cAMP response element-binding protein is a primary hub of activity-driven neuronal gene expression

Abstract

Long-lasting forms of neuronal plasticity require de novo gene expression, but relatively little is known about the events that occur genome-wide in response to activity in a neuronal network. Here, we unveil the gene expression programs initiated in mouse hippocampal neurons in response to different stimuli and explore the contribution of four prominent plasticity-related transcription factors (CREB, SRF, EGR1, and FOS) to these programs. Our study provides a comprehensive view of the intricate genetic networks and interactions elicited by neuronal stimulation identifying hundreds of novel downstream targets, including novel stimulus-associated miRNAs and candidate genes that may be differentially regulated at the exon/promoter level. Our analyses indicate that these four transcription factors impinge on similar biological processes through primarily non-overlapping gene-expression programs. Meta-analysis of the datasets generated in our study and comparison with publicly available transcriptomics data revealed the individual and collective contribution of these transcription factors to different activity-driven genetic programs. In addition, both gain- and loss-of-function experiments support a pivotal role for CREB in membrane-to-nucleus signal transduction in neurons. Our data provide a novel resource for researchers wanting to explore the genetic pathways associated with activity-regulated neuronal functions.

Figure 1.

Comparison of stimulus-driven profiles. A, The heat map illustrates the differential expression of hundreds of genes during neuronal stimulation with different compounds. We stimulated the cultures with bic, fsk, and BDNF for 1, 18, and 48 h, respectively, based on previous literature and on preliminary qRT-PCR analyses (data not shown). B, Panels illustrate the distribution of gene expression changes induced by different treatments. Genes are separately ordered for upregulation and downregulation from most to least changed based on their absolute fold change, and each gene is plotted as a separate entity on the x-axis with the corresponding fold change represented on the y-axis. Upregulations dominated in the response to bic and fsk, whereas in the case of BDNF, downregulations and upregulations were balanced. The total number of genes affected is also indicated in the graphs. C, Venn diagram showing the number of genes in the intersection between the different gene lists. The numbers in parentheses show the percentage of unique genes per condition. D, Bar charts representing the specific percentage of overlapping genes between each pair of conditions, specifying whether common genes change in the same (“Coherent”) or opposite (“Reversed”) directions. E, The correlation heat map shows a significant correlation between bic- and fsk-dependent gene expression programs (p ≤ 0.001). F, Activity-regulated miRNAs. Note that both BDNF and bic cause a number of miRNA downregulations. # indicates that the specified miRNA belongs to the cluster of miRNAs located on chromosome 12.

Figure 2.

Infection of hippocampal cultures by caPRTFs-expressing LV. A, Scheme of lentiviral backbone, cloning sites, and caPRTF constructs. LTR, Long-termination repeats; SynP, synapsin promoter; WPRE, woodchunk hepatitis virus post-transcriptional regulatory element. B, The different caPRTFs activate the corresponding luciferase reporter plasmids in HEK293 cells. The number of reporter sites in each plasmid is indicated. **p ≤ 0.01, ***p ≤ 0.001, t test (n = 7–10 per condition). C, Immunocytochemistry of hippocampal neurons infected with the different caPRTF-expressing and control LV (10DIV/6DINF) using anti-GFP antibody. GFP expression was detectable at 3DINF by direct fluorescence and became progressively stronger, reaching a plateau by 6DINF (results not shown). D, Hippocampal neurons infected with VP16-only lentiviral particles were stained for GFP, NeuN, and GFAP. Green fluorescence shows the colocalization of EGFP with the neuronal marker NeuN and no colocalization with the astrocytic marker GFAP. The same result was obtained with all the caPRTF-expressing LVs (results not shown). E, qRT-PCR demonstrates comparable VP16/GFP expression ratios for all caPRTF viruses with the exception of FOS, which is expressed slightly less efficiently (n = 6 per condition). ***p < 0.01, one-way ANOVA (F_(5,30) = 25.692) plus Tukey's post hoc test in the comparison with GFP-only control; ^&p < 0.01, Tukey's post hoc test in the comparison with VP16-only control. F, Western blot with samples from infected cultured hippocampal neurons and transfected HEK293 cultures. Bars on the left indicate the molecular weight in kilodaltons. Asterisks and arrowheads label the transgenic bands. G, Anti-VP16 immunocytochemistry demonstrates the nuclear expression of chimeric TFs, as exemplified by VP16–CREB. Colocalized pixels are shown in white (right). Bars represent average ± SEM. Scale bar, 10 μm.

Figure 3.

Overview of the CREB, SRF, EGR1, and FOS regulons. A, Hierarchical cluster of PRTF-dependent gene expression changes. B, The distribution of all PRTF-responsive genes as described for Figure 1B. Bars below the distribution plots refer to the percentage of upregulations and downregulations considering only the top 100 genes per condition. Note that, because caEGR1 only controls 85 genes, the analysis is limited to this number. C, Some known and novel candidates were selected for validation on an independent set of samples by qRT-PCR. *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, t test (n = 3 per condition). Error bars represent average ± SEM.

Figure 4.

Probeset-level analysis of caPRTF-dependent gene expression. A, Increased signal for the specific probeset mapping into the lentiviral construct. EGR1 is not shown because the DBD of this TF is represented by only 2 of 13 probes in a single probe set, precluding this type of analysis. B, BDNF is regulated by CREB preferentially via its promoter I (Pr. I, Prom I), whereas bic and fsk can also regulate its expression through promoter IV (Pr. IV, Prom IV). Left, Yellow boxes represent the exon structure of the gene provided by Ensembl. The location of promoters I and IV, as well as CRE sites, are indicated. Each measurement on the array is separated in the graph by a gray vertical line. Blue lines point to the corresponding mapping. The arrow above indicates the sense of transcription. Right, qRT-PCR validation of differential promoter usage by CREB. *p ≤ 0.05, t test (n = 3 per condition) C, Stimulation with fsk and caCREB expression causes a specific upregulation of ICER transcripts (indicated as a gray box). The location of internal promoter CRE sites is also indicated. The regulation of ICER by caCREB was validated by qRT-PCR with ICER-specific primers in independent samples (n = 3 per condition) and with an ICER-promoter luciferase reporter in cotransfected HEK293 cells (n = 6 per condition). ***p ≤ 0.001, t test. D, bic and fsk stimulations and caCREB expression cause the specific upregulation of the short isoform Homer1a (indicated as a gray box).

Figure 5.

Time course of caCREB-dependent gene expression. A, The heat map illustrates the differential expression of hundreds of genes during caCREB expression, both 3 and 6 d after lentiviral infection (Inf.). The top scheme illustrates the experimental design. B, Scatter plot of the fold change correlation between transcriptional changes induced by caCREB after 3 and 6 of infection. C, Box plot representation of average changes in the different set of caCREB regulated genes obtained by k-means clustering. On average, the expression of caCREB for 3 additional days caused a very modest increase of the changes (both upregulations and downregulations) already observed at 3 d of infection.

Figure 6.

Analysis of the CREB, SRF, EGR1, and FOS regulons. A, TF binding site prediction analysis based on the TRANSFAC database reveals a specific enrichment of the corresponding canonical TF binding site for each TF within upregulated genes. Matrices are grouped by TF (from top to bottom: CREB_02, CREB_Q4, CREBP1_Q2, CREB_Q2, CREB_01, CREBP1CJUN_01, CREBP1_01, ATF_01, ATF6_01, SRF_Q6, SRF_C,SRF_01, EGR3_01, EGR1_01, EGR2_01, NGFIC_01, AP1FJ_Q2, AP1_Q2, AP1_Q6. AP1_01, AP1_Q4, AP1_C). Downregulated genes do not show this enrichment. B, Genes found upregulated by caCREB and caSRF in our study are more likely to bind CREB and SRF, respectively, at their promoters according to a recent chromatin immunoprecipitation sequencing experiment by Kim et al. (2010). For caCREB, we present the average of overlap for the 3DINF and 6DINF gene profiles. “Others” refers to the other three caPRTFs, except caCREB or caSRF, respectively. C, The left heat map illustrates CREB-mediated upregulation of a number of miRNAs. A Fisher's exact test was used to calculate statistical significance of the enrichment of predicted targets within CREB-upregulated and -downregulated genes using the Miranda algorithm from microRNA.org (for details, see Materials and Methods). * indicates statistical significance based on an alternative database for miRNA target predictions (Webgestalt). D, Venn diagram illustrating the overlapping genes between any given pair of conditions. The numbers in parentheses indicate the percentage of unique genes per condition. E, The heat map of genes upregulated in at least one of the conditions show unique clusters of PRTF-induced genes (top), whereas PRTF-repressed genes are less segregated (bottom). F, The Mammalian Phenotype Ontology was used to explore the involvement of PRTF-responsive genes in disease. Enriched categories (p ≤ 0.01) were manually collapsed into more general terms to avoid redundancy (see Materials and Methods). This analysis shows a general implication of the TFs CREB, SRF, EGR1, and FOS in nervous system development and cognitive disorders.

Figure 7.

Contribution of PRTF-regulated gene expression to activity-dependent transcription. A, Percentages of common genes between the stimulation-driven and caPRTF-dependent gene profiles. B, Specific coverage of activity-driven gene expression profiles by each PRTF. C, Coverage plots illustrate the dominance of CREB-mediated transcription in fsk-dependent gene expression and the remarkable contribution of FOS to BDNF-dependent gene expression. To generate these plots, activity-upregulated genes were ordered by fold change, and the percentage of overlapping genes with each caPRTF-dependent gene list was calculated in a cumulative manner. The lines therefore represent the percentage of the activity-dependent gene expression program “covered” by each TF at any given fold change cutoff. D, Pairwise correlation analysis of stimulation- and PRTF-dependent gene expression further supports the role of CREB in fsk-mediated transcription, as well as the role of FOS in BDNF-mediated transcription. E, Meta-analysis of different stimulation profiles with PRTF-dependent gene expression programs reveals a dominant effect of CREB in neuronal activity-dependent transcription, closely paralleled by FOS. SRF and EGR1, in contrast, appear to be more specific. Normalized enrichment scores (NES) were calculated using GSEA. *p ≤ 0.05 after false discovery rate correction. F, A graphical summary of the main relationships between CREB, SRF, EGR1, and FOS and the different paradigms of activity-driven gene expression analyzed in this study. The line width represents the strength of the association found for the indicated interactions.

Figure 8.

Attenuation of fsk-dependent transcription by A-CREB. A, Luciferase reporter assay in HEK293 cells revealed the inhibitory effect of A-CREB expression on fsk-induced, CRE-dependent transcription. ^#p ≤ 0.001, virus × treatment effect, two-way ANOVA, F_(1,26) = 24.211; **p ≤ 0.01, ***p ≤ 0.001, t test. B, Lentiviral construct used for the expression of A-CREB in neurons. LTR, Long-termination repeats; SynP, synapsin promoter; WPRE, woodchunk hepatitis virus post-transcriptional regulatory element. C, Example of GFP/A-CREB-expressing cultured hippocampal neurons. D, Western blot showing A-CREB expression in infected neurons (10DIV, 6DINF). E, Distribution of gene expression changes induced by A-CREB expression under basal conditions (left) and during fsk stimulation (right). F, Hierarchical cluster of GFP/A-CREB DMSO/fsk differential gene expression. G, Scatter plot showing that A-CREB expression causes an attenuation of fsk-dependent changes. More than 70% of genes upregulated in the presence of fsk (right of the red dotted line) are below the diagonal, whereas >80% of genes downregulated in the presence of fsk (left of the red dotted line) are above the diagonal. H, k-means clustering of fsk-responsive genes revealed the existence of different profiles of fsk inducibility and A-CREB attenuation. The bold line indicates the average profile per cluster, and the dashed line indicates the basal level (GFP DMSO); AC, A-CREB. I, A-CREB attenuated genes overlap significantly with caCREB-upregulated genes. The 81 genes in this intersection (red line) are listed in Table 3. There is no gene in the intersection between A-CREB attenuated genes and caCREB-downregulated genes (data not shown). J, The percentage of CREB-responsive genes overlapping with A-CREB attenuated genes (clusters 3; for details, see Results) grows steadily as the stronger CREB-associated changes are considered. K, The genes in the intersection between cluster 3 and caCREB-upregulated genes show a positive correlation between caCREB- and fsk-induced changes that decays in the presence of A-CREB. L, Genes in the intersection between CREB-upregulated and A-CREB attenuated sets are likely to contain a CRE site in their promoter.