Quantitative analysis of multisite protein-ligand interactions by NMR: binding of intrinsically disordered p53 transactivation subdomains with the TAZ2 domain of CBP

Abstract

Determination of affinities and binding sites involved in protein-ligand interactions is essential for understanding molecular mechanisms in biological systems. Here we combine singular value decomposition and global analysis of NMR chemical shift perturbations caused by protein-protein interactions to determine the number and location of binding sites on the protein surface and to measure the binding affinities. Using this method we show that the isolated AD1 and AD2 binding motifs, derived from the intrinsically disordered N-terminal transactivation domain of the tumor suppressor p53, both interact with the TAZ2 domain of the transcriptional coactivator CBP at two binding sites. Simulations of titration curves and line shapes show that a primary dissociation constant as small as 1-10 nM can be accurately estimated by NMR titration methods, provided that the primary and secondary binding processes are coupled. Unexpectedly, the site of binding of AD2 on the hydrophobic surface of TAZ2 overlaps with the binding site for AD1, but AD2 binds TAZ2 more tightly. The results highlight the complexity of interactions between intrinsically disordered proteins and their targets. Furthermore, the association rate of AD2 to TAZ2 is estimated to be 1.7 × 10(10) M(-1) s(-1), approaching the diffusion-controlled limit and indicating that intrinsic disorder plus complementary electrostatics can significantly accelerate protein binding interactions.

Figure 1

Portions of the ¹H–¹⁵N HSQC spectra of (a) TAZ2 showing chemical shift changes upon titration with p53 AD1(13–37) and (b) p53 AD1 showing chemical shift changes upon titration of TAZ2. The cross-peak color changes gradually from black (free) to magenta (bound) according to the concentration ratio.

Figure 2

The SVD analysis of the ¹⁵N-TAZ2 titration with unlabeled p53 AD1. (a) Blue bars show the singular values sorted in decreasing order plotted in the logarithmic scale. Red circles show the RMSD (ppm) between the raw data set and the data set reconstructed using the 1 ~ i-th components (abscissa). Inclusion of all (1 ~ 17-th) components for the data reconstruction results in the RMSD of 0, which is not shown in the figure. Inset shows the autocorrelation of v_i vectors plotted against the component number. (b) The shape of v_i vectors for the first five components plotted against the number of titrations. First three components have smooth shape (thick lines with filled circles), resulting in high autocorrelation.

Figure 3

Global fitting of the noise-filtered titration curves for the ¹⁵N-TAZ2 titration with unlabeled p53 AD1. (a) Selection of the data from the global fit of chemical shift changes of HSQC cross peaks of ¹⁵N-TAZ2 as a function of the concentration ratio of AD1/TAZ2. Color codes are shown in the panel along with the residue number. (b) The histograms of the averaged chemical shift differences Δδ_av for the primary (upper) and secondary binding (lower). The black horizontal line shows the mean of all Δδ_av (0.081 and 0.104 ppm for primary and secondary binding, respectively). The residues are categorized into the following groups: (red or blue) mean + 2×SD ≤; (orange or cyan) mean + 1×SD ~ mean + 2×SD; (yellow or pale green) mean ~ mean + 1×SD; and (gray) < mean. (c) Mapping the location of the residues having large Δδ_av onto the NMR structure for the primary (upper) and secondary binding (lower). The color codes are the same as in (b). Three zinc binding sites and four α-helices are shown. Helix α1 corresponds to residues 1765–1785, α2 to 1794–1806, α3 to 1818–1833, and α4 to 1842–1852.

Figure 4

The Δδ_av histograms of the primary (left) and secondary binding (right) obtained from the ¹⁵N-p53 AD1 titration with unlabeled TAZ2 using the K_ds obtained by the ¹⁵N-TAZ2 titration with AD1. The TAZ2 concentration correction factor was 1.08 ± 0.01. The black horizontal line shows the mean of all Δδ_av (0.251 and 0.286 ppm for primary and secondary binding, respectively). The residues are categorized into the groups as described in Figure 3b.

Figure 5

Global fitting of the noise-filtered titration curves for the ¹⁵N-TAZ2 titration with unlabeled p53 AD2. (a) Selection of the data from the global fit of chemical shift changes of HSQC cross peaks of ¹⁵N-TAZ2 as a function of the ratio of AD2/TAZ2. Color codes are shown in the panel along with the residue number. (b) Mapping the location of the residues having large Δδ_av onto the NMR structure for the primary (upper) and secondary binding (lower). The color codes are the same as in Figure 3b, except that Val1802 and Leu1823 are shown by magenta (upper) and Tyr1829 is shown by purple (lower).

Figure 6

Dependence of accurate K_d1 and K_d2 ranges on (a) the number of data points (an interval of ratios), (b) a maximum titrant/protein ratio, (c) protein concentration, and (d) the number of peaks used in the analysis. Representative results are shown (see Figures S11–S14 for details). Conditions of fitting simulations are described in each panel. The red, orange, and yellow squares and cross symbols show that both the fitting errors and the differences between the fitted K_d and the input K_d used for generating the curves are less than 5%, 5 ~ 10%, 10 ~ 20%, and more than 20% of the input K_d values, respectively. Gray circles and diamonds show that only K_d1 or K_d2 were accurately obtained by global fit, because the binding events approached one-site binding at higher K_d2 or at lower K_d1, respectively. It should be noted that a K_d1 of less than 1 nM cannot be estimated by NMR titrations, because such a tight binding does not show fast-exchange shifts (see Figure 7).

Figure 7

(a) K_d1 dependence of the fraction of fast exchange for Scheme 1. Chemical shift changes were assumed to be ~0.1 ppm. Combinations of k_on1, k_on2, k_off1, and k_off2 that satisfy K_d1 and K_d2 of 10⁻¹⁰ ~ 10⁻¹ M (K_d1 < K_d2) were used to calculate lineshapes. Black open squares show the counts of the combinations of rate constants that produce the indicated K_d1 value. Red filled circles show the counts of the combinations of rate constants that show fast-exchange shifts throughout the titrations from 1:0 ~ 1:5 ratios. Green bars are the ratio of these values, corresponding to the fraction of fast exchange at the indicated K_d1 value. (b) The same as (a), except that the interconversion between B1 and B2 is taken into account (Scheme 2). (c) Increase in the fraction of fast exchange by the presence of the B1–B2 interconversion. The gray bar shows the ratio of the fraction of fast exchange in the presence of the B1–B2 interconversion (Scheme 2) to that in the absence of the interconversion (Scheme 1).

Figure 8

A series of ¹H lineshapes for Val1841 observed in the ¹H–¹⁵N HSQC titration of ¹⁵N-TAZ2 with unlabeled p53 AD2 in which TAZ2:AD2 concentration ratios ranged from 1:0 to 1:5. The lineshape color changes from black (free) to magenta (bound) according to the concentration ratio. Continuous lines are obtained from global fitting of lineshapes.

Scheme 1

A two-site binding model.

Scheme 2

A two-site binding model with an interconversion between B1 and B2.