Dancing on DNA: kinetic aspects of search processes on DNA

Abstract

Recognition and binding of specific sites on DNA by proteins is central for many cellular functions such as transcription, replication, and recombination. In the search for its target site, the DNA-associated protein is facing both thermodynamic and kinetic difficulties. The thermodynamic challenge lies in recognizing and tightly binding a cognate (specific) site among the billions of other (non-specific) sequences on the DNA. The kinetic difficulty lies in finding a cognate site in mere seconds amidst the crowded cellular environment that is filled with other DNA sequences and proteins. Herein, we discuss the history of the DNA search problem, the theoretical background and the various experimental methods used to study the kinetics of proteins searching for target sites on DNA.

Figure 1

(A) Schematic representation of the protein–DNA search problem. The protein (green) must find its target site (red) on a long DNA molecule. (B) The target site must be recognized with 1 base-pair (0.34 nm) precision, as displacement by 1 bp results in a different sequence and thus a different site.

Figure 2

Potential modes of target search. The protein can locate its target sequence through several proposed mechanisms: (i) one-dimensional sliding via a random walk along the DNA without dissociation (green) (ii) one-dimensional hopping, where the protein moves along the DNA via a series of microscopic dissociation and re-association events (blue); (iii) jumping or diffusion in 3D (orange); and (iv) intersegmental transfer, involving movement to a different DNA location by a looped DNA strand (purple).

Figure 3

Mechanism of facilitated diffusion. The protein (green) combines translocating on DNA and diffusion in solution to find its target site (red) on DNA. In this model, the search process consists of alternating rounds of 3D and 1D diffusion, each with average duration τ_1D and τ_3D respectively.

Figure 4

(A) Model of 1D sliding: at each step the protein can slide along DNA to the right or left, or dissociate into solution. (B) The sequence-dependent energy landscape of sliding. The protein–DNA binding energy depends on sequence, thus forming a rugged landscape. The parameters determining protein dynamics are the roughness of the energy landscape, σ and the (free) energy of non-specific binding to DNA, E_ns.

Figure 5

The two-state model for one-dimensional translocation of protein along DNA. The search state has a small ruggedness with σ < 2 k_B T allowing the protein to slide rapidly. The recognition state has σ > 5 k_B Trequired for tight binding, which allows recognition of the sequence. Lower mean energy of the recognition state E_r < E_S is required for the protein to spend most of the time sliding and occasionally sample rare sites that have E_R(i) < E_S(i).

Figure 6

Total internal reflection fluorescent microscopy (TIRFM) is used to visualize single proteins moving along individual DNA molecules. A laser is reflected off the interface between an aqueous sample and a microscope slide, which generates an evanescent field decaying exponentially into the aqueous sample and selectively illuminates the fluorophores present within a few hundred nanometers of the surface. Combining TIRFM with methods for confining long DNA molecules by mechanically stretching them within the evanescent field has allowed visualization of single proteins moving along individual DNA molecules.

Figure 7

(A) Kymograph of an individual fluorescently labeled p53 transcription factor moving along flow-stretched DNA. The x axis represents time and the flow is directed upward along the y axis. (B) Trajectories of two p53 proteins diffusing on λ DNA. (C) Mean square displacement (MSD) versus time of the same two trajectories. (D) Histogram of diffusion coefficient D of 162 individual p53 proteins. Figure reproduced with permission from Ref. ^[26].