Bacteria-to-Human Protein Networks Reveal Origins of Endogenous DNA Damage

Abstract

DNA damage provokes mutations and cancer and results from external carcinogens or endogenous cellular processes. However, the intrinsic instigators of endogenous DNA damage are poorly understood. Here, we identify proteins that promote endogenous DNA damage when overproduced: the DNA "damage-up" proteins (DDPs). We discover a large network of DDPs in Escherichia coli and deconvolute them into six function clusters, demonstrating DDP mechanisms in three: reactive oxygen increase by transmembrane transporters, chromosome loss by replisome binding, and replication stalling by transcription factors. Their 284 human homologs are over-represented among known cancer drivers, and their RNAs in tumors predict heavy mutagenesis and a poor prognosis. Half of the tested human homologs promote DNA damage and mutation when overproduced in human cells, with DNA damage-elevating mechanisms like those in E. coli. Our work identifies networks of DDPs that provoke endogenous DNA damage and may reveal DNA damage-associated functions of many human known and newly implicated cancer-promoting proteins.

Keywords: DNA damage response; DNA double-strand breaks; DNMT1; Escherichia coli; cancer; evolution; genome instability; human cells; microbial cancer models; replication fork reversal.

Figure 1.. Comprehensive Discovery of E. coli DNA “Damage-up” Protein Network

(A) Endogenous DNA damage may promote mutations and occurs by unknown means. (B) Screen for overproduction DNA damage-up proteins (DDPs). (1) Fluorescence plate-reader screen of E. coli Mobile overexpression library for fluorescence from SOS-DNA-damage-response reporter (Nehring et al., 2016). (2) Elimination of false-positives by flow-cytometry–single-cell assay. (C) Plate-reader representative results: afu, arbitrary fluorescence units, per OD₆₀₀, (biomass). Red, potential DDPs with fold change >30%. (D) Representative flow-cytometry validation of SOS-positive DDPs. Dashed line, “gate” for SOS-positives (significance, STAR Methods). Blue, vector control; red, DDP producers. (E) % SOS-positive cells for the 208 validated E. coli DDPs (Table S1). (F) DDP network summary; proteins of many different functions are DDPs. (G) LexA-dependence of fluorescence from DDPs shows SOS-response activation/DNA damage. (H) SOS-positive phenotype correlated with RecA*GFP foci, indicating persistent single-stranded DNA. 67 representative DDPs show 32 (48%) with elevated RecA*GFP foci (p < 0.05, unpaired two-tail t-test), r = 0.7, p = 1.3×10⁻¹⁰, Pearson’s correlation, (data, Table S1). Scale bar: 2μm. (I) Mutation-rate increase with DNA-damage levels in representative DDP-producing clones. Above, assay (STAR Methods). Each bar, the mean mutation rate (± SEM) of each strain, N=3 (STAR Methods; Table S1). P-values, fraction of clones with mutation rate significantly higher than vector-only control, one-way Fisher’s exact test.

Figure 2.. Human Homologs of E. coli DDPs a Network Associated with Cancers

(A) Summary of 284 human homologs of E. coli DDPs (Table S2). (B) Protein-protein associations of human DDP homologs (Figure S2; Table S2). (C) Human homologs are overrepresented among known and predicted cancer drivers (blue bar), even without known DNA-repair “caretakers”. (D) hDDP candidates are enriched among genes with cancer-associated copy-number increases, indicating overexpression in cancers (Figure S3A-C, Table S4). (E) Decreased cancer survival with high DDP-homolog RNA levels in cancers: our analyses of TCGA data (STAR Methods). Cancer types, STAR Methods. *, **, ***, high versus low levels of 284 RNAs p ⩽ 0.05; ⩽ 0.01, and ⩽ 0.001, log-rank test. (F) High hDDP candidate RNA levels predict tumor mutation loads (TCGA data). Each dot, Pearson correlation coefficient 284 homolog RNAs/total RNAs versus tumor mutation load. The average correlation strength was in the top 0.5% of correlations for randomly selected groups of genes. X-axis, cancer types.

Figure 3.. Human Homologs Promote DNA Damage in Human Cells

(A) hDDP-candidate-GFP N-terminal fusions (and 3 damage-down-, plus 20 non-DDP controls) were transiently overproduced and green cells screened for DNA damage by flow cytometry. (B) 33 validated hDDPs. Upper: representative flow cytometric assay (STAR Methods, Figure S3I-K; Table S6). Lower: heatmap, flow-cytometric data normalized to GFP-tubulin. Data ranked by cumulative DNA-damage score. Green, damage-up in ⩾ 2 assays; gray, one assay; yellow, damage-down homologs; white, not damage-up. 45% validated; more than among 20 random human genes (p <0.0001, two-tailed unpaired t-test with FDR correction, Figure S3I-K). (C) Increased mutation with overproduced validated hDDPs in human-cell HPRT forward-mutation assays. Lower: mutation rates of selected hDDP overproducers; error bars, 95% CIs. (D) Validated hDDP genes enriched among cancer-associated copy-number increases (p = 0.02, one-way Fisher’s exact test). (E) New and known potential cancer-promoters predicted among 33 validated hDDPs, suggesting potential overexpression cancer-promoting roles for all of these genes. Classes (i) 16%; (ii) 53%; (iii) 6%; and (iv) 25%.

Figure 4.. Kinds, Causes and Consequences of DNA Damage from E. coli DDPs.

Clone by clone data Table S1. (A) DDPs that increase DNA double-strand breaks (DSBs), detected as GamGFP foci. Scale bar: 2μm. Lines, DNA strands; green balls, GamGFP. (B) 87 of the 208 (45% of) E. coli DDPs promote DSBs. (C) Stalled, reversed replication forks (RFs) detected as RDG foci in recA⁻ cells, per (Xia et al., 2016). Scale bar: 2μm. Lines, DNA strands; red lines, new strands; green balls, RDG. (D) 106 of the 208 (51% of) E. coli DDPs promote fork stalling and reversal. (E-I) Flow-cytometric assays for— (E) elevated ROS, DHR fluorescence, example. (F) 56 (27% of) DDPs induce high ROS. (G) DNA damage (% SOS-on cells) from 17 of 43 high-ROS DDPs tested is reduced by ROS-quenching agent thiourea (TU). (H) DNA loss: “anucleate” cells with no DNA, example. Events below the horizontal line, anucleate. (I) 67 of 208 (32% of) DDPs induce DNA loss. (J-L) Sensitivity to DNA-damaging agents implies DNA-repair-pathway reduction (potential saturation), possibly from elevated DNA damage. Relevant DNA-repair-defective controls shown. Assays for slowed growth per J left (STAR Methods). (J) 106 of 208 DDP clones (51%) show phleomycin (DSB) sensitivity. (K) 10 of 208 DDP clones (5%) sensitive to DNA cross-linker mitomycin C (MMC) (reduced NER and/or HDR). (L) H₂O₂ sensitivity (reduced BER) from 75 of 208 DDPs (36%). (M) Stalled replication (RFs) clusters with particular DDPs; DNA breakage does not (STAR Methods). (N) Clustering Z scores reveal DNA-damage signatures. H₂O₂, hydrogen-peroxide sensitivity; Phleo, phleomycin sensitivity; DNA loss (anucleate cells); ROS levels; MMC, (MMC sensitivity); RFs (reversed forks); DSBs. Vertical bars: phenotype scores of each DDP clone. The 6 clusters/DNA-damage signatures suggest at least 6 mechanisms of DNA-damage generation. Protein category enrichment (above, one-way Fisher’s exact test): clusters 2 p = 0.01; 4; p = 0.01, 5 and 6 p = 0.03.

Figure 5.. E. coli Transcription Factors Promote Replication-fork Stalling via DNA Binding

(A) DNA-binding transcription factors (TFs) enriched in DDP clones with high reversed forks (RFs, p =0.002, one-way Fisher’s exact test). (B) TF DNA-binding required for DNA-damage promotion. Representative data, TFs and corresponding mutants: ΔDBD, DNA-binding domain deletion; and single amino-acid changes that reduce DNA-binding. (C) Mean ± SEM of ≥3 experiments. (D) DNA-binding required for RDG (RF) foci (blue arrows). Representative images, scale bar: 2μm. Figure S6A, all genotypes. (E) Mean ± SEM of ≥3 experiments. (F) DNA-binding TF-mCherry foci co-localize with RDG RF foci. Representative data. Blue arrows, co-localized foci, scale bar: 2μm. (G) Mean ± SEM of ≥3 experiments. Figure S6B, images. (H) Co-localization of TF with RDG foci requires TF DNA-binding. (I) RDG ChIP-Seq RF peaks (in ΔrecA) enriched near CsgD-binding sites (green squares; p =0.01, two-tailed z-test versus simulated data, Figure S7 legend). Figure S7A-C, complete set RF peaks. (J) Model: overproduced TFs (orange circles) bound to DNA (parallel lines) induce replication roadblock RFs. Lower model, how RFs might appear downstream of a DNA-bound TF: first, the bound TF slows/impairs the fork; second, a downstream replication-slowing site/occurrence that otherwise would not have stalled replication.

Figure 6.. E. coli and Human Transporters Promote DNA Damage via ROS

(A) E. coli high-ROS clusters enriched for membrane-spanning transporters (p = 0.004 one-way Fisher’s exact test). (B) DNA damage from 5 E. coli transporters reduced by ROS-scavenger thiourea (TU): ROS-dependent. Mean ± range, N=2; representative data. (C) Transporter overproduction elevates ROS levels. (Table S1). Gray, vector. (D) Mean ± range, N=2. (E) pHrodo-green pH stain and flow cytometry in buffers with varied pH show cell subpopulations with decreased pH. (F) Overproducing E. coli H⁺ symporters increases activity/reduces pH: gain-of-function. Grey, vector only. Mean ± range of two experiments. (G) Representative flow-cytometry data. (H) Reduced pH is not correlated quantitatively with increased ROS (R²=0.05, Pearson’s correction), suggesting that the specific cargoes may promote DNA damage. (I) Models. Discussed Figure S4D legend. (J) Overproduced GFP-tagged hDDPs cellular localization. Bar: 5 μm. (K) ROS underlie DNA damage caused by human KCNAB1/2 transporter overproduction. NAC: N-acetyl-cysteine. * p < 0.05 relative to untreated GFP-tubulin control; * p < 0.05 relative to the corresponding NAC-untreated control, unpaired two-tailed t-test.

Figure 7.. E. coli DNA Pol IV, Human DNMT1 Promote DNA Damage via Binding the Replisome Clamp

(A) E. coli Pol IV in cluster with high DNA loss. (B) Left: Pol IV promotion of DNA damage is reduced by overproducing its competitor Pol II. Right: Pol IV promotion of DNA damage requires interaction with beta (β) replisome sliding clamp—ΔBBD, deleted β-binding domain—and is partly independent of Pol IV catalytic activity (cat⁻ mutant). (C) Mean ± SEM of ≥3 experiments. (D) DNA damage reduced by reduction of Pol IV-β interaction with tau-only mutant, which favors Pol III. RecB- and RecF-dependence of Pol IV-induced DNA damage implicate DSBs and single-strand gaps. (E) Mean ± SEM of ≥3 experiments. Pol IV is induced by IPTG. (F) Model: Pol IV induces DNA damage by excess binding the β clamp. Excess β interaction might slow the replisome causing fork breakage/collapse, or displace β-binding DNA-repair proteins, among other possibilities. 8-oxo-dG-independence, Figure S7F,G. (G) Mutant derivatives of human DNA methyltransferase DNMT1 (WT, wild-type). PBD, PCNA-binding domain; U, UHRF1 (ubiquitin-like PHD and RING-finger 1 interacting domain; RFTS, (recruits DNMT1 to DNA-methylation sites); Cat and C1226A, catalytically inactivate mutants, all N-terminally GFP tagged. (H) Human DNMT1 overproduction in human cells promotes γH2AX accumulation methylase-independently and replisome-clamp-interaction dependently. (I) Elevated DNMT1 promotes PCNA monoubiquitination (replication-stress) replisome-interaction dependently. Western blot with anti-PCNA antibody. (J) Model/hypotheses for how excess DNMT1 promotes DNA damage. (K) Hypothesis: DDPs, a cancer-protein function class upstream of DNA repair. Excessive endogenous DNA damage could titrate (thick blue -|) or inhibit (thin black -|) DNA repair causing DNA-repair-protein deficiency without a DNA-repair-gene mutation. Repair deficiency increases mutation rate, and cancer- (or evolution-) driving mutations in cell-biology-altering “gatekeeper” genes that cause the cancer phenotypes.