Advanced glycation end product recognition by the receptor for AGEs

Abstract

Nonenzymatic protein glycation results in the formation of advanced glycation end products (AGEs) that are implicated in the pathology of diabetes, chronic inflammation, Alzheimer's disease, and cancer. AGEs mediate their effects primarily through a receptor-dependent pathway in which AGEs bind to a specific cell surface associated receptor, the Receptor for AGEs (RAGE). N(ɛ)-carboxy-methyl-lysine (CML) and N(ɛ)-carboxy-ethyl-lysine (CEL), constitute two of the major AGE structures found in tissue and blood plasma, and are physiological ligands of RAGE. The solution structure of a CEL-containing peptide-RAGE V domain complex reveals that the carboxyethyl moiety fits inside a positively charged cavity of the V domain. Peptide backbone atoms make specific contacts with the V domain. The geometry of the bound CEL peptide is compatible with many CML (CEL)-modified sites found in plasma proteins. The structure explains how such patterned ligands as CML (CEL)-proteins bind to RAGE and contribute to RAGE signaling.

Figure 1

CEL (CML) containing peptides can be produced by both glycation and chemical synthesis. (A) Fructosyllysine, CML and CEL are the products of early and advanced glycoxidation of sugars. (B) Synthetic CEL-peptide, DEF(CEL)ADE, contains a correct chemical structure of N_ε-carboxy-ethyl-lysine. To characterize CEL-peptide, we collected two 2D homonuclear NMR experiments, ¹H,¹H TOCSY and ¹H, ¹H ROESY. The ¹H, ¹H TOCSY strip shows through bond correlation between the amide proton (8ppm) and side chain protons H_α (4.1 ppm), H_β (1.7 ppm), H_γ (1.2 ppm), H_δ (1.5 ppm), and H_ε (2.85 ppm) of CEL. The ¹H, ¹H ROESY strip shows through space correlations between H_ε and carboxyethyl protons CH(CH₃)-COOH (3.8 ppm) and CH(CH₃)-COOH (1.7 ppm) of CEL, confirming the presence of a proper chemical structure of N_ε-carboxy-ethyl-lysine. See also Figure S1.

Figure 2

RAGE V domain does not discriminate between CML and CEL containing peptides. (A) Overlay of ¹⁵N-HSQC of free (black) and CML-PEP bound (red) V domain. (B) Overlay of ¹⁵N-HSQC of free (black) and CEL-PEP bound (red) V domain. (C) Sequence alignment of V domain and a V-type domain from a heavy chain antibody IgG1 P20.1. Amino acid residues involved in CML (CEL) binding are in red. CDR1 and CDR2, the hypervariable regions of IgG1 P20.1, are in blue. Secondary structure elements are shown above the sequences. See also Figure S3.

Figure 3

Stereoview of the overlay of 25 lowest energy CEL-PEP V domain backbone traces (PDB code 2L7U). N- and C-termini of the V domain and CEL-PEP are indicated. Figure is prepared by using Molmol (Koradi et al, 1996). See also Table S1.

Figure 4

Solution structure of the CEL-PEP-V domain complex. (A) Structure of CEL-PEP bound to V domain. V domain is shown in ribbon representation. Elements of secondary structure are labeled following the immunoglobulin convention(Bork et al., 1994). (B) Electrostatic potential is mapped onto the molecular surface of the V domain. Positively and negatively charged surfaces are indicated in blue and red, respectively. (C) V domain amino acid residues located within 5 Å from the CEL moiety of CEL-PEP. Putative hydrogen bond between the backbone amide proton of Ala5 and the side chain carbonyl group of Asn112 is indicated. Carbon atoms of CEL-PEP and V domain are in yellow and cyan, respectively. (D) Structural alignment of CEL-PEP with three short segments from human serum albumin (HSA) containing lysines(Wa et al., 2007), 11-FKD, 56-AKT, and 261-AKY. The lysines in these sequences were shown to be glycated under elevated concentrations of D-glucose. See also Figure S4 and Table S2.

Figure 5

Mutants of the VC1 domains of RAGE fail to suppress CML-BSA induced RAGE signaling. (A) Cartoon model of how RAGE dimerization promotes V domain binding to multiple CML moieties on CML-BSA (ribbon). The molecular surface of the V domain involved in CML(CEL) binding is in red. Only two V domains are shown. Lysines of BSA, which may undergo glycation are in yellow. The cartoon model was prepared by using SWISS-PDB Viewer (Guex et al, 1997). (B, C) Single K52A and R98A, and double K52A, R98A (KRA) mutants of the VC1 domains do not interfere with CML-BSA induced RAGE signaling in both C6 rat glioma (b) and mouse VSMC cells (c). See also Figure S5.