On the mechanism of synaptic depression induced by CaMKIIN, an endogenous inhibitor of CaMKII

Abstract

Activity-dependent synaptic plasticity underlies, at least in part, learning and memory processes. NMDA receptor (NMDAR)-dependent long-term potentiation (LTP) is a major synaptic plasticity model. During LTP induction, Ca(2+)/calmodulin-dependent protein kinase II (CaMKII) is activated, autophosphorylated and persistently translocated to the postsynaptic density, where it binds to the NMDAR. If any of these steps is inhibited, LTP is disrupted. The endogenous CaMKII inhibitor proteins CaMKIINα,β are rapidly upregulated in specific brain regions after learning. We recently showed that transient application of peptides derived from CaMKIINα (CN peptides) persistently depresses synaptic strength and reverses LTP saturation, as it allows further LTP induction in previously saturated pathways. The treatment disrupts basal CaMKII-NMDAR interaction and decreases bound CaMKII fraction in spines. To unravel CaMKIIN function and to further understand CaMKII role in synaptic strength maintenance, here we more deeply investigated the mechanism of synaptic depression induced by CN peptides (CN-depression) in rat hippocampal slices. We showed that CN-depression does not require glutamatergic synaptic activity or Ca(2+) signaling, thus discarding unspecific triggering of activity-dependent long-term depression (LTD) in slices. Moreover, occlusion experiments revealed that CN-depression and NMDAR-LTD have different expression mechanisms. We showed that CN-depression does not involve complex metabolic pathways including protein synthesis or proteasome-mediated degradation. Remarkably, CN-depression cannot be resolved in neonate rats, for which CaMKII is mostly cytosolic and virtually absent at the postsynaptic densities. Overall, our results support a direct effect of CN peptides on synaptic CaMKII-NMDAR binding and suggest that CaMKIINα,β could be critical plasticity-related proteins that may operate as cell-wide homeostatic regulators preventing saturation of LTP mechanisms or may selectively erase LTP-induced traces in specific groups of synapses.

Figure 1. CN-induced depression is independent from synaptic activity.

A. Persistent synaptic depression induced by transient bath application of antCN27 (5 µM, 30 min) (% depression = 45±8% = mean ± SEM, n = 5). Data were normalized relative to baseline values before drug application. A slight and reversible reduction in presynaptic fiber volley (FV) is observed only during drug application. B. In a series of interleaved experiments, antCN27 was applied in regular ACSF or in the presence of kynurenic acid (Kyn; 10 mM), antagonist of AMPA/kainate receptors (n = 4, each). The inhibition of transmission by Kyn itself was completely reversible (8±2%, n = 4; similar to control experiments with ACSF solution changes (see Fig. 6); t-test, p = 0.28). C. Preincubation with the broad mGluR antagonist LY341495 (20 mM, n = 5) had no effect on CN-depression. D. Summary plot of depression for the different conditions (58±8%, for ACSF; 65±7%, for Kyn and 56±5%, for LY341495; one-way ANOVA, p = 0.62). Insets in A, B are representative field potential waveforms (averages of eight consecutive recordings) obtained at the times indicated by numbers; calibration: 0.4 mV, 5 ms. Norm.: Normalized. Error bars represent SEM in all figures. % depression: average for the last 10 min of recording and relative to baseline transmission, in all figures.

Figure 2. Ca²⁺ is not required for the induction of CN-depression.

A. Depression induced by brief applications of antCN27 (5 µM, 10 min) in interleaved experiments conducted in regular ACSF (“antCN27”) or in a solution with no Ca²⁺ added and containing 10 mM EGTA and 10 µM thapsigargin, Tg (“antCN27+0Ca+Tg”). Application of the last solution by itself reversibly inhibited transmission (“0Ca+Tg”). B. Summary plot of percent depression induced by antCN27 in regular ACSF (40±2%, n = 4), in 0-Ca⁺² solution without Tg (“0Ca”; 56±3%, n = 4; not shown in A) and in 0Ca+Tg solution (69±3%, n = 6). *, p = 0,02; **, p = 0.009; one-way ANOVA, post hoc Tukey HSD test. Data for application of 0Ca+Tg solution only is also shown (6±5%, n = 6. No significant difference with ACSF solution change experiments; p = 0.49, t-test). C. Blockade of NMDAR-dependent Ca²⁺ influx does not reproduce the effect of removing Ca⁺², as revealed by an independent set of interleaved experiments of brief applications of antCN27 alone or in the presence of 100 µM APV during the whole experiment (n = 4, each) D. Percent depression for the experiments shown in C (40±3%, for APV; 38±8%, for regular ACSF, p = 0.98, t-test).

Figure 3. Protein synthesis and degradation are not required for CN-depression.

A. Depression induced by antCN27 (5 µM, 30 min) in the presence of 20 µM anisomycin (Aniso) is comparable to that induced in regular ACSF. Aniso was applied at least 20 min before antCN27 and was maintained for 1 h after starting peptide treatment. B. Summary plot of percent depression for the experiments shown in A and for similar trials in the presence of the proteasome inhibitor MG 132 (10–20 µM) (52±6%, n = 9, for ACSF; 41±6%, n = 5, for Aniso; 42±8%, n = 4, for MG132; one-way ANOVA, p = 0.45).

Figure 4. Occlusion experiments for NMDAR-LTD and CN-depression (I).

A. LTD was induced by bath application of NMDA (20 µM, 5 min) and CN-depression was subsequently induced (5 µM, 30 min; n = 8). The data were realigned according to the time of second drug application. B. Similar experiments to A, with drugs applied in reverse order (n = 7). C. Percent depression caused by antCN27 applied after LTD (“2nd”; from A) is not significantly different to that observed in regular conditions (“1st”; from B) (57±4%, 1st; 24±14%, 2nd; measured 50 min after antCN27 removal; t-test, p = 0.06). D. The magnitude of LTD induced in regular conditions (“1st”; from A) and after CN-depression (“2nd”; from B), also shows no statistical difference (55±4%, 1st; 31±12%, 2nd; measured 45 min after NMDA removal; t-test, p = 0.07). To quantify depression induced by the second treatment, data were renormalized to the level of transmission before drug application.

Figure 5. Occlusion experiments for NMDAR-LTD and CN-depression (II).

Slices from the same animal were pre-incubated in interface chambers with NMDA/antCN27 (test slices) or underwent ACSF solution changes mimicking drug application and washout (control slices). Subsequently, simultaneous FP recording and application of the second treatment was conducted for pairs of test and control slices. A, B. Test slices were pre-incubated with NMDA (20 µM, 10 min). A. Left, superimposed FP traces obtained for increasing stimuli from a slice pre-incubated with NMDA and its control. Right, I-O curves. % LTD was estimated by comparing I-O slope (% LTD = 69±7%; n = 4). B. AntCN27 was simultaneously applied to test (after NMDA) and control slices in the recording chamber. AntCN27-induced depression (last 10 min of recordings) was comparable in both groups (25±14%, for NMDA-preincubated slices versus 44±11%, for control slices, n = 4, paired t-test, p = 0.16). C. Test slices were pre-incubated with antCN27 (5 µM, 30 min) and NMDA (20 µM, 5 min) was later applied to test and control slices in the recording chamber (% depression = 54±6%, after antCN27 versus 53±10%, for control slices: n = 5, t-test, p = 0.98).

Figure 6. Correlation of CN-depression with average CaMKII enrichment at synapses. A.

Superimposed to antCN27-induced depression in juvenile rats (42±4%, for P18–P25, n = 13) it is shown the average of control experiments conducted to evaluate signal stability during long-lasting experiments with solution recirculation. In controls (“ACSF”) no drug was applied but the solution was changed by fresh oxygenated ACSF to mimic the drug washout performed in test experiments (% rundown: 1±6%, n = 4) B. The same as in A, for neonate animals (P7–P10; % depression = 25±5%, n = 16). Note the rundown of synaptic potentials observed in younger rats (% rundown: 20±4, n = 7). If data is compared without correcting for rundown, depression is significantly lower in neonate rats (filled symbols in A, B; t-test, p = 0.008). C. Summary plot of percent decrease in transmission after antCN27 treatment (last 10 min) divided by the mean spontaneous decay measured at similar time in control experiments (**: p = 8×10⁻⁵, t-test). Data from 10 neonate and 11 juvenile rats.