PoreDesigner for tuning solute selectivity in a robust and highly permeable outer membrane pore

Abstract

Monodispersed angstrom-size pores embedded in a suitable matrix are promising for highly selective membrane-based separations. They can provide substantial energy savings in water treatment and small molecule bioseparations. Such pores present as membrane proteins (chiefly aquaporin-based) are commonplace in biological membranes but difficult to implement in synthetic industrial membranes and have modest selectivity without tunable selectivity. Here we present PoreDesigner, a design workflow to redesign the robust beta-barrel Outer Membrane Protein F as a scaffold to access three specific pore designs that exclude solutes larger than sucrose (>360 Da), glucose (>180 Da), and salt (>58 Da) respectively. PoreDesigner also enables us to design any specified pore size (spanning 3-10 Å), engineer its pore profile, and chemistry. These redesigned pores may be ideal for conducting sub-nm aqueous separations with permeabilities exceeding those of classical biological water channels, aquaporins, by more than an order of magnitude at over 10 billion water molecules per channel per second.

Fig. 1

Water wire from Aquaporin 1 (AQP1) was used as a template to redesign OmpF pore geometry. a The left panel shows a frame from an MD simulation of single-file water permeation through AQP1. The pore wall residues capable of forming hydrogen bonds with the permeating water wire have been highlighted in yellow. The water wire is isolated with its geometry preserved and is thereafter placed in the OmpF pore. The pore-constricting residues are altered such that they fill up the space around the water wire forming a molecular mold of the selective internal geometry of AQP1 within OmpF beta scaffold. b The three distinct internal pore geometries of OmpF that resulted from the employed redesign procedure included: (i) off-center pore closure design (OCD), (ii) uniform pore closure design (UCD), and (iii) cork-screw design (CSD)

Fig. 2

OCD-TFTrp design shows steric clash but UCD does not. The OCD_TFTrp design has adjacent tryptophans clashing (left) resulting in some of the side chains facing away from the pore lumen, thereby yielding pore sizes larger than expected. However, in a UCD design (right), an R82L mutation alleviates a steric clash with Trp62 (unlike OCD-TFTrp). UCD designs are seen to intersperse smaller side-chain hydrophobic amino acids between longer ones so their side chains face the pore lumen resulting in smaller pore sizes

Fig. 3

Twenty OmpF mutants spanning the entire sub-nm range were designed. a Plot of the number of mutations vs. pore diameter for 20 mutants (including three mutants that were validated experimentally before MD simulations). The general trend indicates that the smaller the desired pore, the greater the number of mutations required. b Plot of the number of designs for each pore size and type classification

Fig. 4

Osmotic shock stopped-flow light scattering experiments were used to assess transport properties. Stopped-flow light scattering experiments revealed an order of magnitude or higher permeability than aquaporins for WT OmpF protein and its mutants as well as solute retention trends seen in OmpF protein mutants. a When OmpF (or OmpF mutant) containing proteoliposomes are mixed with hypertonic solutions, two different transport models can be observed based on whether the solute is permeable to the porin or not. b In the stopped-flow setup, for solute excluded model, normalized light scattering intensity levels off during the second stage as there is no inflow of water and solutes; for solute permeable model, normalized light scattering intensity decreased during the second stage due to inflow of water and solutes. c OmpF (WT) rejects PEG600 (600 Da) and larger molecules and thus only the PEG600 curves show no decreasing portion of the curve. d UCD rejects NaCl (58.5 Da) and larger molecules as there is no decreasing portion of the stopped-flow curve for any of the solutes tested. e Summary of the estimated solute rejection (light bars) and single-channel permeability (dark bars) of OmpF WT and the three OmpF mutants (details in Supplementary Figures 3 and 4). The two y-axes represent permeability (black left y-axis) or the molecular weight cutoff data (red right y-axis). Curves shown in panels c and d are averages of 6–10 traces from each stopped-flow light scattering experiment. Each experiment was conducted at least three times with independent vesicle preparations (complete data in Supplementary Methods and Supplementary Figure 3)

Fig. 5

MD simulations of OmpF corroborate experimentally observed permeability and selectivity trends. a Typical simulation system. (Top) Cut-away view of the system revealing a transmembrane water passage through an OmpF monomer. The OmpF monomer is depicted in purple, the lipid-bilayer in cyan, water molecules as red and white spheres, and Na⁺ and Cl^– ions as orange and green spheres, receptively. (Bottom) Top-down view of the system. The OmpF trimer is drawn using a cartoon representation, the lipid-bilayer as cyan bonds; water and ions are not shown. b Simulated osmotic permeability (averaged over 12,500 frames) of OmpF variants (red) and the corresponding experimental values (gray). c Ionic conductance of OmpF trimers obtained from applied field simulations under a 500 mV transmembrane voltage and averaged over 10,417 frames. d Water occupancy of OmpF variants. The green volume depicts the average location of water molecules in each channel characterized as a 0.3 g/cm³ isosurface of water oxygen density. For reference, each channel is shown using a semitransparent cartoon representation. e Major axis dimensions of the pores measured from PoreDesigner before MD (gray) and from the last 100 frames of MD (red). The error bars represent standard deviations. A 0.4 nm line represents the PoreDesigner design constraint of identifying pore designs smaller than 0.4 nm. f The average number of hydrogen bonds made between water and an OmpF monomer in each of the regions depicted in panel d and averaged over 14,583 frames