Identification of the N-glycosylation sites on glutamate carboxypeptidase II necessary for proteolytic activity

Abstract

Glutamate carboxypeptidase II (GCPII) is a membrane peptidase expressed in the prostate, central and peripheral nervous system, kidney, small intestine, and tumor-associated neovasculature. The GCPII form expressed in the central nervous system, termed NAALADase, is responsible for the cleavage of N-acetyl-L-aspartyl-L-glutamate (NAAG) yielding free glutamate in the synaptic cleft, and is implicated in various pathologic conditions associated with glutamate excitotoxicity. The prostate form of GCPII, termed prostate-specific membrane antigen (PSMA), is up-regulated in cancer and used as an effective prostate cancer marker. Little is known about the structure of this important pharmaceutical target. As a type II membrane protein, GCPII is heavily glycosylated. In this paper we show that N-glycosylation is vital for proper folding and subsequent secretion of human GCPII. Analysis of the predicted N-glycosylation sites also provides evidence that these sites are critical for GCPII carboxypeptidase activity. We confirm that all predicted N-glycosylation sites are occupied by an oligosaccharide moiety and show that glycosylation at sites distant from the putative catalytic domain is critical for the NAAG-hydrolyzing activity of GCPII calling the validity of previously described structural models of GCPII into question.

Figure 1.

An example of identification of a glycosylation site using deglycosylation in normal and isotopic water (H₂¹⁸O). Detailed view of the isotopic cluster of the peak corresponding to the DFTEIASKFSERLQ peptide covering the N638 site is provided. The peptide deglycosylated in normal water has a typical isotopic distribution, but the mass of the peptide deglycosylated in presence of ¹⁸O is shows a 2 D mass shift. The incomplete mass shift is because deglycosylation was done in a mixture of normal and isotopic water (83% of H₂¹⁸O). During the hydrolysis of the N-glycosidic bond, the mass of the deglycosylated peptide is increased by 1 mass unit, thus yielding a teoretical monoisotopic mass [M + H]⁺ of 1670.83.

Figure 2.

Expression and secretion of wild-type recombinant GCPII in the presence of tunicamycin. S2 cells stably transfected with cDNA coding for wild-type rhGCPII were grown in the presence or absence of tunicamycin, an inhibitor of N-glycosylation. Thirty-six hours postinduction, the cells and conditioned media were harvested, resolved by 9% SDS-PAGE, electroblotted on a nitrocellulose membrane, and immunostained. Portion of cell lysates and the conditioned media were subjected to PNGase F treatment to assess degree of N-glycosylation of the individual rhGCPII forms. rhGCPII, purified rhGCPII (100 ng); cells/medium, C—cell lysates, M—conditioned media; Tunicamycin +/−, cells grown in presence/absence of tunicamycin; PNGase F +/−, samples treated/not treated with PNGase F; Activity +/−, NAAG-hydrolyzing activity detectable/not detectable.

Figure 3.

Schematic representation of the GCPII domain structure and glycosylation mutants used in this study. The diagram shows wild-type human GCPII and mutants with potential N-glycosylation sites mutated. Individual domains according to Rawlings and Barrett (1997): CD, putative catalytic domain; polypeptides spanning amino acids 44–150, 151–274, and 587–750, domains of unknown function. Y symbols are potential N-glycosylation sites. Asterisks indicate Asn or Thr residues mutated to Ala.

Figure 4.

Expression and hydrolytic activities of wild-type and mutated rhGCPII. S2 cells stably transfected with cDNA for rhGCPII or N-glycosylation mutants thereof were grown in SF900II serum-free medium. Protein expression was induced with 500 μM CuSO₄ and the conditioned media harvested three days later. The media were dialyzed and assayed for rhGCPII expression and carboxy-peptidase activities. (A) Immunoblot analysis of rhGCPII expression. Fifteen microliters (5 μL in the case of the rhGCPII) of the conditioned medium mixed with a denaturing loading buffer was loaded into a single lane, proteins resolved by 9% SDS-PAGE, electroblotted on a nitrocellulose membrane, and immunostained using anti-GCPII antibody as described in Materials and Methods. Relative band intensities were recorded with a CCD-camera and rhGCPII amount in each sample calculated from a calibration curve of known rhGCPII concentrations. (B) Carboxypeptidase activities of the individual rhGCPII mutants. Dialyzed conditioned media were mixed with the reaction buffer (the final volume of 180 μL), and the reactions were started by addition of 20 μL of 1 μM NAAG. Following 20-min incubation, 200 μL of 200 mM sodium phosphate was added, reaction products were separated on an anion-exchange column, and eluted labeled glutamate was quantified by liquid scintillation. Measured activities were related to the amount of each mutant in the conditioned medium, as determined by Western blot densitometry. The results are shown in the format of mean ± standard deviation.