Genome-Wide Analysis of DtxR and HrrA Regulons Reveals Novel Targets and a High Level of Interconnectivity Between Iron and Heme Regulatory Networks in Corynebacterium glutamicum

Abstract

Iron is vital for most organisms, serving as a cofactor in enzymes, regulatory proteins, and respiratory cytochromes. In Corynebacterium glutamicum , iron and heme homeostasis are tightly interconnected and controlled by the global regulators DtxR and HrrA. While DtxR senses intracellular Fe²⁺, HrrSA is activated by heme. This study provides the first genome-wide analysis of DtxR and HrrA binding dynamics under varying iron and heme conditions using chromatin affinity purification and sequencing (ChAP-Seq). We revealed 25 novel DtxR targets and 210 previously unrecognized HrrA targets. Among these, metH, encoding homocysteine methyltransferase, and xerC, encoding a tyrosine recombinase, were bound by DtxR exclusively under heme conditions, underscoring condition-dependent variation. Activation of metH by DtxR links iron metabolism to methionine synthesis, potentially relevant for the mitigation of oxidative stress. Beyond novel targets, 16 shared targets between DtxR and HrrA, some with overlapping operator sequences, highlight their interconnected regulons. Strikingly, we demonstrate the significance of weak ChAP-Seq peaks that are often disregarded in global approaches, but feature an impact of the regulator on differential gene expression. These findings emphasize the importance of genome-wide profiling under different conditions to uncover novel targets and shed light on the complexity and dynamic nature of bacterial regulatory networks.

Keywords: chromatin affinity purification and sequencing; heme; homeostasis; iron; transcription factors.

FIGURE 1

Genome‐wide profiling of DtxR and HrrA DNA‐binding in Corynebacterium glutamicum . (A) Schematic overview of the global iron and heme regulators DtxR and HrrA and the shared target gene hmuO encoding for a heme oxygenase. In (B) and (C), mapping of ChAP‐seq reads for DtxR (orange) and HrrA (blue), respectively, to the C. glutamicum ATCC 13032 genome is shown. DNA was obtained by affinity purification of DtxR and HrrA from cultures grown under iron excess (top, 100 μM FeSO₄), heme (middle, 4 μM heme) and iron depletion (bottom, 0 μM FeSO₄). Shown is one representative of each triplicate. Further replicates are shown in Figure S3. Note that the outstanding peak in the iron depletion condition for DtxR, found also smaller in HrrA binding, is a cryptic one and not real, resulting from technical issues as depicted in Figure S4. (D) and (E) represent the Pearson correlation of identified peaks among all replicates for DtxR and HrrA respectively binding at the two different conditions of iron excess (100 μM FeSO₄) and heme (4 μM).

FIGURE 2

Global analysis of DtxR peaks showed correlation between peak intensity and motif conservation. (A) Pie charts comparing the number of targets bound by DtxR in this ChAP‐Seq experiment that were already confirmed by previous studies (Brune et al. ; Wennerhold and Bott 2006) (previously known targets), novel targets, and those that were previously predicted from motif search, but could not be found in vitro (novel targets; predicted by motif). (B) The ChAP‐Seq peak intensities in arbitrary units for the iron excess (darker color) or heme (lighter color) condition were correlated to the peak distance relative to the transcriptional start site (TSS) for DtxR (orange) and HrrA (blue), respectively. (C) MEME‐ChIP motif prediction of the DtxR binding motif based on ChAP‐Seq binding peaks extracted from iron excess and heme conditions (Bailey and Elkan 1994). (D) MUSCLE (Multiple Sequence Comparison by Log‐Expectation) alignment (Madeira et al. 2024) of previously predicted DtxR binding motif (Brune et al. 2006) and all fitting motifs found throughout the ChAP‐Seq targets using FIMO (p < 1.0e⁻⁰⁵) (Grant et al. 2011), sorted from lowest to highest p‐value. Results with a higher p‐value can be found in Figure S7. Targets in light blue represent novel, so far unknown targets. (E) Correlation of peak intensities in iron excess (dark blue) or heme (light blue) condition with the p‐value of the binding motif as calculated by FIMO (Grant et al. 2011).

FIGURE 3

Binding peaks and reporter outputs of selected novel binding targets of DtxR. (A) Exemplarly, six known DtxR targets that were confirmed within this in vivo ChAP‐Seq experiment are shown featuring strong, medium and low binding peak intensities, respectively. (B‐D) Binding of DtxR to selected novel targets (NCgl01781, metH and xerC) under iron excess (black), heme (blue) and iron depletion (orange) conditions. n represents the number of replicates where a significant peak was identified. Additionally, bar plots represent the specific fluorescent reporter output after 2 h of either Corynebacterium glutamicum WT (filled bar) or a dtxR deletion strain ΔdtxR (striped bar) transformed with a reporter plasmid coupling the activity of the respective promoter region to venus expression. Statistical significance was confirmed by Student's t‐test (p ≤ 0.05).

FIGURE 4

Shared targets of the regulators DtxR and HrrA show interconnection between iron and heme regulatory networks. (A) Quantitative overview of shared targets regulated by DtxR and HrrA. (B) Upstream region of hmuO (grey). Predicted binding regions for DtxR and HrrA are indicated by orange and blue boxes. The sequence corresponding to the actual binding motif as revealed by FIMO analysis (Grant et al. 2011) is highlighted in the respective color. (C–F) Peak detection in the region of hmuO, sdhCD, xerC, and hrrA, respectively, with gene locations represented by grey arrows. Binding peaks are shown for iron excess (black), heme (blue) and iron depletion (orange). Grey vertical lines mark the peak maxima.

FIGURE 5

Weak binding targets should not be ignored—Correlation of ChAP‐Seq peak intensity and differential gene expression. (A) Exemplarly depiction of a strong DtxR binding peak (irp1, iron excess condition) versus a weak binding peak (ripA, iron excess condition). (B) Peak intensities of the ChAP‐Seq for DtxR under iron excess conditions (dark blue) were compared to the RNA ratio under iron excess (ΔdtxR/wild type) from a microarray analysis (Wennerhold and Bott 2006) (dark orange) as well as to the relative expression under iron excess in the deletion strain ΔdtxR compared to wild type analyzed via RT‐qPCR (Brune et al. 2006) (light orange). (C) Peak intensities of the ChAP‐Seq of HrrA in the presence of heme (dark blue) was compared to the log₂(ΔhrrA/wild type) obtained from the time‐resolved RNA‐seq in the presence of heme (Keppel et al. 2020) (shades of orange) for a selection of targets with highest and lowest peak intensities. (D) 2D‐scatterplot showing no significant correlation between ChAP‐Seq peak intensities of HrrA in the presence of heme and the absolute value of log₂(ΔhrrA/wild type) obtained from the time‐resolved RNA‐seq data under heme conditions (Keppel et al. 2020) for all identified targets.