Diffusible, nonfibrillar ligands derived from Aβ_1–42 are potent central nervous system neurotoxins

Preparation and Characterization of ADDLs.

Unless stated otherwise, ADDL solutions were prepared by incubating Aβ_1–42 (see ref. 30 for synthesis) for 24 hr with clusterin (as described in ref. 20). Solutions were centrifuged (14,000 × g for 10 min), and the supernatant was used for all assays. ADDLs also were prepared without clusterin in two ways: (i) Aβ_1–42 was brought to 100 μM in cold F12 medium (Life Technologies, Gaithersburg, MD), the solution vortexed, incubated at 4–8°C for 24 hr, and centrifuged as above; and (ii) Aβ_1–42 was brought to 50 nM in 37°C brain slice culture medium (see below) for 24 hr and used directly.

Mouse Brain Slice Culture and Assay for Viability.

Brain slices from strain (B6 × 129)F₂/J and strain JR 2385 (The Jackson Laboratories) were cultured as described (34), except growth medium was DMEM, 10% fetal calf serum, and antibiotic/antimycotic (all from Life Technologies), and horizontal slices of 200 μm were used. After overnight culture, medium was changed to defined medium (DMEM, N2 supplements antibiotic/antimycotic) with or without ADDLs. Viability was assessed after 24 hr by Live/Dead two-color fluorescence assay according to the manufacturer’s instructions (Molecular Probes). Slices were washed in Hanks’ balanced salt solution (HBSS) and exposed to 4μm calcein-AM and 2 μM ethidium homodimer in HBSS for 20 min at 37°C. Dye uptake was detected by using a Nikon Diaphot with filter cubes for fluorescein (for calcein in live cells) and Texas red (for ethidium homodimer in dead cells). Image analysis to quantify Live/Dead fluorescence was performed by using metamorph (Universal Imaging, Philadelphia).

Binding of ADDLs to Cell Surfaces.

Cell suspensions (2.5 × 10⁵ cells/500 μl PBS) were incubated with 5 μM ADDLs at 4°C for 1 hr. Cells were pelleted and resuspended in 500 μl ice-cold PBS and incubated with biotinylated 6E10 mAb (1 μl; Senetek) for 30 min. Cell were washed and then incubated in 500 μl PBS with fluorescein isothiocyanate-conjugated streptavidin (1:500; Amersham) for 30 min. Relative binding was quantified by FACScan (Becton Dickinson), multiplying mean fluorescence by total number of events, and subtracting values for background cell fluorescence in the presence of 6E10 and secondary antibody.

Preparation of Tryptic Peptides.

Confluent B103 cells (35) were removed by trypsinization (0.25%; Life Technologies) for ≈3 min. Trypsin-chymotrypsin inhibitor (Sigma; 0.5 mg/ml in Hanks’ buffered saline) was added, and cells were pelleted via centrifugation (500 × g, 5 min). Supernatant (≈12 ml) was concentrated to ≈1.0 ml by using a Centricon 3 filter (Amicon) and frozen after protein concentration was determined. For blocking experiments, sterile concentrated tryptic peptides (0.25 mg/ml) were added at the same time as ADDLs.

Electrophysiology.

Long-term potentiation (LTP) experiments were performed on P21 rat hippocampal slices, as described (36).

ADDLs: Aβ-Derived Neurotoxins That Are Soluble and Fibril-Free.

Although the toxic form of Aβ putatively is fibrillar (21, 22), neurotoxins that do not behave as sedimentable fibrils will form when Aβ_1–42 is incubated with clusterin (20). When examined by AFM, these preparations were completely fibril-free, exclusively comprising small globular structures (AFM; Fig. 1, Right). Equivalent results were obtained by conventional electron microscopy (data not shown). In contrast, Aβ_1–42 that self-associated without clusterin under standard conditions (31) showed typical fibrillar structure (Fig. 1, Left). The fibril-free Aβ derivatives will be referred to as ADDLs.

As done previously for fibrils (31), size characterization of ADDLs by AFM section analysis indicated that the predominant species were globules ≈4.8–5.7 nm along the z-axis. Comparison with small globular proteins (Aβ_1–40 monomer, aprotinin, basic fibroblast growth factor, carbonic anhydrase) suggested that ADDLs had mass between 17 and 42 kDa.

ADDLs of this mass would be too small to contain clusterin (M_r 80,000), indicating a chaperone-like function for clusterin (present at molarity 1:40 relative to Aβ). To verify this, however, conditions were sought in which ADDLs could form without clusterin. It was found that ADDLs could form in clusterin-free Aβ solutions if incubation was at reduced temperature (4–8°C). Cold-induced ADDLs were indistinguishable from those chaperoned by clusterin. In addition, ADDLs could form in clusterin-free tissue culture medium held at 37°C if Aβ was very dilute (50 nM), consistent with a potential to form physiologically. Morphologically, all ADDL solutions were stable at least 24 hr.

The fibril-free nature of ADDLs established by AFM was verified by nondenaturing gel electrophoresis. Nondenaturing gels showed ADDLs were oligomeric (Fig. 1, Inset), with the predominant species at 27 kDa and a minor species at 17 kDa. Western blot analysis of ADDL preparations resolved by SDS/PAGE showed similar bands at 22 and 17 kDa (Fig. 1, lane W). The presence of similar molecular weight Aβ species in nondenaturing and SDS gels indicates the oligomeric nature of ADDLs was not detergent-induced. Silver-stained SDS gels (Fig. 1, lanes 1–4) showed only the larger, more abundant ADDL oligomer, which was present whether ADDLs were clusterin- or cold-induced (lanes 1 and 2, respectively; lane 1 also shows the 40-kDa clusterin monomer). Monomeric Aβ seen in these SDS gels was not eliminated by prior Centricon 10 fractionation. Centricon retentate (lane 3) was indistinguishable from unfractionated ADDLs (lane 2), despite the ability of monomer to pass through the 10-kDa pore (eluate, lane 4). This result would be expected if the ADDLs were only partially detergent-stable.

Cell Death in Organotypic Mouse Brain Slice Cultures.

ADDL toxicity was tested in organotypic mouse brain slice cultures, which provided a physiologically relevant model for mature CNS. Whether induced by clusterin (Fig. 2), by low temperature, or by low Aβ concentration (data not shown), ADDLs were potent neurotoxins. To obtain high levels of viability in controls (below), cultures were supported by a filter at the medium–atmosphere interface. ADDLs thus had to pass through support filters to reach the cultures, showing a diffusible nature consistent with their small size.

Cell death, as shown by “false yellow staining” (Fig. 2A), was almost completely confined to the stratum pyramidale (CA3–CA4) and stratum granulosum (DG), suggesting strongly that principal neurons of the hippocampus (pyramidal and granule cells, respectively) were targets of ADDL-induced toxicity. Loss of other cell types cannot as yet be ruled out. Neurons but not astrocytes, however, were killed in dissociated hippocampal cell cultures (37) by 24-hr ADDL exposure (data not shown), consistent with the organotypic culture results. Organotypic cultures treated with conventional aggregated preparations of 20 μM Aβ had control-level cell death (Fig. 2 B and C), as expected from the nondiffusible nature of fibrils. Cell death in slices typically was less than 5% in controls with unsupplemented medium (Fig. 2D) or with clusterin (data not shown).

ADDLs Are Toxic at Nanomolar Doses.

ADDLs were diluted logarithmically to estimate their potency in evoking cell death (Fig. 2D). Fig 2D Inset illustrates null and maximal cell death responses. Image analysis was used to quantify dead cell and live cell staining in fields containing the DG/CA3 areas. Even after 1,000-fold dilution (5 nM Aβ), ADDL-evoked cell death was >20%, greater than half the maximum. This high potency, coupled with diffusibility demonstrated above, makes ADDL toxicity especially pernicious.

ADDLs Bind to Particular Cell Surface Proteins.

Toxin receptors recently have been identified for conventionally prepared fibrillar Aβ (38, 39). Because neuronal death at low ADDL doses suggested possible involvement of signaling mechanisms, experiments were undertaken to determine if specific cell surface binding sites existed for ADDLs. Fig. 3 shows FACScan analysis of ADDL immunoreactivity in suspensions of the B103 CNS neuronal cell line (35) and of dissociated hippocampal cells. For B103 cells, addition of ADDLs caused a large increase in cell-associated fluorescence. Suspensions of hippocampal cells also bound ADDLs, but less well than B103 cells. Because hippocampal tissue was trypsinized (with only a 2-hr recovery) to obtain cells for analysis, the relatively low level of binding might be caused by toxin receptor proteolysis, although this has yet to be established. However, yeast cells, which present primarily a carbohydrate surface, showed no ADDL-dependent fluorescence. Even brief trypsinization of B103 cell surfaces inhibited subsequent ADDL binding by more than 90% (Fig. 3). ADDL binding sites thus are found in the particular molecular moieties removed from the membrane by trypsin.

Consistent with removal of binding sites by trypsin, it was found that cell-surface tryptic peptides released into the culture medium (0.25 mg/ml) inhibited ADDL binding by >90% (Fig. 3 Right). Controls exposed to BSA, even at 100 mg/ml, had no loss of binding. Tryptic peptides, if added after ADDLs were already attached to cells, did not lower fluorescence intensities; the peptides thus did not compromise quantitation of bound ADDLs. Besides blocking ADDL binding, the tryptic peptides also inhibited ADDL-evoked cell death (Fig. 3; 75% reduction in cell death, P < 0.002). Overall, the data show that ADDL binding sites comprise particular domains of cell surface proteins and that these domains, when solubilized by trypsin, provide neuroprotective, ADDL-neutralizing activity.

Fyn Kinase Knockout Protects Against ADDL Neurotoxicity.

The impact of ADDLs on brain slices was compared in isogenic fyn^−/− and fyn^+/+ animals. Fyn is up-regulated in AD-afflicted neurons (29) and belongs to the Src-family of protein tyrosine kinases, which are central to multiple cellular signals and responses (40). Fyn may be activated by conventional Aβ (41), and Fyn knockout mice have reduced apoptosis in developing hippocampus (42).

In hippocampal slices from Fyn knockout animals, ADDL-evoked cell death did not occur (Fig. 4 Upper Right). The amount of death in these slices was indistinguishable from controls (Fig. 4 Lower). Quantitatively, cell death with ADDLs present was five times greater in Fyn wild-type than in Fyn knockout slices. Analysis (ANOVA) with the Tukey multiple comparison gave a value of P < 0.001 for the ADDL Fyn wild-type data compared with all other conditions. Although loss of Fyn kinase clearly protected DG and CA3 hippocampal regions from cell death induced by ADDLs, the neuroprotective effect was selective; hippocampal cell death evoked by N-methyl-d-aspartate (NMDA) receptor agonists (43, 44) was unaffected (data not shown). Results establish that the mechanism through which ADDLs exerted their toxicity is blocked by knockout of Fyn protein tyrosine kinase.

ADDLs Disrupt LTP.

LTP is a classic paradigm for synaptic plasticity and a model for memory and learning, faculties that are selectively lost in early stage AD. Because of the importance of Fyn to LTP (42), experiments were done to examine the effects of ADDLs (made in the cold) on medial perforant path-granule cell LTP. In hippocampal slices from young adult rats, inhibition of LTP by ADDLs was clearly evident (Fig. 5). Hippocampal slices (n = 6) exposed to 500 nM ADDLs for 45 min prior showed no potentiation in the population spike 30 min after the tetanic stimulation (mean amplitude, 99 ± 7.6%). In contrast, LTP was readily induced in slices incubated with vehicle (n = 6), with an amplitude of 138 ± 8.1% for the last 10 min; this value is comparable to that previously demonstrated in this age group (36). Although LTP was absent in ADDL-treated slices, their cells were competent to generate action potentials and showed no signs of degeneration. Thus, in less than an hour, ADDLs disrupted LTP.