Interferons reshape the 3D conformation and accessibility of macrophage chromatin

Abstract

Engagement of macrophages in innate immune responses is directed by type I and type II interferons (IFN-I and IFN-γ, respectively). IFN triggers drastic changes in cellular transcriptomes, executed by JAK-STAT signal transduction and the transcriptional control of interferon-stimulated genes (ISG) by STAT transcription factors. Here, we study the immediate-early nuclear response to IFN-I and IFN-γ in murine macrophages. We show that the mechanism of gene control by both cytokines includes a rapid increase of DNA accessibility and rearrangement of the 3D chromatin contacts particularly between open chromatin of ISG loci. IFN-stimulated gene factor 3 (ISGF3), the major transcriptional regulator of ISG, controlled homeostatic and, most notably, induced-state DNA accessibility at a subset of ISG. Increases in DNA accessibility correlated with the appearance of activating histone marks at surrounding nucleosomes. Collectively our data emphasize changes in the three-dimensional nuclear space and epigenome as an important facet of transcriptional control by the IFN-induced JAK-STAT pathway.

Keywords: Cell biology; Epigenetics; Molecular biology; Molecular mechanism of gene regulation.

Graphical abstract

Figure 1

IFN treatment rearranges host cell genome 3D structure (A and B) Hi-C contact maps around the Gbp locus of untreated (upper middle) and A IFN-I treated (2h) or B IFN-γ treated (2h) (lower middle) primary murine bone marrow-derived macrophages (BMDM; merge of two replicates per condition). Upper and lower panel, PC1 values indicating compartments. (C and D) Ratio plots around the Gbp locus comparing contact maps of C IFN-I or D IFN-γ treated and untreated BMDM, generated using the flexible binning method Serpentine. Black vertical lines indicate the borders of the Gbp locus. Red regions indicate increased, blue regions decreased interaction after treatment with IFN. (E) Quantification of PC1 differences (40 kbp bins) at indicated ISG clusters in response to IFN-I or IFN-γ treatment (2h), as compared to control regions of the same sizes, located up- and downstream of the respective regions. Mean differences across all bins overlapping the respective regions are shown

Figure 2

IFN-I treatment reshapes chromatin-chromatin contacts in ISG clusters (A–I) Hi-C contact maps (merge of two replicates per condition, log1p scale) of untreated and IFN-I treated (2h) BMDM. Visualization of pattern detection with chromosight (loops between two loci are indicated as arcs). Color coding of arcs corresponds to Pearson correlation scores. Loops with a score >0.35 are shown (maximum size/ylim = 500 kbp). Lower panel, IRF9/STAT1 ChIP-seq tracks after IFN-I (1.5h) stimulation and gene annotations are shown to visualize ISGF3/GAF binding sites. Only ISG of the corresponding gene clusters are visualized

Figure 3

Effects of IFN-I and IFN-γ on loops within ISG clusters and with outside regions (A–D) Boxplots of inter- (one anchor in cluster region) and intra-cluster (both anchors in cluster region) loop scores for ISG loci in untreated (gray), IFN-I (2h, green) or IFN-γ (2h, purple) treated BMDM. (E) Heatmap summarizing the quantification of inter-/intra-cluster loop strength ratios. Ratios of median inter- and intra-cluster loop scores for each cluster untreated, IFN-I or IFN-γ treated BMDM are shown

Figure 4

Inducibility by interferons correlates with changes in A compartment strength (A) Scatterplot comparing log2-fold-changes (log2FC) in mRNA abundances from IFN-I (2h) and IFN-γ (2h) treated BMDM. Genes significantly up-regulated (log2FC ≥ 1, adjusted p value ≤ 0.05) in one, but not the other treatment (log2FC < 1) are colored in green (IFN-I) and purple (IFN-γ), respectively. (B) Differences in PC1 (as described in Figure 1E) after treatment with IFN-I or IFN-γ (2h) at gene loci, specifically induced by IFN-I or IFN-γ (2h) in RNA-seq. Mean values of PC1 differences for bins overlapping each gene region are plotted. For each gene, two control regions of the same size, respectively 1 Mb up- and downstream of the gene, are considered (p = 1.9 × 10⁻⁶ for IFN-I, p = 0.027 for IFN-γ, Wilcoxon rank-sum test for unpaired data). (C) Similar to B, for gene groups that show extreme (log2FC > 5) or moderate (log2FC 1-5) induction in RNA-seq in response to the respective IFN stimuli (IFN-I or IFN-γ, 2h; p = 1,0 × 10⁻⁷ for IFN-I; p = 0.0041 for IFN-γ, Wilcoxon rank-sum test for unpaired data). (D and E) Upper and middle panels: Hi-C contact maps (merge of two replicates per condition, log1p scale) of untreated and IFN-I or IFN-γ-treated (2h) BMDM. Visualization of pattern detection with chromosight (loops between two loci are indicated as arcs). Arcs are color-coded according to their Pearson correlation scores. Loops with a score >0.35 are shown (maximum size/ylim = 500 kbp). Lower panel: IRF9/STAT1 ChIP-seq tracks after the respective treatment (1.5h) and gene annotations are shown to visualize ISGF3/GAF binding sites

Figure 5

ISGF3 complex-dependent effects of IFN signaling on chromatin accessibility (A and B) Summary profile plots of chromatin accessibility in BMDM generated by using normalized read coverages for untreated and IFN-I/IFN-γ treated wildtype and Irf9−/− BMDM as indicated. The colored profile is an average of the top 200 genes (log2FC) upregulated after IFN-I (2h; green profile) and IFN-γ (2h; purple profile) treatment, respectively, according to RNA-seq. The gray profile is an average of the respective remaining gene regions. (C and D) Heatmaps of chromatin accessibility in regions of the top 200 genes (log2FC) upregulated after IFN-I (2h) and IFN-γ (2h) treatment, respectively, according to RNA-seq. (E and F) Similar to A, B. The colored profile is an average of genes induced by the respective treatments with a log2FC > 5, the gray profile indicates an average of genes induced with a log2FC of 1-5. (G and H) Similar to C, D, but considering gene groups shown in E, F, respectively. Profiles and heatmaps in A-H are shown for the regions of the genes, including 2 kbp upstream of the TSS and 1kbp downstream of the TES as indicated below the plots. Shown are merged data from three biological replicates (See also Figure S4). (I) Interaction strength (as inferred from normalized Hi-C matrices; y axis limit 0.03) between regulatory regions overlapping the ISG clusters shown in Figure 2. Signals from untreated, IFN-I (2h) and IFN-γ (2h) treated BMDM are shown. All pair-wise interactions between regulatory regions within the same clusters are considered. Control pairs indicate the interaction between regulatory regions and other, non-regulatory regions

Figure 6

ISGF3 complex-dependent chromatin opening at ISG loci in homeostatic and interferon-induced states (A–F) Volcano plots of mRNA expression in BMDM in respective conditions. Each dot represents a gene. The log2-transformed fold change and -log10-transformed adjusted p values for gene expression are shown in x and y axis, respectively. (A) Irf9−/− vs wildtype BMDM in homeostatic condition: yellow dots represent genes significantly downregulated in Irf9−/− according to RNA-seq (log2FC ≤ 1, adjusted p value ≤ 0.05) and red dots represent genes which in addition showed significantly decreased accessibility at their respective loci according to ATAC-seq in Irf9−/− BMDM (log2FC ≤ 1, adjusted p value ≤ 0.05). (B) IFN-I (2h) stimulated vs untreated BMDM; C IFN-γ (2h) stimulated vs untreated BMDM. In the panels, yellow dots represent the genes that were significantly upregulated after either IFN treatment (log2FC ≥ 1, adjusted p value ≤ 0.05) according to RNA-seq. The red dots represent genes which in addition showed significant increase in chromatin accessibility (log2FC ≥ 1, adjusted p value ≤ 0.05) after corresponding IFN treatment at their genomic loci according to ATAC-seq data. (D and E) The blue dots represent genes which in addition, showed a significant decrease in chromatin accessibility at their genomic loci in Irf9−/− BMDM in response to 2h of either IFN treatment (ATAC-seq peaks, log2FC ≤ −1, adjusted p value ≤ 0.05). (F and G) Genome browser tracks for ATAC-seq at respective gene loci in wildtype and Irf9−/− BMDM treated with IFN-I or IFN-γ for 2h (one representative replicate). Data in A-E are derived from three biological replicates

Figure 7

Histone modifications at ISG promoters correlate with the local chromatin accessibility (A, C, E, G, and I) Genome browser tracks representing published ChIP-seq datasets in BMDM with antibodies against the following proteins after IFN-I stimulation: IRF9 (1.5h), H3K27ac (1h) and Pol II (2h) showing promoter occupancy at indicated gene loci (one representative replicate). (B, D, F, H, and J) Site-directed ChIPs (Mx1, Mx2, Oas1a, Oas2, and Irf1) were performed in bone marrow-derived macrophages isolated from wildtype and Irf9−/− BMDM, treated for 2h either with IFN-I or IFN-γ and processed for ChIP with antibodies targeting H3K27ac and H3K27me3 as indicated (See also Figure S5). Data represent mean ± SD of biological triplicates, analyzed for statistical significance by Student’s two-tailed, unpaired t-test using Graph Pad Prism software. ∗p < 0.05; ∗∗p < 0.01; ∗∗∗p < 0.001