Histidine-rich enantiomeric peptide coacervates enhance antigen sequestration and presentation to T cells

Abstract

Peptides and peptidomimetics that self-assemble through LLPS have recently emerged as vital building blocks for creating functional biomaterials, thanks to their unique physicochemical properties and dynamic nature. One of life's most distinctive features is its selectivity for chiral molecules. To date, coacervates comprised of d-amino acids have not been reported. Here, we demonstrate that histidine-rich repeats of (GHGXY)₄ (X = L/V/P) and their enantiomers undergo LLPS, paving the way for improved coacervate stability. Through a series of biophysical studies, we found that the droplet size can be tuned based on L, V, or P substitution, and molecular cargo between 600 and 150 000 Da is efficiently recruited in a bioactivity-preserving aqueous environment during phase separation. Mechanistic studies reveal that the droplets enter cells via energy-dependent endocytic pathways, exhibit composition-selective fusion properties, and effectively deliver molecular therapeutics across various cell types. Finally, we demonstrate that the coacervates enhance antigen presentation to CD4⁺ and CD8⁺ T cells, resulting in robust proliferation and the production of functional cytokines. Our study outlines the development and characterization of enantiomeric peptide coacervates as promising vaccine delivery vehicles with tunable physicochemical properties.

Fig. 1. Chiral (GHGXY)₄ sequences and their LLPS properties. (A) The sequence of l- and d-peptides and their average hydrophilicity index (AHI). The AHI index values were calculated using the online peptide calculator. (B) Schematic of l- and d-peptide dissolution, followed by optical microscopy imaging. (C) Optical micrographs of chiral (GHGXY)₄ peptides (scale: 50 μm). (D) DLS analysis shows size variation between l- and d-(GHGLY)₄, (GHGVY)_4, and (GHGPY)₄ (L > V > P). Data is an average (mean ± SEM) of 3 technical replicates with 14 scans for each measurement. (E and F) Phase diagram of l- and d-(GHGXY)₄ peptides at different concentrations. Filled circles/squares: complete coacervate formation; open circles/squares: no coacervate formation; half-filled circles: low coacervate formation. Turbidity (λ = 600 nm) measured over time (3 h) for (G) GL 20, (H) GV 20, (I) GP 20. The inset shows the full kinetics up to 24 h. Filled circles: l-peptides; open circles: d-peptides. Grey circles represent the control (1× PBS).

Fig. 2. All-atom simulations illustrate molecular interactions in LLPS by (GHGXY)₄ peptides. Initial and final snapshots of multichain all-atom simulations for (A and D) GL 20, (B and E) GV 20, and (C and F) GP 20, using 10 monomeric peptides for each within a box. The contact map for (G) GL 20, (H) GV 20, and (I) GP 20 is generated by merging all chains in the simulation box into a single droplet. This contact map offers an overview of the molecular interactions within each chain that drive and stabilize LLPS by these peptides. The color scale ranges from lowest (0, white) to highest (1, color) contact probability between the amino acids of two such peptides (horizontal and vertical axes). R_g plots confirm LLPS for the monomer and decamer of (J) GL 20, (K) GV 20, and (L) GP 20. (M) The percentage of secondary structure is calculated from all-atom simulations for (GHGXY)₄ peptides.

Fig. 3. Localization of GL 20, Gl 20, GV 20, Gv 20 within hiPSC-CMs. Fluorescence microscopy images of eGFP loaded (A) GL 20, GV 20, and GP 20 coacervates (scale bar: 100 μm). (B) % eGFP load by GL 20, GV 20, and GP 20 droplets. **p < 0.01, ****p < 0.0001 as determined by a one-way ANOVA. Representative confocal images from hiPSC-CMs treated with (C) GL 20, (D) Gl 20, (E) GV 20, (F) Gv 20, (G) eGFP control (teal). The cellular membrane was identified with WGA membrane stain (purple). Micrographs were presented as single plane and 3D snapshots from the bottom view perspective (scale bars: 20 μm).

Fig. 4. Mechanisms of cellular uptake studies. (A) Schematic of in vitro antigen presentation assay depicting IL-2 production by hybridoma cells overlaid on BMDCs treated with OVA-loaded coacervates. (B and C) Schematic representation of OVA loaded L or D coacervates in ATP-depleted cells at 4 °C and 37 °C. (D) IL-2 production by OVA-loaded L or D coacervates upon ATP depletion, and at 4 °C, normalized to 37 °C (Cntrl). (E) Schematic of different endocytosis inhibitors and their target pathways. (F) Effect of endocytosis inhibitors on the uptake of L or D (GHGXY)₄ (L/V) coacervates loaded with OVA. A pronounced inhibitory effect was observed for Wortmannin (Wort), which inhibits macropinocytosis. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001 as determined by one-way ANOVA.

Fig. 5. Kinetics of antigen presentation and antigen presentation pathways in BMDCs treated with OVA-loaded coacervates. (A) DQ-OVA fluorescence in mouse BMDCs treated with saline or soluble DQ-OVA compared to (B) DQ-OVA delivered using GL 20 or GV 20 coacervates. (C) Comparison of antigen presentation between GL 20 and GV 20 coacervates loaded with 1 μM OVA as a function of time compared to soluble OVA. (D) Comparison of antigen presentation kinetics between GL 20 or GV 20 coacervates and their enantiomers. All coacervates were loaded with 10 μM OVA. (E and G) Schematics illustrating the inhibition of MHC-I and MHC-II antigen presentation pathways. (F) Reduced IL-2 production in the presence of MHC I inhibitors (bortezomib, brefeldin A, and lactacystin) or (G) MHC-II inhibitors (3-MA, NH₄Cl, and bafilomycin) following delivery of OVA using enantiomeric GL 20 or GV 20 coacervates. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001, as determined by one-way ANOVA.