Metabolic resistance of Aβ3pE-42, a target epitope of the anti-Alzheimer therapeutic antibody, donanemab

Abstract

The amyloid β peptide (Aβ), starting with pyroglutamate (pE) at position 3 and ending at position 42 (Aβ3pE-42), predominantly accumulates in the brains of Alzheimer's disease. Consistently, donanemab, a therapeutic antibody raised against Aβ3pE-42, has been shown to be effective in recent clinical trials. Although the primary Aβ produced physiologically is Aβ1-40/42, an explanation for how and why this physiological Aβ is converted to the pathological form remains elusive. Here, we present experimental evidence that accounts for the aging-associated Aβ3pE-42 deposition: Aβ3pE-42 was metabolically more stable than other Aβx-42 variants; deficiency of neprilysin, the major Aβ-degrading enzyme, induced a relatively selective deposition of Aβ3pE-42 in both APP transgenic and App knock-in mouse brains; Aβ3pE-42 deposition always colocalized with Pittsburgh compound B-positive cored plaques in APP transgenic mouse brains; and under aberrant conditions, such as a significant reduction in neprilysin activity, aminopeptidases, dipeptidyl peptidases, and glutaminyl-peptide cyclotransferase-like were up-regulated in the progression of aging, and a proportion of Aβ1-42 may be processed to Aβ3pE-42. Our findings suggest that anti-Aβ therapies are more effective if given before Aβ3pE-42 deposition.

Figure S1.. Amino- and carboxyl-terminal structures of Aβ deposited in AD brain.

Aβ peptides were extracted from cerebral cortices of AD patients by formic acid and subjected to Western blot analysis using the anti-Aβ antibodies to the amino-terminal structure (panels a, b, c, d, e, f, g) and to the carboxyl-terminal structure (panels h, i, j). The antibodies have been described previously (Saido et al, 1996). AβN1(D) designates Aβ that starts with L-aspartate at position 1; AβC40(V) designates Aβ that ends with valine at position 40. On three lanes of the right side are shown 5, 16.6, and 50 ng of the following control synthetic peptides, respectively: Aβ1(D)-42, Aβ1(iD)-42, Aβ1(rD)-42, Aβ3(E)-42, Aβ3(pE)-42, Aβ11(pE)-42, Aβ17(L)-42, Aβ1(D)-40, Aβ1(D)-42, and Aβ1(D)-43 in panels a, b, c, d, e, f, g, h, i, j, respectively. Note that Aβ3(pE)-42 and Aβ11(pE)-42 form monomers, dimers, and oligomers under the experimental conditions employed. Lanes 1–3 are from early-onset AD patients (age at death: 45 ± 1.0) and 4–15 from late-onset AD patients (74 ± 6.6). Aβ3(pE)-42 was the predominant variant in all cases, and the ratio of Aβ3(pE)-x to AβN1(D)-x was 8.65. iD: L-isoaspartate; rD: rectus (D configuration) aspartate; pE: pyroglutamate. All amino acids are in the L-configuration unless otherwise stated. Table S2 describes the detailed properties of the AD samples. Intensities of immunoreactive bands on the blots were quantified as described in experimental procedures. Each column with a bar represents the mean ± SEM. *P < 0.01, significantly different from N1(D), †P < 0.01, significantly different from C40 (V) or C43(T). n.d, not detectable.

Figure S2.. Isogenic internally radiolabeled synthetic Aβ peptide variants used in the present study.

These peptides were synthetized, purified, and validated as previously reported (Iwata et al, 2000).

Figure 1.. Catabolism of Aβx-42 peptides in the hippocampus.

(A, B, C, D, E, F) Variants of ³H/¹⁴C-Aβx-42 were subjected to in vivo degradation and subsequent analysis as previously described (Iwata et al, 2000). Briefly, 0.5 μg Aβx-42 peptide dissolved in phosphate-buffered saline was unilaterally injected into the CA1 sector of the rat hippocampus and subjected to catabolism until the animals were euthanized by decapitation at the indicated time points. There was no contamination of the injection area by plasma or cerebrospinal fluid as immunohistochemically confirmed using anti-rat IgG. After extraction, the products were analyzed by reversed-phase HPLC connected to a flow scintillation monitor. The HPLC profiles in a ¹⁴C mode at time 0 (red), 10 (blue), and 30/60 (black) minutes after the in vivo injection are shown. The elution profiles in ¹⁴C and ³H modes were essentially identical. The major peaks at time 0 indicated by the arrows correspond to the intact substrates. The black arrowhead shows Aβ10-37 in (A) (Aβ1-42), and green arrowheads show possible intermediates in other panels. Digitized data were used to calculate the in vivo half-lives of the peptides as shown in Fig S2 and Table 1.

Figure S3.. Comparison of in vivo catabolic rates of Aβx-42 variants.

Digitized data of remaining amounts of intact Aβx-42 shown in Fig 1 were plotted, and then exponential approximation curves were drawn using Microsoft Excel. Each analysis of the in vivo catabolic rate of the Aβx-42 variant was carried out by independent experiments with more than five time points.

Figure 2.. Deposition of Aβ1-42 and Aβ3pE-42 in the brains of aged Mme-deficient APP-Tg mice.

(A) Immunohistochemical staining of the brains of 24-mo-old Mme ^+/+APP-Tg and Mme^−/−APP-Tg mice using anti-Aβ antibodies, N1D and N3pE. Immunostained sections from two mice in each case are shown. Scale bar, 500 μm. (B) Aβ deposits in brain sections from Mme^+/+APP-Tg and Mme^−/−APP-Tg mice (aged 12, 18, and 24 mo) were stained with thioflavin or immunostained with amino-terminal specific antibodies for Aβ (N1D and N3pE), anti-pan Aβ antibody (4G8), and carboxyl-terminal specific antibodies for Aβ (C40 and C42), and then quantified as described in the Materials and Methods section. Amyloid load is expressed as a fluorescence intensity in the measured area or a percent of the measured area. Each column with a bar represents the mean ± SEM. Multiple comparisons were done by a one-way ANOVA, followed by a post hoc test as described in the “Materials and Methods” section. The numbers of analyzed animals were as follows: 12 mo old, 5 male and 6 female Mme^+/+APP-Tg, and 4 male and 8 female Mme^−/−APP-Tg; 18 mo old, 10 male and 10 female Mme^+/+APP-Tg, 6 male and 4 female Mme^+/−APP-Tg, and 9 male and 5 female Mme^−/−APP-Tg; and 24 mo old, 7 male and 10 female Mme^+/+APP-Tg, 10 male and 10 female Mme^+/−APP-Tg, and 4 male and 9 female Mme^−/−APP-Tg mice. *P < 0.05, significantly different from Mme^+/+APP-Tg mice in the same ages. n.t., not tested. (C) Aβ plaque sizes in brain sections from Mme^+/+APP-Tg, Mme^+/−APP-Tg, and Mme^−/−APP-Tg mice (female, 24 mo old) were analyzed using MetaMorph image analysis software. Two or three sections from one individual (a total of 172 sections) were analyzed, and data were averaged. The area per section analyzed was 13.8 ± 0.058 mm². The numbers of analyzed animals were as follows: 11 female Mme^+/+APP-Tg, 10 female Mme^+/−APP-Tg, and 9 female Mme^−/−APP-Tg mice. Each point with a bar represents the mean ± SEM. Where the SEMs are not shown, they are smaller than the symbols. Differences in the pattern of plaque size distribution between N1D- and N3pE-positive plaques in all cohorts of mice were analyzed by repeated-measures two-way ANOVA, which revealed significant main effects of plaque size (F_{(26, 754)} = 501.535; P < 0.001) and amino-terminal structure (F_{(1, 754)} = 343.330; P < 0.001) and a significant interaction (F_{(26, 754)} = 75.525; P < 0.001). Interactions between the amino-terminal structure and genotype for particular plaque sizes (100–200, 1,500–2,500, and 10,500–20,000 μm²) were also analyzed by repeated-measures two-way ANOVA, followed by a post hoc test. F and P-values are as follows: F_(2,27) = 2.291 (P = 0.121), F_(2,27) = 7.925 (P = 0.002), and F_(2,27) = 3.133 (P = 0.060), respectively. The asterisk, dagger, and double dagger indicate a significant difference with P-values less than 0.05. Data from APP-Tg mice (male, 24 mo old, and female, 18 mo old) are shown in Fig S4. (D) Ratios of N3pE- to N1D-positive areas in Mme^+/+APP-Tg, Mme^+/−APP-Tg, and Mme^−/−APP-Tg mouse brains (male and female, 24 mo old) were compared. Immunostaining for N3pE and N1D was carried out using two to three sets of serial brain sections from the individual, and the average was used as a determinant. Each column with a bar represents the mean ± SEM. The make-up of the animal group (number, males, females, etc.) was the same as that shown in Fig 2B. Two-way ANOVA (gender, genotype) showed a significant main effect of the Mme genotype (F_{(2, 44)} = 9.434; P < 0.001). Ratios of N3pE- to N1D-positive areas in Mme^+/+APP-Tg were significantly different from other genotypes (*P < 0.001).

Figure S4.. Comparison of N1D- and N3pE-positive amyloid plaque distribution in APP-Tg mice (male, 24 mo old, and female, 18 mo old).

Two or three sections from one individual were analyzed, and data were averaged. The number of analyzed animals was as follows: (male, 24-mo-old) 7 Mme^+/+APP-Tg and 10 Mme^+/−APP-Tg; and (female, 18-mo-old) 8 Mme^−/−APP-Tg, 7 Mme^+/+APP-Tg, 10 Mme^+/−APP-Tg, and 8 Mme^−/−APP-Tg mice. Each point with a bar represents the mean ± SEM. Where SEMs are not shown, they are smaller than the symbols. F and P-values are as follows: male, 24 mo old, significant main effects of the plaque size (F_{(26, 624)} = 354.638; P < 0.001) and amino-terminal structure (F_{(1, 624)} = 239.434; P < 0.001) and a significant interaction (F_{(26, 754)} = 59.235; P < 0.001). Female, 18 mo old, significant main effects of the plaque size (F_{(26, 364)} = 286.961; P < 0.001) and amino-terminal structure (F_{(1, 364)} = 293.169; P < 0.001) and a significant interaction (F_{(26, 364)} = 31.525; P < 0.001). Interactions between the amino-terminal structure and the genotype for particular plaque sizes (100–200, 1,500–2,500, and 10,500–20,000 μm²) were also analyzed by repeated-measures two-way ANOVA, followed by a post hoc test: male, 24 mo old, F_(2,22) = 1.514 (P = 0.236), F_(2,22) = 11.258 (P < 0.001), and F_(2,22) = 4.455 (P = 0.255), respectively; and female, 18 mo old, F_(1,13) = 0.544 (P = 0.474), F_(1,13) = 6.719 (P = 0.022), and F_(1,13) = 2.355 (P = 0.149), respectively. The asterisk, dagger, and double dagger indicate a significant difference with P-values less than 0.05.

Figure 3.. Mass spectrometric profiles from detergent-insoluble/formic acid–soluble fractions of brains from aged APP-Tg mice.

(A) Monoisotopic mass of Aβ variants in the detergent-insoluble/formic acid–soluble fractions from 24-mo-old APP transgenic and non-transgenic brains was determined after the digestion of lysyl endopeptidase, because Aβ with 3pE at the amino-terminal shows poor ionization properties. (A, B) m/z range between 1,740 and 1,780 in panel (A) is shown at a higher magnification. The mass signals without annotation were not related to Aβ. Mass spectrometric profiles in ranges of m/z 1,480–1,940 and m/z 4,000–4,600 are shown in Fig S5.

Figure S5.. Mass spectrometric profiles from detergent insoluble/formic acid-soluble fractions of brains from aged APP-Tg mice.

(A, B) Mass spectrometric profiles in ranges of m/z 4,000–4,600 (A) and m/z 1,480–1,940 (B). Mass signals without annotation were not related to Aβ. Signals from WT mice, which are regarded as background, were subtracted from Mme^+/+APP-Tg and Mme^−/−APP-Tg mice, respectively.

Figure 4.. Diverse effects of Mme deficiency on extracellularly soluble and insoluble levels of Aβ variants in aged Mme-deficient APP-Tg mice.

(A) Brain tissue fractions (upper panel: extracellularly soluble fraction, 0.5 μg protein; lower panel: detergent-insoluble/formic acid–extractable fraction, 20 ng protein) of non-transgenic and APP transgenic mice with or without the Mme gene (12, 18, and 24 mo old) were subjected to Western blot analyses using amino-terminal specific antibodies for Aβ (N1D and N3pE), anti-pan Aβ antibody (4G8), and carboxyl-terminal specific antibodies for Aβ (C40 and C42). (B, C) Extracellularly soluble fraction and (C) detergent-insoluble/formic acid–extractable fraction intensities of immunoreactive bands on blots shown in Fig S6 were quantified as described in experimental procedures. The intensities were normalized against the data from 24-mo-old Mme^+/+APP-Tg mice. (B, C) Amounts of immunoreactive Aβ variants in 24-mo-old Mme^+/+APP-Tg mouse brains to N1D, N3pE, 4G8, C40, and C42 are 15.80, 0.028, 10.12, 8.18, and 1.70 ng/μg protein in (B), and 241.3, 1.150, 895.7, 461.6, and 91.7 ng/μg protein in (C), respectively. Each column with a bar represents the mean ± SEM of 4–6 female mice. *P < 0.05, significantly different from Mme^+/+APP-Tg mice at the same ages. Two-way ANOVA revealed significant interactions between Mme deficiency and ages on N3pE levels in soluble (F_(2,22) = 14.612; P < 0.001) and in the detergent-insoluble/formic acid–extractable (F_(2,22) = 1.193; P < 0.05) fractions. (D) Levels of Aβ1-40, Aβ1-42, Aβ3pE-40, and Aβ3pE-42 in soluble (TBS-extractable) and insoluble (GuHCl-extractable) fractions extracted from the brains of 24-mo-old female Mme^+/+APP-Tg and female Mme^−/−APP-Tg mice were determined using sandwich ELISA. Percentages of Aβ1-x and Aβ3pE-x to total Aβ (sum of Aβs from both the soluble and insoluble fractions) and ratios of Aβ3pE-x to Aβ1-x (sum of both Aβx-40 and Aβx-42) in soluble and insoluble fractions are shown in the right panels. Each column with a bar represents the mean ± SEM of seven mice. Significant differences between two groups were determined using a t test or a Mann–Whitney U test (*P < 0.05, **P < 0.005, and ***P < 0.001).

Figure S6.. Western blot analysis of extracellularly soluble and detergent-insoluble/formic acid–extractable fractions.

(A, B, C) Blots analyzed for the amounts of Aβ variants in the brains of APP-Tg mice at 24 (A), 18 (B), and 12 mo (C) of age are displayed. Samples from different individuals and synthetic Aβ were used for each blot. APP, +: APP-Tg mice; APP, −: wild-type mice

Figure 5.. Association of in vitro and in vivo radiolabeling of amyloid with [¹¹C]PiB and Aβ3pE-42.

(A) Confocal fluorescence microscopic images of amyloid plaques in 24-mo-old APP-Tg mice doubly stained with PiB/N1D (top 3 panels) and PiB/N3pE (bottom 3 panels). Scale bar, 50 μm. (B) Brain sections from 24-mo-old Mme^+/+APP-Tg and Mme^−/−APP-Tg mice were subjected to autoradiography with [¹¹C]PiB (left panel), and thereafter immunostained with polyclonal anti-Aβ3pE antibody (right panel). Colocalization of radiolabeling with Aβ3pE deposition is shown in the lower panels. Scale bar, 1.0 mm. (C) Intensities of [¹¹C]PiB signals (normalized by the intensity of non-specific cerebellar labeling) in the neocortex and hippocampus of 24-mo-old APP-Tg were significantly elevated and inversely correlated with the Mme gene dose. Open symbols show individual values obtained by the in vitro autoradiography of brain sections. A solid bar represents the mean value in each group. The following genotypes were tested: Mme^+/+APP-Tg (10 females), Mme^+/−APP-Tg (10 females), and Mme^−/−APP-Tg (6 females). (D) Longitudinal changes of in vivo [¹¹C]PiB retentions estimated as non-displaceable binding potential (BP_ND) in the neocortex (left) and hippocampus (right) of Mme^+/+APP-Tg (open circles; n = 4) and Mme^−/−APP-Tg (closed circles; n = 3) mice at 9 (top), 13 (middle), and 20 mo of age. Data from the same individuals are connected by solid lines. There were significant main effects of age (F_(2,4) = 70.9 and 118.9; P < 0.0001 in the neocortex and hippocampus, respectively) and genotype (F_(1,5) = 18.7; P < 0.01; and F_(1,5) = 15.9; P < 0.05 in the neocortex and hippocampus, respectively) detected by repeated-measures two-way ANOVA.

Figure S7.. Colocalization of Aβ3pE with ApoE in the cores of amyloid plaques.

(A) Brain sections from 24-mo-old Mme^+/+APP-Tg mice were immunostained with anti-ApoE (left), and N1D or N3pE antibody (middle), and the images were merged (right). Colocalization of Aβ3pE-x, but not Aβ1-x, with ApoE, which is known to be involved in Aβ aggregation, in the cores of amyloid plaques is shown in the lower right panel. Scale bar, 20 μm. (B) Intensities of ApoE-positive signals in the neocortices of 24-mo-old APP-Tg mice were significantly elevated by the Mme deficiency. Each column with a bar represents the mean ± SEM of 9–10 female mice. An asterisk shows a significant difference with a P-value less than 0.05. (C) Levels of ApoE and α1-antichymotrypsin in the soluble fraction (the interstitial fluid + cytosol) of Mme^+/+APP-Tg and Mme^−/−APP-Tg mice at different ages (3 and 18 mo) were determined by Western blot analysis. Each column represents the mean ± SEM of seven mice. An asterisk shows a significant difference at P < 0.05.

Figure 6.. Generation of App^NL-(ΔDA)-F and App^{NL(-ΔDA)-Q-F} KI mice and their Aβ pathology.

(A) Amino acid sequences of humanized Aβ with mutations in several lines of App KI mice. In this study, we generated two additional lines of App KI mice: in the App^NL-(ΔDA)-F KI mice, the first two amino acids of Aβ (DA) are deleted. In the App^{NL-(ΔDA)-Q-F} KI mice, the third amino acid of Aβ (E) in App^NL-(ΔDA)-F is converted to Q. These experimental designs were made based on our previous observation, showing that cortical neurons expressing APP cDNAs with the NL-(ΔDA)-Q mutation, but not with NL or NL(ΔDA) mutations, produced Aβ3pE-40/42 (Shirotani et al, 2002). (B) Immunohistochemical staining of the brains of 12-mo-old Mme^+/+App^NL-F and Mme^−/−App^NL-F KI mice using anti-Aβ antibodies, N1D and N3pE. Scale bar, 500 μm. Amyloid load is expressed as a fluorescence intensity in the measured area or a percent of the measured area. Each column with a bar represents the mean ± SEM of 3 female and 3 male mice. An asterisk shows a significant difference with a P-value less than 0.05. (C) Immunohistochemical staining of the brains of 18-mo-old App^NL-(ΔD)-F and App^{NL-(ΔDA)-Q-F} KI mice with/without Mme using anti-Aβ antibodies, C42 and N3pE. Scale bar, 500 μm. (D) Levels of Aβx-40, Aβx-42, Aβ3pE-40, and Aβ3pE-42 in soluble (TBS-extractable) and insoluble (GuHCl-extractable) fractions extracted from the brains of several lines of 18-mo-old App KI mice were determined by sandwich ELISA. Each column with a bar represents the mean ± SEM of three to four mice. TS-Aβ40/42: two-way ANOVA (genotype and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(4, 22)} = 33.801; P < 0.001). GuHCl-Aβ40/42: two-way ANOVA (genotype and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(4, 22)} = 34.534; P < 0.001). TS-Aβ3pE40/42: two-way ANOVA (genotype and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(4, 22)} = 61.273; P < 0.001). GuHCl-Aβ3pE40/42: two-way ANOVA (genotype and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(4, 22)} = 46.041; P < 0.001). Levels of Aβx-40(42) or Aβ3pE-40(42) in App^NL-F were significantly different from other genotypes in each fraction (*P < 0.001).

Figure S8.. Aβ3pE-x deposition in the brains of App KI mice at 2 mo of age.

Biochemical quantification of total Aβ and Aβ3pE-x in mouse brains. Aβx-40, Aβx-42, Aβ3pE-40, and Aβ3pE-42 in the TS and GuHCl fractions of cortical tissue from 2-mo-old female mice were quantified by sandwich ELISA. Data represent the mean ± SEM (n = 3). N.D., not detectable. TS fraction, Aβx-40: one-way ANOVA showed a significant main effect of the genotype (F_{(4, 14)} = 691.276; P < 0.001). Aβ levels of App^NL-F were significantly different from other genotypes (*P < 0.001). TS fraction, Aβx-42: one-way ANOVA showed a significant main effect of the genotype (F_{(4, 14)} = 188.082; P < 0.001). Aβ levels of App^NL-F were significantly different from other genotypes (*P < 0.001). GuHCl fraction, Aβx-40: one-way ANOVA showed a significant main effect of the genotype (F_{(4, 14)} = 257.257; P < 0.001). Aβ levels of App^NL-F were significantly different from WT and App^NL (†P < 0.001). GuHCl fraction, Aβx-42: one-way ANOVA showed a significant main effect of the genotype (F_{(4, 14)} = 106.529; P < 0.001). Aβ levels of App^NL-F were significantly different from other genotypes (*P < 0.001). Levels of Aβ3pE-x in both TS and GuHCl fractions were not statistically analyzed.

Figure S9.. Aβ3pE-x deposition in the brains of App^NL-F KI mice at 15 and 24 mo of age.

(A) Aβ1-x and Aβ3pE-x depositions were detected by immunostaining of brains from 15- and 24-mo-old App^NL-F KI mice using anti-Aβ1-x antibody (N1D) and anti-Aβ3pE-x antibody (N3pE). Scale bars, 500 μm. (B) Biochemical quantification of total Aβ and Aβ3pE-x in mouse brains. Aβx-40, Aβx-42, Aβ3pE-40, and Aβ3pE-42 in the TS and GuHCl fractions of cerebral cortices from 15- and 24-mo-old mice were quantified by sandwich ELISA. Data represent the mean ± SEM. The numbers of analyzed animals were as follows: 1 female and 2 male WT, 1 female and 2 male App^NL KI, and 2 female and 2 male App^NL-F KI mice. Note that the y-axis is on a log scale. N.D., not detectable. TS fraction, Aβx-40/42: three-way ANOVA (genotype, age, and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(2, 30)} = 168.102; P < 0.001). GuHCl fraction, Aβx-40/42: three-way ANOVA (genotype, age, and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(2, 30)} = 79.331; P < 0.001). TS fraction, Aβ3pE-40/42: three-way ANOVA (genotype, age, and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(2, 30)} = 108.065; P < 0.001). GuHCl fraction, Aβ3pE-40/42: three-way ANOVA (genotype, age, and amino-terminal of Aβ) showed a significant main effect of the genotype (F_{(2, 30)} = 44.375; P < 0.001). Aβ levels in App^NL-F were significantly different from other genotypes in each fraction or each age (*P < 0.001), except Aβ3pE-40 level in each fraction of App^NL-F at an age of 15 mo. (C) Ratio of Aβ3pE-x to Aβx-40/42 (sum of Aβx-40 and Aβx-42) in the TS and GuHCl fractions. Each column with a bar represents the mean ± SEM of four mice. Significant differences between two groups were determined using the Mann–Whitney U test (*P < 0.05).

Figure S10.. Possible pathway(s) for generation of Aβ3pE-42 from Aβ1-42.

DPP, dipeptidyl peptidase 4; APA, aminopeptidase A (acidic amino acid); APN, aminopeptidase N (neutral amino acid); QPCT, glutaminyl-peptide cyclotransferase; QPCTL, glutaminyl-peptide cyclotransferase-like. The N_3E is the only final precursor for N_3pE.

Figure 7.. Changes in expression levels of exopeptidases and glutaminyl-peptide cyclotransferases involved in Aβ3pE-x generation by Mme deficiency.

(A) Aβ1-40–degrading activities by immunopurified APA, APN, and DPP4 from mouse brains. Aβ1-40 (2 mg) was incubated with each peptidase at 37°C for 5 h, and the amount of intact Aβ remaining was quantified using an HPLC system as described in the Materials and Methods section. Each column represents the mean ± SD of three assays. (B) Protein contents of APA, APN, and DPP4 in the brain membrane fractions of Mme^+/+APP-Tg and Mme^−/−APP-Tg mice at different ages (3 and 18 mo old) were determined by Western blot analysis with a specific antibody against each peptidase. Each column represents the mean ± SEM of seven mice. An asterisk and a hash show a significant difference at P < 0.05. (A, B, C) Specific activities for Aβ1-40 degradation by each peptidase were calculated based on the data from (A, B). (D) Levels of glutaminyl-peptide cyclotransferase (Qpct) and glutaminyl-peptide cyclotransferase-like (Qpctl) mRNAs in the cerebral cortices of Mme^+/+APP-Tg and Mme^−/−APP-Tg mice at 18 mo of age were determined by qRT-PCR. Each column represents the mean ± SEM of seven mice. Statistical analysis was carried out by a t test with ΔCt values. Asterisks show a significant difference at P < 0.05. (E) Protein contents of TRHDE in the brain membrane fractions of Mme^+/+APP-Tg and Mme^−/−APP-Tg mice at different ages (3 and 18 mo old) were determined by Western blot analysis with a specific antibody. Each column represents the mean ± SEM of seven mice. An asterisk shows a significant difference at P < 0.05.