Microscopic mechanism of DNA damage searching by hOGG1

Abstract

The DNA backbone is often considered a track that allows long-range sliding of DNA repair enzymes in their search for rare damage sites in DNA. A proposed exemplar of DNA sliding is human 8-oxoguanine ((o)G) DNA glycosylase 1 (hOGG1), which repairs mutagenic (o)G lesions in DNA. Here we use our high-resolution molecular clock method to show that macroscopic 1D DNA sliding of hOGG1 occurs by microscopic 2D and 3D steps that masquerade as sliding in resolution-limited single-molecule images. Strand sliding was limited to distances shorter than seven phosphate linkages because attaching a covalent chemical road block to a single DNA phosphate located between two closely spaced damage sites had little effect on transfers. The microscopic parameters describing the DNA search of hOGG1 were derived from numerical simulations constrained by the experimental data. These findings support a general mechanism where DNA glycosylases use highly dynamic multidimensional diffusion paths to scan DNA.

Figure 1.

Molecular clock method and measurement of dissociative and associative site transfer pathways. (A) DNA substrates used in this study. Substrates had target site spacings in the range 5–156 bp. (B) The molecular clock assay uses a trap (T) to capture enzyme molecules that have dissociated from DNA during the process of transferring between two target sites. Thus, transfers that occur by associative and dissociative pathways can be resolved. (C) Simulated experimental outcomes for the molecular clock assay. Since the probability of trapping a dissociated enzyme depends on the trap concentration, the contribution of the dissociative pathway decreases in a hyperbolic fashion with increasing trap concentration. If an associative pathway also exists, a plateau level of trap resistant transfers will be reached.(D) Separation of base excision products of substrate S20 in the presence and absence of trap by denaturing polyacrylamide gel electrophoresis. Typically, substrates were 5′ ³²P labeled. Reactions contained S20 (20 nM) and hOGG1 (1 nM). At each time point P_trans^obs = ([A] + [C] - [AB] - [BC])/([A] + [C] + [AB] + [BC]) was calculated. (E) Linear extrapolation of P_trans^obs to zero time gives the true P_trans. (F) Trap and spacing dependence of P_trans′. P_trans′ is calculated by dividing P_trans by the ^oG excision efficiency (E = 0.85).

Figure 2.

Associative transfers persist with target sites on opposite strands and when the phosphate backbone is blocked. (A)^oG sites were placed on opposite DNA strands (S10^opp) and the transfer probabilities were measured. (B) Fluorescein iodoacetamide was used to modify a single phosphorothioate linkage in the phosphate backbone connecting two ^oG sites separated by 15 bp (S15^Fluor) and the transfer probabilities were measured and compared with an identical substrate without the block. In these measurements the internal B fragment is labeled. The two B bands result from the different mobilities of the β and δ elimination products derived from base treatment of the abasic reaction product. See Supplementary Figure S4B and S4C for full time courses.

Figure 3.

Monte Carlo simulations of site transfer using a combined 2D-3D model. (A) In the simulations, a protein trajectory begins with a random walk on the DNA surface (associative transfers), which are exited with a probability p_exit that is determined from empirically modeling the experimental associative transfer data (see Supplementary Information and Supplementary Figure S8) leading to dissociation events where 3D diffusion occurs (D₃ = 1.0 × 10⁸ nm²/sec). Once the enzyme is greater than r_trap distance away from the DNA it is in a trappable dissociative transfer state; the enzyme either rebinds or is lost to bulk when the escape radius has been reached (r_escape). Each time the protein comes in contact with the DNA the x-position along the DNA long axis is recorded into a histogram. The site spacing dependence of the binned contact probabilities were fitted to the experimental data. (B) Simulated fits to the experimental data for P_assoc′ and P_trans′. The curves are derived from the normalized histograms for associative transfer only (dotted line) or combined dissociative and associative transfers (solid line). The histograms were derived from the analysis of 10 000 simulated trajectories.

Figure 4.

A single associative-dissociative transfer cycle of hOGG1. The ensemble mean binding lifetime of hOGG1 to non-target DNA is τ_bind = 3 ms. During this time the average hOGG1 molecule scans 60 bp of DNA as determined from numerical analysis of the data in Figure 3B (details in Supplementary Information). On average, each binding event consists of three associative-dissociative transfer cycles before a dissociation event leads to escape from the DNA (only one cycle is depicted). During a binding event, hOGG1 samples stationary states (25,26,41), mobile associative states, and dissociated states. The lifetime of the stationary state must consume the large part of τ_bind (i.e. τ_stat ∼ ms) (33,42), and must be much greater than the lifetime of the mobile associative state because movement requires weak interactions. The transition from the stationary to mobile associative state involves a conformational change in hOGG1 and the DNA (depicted with a solid two-headed arrow) as observed in rapid kinetic and structural studies (33,42,41). Numerical simulations indicate that the average binding event consists of four associative transfers and three dissociative transfers (three complete cycles). The time spent in a single dissociative and associative transfer step is on the order 10–100 ns and 10–100 μs, respectively (see text and Supplementary Information).