RadD is a RecA-dependent accessory protein that accelerates DNA strand exchange

Abstract

In rapidly growing cells, with recombinational DNA repair required often and a new replication fork passing every 20 min, the pace of RecA-mediated DNA strand exchange is potentially much too slow for bacterial DNA metabolism. The enigmatic RadD protein, a putative SF2 family helicase, exhibits no independent helicase activity on branched DNAs. Instead, RadD greatly accelerates RecA-mediated DNA strand exchange, functioning only when RecA protein is present. The RadD reaction requires the RadD ATPase activity, does not require an interaction with SSB, and may disassemble RecA filaments as it functions. We present RadD as a new class of enzyme, an accessory protein that accelerates DNA strand exchange, possibly with a helicase-like action, in a reaction that is entirely RecA-dependent. RadD is thus a DNA strand exchange (recombination) synergist whose primary function is to coordinate closely with and accelerate the DNA strand exchange reactions promoted by the RecA recombinase. Multiple observations indicate a uniquely close coordination of RadD with RecA function.

Figure 1.

RadD stimulates RecA mediated strand exchange. (A) Reaction scheme. (B) Strand exchange reaction time courses in reactions lacking RadD or with RadD or RadD K37R added immediately after the dsDNA. Reactions contained 20 μM circular φX174 ssDNA (3.7 nM in molecules), 20 μM linear φX 174 dsDNA (1.86 nM in molecules), 3 μM RecA protein, 2.1 μM SSB, and 3.7 nM RadD protein (a 2:1 ratio of RadD molecules to linear dsDNA (ldsDNA) molecules). (C) Quantifications of nicked circular (nc) DNA from three independent strand exchange reactions shown in A with the average values plotted and standard deviations represented with error bars. (D) Strand exchange reactions carried out at the optimal 1 RecA per 3 nt cssDNA ratio in the absence or presence of RadD or RadD K37R, added immediately after the linear dsDNA. All components are at concentrations listed for panel B except that the RecA concentration is increased to 6.7 μM, a concentration sufficient to saturate the available ssDNA binding sites. (E) Quantifications of nc DNA from three independent strand exchange reactions shown in panel D with average values plotted and strand deviations represented.

Figure 2.

RadD function is RecA-dependent. (A) Isolated protein-free strand exchange intermediates were incubated alone, with RecA (3 μM), or RadD (3.7 nM). Results from experiments prepared from three independent preparations of joint molecules (JM) are shown. (B) Raw quantifications of nc DNA from three independent experiments started from three separate preparations of JMs. (C) Quantifications of nc DNA from all three gels shown in (A), averaged, with results normalized such that the start and end points of the RecA reaction are set at 0 and 100, respectively.

Figure 3.

Stimulation of RecA mediated strand exchange by RadD; effects of concentration. Strand exchange reactions with RadD titrated from 1 to 50 nM. (A) Sample reaction with RadD titration. Reactions were carried out under the conditions of Figure 1D (with sufficient RecA to saturate available ssDNA binding sites), except that the RadD concentration was varied and reactions were stopped after 2 min. (B) Quantification of three experiments identical to that in panel A. Arrow indicates the concentration of RadD that would be equivalent to the concentration of linear dsDNA molecules and thus the maximum concentration of RecA-generated branched intermediates in the experiment.

Figure 4.

RecA protein filaments are disassembled by RadD. (A) Top panel – ATP hydrolysis profiles of RecA during strand exchange without and with varying concentrations of RadD. Reactions were initiated by the addition of duplex DNA at 15 min. Where RadD is present, it was added at the concentrations indicated and at the same time as the duplex DNA. Bottom panel – RecA ATP hydrolysis trace on single stranded DNA in the presence of various RadD K37R concentrations as indicated. RadD was added at 10 min after the reaction was initiated at 37°C. B. Representative electron microscopy images of RecA filaments on single stranded DNA without RadD (top) and with RadD (bottom). Black arrows indicate regions of circular ssDNA coated with RecA. Red arrows indicate regions of ssDNA coated with SSB. (C) Quantification of observed RecA filament lengths. RadD K37R titration into RecA ATP hydrolysis reactions after 10 min of RecA incubation with DNA. Numbers reflect the total number of filament lengths that fell into each size bin. For reactions without and with RadD, n = 52 and 62, respectively.

Figure 5.

Effects of altering order of addition. RadD stimulates strand exchange when added to the reaction at different pre-incubation steps. Reaction conditions were identical to those used in Figure 1B, with 20 μM nt cssDNA and ldsDNA, 3 μM RecA, and 3.7 nM RadD. (A) Strand exchange time courses of reactions where RadD is excluded, added with RecA, added with SSB and ATP, or added with ldsDNA (at time zero). (B) Diagram of strand exchange reaction incubations and order of addition of reagents. The reactions are initiated by the addition of ldsDNA. (C) Quantifications of nc DNA from three independent sets of order of addition experiments with the average value plotted and standard deviations represented as error bars.