Erythropoietin enhances hippocampal long-term potentiation and memory

Abstract

Background: Erythropoietin (EPO) improves cognition of human subjects in the clinical setting by as yet unknown mechanisms. We developed a mouse model of robust cognitive improvement by EPO to obtain the first clues of how EPO influences cognition, and how it may act on hippocampal neurons to modulate plasticity.

Results: We show here that a 3-week treatment of young mice with EPO enhances long-term potentiation (LTP), a cellular correlate of learning processes in the CA1 region of the hippocampus. This treatment concomitantly alters short-term synaptic plasticity and synaptic transmission, shifting the balance of excitatory and inhibitory activity. These effects are accompanied by an improvement of hippocampus dependent memory, persisting for 3 weeks after termination of EPO injections, and are independent of changes in hematocrit. Networks of EPO-treated primary hippocampal neurons develop lower overall spiking activity but enhanced bursting in discrete neuronal assemblies. At the level of developing single neurons, EPO treatment reduces the typical increase in excitatory synaptic transmission without changing the number of synaptic boutons, consistent with prolonged functional silencing of synapses.

Conclusion: We conclude that EPO improves hippocampus dependent memory by modulating plasticity, synaptic connectivity and activity of memory-related neuronal networks. These mechanisms of action of EPO have to be further exploited for treating neuropsychiatric diseases.

Figure 1

Experimental design of the in vivo studies. The time line of behavioral testing and brain dissection is presented. EPO or placebo was injected every other day for 3 weeks (11 injections in total). Tests performed were elevated plus maze (EPM), open field (OF), hole board (HB), rota-rod (RR), and fear conditioning (FC), including training and testing 72 h later.

Figure 2

Effects of EPO on hippocampus dependent memory. Percentage of freezing as a readout of memory function in fear conditioning shows significant effects upon EPO treatment in the contextual memory (context) task at 1 week (a) and 3 weeks (b), but no longer at 4 weeks (c) after the last EPO injection. Percentage of freezing measured during training (baseline), exposition to the new context (pre-cue), and testing for cued memory (cue) is not different between the groups. No differences are seen in EPM (d), OF (e), HB (f), and RR (g). Mean ± S.E.M. N = 28 for experiment in (a) and N = 14 for all other experiments (b-g).

Figure 3

Neurophysiology of acute hippocampal slices: Extracellular recordings. (a-b) Input-output relation is not altered at Schaffer collateral-CA1 synapses in EPO-treated mice. (a) Sample recordings at 50% of maximal response (average of four traces) are shown for control and EPO-treated mice. (b) Input-output curve as a measure of baseline excitatory synaptic transmission: fEPSP slope, plotted against the stimulation strength, is not altered in EPO-treated mice compared to control (P = 0.3094). Inset: Half maximal stimulation strengths are not significantly different. (c-d) Paired-pulse facilitation is enhanced in EPO-treated mice. (c) Sample traces are presented. (d) Paired-pulse ratio (fEPSP slope for the second stimulus/fEPSP slope for the first stimulus) at inter-stimulus intervals of 25–150 ms is significantly greater in EPO-treated mice. (e-h) Increased LTP at Schaffer collateral CA1 synapses in EPO-treated mice. (e) Sample traces of responses are shown before and after high frequency stimulation (HFS; 3 × 100 Hz for 1 s each, 20 s interval). (f) Long-term potentiation elicited by HFS: Slopes of fEPSP are normalized to baseline and plotted against time. Time-point 0 represents application of HFS. (g) Magnitude of STP, determined as maximal responses within 1 min after HFS, is significantly greater in EPO-treated mice. (h) Magnitude of LTP, determined as responses between 50 and 60 min after HFS, is significantly greater in EPO-treated mice. (i-l) Increased STD at Schaffer collateral-CA1 synapses in EPO-treated mice. (i) Sample traces of responses are shown before and after low frequency stimulation (LFS; 1 Hz for 900 stimulations). (j) Long-term depression elicited by LFS: Slopes of fEPSP are normalized to baseline and plotted against time. Time 0 represents application of LFS. (k) Magnitude of STD, determined as maximal responses within 1 min after LFS, is significantly greater in EPO-treated mice. (l) Magnitude of LTD, determined as responses between 50 and 60 min after LFS, is not significantly changed in EPO-treated mice (P = 0.0869).

Figure 4

Neurophysiology of acute hippocampal slices: Intracellular recordings. (a-c) EPO enhances inhibitory transmission. (a) Representative recordings of spontaneous, pharmacologically isolated inhibitory postsynaptic currents (sIPSCs) from CA1 neurons. (b) Averaged amplitude of sIPSCs is not significantly altered in EPO-treated mice (N = 6 neurons/5 mice) compared to control (N = 4 neurons/4 mice; P = 0.0869). (c) Averaged frequency of sIPSCs is significantly enhanced in EPO-treated mice (N = 6 neurons/5 mice) compared to control (N = 4 neurons/4 mice). (d-f) EPO decreases excitatory transmission. (d) Representative recordings of spontaneous, pharmacologically isolated excitatory postsynaptic currents (sEPSCs) from CA1 neurons. (e) Averaged amplitude of sEPSCs is significantly decreased in EPO-treated mice (N = 4 neurons/4 mice) compared to control (N = 4 neurons/3 mice). (f) averaged frequency of sEPSCs is significantly decreased in EPO-treated mice (N = 4 neurons/4 mice) compared to control (N = 4 neurons/3 mice).

Figure 5

Multi-electrode array studies of primary hippocampal neurons. (a-b) Characterization of the cultures. (a) Immunocytochemical staining demonstrates maturation of cellular networks from day 10 to day 30. Propidium iodide staining of all nuclei (red), visualization of cell types by MAP-2 (mature neurons) or GFAP (astrocytes) staining (green), as well as merged pictures are presented (scale bar = 100 μm). (b) Cellular composition of networks remains stable over time and is not altered by EPO treatment (0.3 IU/ml every other day) from day 5 through 25 in culture (Mean ± S.E.M. of N = 3 independent cultures per time point). (c) Demonstration of primary hippocampal neurons grown on multi-electrode array dishes, containing 60 electrodes/dish. (d-e) Spontaneous electrical activity of primary hippocampal neuronal networks in culture is measured daily from week 3 through week 7. Group statistics of the multi-electrode array recordings over each week show significant dissociation over time of EPO versus control cultures. (d) Silencing group statistics reveal a global decrease of channels with low activity in control cultures that cannot be observed in EPO-treated cultures. (e) Bursting group statistics show that the percentage of strongly bursting channels increases in the EPO group after termination of treatment. Medians ± S.E.M. presented of N = 7 independent cultures. P values are given in the text.

Figure 6

Autaptic hippocampal neuronal cultures. (a-g) Whole-cell electrophysiological recordings from single hippocampal neurons treated with either EPO (0.3 IU/ml) or control (diluent only) on day 7 and measured from day 9–14. Results indicate a reduction in the amount of primed vesicles without altering efficiency of vesicle fusion and vesicle dynamics. Mean ± S.E.M. presented. N = 40–60. (h) Analysing the number of synaptic boutons upon immunocytochemical staining for synapsin1 revealed an almost identical increase of boutons over time in EPO-treated and control neurons. Performed at 40x. Cumulative distribution over days 9–14. N = 100–120.