Accurate de novo design of high-affinity protein-binding macrocycles using deep learning

Abstract

Developing macrocyclic binders to therapeutic proteins typically relies on large-scale screening methods that are resource intensive and provide little control over binding mode. Despite progress in protein design, there are currently no robust approaches for de novo design of protein-binding macrocycles. Here we introduce RFpeptides, a denoising diffusion-based pipeline for designing macrocyclic binders against protein targets of interest. We tested 20 or fewer designed macrocycles against each of four diverse proteins and obtained binders with medium to high affinity against all targets. For one of the targets, Rhombotarget A (RbtA), we designed a high-affinity binder (K_d < 10 nM) despite starting from the predicted target structure. X-ray structures for macrocycle-bound myeloid cell leukemia 1, γ-aminobutyric acid type A receptor-associated protein and RbtA complexes match closely with the computational models, with a Cα root-mean-square deviation < 1.5 Å to the design models. RFpeptides provides a framework for rapid and custom design of macrocyclic peptides for diagnostic and therapeutic applications.

Fig. 1. RFpeptides is a diffusion-based pipeline for the de novo design of protein-binding macrocycles.

a, Cyclically symmetric relative position encoding enables the generation of macrocyclic peptide backbones with N and C termini linked by a peptide bond. The relative position encodings are cyclized by switching from positive relative position encodings (that is, to the right) to negative encodings (that is, to the left) when index j is more than halfway around the peptide relative to index i. b, RFpeptides produces diverse and designable cyclic peptides. Left: structural clusters calculated using t-distributed stochastic neighbor embedding (tSNE)^, to reduce the dimensionality of an all-by-all TMscore matrix computed with TMalign on an unfiltered set of 1,200 macrocycles generated using RFpeptides. Right: six RFpeptides outputs from differing structural clusters, all with <1 Å backbone r.m.s.d. between the design model (blue) and the structure predicted by AfCycDesign (gold). comp., component. c, Self-consistency of designed macrocycles of various lengths. For each peptide length, the fraction (with n = 200 per length) of backbones with at least one of the of eight LigandMPNN sequences predicted by AfCycDesign to refold with pLDDT > 0.8 and within 2.0 Å backbone r.m.s.d. of the designed structure. Success rates for all sampled backbones are in blue and success rates only counting unique structural clusters (as calculated using MaxCluster^, at a TMscore threshold of 0.5) are in orange. d, For multichain diffusion trajectories (for example, macrocycle binder design), the relative positional encoding for the macrocycle chain is cyclized, whereas interchain and target chain relative positional encoding is kept as standard. e, Pipeline for the design of protein-binding macrocycles using RFpeptides. Macrocycle backbones are generated from randomly initialized atoms by a stepwise RFdiffusion-based denoising process, followed by amino acid sequence design using ProteinMPNN. Design models are downselected on the basis of the computational metrics from structure prediction using AfCycDesign and physics-based interface quality metrics using Rosetta. f, RFpeptides generates diverse macrocycles against selected targets. Four diverse cyclic peptide binders against the same target were generated using RFpeptides, with AfCycDesign iPAE < 0.3 and Cα r.m.s.d. < 1.5 Å between the design model (blue) and AfCycDesign prediction (gold). Source data

Fig. 2. De novo design and characterization of macrocyclic binders to MCL1 and MDM2.

a, AfCycDesign prediction of MCB_D2 (purple) bound to MCL1 (gray surface). MCB_D2 side chains are shown as sticks. b, Affinity determination of MCB_D2 using SPR. SPR sensorgram from a nine-point single-cycle kinetics experiment (twofold dilution, highest concentration: 20 µM). Experimental data are shown in purple and global fits are shown with black lines. The K_d is also shown on the plot. c, Experimentally determined complex structures closely match the design model. Overlap of the X-ray crystal structure (gold and gray) with the design model for MCB_D2 (purple). The Cα r.m.s.d. for the macrocycle is 0.7 Å when the experimental structure and design models are aligned by MCL1 residues. Close-up views demonstrate strong agreement between the side-chain rotamers of the design model and the X-ray structure. d, Overlay of the macrocycle model to the crystal structure shows a Cα r.m.s.d. of 0.4 Å with nearly identical backbones and side-chain rotamers. e, Close-up view of the macrocycle-bound MCL1 structure showing the cation–π interaction at the interface. f, Close-up view of the macrocycle-bound MCL1 structure showing the hydrophobic contacts at the interface. g, AfCycDesign prediction of MDB_D8 design (blue) in complex with MDM2 (gray) shown as cartoons with interacting side chains shown as sticks, bound to MDM2 shown as surface. h, Affinity determination of MDB_D8 using SPR. SPR sensorgram from a nine-point single-cycle kinetics experiment (fivefold dilution, highest concentration: 50 µM). Experimental data are shown in blue and global fits are shown with black lines. The K_d is also shown on the plots. i, Overall and close-up views of the AfCycDesign prediction of the MDB_D8 design model, highlighting key interactions with the MDM2. Source data

Fig. 3. De novo design of high-affinity macrocycle binders to GABARAP.

a, AfCycDesign predicted model for design GAB_D8 bound to GABARAP shown as surface, with hotspot residues highlighted in green. b, Affinity determination of GAB_D8 using SPR. SPR sensorgram from a nine-point single-cycle kinetics experiment (fivefold dilution, highest concentration: 20 µM). Experimental data are shown in orange and global fits are shown with black lines. The K_d is also shown on the plot. c, Superposition of chains E and F from the X-ray crystal structure of GAB_D8 bound to GABARAPL1 and the AfCycDesign model. d, AfCycDesign predicted model for design GAB_D23 bound to GABARAP shown as surface, with hotspot residues highlighted in green. e, Affinity determination of GAB_D23 using SPR. SPR sensorgram from a nine-point single-cycle kinetics experiment (fivefold dilution, highest concentration: 20 µM). Experimental data are shown in pink and global fits are shown with black lines. The K_d is also shown on the plot. f, Alignment of chains A and B from the X-ray crystal structure of GAB_D23 bound to GABARAP and the AfCycDesign model. g, Alignments of GAB_D8 and GAB_D23 macrocycle models to X-ray crystal structures show close matches. h, Comparison of GAB_D8 and GAB_D23 binding modes in the design models. i, Competitive AlphaScreen dose-response plot, IC₅₀ from the average of three experiments. Donor and acceptor beads in the assay are bound to GABARAP and GABARAP-binding peptide K1, respectively. Source data

Fig. 4. Accurate de novo design of a high-affinity cyclic peptide binder against the predicted structure of RbtA from A. baumannii.

a, AfCycDesign prediction of design RBB_D10 (violet cartoon) bound to the AF2-predicted β-helix domain of RbtA shown as gray surface. Hotspot residues from RbtA used during the backbone design step are shown in green. b, SPR sensorgram from nine-point single-cycle kinetics experiment (fivefold dilution, highest concentration: 20 µM). The K_d determined from the SPR experiment is also denoted on the plot. c, Close agreement of the RF2-predicted structure of RbtA (gray) with the X-ray structure (gold) of the RbtA N-terminal domain determined here confirms the predicted structure of the target used for the macrocycle design calculations. d, Alignment of the design model of RbtA-bound RBB_D10 (violet and gray) to the X-ray structure (gold) shows a close match between the design model and the experimentally determined structure (Cɑ r.m.s.d. for macrocycle: 1.4 Å). Close-up view of the RbtA-bound RBB_D10 with side chains shown as sticks. e, Overlay of RBB_D10 design model (after the AfCycDesign prediction step) aligned to the X-ray structure without RbtA demonstrates a nearly identical match for backbone coordinates and side-chain rotamers (Cɑ r.m.s.d.: 0.4 Å). The design model and X-ray structure are shown in violet and gold, respectively. f, Close-up view of the macrocycle-bound RbtA structure and design model showing polar side chain-to-backbone interactions mediated by RBB_D10 residue Asn12 at the interface. g, Close-up view of the polar side chain-to-side chain interactions mediated by RBB_D10 residue Asp6 at the interface. h, Close-up view of the hydrophobic interactions between RbtA and RBB_D10 at the binding interface. Source data