Data-driven prediction and design of bZIP coiled-coil interactions

Abstract

Selective dimerization of the basic-region leucine-zipper (bZIP) transcription factors presents a vivid example of how a high degree of interaction specificity can be achieved within a family of structurally similar proteins. The coiled-coil motif that mediates homo- or hetero-dimerization of the bZIP proteins has been intensively studied, and a variety of methods have been proposed to predict these interactions from sequence data. In this work, we used a large quantitative set of 4,549 bZIP coiled-coil interactions to develop a predictive model that exploits knowledge of structurally conserved residue-residue interactions in the coiled-coil motif. Our model, which expresses interaction energies as a sum of interpretable residue-pair and triplet terms, achieves a correlation with experimental binding free energies of R = 0.68 and significantly out-performs other scoring functions. To use our model in protein design applications, we devised a strategy in which synthetic peptides are built by assembling 7-residue native-protein heptad modules into new combinations. An integer linear program was used to find the optimal combination of heptads to bind selectively to a target human bZIP coiled coil, but not to target paralogs. Using this approach, we designed peptides to interact with the bZIP domains from human JUN, XBP1, ATF4 and ATF5. Testing more than 132 candidate protein complexes using a fluorescence resonance energy transfer assay confirmed the formation of tight and selective heterodimers between the designed peptides and their targets. This approach can be used to make inhibitors of native proteins, or to develop novel peptides for applications in synthetic biology or nanotechnology.

Fig 1. Schematic representation of the model-building and design protocol used to generate selective bZIP-interacting peptides.

(A) Experimentally determined dissociation constants for 4,549 bZIP interaction pairs were used as input to train a scoring model. (B) Weights corresponding to contributions from pairs and triplets of residues were fit to experimental binding data using a regression technique. The appropriate optimized weights can be summed to provide a predicted binding energy for two aligned bZIP coiled-coil sequences. (C) Binders were designed by using coiled-coil heptads as building blocks. Optimal combinations of heptads to construct tight-binding and selective designs were identified using integer linear programming in conjunction with the developed scoring function. (D) Designed sequences exhibit tight and selective binding to target bZIP coiled coils. Each square in the cartoon corresponds to a native human bZIP coiled coil, and cells are colored by the strength of interaction of each bZIP with the indicated designed peptide; darker shades correspond to stronger binding. Names of the bZIP proteins corresponding to each cell are given in S5 Table.

Fig 2. Interpretation of the model weights.

Optimized weights correlate with experimentally measured coupling energies reported in the literature: (A) g-e' R _ge = 0.94 (p = 5x10^–5) and (B) a-a' R _aa = 0.89 (p = 6x10^–4) [5,22,23]. (C, D) Examples illustrating triplets of residues that are predicted to be stabilizing (C) or destabilizing (D) according to the derived model. PDB ID 4DMD was used to illustrate the triplets; the structure in panel (D) was obtained by modeling glutamic acid at position 20 using the SCWRL4 side-chain prediction program [57].

Fig 3. Specificity profiles of four designs tested at 37°C.

The designed binders interact strongly with their targets as rhodamine-labeled peptides (bold red circles). Thin red circles show interactions with other bZIPs in the same family as the target. The ATF5-d1 design bound more tightly to ATF4 (thin red circle) than to ATF5. The designed proteins do not form strong homodimers (black bars), and there are large specificity gaps between the design/target interactions and design/off-target interactions (white and grey bars, colored according to target-off-target sequence identity at a, d, e and g positions). All K_d values are listed in S5–S12 Tables.

Fig 4. Designed bZIP-binding peptides inhibit interactions of native bZIP dimers.

(A) JUN-d1 inhibits the interaction of 10 nM JUN with 50 nM FOS with an IC₅₀ of 245 nM at 37°C. (B) XBP1-d1 inhibits the interaction of 10 nM XBP1 with 50 nM CREBZF with an IC₅₀ of 136 nM at 23°C. (C) ATF4-d1 inhibits the interaction of 10 nM ATF4 with 200 nM FOS with an IC₅₀ of 279 nM at 37°C. The dissociation constants at the indicated temperatures are K_d ≤ 1 nM for FOS-JUN, K_d ≤1 nM for XBP1-CREBZF, and K_d = 60 nM for ATF4-FOS, according to [18]. Fluorescence intensities were measured at both 37°C and 23°C, and the IC₅₀ value was fit and reported for the highest temperature that gave a well-defined lower baseline. The target bZIP in each complex was labeled with the FRET donor (fluorescein), the partner was labeled with the TAMRA FRET acceptor, and the design was unlabeled. Fluorescence emission was monitored at 525 nm and is reported in relative fluorescence units.