fluorescence signal is shown at the top along with the individual channels. Co-localization of the PNA and mG signals was not observed. Conversely, the mG signal did colocalize with ezrin, a marker of RPE cell apical cell processes (Huang et al., 2009), as described in (Choi et al., 2021). The scale bar represents 50 μm. B) A retinal flatmount from an Rpe65^CreERT2 mT/mG^+/− mouse treated with tamoxifen to induce Cre activity. The flatmount was co-stained with PNA to allow visualization of cone photoreceptors and imaged with its RPE-associated side facing the camera. The composite fluorescence signal is shown to the left along with the individual channels. Magnified images corresponding to the indicated boxes are shown below each wholemount image. The green fluorescent and PNA signals did not colocalize demonstrating that Cre recombinase in not expressed in the cone photoreceptors of this animal model. The green fluorescence shown in the magnified images originated from RPE cells that remained attached to the neural retina during the dissection procedure. The scale bar in the whole retina image represents 1000 μm. That in the bottom zoomed image represents 100 μm. Used with permission from (Choi et al., 2021).

Figure 4.. Overview of the RPE65 protein structure.

A) The RPE65 crystal structure viewed down its beta-propeller axis. The propeller blades are marked with Roman numerals. The tripartite active site cavity is delineated with a grey surface. The iron ion (red-brown sphere) is shown along with its 4-His/3-Glu coordination motif (orange sticks). B) Orthogonal view of the RPE65 structure displaying the helical cap on the top surface of the beta propeller. A cluster of hydrophobic and positively charged residues that mediate membrane binding are shown as wheat-colored sticks. C) Structure of the RPE65 iron center. D). Structure of the RPE65 dimeric assembly showing the localization of the membrane binding elements to a common face of the dimer and their close proximity to the active site openings (indicated by curvy arrows).

Figure 5.. Molecular packing and conformational difference observed in lipid-embedded RPE65 crystals.

A) Orthogonal views down the crystallographic axes demonstrate well-packed RPE65 sheets separated by 20-30 Å gaps (grey layers) that extend in two dimensions and contain lipid-detergent mixed-micelle sheets. The membrane binding surface of RPE65 (orange) faces the lipid-filled sheet. B) Conformational differences in the membrane-binding surface and active site entrance observed in lipid-embedded RPE65 crystals and delipidated RPE65 crystals. Arrows pointing from the delipidated (grey) to the lipid-embedded (yellow) structures are shown to help illustrate the structural differences. Phe¹⁹⁶, Phe²⁶⁴ and Trp²⁶⁸ in the lipid-embedded structure form a continuous aromatic surface near the active site entrance (denoted by the broad green arrow). Used with permission from (Kiser et al., 2012).

Figure 6.. Structural and activity relationships among retinoids and non-retinoid RPE65 inhibitors.

A) Comparison of the chemical structures of C15 retinyl cation to retinylamine, emixustat, and MB-001 demonstrate the close relatedness of the latter two compound to the retinoid carbon backbone, indicating their ability to serve as retinoid mimetics for structural studies. B) Inhibitory effects of retinylamine, emixustat, and MB-001 on retinoid isomerase activity in vitro. Bovine RPE microsomes were used as the enzyme source for this assay. C) Inhibitory effects of retinylamine, emixustat, and MB-001 on visual chromophore regeneration in mice. Modified and used with permission from (Kiser et al., 2015).

Figure 7.. Structure of RPE65 in complex with the retinoid-mimetic MB-001 and palmitate.

A) Cut-away view of the RPE65 active site showing the binding sites for MB-001 (orange sticks) and palmitate (cyan sticks) within the proximal and distal regions of the active site cavity defined with respect to the active site opening at the membrane binding surface (marked by an asterisk). The iron ion is shown as a red-brown sphere. B) Detailed view of the residues forming the different regions of the active site cavity. C) Two-dimensional representation of the MB-001/palmitate interaction with the RPE65 active site. Modified and used with permission from (Kiser et al., 2015).

Figure 8.. Comparison of the active sites between RPE65 and the metazoan-like, apocarotenoid-cleaving CCD, NdCCD.

A) Structure RPE65 in complex with MB-001 (orange sticks) and palmitate (cyan sticks) (PDB accession code 4RSE). Residues the vicinity of the bound ligands are shown as wheat-color sticks. The iron ion is shown as a brown sphere and waters are red spheres. The electrostatic surface in the vicinity of the bound ligands is shown with red and blue representing negative and positive electrostatic potential, respectively. B) Structure of NdCCD in complex with an apocarotenoid product (orange sticks). Note the conserved negative electrostatic potential found within the retinoid/apocarotenoid binding sites of both proteins as well as the presence of buried water molecules in the central region of both active sites. Also note the conformational difference between Tyr²⁷⁵ in RPE65 and Phe²⁵² in NdCCD that produces significantly different shapes near the substrate entrance as well the presence of the ‘RPE65-specific’ residues, Phe²⁶⁴ and Trp²⁶⁸, near Tyr²⁷⁵, which also contribute to the active site geometry. Modified and used with permission from (Daruwalla et al., 2020).

Figure 9.. Summary of isotope-labeling studies performed on the RPE65-catalyzed isomerohydrolase reaction.

Note the unusual cleavage of the C15-O bond as opposed to acyl bond cleavage more commonly observed in biological ester hydrolysis reactions. Used with permission from (Kiser et al., 2015).

Figure 10.. Proposed mechanism of the RPE65-catalyzed isomerohydrolase reaction.

Individual steps are described in Section 6 of the main text. Modified and used with permission from (Kiser et al., 2015).

Figure 11.. Analysis of emixustat enantiomer binding to and inhibition of RPE65.

A) RPE65 crystals obtained in the presence of racemic emixustat show preferential binding of the (R) stereoisomer. B) In vitro RPE65 activity assays demonstrate a roughly two-fold greater potency of the R isomer of emixustat as compared to the S isomer. Crystal structures of RPE65 in complex with pure R-emixustat (C) and pure S-emixustat (D) demonstrate more a more favorable hydrogen bonding pattern for the former stereoisomer, thus explaining its greater inhibitory potency. The mesh in panels A, C, and D represents unbiased σA-weighted omit mFo-DFc electron density contoured at 3 RMSD. Dashed lines indicate hydrogen bonds with bond lengths given in Angstroms. Modified and used with permission from (Zhang et al., 2015).

Figure 12.. Comparison of emixustat and MB-004 binding to the RPE65 active site.

A) The cyclohexyl ring of emixustat is located close to a water-filled pocket within the membrane-proximal region of the active site pocket. Owing to its bulkiness, the cyclohexyl moiety is unable to occupy a nearby apolar pocket (red arrow). B) One half of the MB-004 dipropyl moiety occupies the aforementioned hydrophobic cavity forming non-bonded contacts with residues lining the pocket. The other half of this moiety resides in approximately the same position as the cyclohexyl moiety of emixustat. Ligands are shown as van der Waals spheres with carbon, nitrogen and oxygen atoms colored orange, blue and red, respectively. Used with permission from (Kiser et al., 2017).

Figure 13.. Effects of acute RPE65 inhibition by emixustat on mouse cone dark adaptation in vivo.

A) The recovery of cone b-wave flash sensitivity following a 90% bleach was compared between vehicle- and emixustat-treated Gnat1^−/− mice The late, RPE visual cycle-driven phase of cone dark adaptation was suppressed by emixustat. By contrast, the early, Müller cell-driven phase of the cone dark adaptation curve was unaffected indicating the presence of visual chromophore sources that are not acutely dependent on RPE65 activity. B) Impact of RPE65 inhibition by emixustat on in vivo Gnat1^−/− mouse cone photoreceptor responses during and after prolonged exposure to background light. Cone b-wave sensitivity was monitored during a 30 min exposure to bright (300 cd/m²) white background light (gray bar), and then for 35 min in darkness. Compared to vehicle controls, cones from mice treated with emixustat were equivalently desensitized by the background light but had largely suppressed subsequent dark adaptation. Modified and used with permission from (Kiser et al., 2018)

Figure 14.. Two-dimensional topology diagram of RPE65 mapped with corresponding residues showing sites found to be mutated in retinal disease.

Dashed lines indicate residues involved in iron coordination.

Figure 15.

Impact of a Glu148Asp-equivalent mutation on the structure of the CCD iron center. A) Stereo-view of the iron center of an RPE65 homolog, SynACO, showing the interaction of Glu¹⁵⁰ (equivalent to Glu¹⁴⁸ in RPE65) with the iron-coordinating His²³⁸ residue (equivalent to His²⁴¹ in RPE65). B) The Glu¹⁵⁰Asp mutation alters the conformation of His²³⁸ resulting in a loss of its interaction with the iron ion and lower iron occupancy in the active site. The blue mesh in both panels represents the final σA-weighted 2Fo-Fc maps contoured at 1 RMSD. Modified and used with permission from (Sui et al., 2016).

Figure 16.. Location of the Asp⁴⁷⁷ residue within the RPE65 structure and creation of an RPE65/SynACO chimera system for structural study of the Asp⁴⁷⁷Gly mutation.

A) Location of the Asp⁴⁷⁷-containing loop within the three-dimensional structure of RPE65. B) Structure of the Asp⁴⁷⁷ loop region in RPE65/SynACO chimera (blue to green gradient) compared to bovine RPE65 (grey). Auxiliary substituted residues in the chimera and the corresponding residues in bovine RPE65 are colored light orange and grey, respectively. The Leu residue substituted at position 44 is omitted for clarity. The Asp⁴⁷⁷ position is marked by an asterisk. Top residue labeling refers to the ACO/RPE65 sequence while the numbers on bottom (in grey) refer to the native RPE65 sequence. Note the structural equivalence between the two proteins in this region. C) Comparison of the same loop region of the RPE65/SynACO chimera Asp⁴⁷⁷Gly mutant to the original chimera structure shows only modest structural differences indicating that the Gly substitution does not grossly destabilize the Asp⁴⁷⁷ loop region. Modified and used with permission from (Choi et al., 2018).

Figure 17.. Involvement of the Asp⁴⁷⁷ loop in crystal packing of RPE65/SynACO chimera Asp⁴⁷⁷Gly mutant.

A) Molecular packing in the trigonal crystal form revealing an interaction of the Asp⁴⁷⁷Gly loop and surrounding residues (shown as van der Waals spheres) with the other molecule in the asymmetric unit (contact I), which in turn also interacts with a symmetry-related molecule through the region surrounding the Asp⁴⁷⁷Gly loop (contact II). B) Details of the interactions formed between the Asp⁴⁷⁷Gly loop and its interaction partners. Dashed lines indicate van der Waals contacts (width proportional to number of atomic contacts), solid blue lines indicate hydrogen bonds and solid red lines indicate salt bridges. C) Molecular packing in the monoclinic crystal form mediated by the Asp⁴⁷⁷Gly loop and surrounding residues. Contact III occurs between the two molecules of the asymmetric unit whereas contact IV involves a symmetry-related molecule. These two contacts are related by a slight rotation. D) Interactions formed between the Asp⁴⁷⁷Gly loop and residues from its interacting partners in the monoclinic crystal form. In all four contacts, the introduction of an Asp side chain at position 434 would result in steric clashes which explains why these two crystal forms were only observed for the Asp⁴⁷⁷Gly mutant. Used with permission from (Choi et al., 2018).