A transcriptional constraint mechanism limits the homeostatic response to activity deprivation in mammalian neocortex

Abstract

Healthy neuronal networks rely on homeostatic plasticity to maintain stable firing rates despite changing synaptic drive. These mechanisms, however, can themselves be destabilizing if activated inappropriately or excessively. For example, prolonged activity deprivation can lead to rebound hyperactivity and seizures. While many forms of homeostasis have been described, whether and how the magnitude of homeostatic plasticity is constrained remains unknown. Here, we uncover negative regulation of cortical network homeostasis by the PARbZIP family of transcription factors. In cortical slice cultures made from knockout mice lacking all three of these factors, the network response to prolonged activity withdrawal measured with calcium imaging is much stronger, while baseline activity is unchanged. Whole-cell recordings reveal an exaggerated increase in the frequency of miniature excitatory synaptic currents reflecting enhanced upregulation of recurrent excitatory synaptic transmission. Genetic analyses reveal that two of the factors, Hlf and Tef, are critical for constraining plasticity and for preventing life-threatening seizures. These data indicate that transcriptional activation is not only required for many forms of homeostatic plasticity but is also involved in restraint of the response to activity deprivation.

Keywords: homeostatic plasticity; mouse; neocortex; neuron; neuroscience; synapse.

Figure 1.. RNA-sequencing identifies transcripts affected by activity deprivation including the PARbZIP family of transcription factors.

(A) Volcano plots of bulk RNA-seq from sorted fluorescently labeled pyramidal cells (left) and PV⁺ interneurons (right). Dashed lines indicate a fold change of 2 and adjusted p value of 0.05. Differential expression analysis revealed that TTX resulted in upregulation (513 in pyramidal, 1415 in PV⁺ interneurons) as well as downregulation (605 in pyramidal, 1127 in PV⁺ interneurons) of genes, among which Hlf and Tef were identified as upregulated with activity block in both excitatory and inhibitory neurons. Statistical analysis (Wald test followed by Benjamini-Hochberg correction) reveals that Hlf and Tef are significantly upregulated in both pyramidal cells and PV⁺ interneurons, while Dbp and Nfil3 are not significantly altered in either cell type. (B) Bar graphs displaying transcript per million (TPM) values of Hlf (left panel) and Tef (right panel) in pyramidal cells (left) and interneurons (right) in control and 5-day TTX treated slices. Bars are mean values +/- SEM, open symbols are individual experiments. (C). Quantitative real-time PCR analysis of Hlf and Tef expression in whole cortex lysates following a time course of activity deprivation (n = 3–4 slices per time point; error bars are SEM). Two-way ANOVA reveals significant differences between Hlf/Tef and RPL10 (p<0.05).

Figure 2.. Calcium imaging reveals exaggerated response to activity deprivation in Hlf^−/−/Dbp^−/−/Tef^−/− triple knockout (TKO) slices.

(A). A confocal image of GCaMP6f fluorescence during an upstate in wild-type (WT) control slice (top panel) and a standard deviation projection of the same field of view of calcium signal during 1 min of recording (bottom panel). Scale bar = 50 µm. ROIs were manually selected around active cells identified by high standard deviation values. (B, C) GCaMP6f fluorescence heat map of selected ROIs (each row is one cell) during 1 min of recording (top panels) also shown as overlapping traces (gray, bottom panels) and an average fluorescence trace (black, bottom panels) in WT (B) and TKO slices (C) from control (left) and TTX-treated conditions (right). Traces show absolute dF/F, heatmap scale is normalized for each cell so that the full intensity range corresponds to the range of dF/F. (D) Quantification of peak frequency in GCaMP6f fluorescence traces. N = 16 slices for WT Control, N = 13 WT TTX, N = 8 TKO Control, and N = 11 TKO TTX. Error bars indicate SEM. TTX treatment significantly increases peak frequency in WT slices with significant (p<0.0001) interaction between treatment and genotype. The increase is more dramatic in the TKO slices. Two-way ANOVA with Tukey’s correction for multiple comparisons to test statistical significance between conditions *p≤0.0001.

Figure 2—figure supplement 1.. Ca²⁺ activity in mutant slices is similarly exaggerated after 2 and 5 days of activity withdrawal.

(A) Quantification of peak frequency (from Figure 1D) normalized to control in WT and TKO slices after 2 days of activity deprivation. (B) Quantification of peak synchrony values in each of the conditions in (A). Open symbols are individual slice cultures, filled bars are mean ± SEM. Synchrony values in WT condition are close to 1 and do not show further increase in the TKO slides. (C) Quantification of peak frequency after 5 days of activity deprivation and traces from representative slices (D) of the genotypes in (C). Increasing TTX incubation time to 5 days of TTX does not change the TKO phenotype. Peak frequency increased in WT (from 0.06 ± 0.01 to 0.24 ± 0.02) and this response is exaggerated in the TKO (from 0.05 ± 0.005 to 0.47 ± 0.04; a 2.5-fold greater increase than in WT). As at 2 days, two-way ANOVA revealed significant main effects for TTX (p < 0.0001) and genotype (p < 0.0001) and a significant interaction between treatment and genotype (p < 0.0001) and post hoc test (Tukey) revealed a significant difference between WT TTX and TKO TTX (p < 0.0001), but no difference between WT and TKO control activity (p = 0.97). Also, as at 2 days, synchrony increased dramatically in the presence of TTX in both genotypes (to 0.96 and 0.93) but this was not significantly different and there was also no significant difference in the values at baseline in the two genotypes (0.54 and 0.58). N = 9 for WT control, N = 9 for WT TTX, N = 13 for TKO control, and N = 9 for TKO TTX. TKO, triple knockout; WT, wild-type.

Figure 2—figure supplement 2.. Ca²⁺ activity recovers to baseline levels following washout of TTX in both wild-type and mutant slices.

(A) Representative GCaMP6f fluorescence intensity over 1 min of recording in WT (left panels) and TKO slices (right panels) during control (top row), immediately after TTX washout (middle row) and after 2 days of recovery following TTX washout (bottom row). (B) Quantification of peak frequency in each of the conditions in (A). Open symbols are individual slice cultures, filled symbols are mean ± SEM. Two-way ANOVA revealed significant main effect for drug treatment (p < 0.0001) and genotype (p = 0.0009) and a significant interaction between treatment and genotype (p = 0.017). Although TTX incubation has a much stronger effect on spontaneous Ca²⁺ activity immediately after washout in mutant slices (p < 0.0001, post hoc Tukey test), the activity returns to baseline in both genotypes (p = 0.99, post hoc Tukey test). N = 5 for WT age-matched control, N = 3 for TKO age-matched control, N = 11 for WT TTX, N = 11 for TKO TTX, N = 5 for WT recovery, and N = 4 for TTX recovery. TKO, triple knockout; WT, wild-type.

Figure 3.. Frequency but not amplitude of excitatory synaptic currents is disproportionally upregulated in TTX-treated TKO slices.

(A) Representative traces of mEPSC recordings from WT control (black), WT TTX-treated (red), TKO control (gray), and TKO TTX-treated (blue) slices. Right panel, average mEPSC waveforms for the same conditions. Both the frequency and the amplitude is increased in TTX-treated slices; however, the increase in frequency is more dramatic in TKO slices. (B) Quantification of mEPSC frequency for each condition. Colored bars with error bars are mean ± SEM, open circles are individual cells; N = 24 for WT control, N = 29 for WT TTX, N = 18 for TKO control, and N = 24 for TKO TTX. Two-way ANOVA revealed significant main effect of TTX treatment (p < 0.0001), genotype alone (p=0.030) and interaction between treatment and genotype (p = 0.041). Post hoc Tukey test revealed enhanced effect of TTX on mEPSC frequency in TKO cells compared to WT (p = 0.009, **). (C) Cumulative probability histogram for mEPSC inter-event intervals in each condition. (D) Cumulative probability histogram for mEPSC amplitudes in each condition. (E) mEPSC amplitudes for each condition. Two-way ANOVA revealed significant main effect for drug treatment (p < 0.0001) but not genotype (p = 0.74) or interaction between treatment and genotype (p = 0.55). TTX treatment enhanced mEPSC amplitude in both WT (p = 0.012, Tukey post hoc test, *) and TKO (p = 0.0035, Tukey post hoc test, **) to the same extent (p = 0.89, WT TTX compared to TKO TTX, Tukey post hoc test, N.S.). TKO, triple knockout; WT, wild-type.

Figure 4.. Inhibitory synaptic currents are not affected by the Hlf^−/−/Dbp^−/−/Tef^−/− mutation in the TTX condition.

(A) Representative traces of mIPSC recordings from WT control (black), WT TTX-treated (red), TKO control (gray), and TKO TTX-treated (blue) slices. Right panel, average mIPSC waveforms for the same conditions. TTX treatment results in a diminished effect on mIPSC frequency in TKO and does not further decrease the amplitude of mIPSCs in TKO slices. (B) Quantification of mIPSC frequency. Colored bars with error bars are mean ± SEM, open circles are individual cells. Two-way ANOVA revealed a significant main effect of TTX treatment (p < 0.0001) but not genotype (p = 0.54). There was no significant interaction between treatment and genotype (p = 0.40), N = 28 for WT control, N = 37 for WT TTX, N = 23 for TKO control, and N = 20 for TKO TTX. TTX treatment decreased mIPSC frequency in WT (p = 0.0007, post hoc Tukey test) but not in TKO cells (p = 0.14, post hoc Tukey test). mIPSC frequency in TTX-treated cells is not different in TKO slices compared to WT (p = 0.72). The normalized change in frequency (TTX normalized to Control) was 0.55 in WT and 0.70 in TKO. We performed a power analysis that revealed that for the observed effect size and variance a sample of 68 neurons per condition would be required for significance. In (B), (C), and (E), cumulative probability histogram for mIPSC inter-event intervals in each condition. (D) Cumulative probability histogram for mIPSC amplitudes in each condition. (E) Quantification of mIPSC amplitudes for the same conditions as in (B). Two-way ANOVA revealed significant main effect of TTX (p = 0.002), and genotype (p = 0.0067), and a significant interaction between treatment and genotype (p = 0.005). TTX treatment decreased mIPSC amplitude in WT (p < 0.0001, Tukey post hoc test, ***), but not in TKO cells (p = 0.997, Tukey post hoc test, N.S.) presumably due to significantly lower baseline mIPSC amplitude in TKO slices compared to WT (p = 0008, post hoc Tukey test, ***). TKO, triple knockout; WT, wild-type.

Figure 5.. The effects of TTX on intrinsic excitability are not altered in TKO pyramidal neurons.

(A) Comparisons of frequency-current relationships for layer five pyramidal neurons in control (black, closed circles) and TTX-treated (red, closed circles) WT slices, and in control (gray, open circles), and TTX-treated (blue, open circles) TKO slices, N = 27 cells for WT TTX, N = 16 for WT control, N = 8 for TKO control, and N = 17 for TKO TTX; error bars are SEM. Two-day TTX treatment increases intrinsic excitability in both WT and TKO slice cultures to a similar extent. A three-way mixed ANOVA with between subjects factors of treatment and genotype, and a within subjects factor of current level, revealed significant main effects for TTX treatment (F(1,60) = 18.1, p = 7.3e−05) and current level (F(11,660) = 2.3e−190) but not for genotype (F(1,60) = 0.06, p = 0.94). There was a significant interaction between treatment and current level (p = 0.06) but not for interactions of genotype with current level (p = 0.93) or with both current level and treatment (p = 0.99). (B) Example traces of a train of action potentials from a pyramidal neuron in response to a 175 pA 0.5 s depolarizing current injection in control (left), TTX-treated (right), WT (top), or TKO (bottom) slices. TKO, triple knockout; WT, wild-type.

Figure 6.. Presence of one allele of Hlf or Tef largely restores the WT response to activity deprivation.

Violin plots show the distribution of peak frequencies measured from TTX-treated (upper, darker colors, filled symbols) and control (lower, lighter colors, open symbols) slice cultures made from animals carrying 0, 1, 2, or 4 alleles of the PARbZIP TFs Hlf and Tef. Data are those used in Table 1 with the X-axis corresponding to models 6 (TTX) and 12 (Control). Horizontal positions of individual data points are jittered to prevent overplotting. Horizontal lines at top indicate results of post hoc t tests between levels for the TTX data with Tukey correction for multiple comparisons. *adj. p < 0.05, **adj. p < 0.01, ***adj. p < 0.001, N.S. – not significant, adj. p > 0.05. No post hoc testing was performed for the Control data since the fit of model 12 was not significant. WT, wild-type.

Figure 7.. Presence of one allele of a PARbZIP TF improves survival relative to TKO animals.

TKO mice have dramatically decreased survival (red line) compared to wild-type (WT) mice (black line). Presence of one copy of either Hlf (green line) or Tef (purple line) prevents premature death and the survival curves are not statistically different from WT, p = 0.12 and p = 0.56, respectively, Log-rank test with Bonferroni correction for multiple comparisons. DBP heterozygous mice (blue line) also have improved survival over TKO mice (p = 0.003) but are still statistically more likely to die prematurely than WT mice (p = 0.0003). N = 59 for DBP heterozygous, N = 96 for TKO, N = 36 for HLF heterozygous, N = 23 for WT, and N = 179 for TEF heterozygous. TKO, triple knockout.