Binding specificity of Toll-like receptor cytoplasmic domains

Abstract

MyD88 participates in signal transduction by binding to the cytoplasmic Toll/IL-1 receptor (TIR) domains of activated Toll-like receptors (TLR). Yeast two-hybrid experiments reveal that the TIR domains of human TLR differ in their ability to associate with MyD88: The TIR of TLR2 binds to MyD88 but the TIR of the closely related TLR1, 6, or 10 do not. Using chimeric TIR domains, we define the critical region responsible for differential MyD88 binding, and use a computational analysis of the critical region to reveal the amino acids that differ between MyD88 binders and non-binders. Remarkably, a single missense mutation created in TLR1 (N672D) confers on it the ability to bind MyD88, without affecting its association with other proteins. Mutations identified as critical for MyD88 binding also affect signaling of TLR pairs in mammalian cells. To investigate the difference between MyD88 binders and non-binders, we identify novel interacting proteins for each cytoplasmic domain of TLR1, 2, 6, and 10. For example, heat shock protein (HSP)60 binds to TLR1 but not to TLR2, and HSP60 and MyD88 appear to bind the same region of the TIR domain. In summary, interactions between the TLR, MyD88, and novel associated proteins have been characterized.

Figure 1

(A) MyD88 binds to the TLR cytoplasmic domains 2, 5, 7, and 8. Yeast were transformed with the Gal4 BD fusions indicated (along top) and the Gal4 AD fusions indicated (at left). Transformants were selected on synthetic media lacking tryptophan and leucine (−TL, top panel), and protein interactions were identified by plating transformants on synthetic media lacking tryptophan, leucine, and histidine, and supplemented with 10 mM 3AT media (−TLH/+10 mM 3AT, bottom panel). (B) The reciprocal TLR2-MyD88 interaction. Cells expressed the BD fusions indicated (along bottom) and the AD fusions indicated (at left). Transformants were selected on −TL media (top panel) and on −TLH/+10 mM 3AT (bottom panel).

Figure 2

(A) ClustalW alignment of the human TLR cytoplasmic domains (Cyd) showing the closely related MyD88 non-binders 1, 6, and 10, and the next nearest relative, TLR2, which binds MyD88. Numbers in red indicate percent identity, and in blue indicate percent similarity between the TLR1 Cyd and the other TLR cytoplasmic domains. (B) Protein alignment of the TIR region that converts the cytoplasmic domains of TLR1 and 6 into MyD88-binding proteins. Boxes 1 and 2 (red bars) are highly conserved hallmarks of the TIR domain and are critical for receptor signaling. 'Short' or 'long' bars indicate regions of TLR2 or 5 swapped into TLR1, 6, and 10 to generate cytoplasmic domain chimeras. Asterisks at the top indicate positions of gain-of-function point mutations in TLR1, and analogous residues in TLR2.

Figure 3

Point mutations in the TLR2 cytoplasmic domain abrogate MyD88 binding. Yeast co-transformed with the AD fusions indicated (at right) and the BD fusions indicated (along top) were selected on −TL media (left panel) and on −TLH/+3 mM3AT media (right panel).

Figure 4

MyD88 binds chimeric cytoplasmic domains of TLR1 and 6. Yeast were co-transformed with the BD fusions indicated (along top) and the AD fusions indicated (at right). The transformation reaction was split in half and spotted onto −TL media (top panel) and onto −TLH/+3 mM3AT media (bottom panel). The "wt" indicates wild-type cytoplasmic domains, "long" indicates TLR2 amino acids 641–700, or TLR5 amino acids 693–758, swapped into the cytoplasmic domains of TLR1, 6, or 10, replacing the endogenous region, and "short" indicates TLR2 amino acids 659–700 swapped into the TLR cytoplasmic domains.

Figure 5

(A) Predicted co-variation in the TLR1 TIR domain. A coupling energy analysis was run designating the TLR1 N672 amino acid as the invariant position (red). The statistical coupling analysis provided a vectorized numerical value, $\left|\mathrm{\Delta }\mathrm{\Delta }{\mathrm{G}}_{\text{ji}}^{\text{stat}}\right|$ , for each residue, which reflects the statistical coupling of the residues to N672. The values for each amino acid were linked to the crystal structure of the TLR1 TIR domain and imported into the PyMol program. The image was colorized in PyMol, using 'b-factors', and a heat map was generated of the domain. Orange indicates relatively strong co-variation with the invariant residue, yellow indicates weaker correlation, and green or blue indicates no evidence of co-variation between the N672 and a given residue. See Supplemental data for the multiple sequence alignment and $\left|\mathrm{\Delta }\mathrm{\Delta }{\mathrm{G}}_{\text{ji}}^{\text{stat}}\right|$ values. (B) A closer view of the positions of the TLR1 N672 and F637 side chains, as predicted by the TIR crystal structure. Other amino acids with side chains that appear spatially oriented near F637, H638, and N672 in the crystal structure are also labeled.

Figure 6

(A) Gain-of-function point mutations in TIR1 confer MyD88 binding activity. Yeast were transformed with the BD fusions indicated (along top) and the AD fusions indicated (at left). Transformants were selected on −TL media (top panel) and on −TLH/+10 mM 3AT media (middle panel). The bottom panel shows comparable expression of the BD-TLR cytoplasmic domain fusions. Lanes on the Western blot correspond to labeled columns in (A). Cultures were inoculated from the −TL spots in (A) (asterisk indicates row of spots used for inoculation) and grown to log phase in media lacking tryptophan to select for the BD fusions. Protein lysates were prepared and 5 × 10⁶ cell equivalents each were immunoblotted for the Gal4 BD. (B) Serial dilutions of transformants showing a two-hybrid signal for MyD88 binding. The experiment in (A) was reproduced with independent clones bearing the samemutations.AD fusions are indicated along the top and BD fusions are indicated along the bottom. Transformants were grown in −TL liquid media, diluted to OD₆₀₀ = 0.45, and a series of tenfold dilutions were made for each culture. Of each serial dilution, 10 µL was spotted on −TL (top panel) and −TLH/+10 mM 3AT media (bottom panel).

Figure 7

A precise combination of residues is required for TLR signaling. The CD4-TLR chimeras harbored the transmembrane and cytoplasmic domains of wild-type TLR2 (2wt), double mutant TLR2 Y641F/D678N (T2dm), wild-type TLR1 (1wt), or double mutant TLR1 F637Y/N672D (T1dm). The constructs were transfected into CHO cells alone or in the indicated pairs, and signal transduction was assessed by activation of the ELAM-1 promoter driving a firefly luciferase gene. Activation was measured in relative luciferase units (RLU). See Materials and methods.

Figure 8

Binding of TLR and chimeras to newly identified proteins. Yeast expressing the BD fusions indicated (at left) and the AD fusion partners indicated (along bottom, see Table 1) were grown on −TL media (top panel), then replica-plated onto −TLH/+3 mM 3AT media (bottom panel).