De novo design of a fluorescence-activating β-barrel

Abstract

The regular arrangements of β-strands around a central axis in β-barrels and of α-helices in coiled coils contrast with the irregular tertiary structures of most globular proteins, and have fascinated structural biologists since they were first discovered. Simple parametric models have been used to design a wide range of α-helical coiled-coil structures, but to date there has been no success with β-barrels. Here we show that accurate de novo design of β-barrels requires considerable symmetry-breaking to achieve continuous hydrogen-bond connectivity and eliminate backbone strain. We then build ensembles of β-barrel backbone models with cavity shapes that match the fluorogenic compound DFHBI, and use a hierarchical grid-based search method to simultaneously optimize the rigid-body placement of DFHBI in these cavities and the identities of the surrounding amino acids to achieve high shape and chemical complementarity. The designs have high structural accuracy and bind and fluorescently activate DFHBI in vitro and in Escherichia coli, yeast and mammalian cells. This de novo design of small-molecule binding activity, using backbones custom-built to bind the ligand, should enable the design of increasingly sophisticated ligand-binding proteins, sensors and catalysts that are not limited by the backbone geometries available in known protein structures.

Extended Data Figure 1:. Parametric design: workflow and shortcomings.

a, Schematic representation of the parametric approach to generate β-barrel designs. b-d, Comparison between β-barrels of type (n=8;S=8, b), type (n=8;S=10, c) and type (n=8;S=12, d); showing an example of 2D map with residue connectivity (top), the arrangement of the Cβs in the Cβ-strips (middle) and the packing pattern of the core side-chains (bottom). The difference in shear number translates into different overall strand staggering and barrel radii. The number of core Cβ-strips (top, middle) results in different arrangements of side-chains in the core of the barrel. e&f, The parametric designs exhibited distorted hydrogen bonds, reflected by the shear distance (defined in e) between paired antiparallel β-strands residues. The shear distance in the design deviate from the distribution observed in native β-sheet proteins (f).

Extended Data Figure 2:. Glycine kinks release strain in β-barrel backbones.

a, Fraction of retained hydrogen bond interactions after relaxation with Rosetta (‘relax’) of uniform polyvaline backbones (white) and polyvaline backbones with a glycine in the middle of each Cβ-strip (grey). We compare disconnected strand arrangements generated with the parametric hyperboloid model (n=225 independently generated models), the cylindric model (n=36 independently generated models), the coiled-coil model (n=150 independently generated models) and assembled based on a 2D map (n=144 independently generated models). Center line, median; box limits, upper and lower quartiles; whiskers, minimum and maximum values; points, outliers. b&c, In polyvaline backbones (n=189 independently generated models) relaxed with constraints to maintain hydrogen bonds between strands, several residues have unfavourable left-handed twist (c). The local strand twist is calculated on a sliding window of 4 residues along β-strands, as the angle between the vectors Cα1- Cα3 and Cα2- Cα4. The handedness of the twist is defined as the triple scalar product between these two vectors and the central axis of the barrel. Positive and negative values denote right-handed and left-handed twist, respectively. (b). d, After relaxation (‘FastRelax’), the valine positions in the middle of each Cβ-strip remained in the β-sheet specific ABEGO space (right); or were shifted towards the positive Φ space (E ABEGO) if mutated to glycines (bottom). e, A similar torsion angle distribution was observed for glycines in the β-strands of native β-barrels (n=35 high resolution crystal structures). f, In comparison with regular β-strands (top), the presence of glycine kinks (bottom) increases the local bending of the strands and creates corners in an otherwise circular barrel cross-section. g, The bending angle α is calculated on a sliding window of 3 residues.

Extended Data Fig. 3:. Placement of β-bulges, β-turns and the tryptophan corner.

a, Change of curvature (from convex to concave) and protrusion (dashed circle) of the longest hairpin associated with the placement of a glycine kink at position 44. b, relationship between the “corners” in the β-sheet (dashed line) generated by the glycine kinks and the type and position of the β-bulges and β-turns (Supplementary methods). Cα are shown as spheres and colored by ABEGO type. The bottom of the barrel was defined as the side of the N- and C-termini. c, The type I β-turn (‘AA’ ABEGO type) is frequently found at the second position relative to a β-bulge in native proteins and was selected to connect bottom hairpins. d, This choice is further supported by the enrichment of type I (AA) turns over the canonical type I’ turn (GG) in native β-barrels (n=35 high resolution crystal structures). e&f, Poly-valine backbones built with β-bulges and the corresponding β-turns (n=194 independently generated models) retain more hydrogen bonds after relaxation than backbones built without β-bulges and with canonical type I’ β-turns (n=186 independently generated models) (e) and exhibit better scored hydrogen bonds per β-strand residue flanking the β-turns (f). Center line, median; box limits, upper and lower quartiles; whiskers, minimum and maximum values; points, outliers. g, Superposition of tryptophan corner motifs (n=41 high resolution crystal structures) extracted from native β-barrels. h-j, Amino acid preference and torsional constraints derived from the set and used to model the tryptophan corner. Bounded constraints limits are shown as dashed lines.

Extended Data Fig. 4:. Biochemical and structural characterizations of designs BB1–4.

a, Results of experimental characterization of the nonfunctional designs (BB1–4). Reproducibility is described in the Methods. †E-value is calculated by BLAST the non-redundant protein database. b, Far-UV CD spectra of designs BB2 and BB3 at 25°C. c, SEC-MALS analysis showed a major monomer peak for BB1 and a major tetramer peak for BB2. d, Variants of BB1 with residues of the tryptophan corner and glycine kinks mutated to alanine were purified and sized. SEC are superimposed to the SEC trace of wild-type BB1 (WT). The mutations of all residues of the tryptophan corner eliminate the monomeric peak. Most of the glycine kink mutations negatively affect the monomeric species. The exceptions are Gly53 and Gly55, which are following each other on the fourth strand. Only one glycine kink per strand might be sufficient to introduce enough negative twist to un-strain the β-barrel. e-f, Deviations between BB1 design model and crystal structure. (e) One of the three bottom turns of the crystal structure (grey) significantly deviates from the design model (magenta) and forms additional crystal contacts (indicated by a dashed circle). (f) Three phenylalanine side-chains have different rotameric states. In the crystal structure, Phe41 interacts with Gly53 (which shows the most backbone deviation between the crystal structure and the design) to form an aromatic rescue motif. It is likely that the Phe rotamers discrepancy reflect a scoring/sampling challenge to accurately capture such aromatic rescue; MD simulation starting from the crystal structure (cyan) was also unable to recover the correct Phe41-Gly53 interaction. g, Biophysical properties (absorbance/fluorescence spectra, quantum yield and binding affinity) of mFAP1 and mFAP2 in complex with DFHBI. Average values from three biological replicates were used for the nonlinear regression to determine the K_D. The error estimates are the standard deviation from the fitting calculation. *λ_abs is peak absorbance wavelength, λ_ex is peak excitation wavelength and λ_em is peak emission wavelength. †Absolute quantum yield is measured with an integrating sphere; Relative quantum yield is measured using acridine yellow and fluorescein as the standards. ‡reported value. §From. ||From.

Extended Data Fig. 5:. RIF docking grid-based search algorithm, β-barrel scaffold construction and post-design ligand docking simulations.

a, Illustration of grid-based hierarchical search strategy in RIF docking. After generating an ensemble of interactions for the target ligand (Figure 3), each one of the selected scaffold is docked into the fixed “rotamer interaction field (RIF)” using the grid-based hierarchical searching algorithm. This search procedure starts from coarse sampling grids to fine sampling grids in 3D space. An example 2D grid scheme is shown in the upper row, from the lowest resolution (coarse sampling, left) to the highest resolution (fine sampling, right). At each searching stage, the backbone is assigned to different grids based on its relative position and the resulting docking configurations are scored. The top-scored backbone positions (highlighted by cyan circles in the 2D scheme) are shown as 3D structures in the lower row for each searching resolution and are continued for the next grid search and scoring. The 3D structure example shown here was streptavidin structure (PDB ID: 1STP) with grid searching resolutions of 8.0Å, 4.0Å, 2.0Å, and 1.0Å. b-d, β-barrel scaffold construction for small molecule binding. Three geometric constraints (b) were used to describe each backbone hydrogen bond and drive the backbone assembly during Rosetta low-resolution centroid modeling. Backbones generated with all three constraints had a very narrow Φ/Ψ distribution as a result of strong constraints (c, Ramachandran plot in upper left, Set 1, density colored in blue); by omitting N-H-O angle constraint, backbone torsion diversity slightly improved (c, upper right, Set 2). These two raw backbone sets yielded few non-redundant RIF docking solutions (d, blue bars). After two rounds of sequence design calculation using Rosetta full-atom force field (Supplementary Methods), regularized backbones (peptide bonds with proper dihedral geometry) and broadened Φ/Ψ distribution (c, Ramachandran plot in the lower row, density colored in orange) yielded more unique RIF docking solutions (d, orange bars). e, Computed metrics for 42 designs ordered and tested. Results from ab initio folding simulation were scaled to 0.0 to 1.0, with 1.0 represents a funnel-shaped folding landscape. f, Alternative ligand binding conformations revealed by post-design ligand docking simulations. The lowest-energy docking conformation using the design model (by simply taking out the ligand from the pocket) was similar to the designed DFHBI-binding mode (top left, grey; designed binding mode was circled in grey in the energy landscape in the lower row). Docking simulations using MD-refined the apo protein model revealed an alternative equal-energy docking conformation (top right, green) indicated by a green circle in the docking energy landscapes (lower row). Both binding modes rely on three hydrogen bonding residues from RIF docking (upper row).

Extended Data Fig.6:. Biochemical and structural characterization of design b10, b32, b11.

a, Size-exclusion chromatogram (SEC) of His6-tagged b10 and b32 after Ni-NTA affinity purification. The monodispersed peaks of absorbance at 280nm of b10 and b32 (cyan and lavender, respectively) have an elution volume compatible with the monomeric β-barrel (14kDa), based on their relative position to the protein standard peaks (dashed line). n biological replicates were performed with similar observation: n=4 for b10, n=5 for b32. b, Comparison of ligand binding pocket in b10 design model (middle, grey) with the crystal structure (left, cyan). The side-chain disagreements are highlighted with a dashed black circle on the right panel. c&d, The designed disulfide bond as a stabilizing mechanism. SEC curves of His6-tagged b11 (purple line) and b38 (dark yellow line) were overlaid to show the appearance of a monomer peak for b11 (the same standard as in a was applied here). A disulfide bond connecting the N-terminal helix to a β-strand (Q1C and M59C, circled in d) along with four mutations of neighboring residues, were introduced into design b38 (dark yellow) to make design b11 (purple). n biological replicates were performed with similar observation: n=3 for b38, n=5 for b11. e, Far-UV circular dichroism(CD) spectra of b10, b32 and b11. Left: spectra at different temperatures within one heating-cooling cycle; Right: thermal melting curves (b10’s CD signal was monitored at 220nm; b32 and b11 at 226nm). b11 likely forms an amyloid-like beta structure at 95°C (left, bottom row) with a negative peak around 226nm and refolds back after cooling to 25°C. The thermal stability of b11 decreases when the disulfide was reduced with 1mM tris(2-carboxyethyl) phosphine (TCEP) (right, bottom row). Measurements were performed once for each design (n=1). f, Fluorescence emission spectra of b32, b11 and b11L5F in complex with DFHBI. With 200 µM proteins, b32, b11 and b11L5F can activate 10 µM DFHBI fluorescence by 8-, 12- and 18-fold, respectively. n=2 biological replicates were performed with similar results. g, The residues designed to interact with DFHBI contribute to b11 and b32 activity. Single or double knockouts of hydrogen bonding residues (Y71, S23, N17 and T95) and a hydrophobic packing residue (M15) showed decreased fluorescence intensity at 500nm in comparison with the wild-type b11 or b32 (WT). Mutants were purified once for activity measurement. h&i, Re-designed 5-residue fifth turn in b11L5F. The original bulge-containing “AAG” β-turn in b11 (Extended Data Fig. 3b) was redesigned into a 5-residues turn. b11L5F was detected by yeast surface display and flow cytometry (i and Supplementary Data). Yeast cells displaying b11 and b11L5F showed an increased 520nm fluorescence signal (excited by 488nm laser, i). n=3 biological replicates were performed with similar observation.

Extended Data Fig. 7:. Deep mutational scanning maps for b11L5F.

a, The complete function (left) and protease stability (middle and right) landscapes of b11L5F. Fluorescence activation scores, trypsin and chymotrypsin stability scores were calculated as described in Supplementary Methods and demonstrated in the Supplemented Data (b11L5F_DMS_analysis.ipy). n=2 biological replicates with >10-fold sequencing coverage. Red color represents beneficial effect while mutations colored in blue color are detrimental (relative to the wild-type b11L5F). Wild-type residues at each position are indicated by black dots. b, b11L5F backbone model colored by the average stability scores. Glycine backbone Cα are shown as spheres. c&d, Mutational scanning maps of glycine kinks (G25, G43, G53, G55, G81 and G105) and tryptophan corner positions (G9, W9 and R109) (c), and of glycines in the β-turns and prolines (d). e, Statistics of the fluorescence activation and stability scores. The standard deviation between the two replicates used for calculating fluorescence activation scores is smaller than 2 for most the data points (left); 95% confidence interval calculated for the proteolysis/stability analysis is less than 0.25 for most the experimental protease EC50 values (middle and right).

Extended Data Fig. 8:. Experimental and computational improvement based on b11L5F.

a-c, Incorporation of point mutations from deep mutational scanning. Beneficial mutations that improve fluorescence activity without compromising protein stability (positive scores relative to wild-type b11L5F; a, left, n=2 biological replicates) were mapped onto b11L5F backbone model (a, right). Purified b11L5F variants incorporating those single, double or triple mutations showed consistently improved fluorescence activity (b). Binding titration curves were obtained for all six possible triple mutants (b, right, n=1 biological measurement). b11L5F with V103L, V95A, V83I, C59V and C1S were renamed as “b11L5F.1” (c). d, Characterization of five designs from the second round of design calculation. Three of the five designs (nC1–5) based on b11L5F showed improved binding activities by titrating purified proteins into 0.5µM DFHBI (d, n=1 biological sample was used for the measurement). The best variant (nC5) was renamed as “b11L5F.2”. e, Ligand docking simulations with the MD-refined apo b11L5F.2. Energy landscape was plotted by comparing all the docking conformations to the design model (left). The lowest-energy docking conformations (highlighted in green circle) match the design model (right, design mode in silver and docking model in green). f&g, Characterization of three best variants (mFAP0–2) from combinatorial library selections. Yeast cells displaying mFAP proteins incubated with 5µM DFHBI analyzed by flow cytometry (f, excited by 488nm laser, n=1 biological sample was used for the measurement with proper controls). Purified proteins showed up to 100-fold fluorescence activation (5µM protein + 0.5µM DFHBI, excited at 450nm and monitored at 500nm and 510nm in a plate reader, n=1 biological measurement). h, Far-UV circular dichroism(CD) characterization of b11L5F.1, b11L5F.2, mFAP0, mFAP1 and mFAP2. Left: spectra at different temperatures within one heating-cooling cycle; Right: thermal melting curves (CD signals were monitored at 226nm, spectra were recorded once (n=1) with internal noise estimation).

Extended Data Fig. 9:. Crystal structure of b11L5F_LGL, mFAP0 and mFAP1.

a-g, b11L5F_LGL crystal structure. (Protein samples of all six triple mutants in Extended Data Fig. 8b(right) were prepared for crystallization. b11L5F_LGL with V83L/V95G/V103L combination was successfully crystallized). Crystal contacts between protein copies in one asymmetric unit (yellow) were mediated by two tyrosines (stick representation, grey dashed circle); contacts between three asymmetric units (yellow, blue and green) were formed between β-turns (black dashed circle), which might have displaced one of the top β-turns (c). Overall backbone and side chain conformations in the design model matched the crystal structure with a backbone Cα RMSD of 1.02Å (b, crystal in yellow and design model in silver), and the designed disulfide bond was present in the crystal structure (d). Ligand density in the crystal structure was ambiguous: 2Fo − Fc omit map showing the electron density after refinement without placing DFHBI (e), the best ligand placement to match the density (f), and designed ligand binding interactions (silver) overlaid with the crystallized binding pocket (g). h&i, Crystal contacts in the DFHBI-bound structures of mFAP0(h) and mFAP1(i). Contacts between proteins copies in one asymmetric unit were formed around 40V and 54Y (grey dashed circle) that were introduced for helping crystallization (Extended Data Fig. 10a). Contacts between asymmetric units were formed between β-turns (black dashed circle). j, 2Fo−Fc omit electron density of DFHBI in the mFAP0-DFHBI complex crystal structure. DFHBI density contoured at 1.0σ is clear and matches the planar conformation of the ligand (right). k, Superposition of mFAP0 design model (silver) and the crystal structure (magenta). Hydrogen bonds were indicated with dashed lines. e, Helical capping interactions mediated by P62D mutation in mFAP1 crystal structure.

Extended Data Fig. 10:. Mapping of mutations introduced into b11 to yield the final brighter variants, biophysical characterization of mFAP1&2, and epifluorescent images. a, Sequence alignment of b11-based DFHBI-binding fluorescence-activating proteins.

Orange boxes indicate mutations or loop insertions introduced by computational design; purple boxes highlight mutations rationally introduced based on the deep mutational scanning maps (Extended Data Fig. 7&8); green boxes indicate mutations or loop insertions that were incorporated during combinatorial library selections; K40V and K54Y in light blue boxes were introduced to help crystal formation (Extended Data Fig. 9h&i). Despite having hydrophobic residues on the surface, mFAP2 remains soluble at 150mg/mL. b, mFAPs mutations mapped on the design models. Common mutations in all three mFAPs were highlighted in bold. c, Absorbance spectra for DFHBI, mFAP1- and mFAP2-DFHBI complexes (n=4 biological replicates with similar observation). d, Extinction coefficient determination for DFHBI at 418nm. e, Normalized absorbance and fluorescence spectra of mFAP1- and mFAP2-DFHBI complex (n=2 biological replicates with similar observation). f&g, Widefield epifluorescence (bottom) and brightfield (top) images of E.coli and yeast cells with 20µM DFHBI. Untransformed E.coli Lemo21 cells (f, left, n=2 biological replicates with similar observation) and yeast EBY100 cells displaying ZZ domain (g, left, n=2 biological replicates with similar observation) were treated with the same amount of DFHBI and imaged in the same way (1000mA 470nm LED and 200ms exposure time).

Figure 1:. Principles for designing β-barrels.

(a and b) Two methods for β-barrel backbone generation. a, Parametric generation of 3D backbones based on the hyperboloid model. The cross-section of the barrel is controlled on the global level with parameters (r, r_A and r_B). b, Specification of residue connectivity in a 2D map followed by assembly of 3D backbones with Rosetta. The cross-section geometry is controlled on the local level with torsion angle bins specified for each residue. c, Incorporation of glycine kinks and β-bulges reduces Lennard Jones repulsive interactions in β-barrels. Full backbones are shown on the left and one Cβ-strip is shown on the right. (Top) No β-bulge, no glycine kink; (Middle) one glycine kink in the middle of each Cβ-strip, no β-bulge; (Bottom) one glycine kink in the middle of each Cβ-strip, and β-bulges placed near the β-turns. d, Blueprint used to generate a β-barrel of type (n=8;S=10) with a square cross-section suitable for ligand binding. The values of the barrel radius (r) and tilt of the strands (θ) used to place glycines are determined by the choice of n and S. The residues in the 2D blueprint (left) and the 3D structure (middle) are colored by backbone torsion bins (right, Rosetta’s ABEGO types nomenclature). Shaded and open circles represent residues facing the barrel interior and exterior, respectively. Glycine positions are shown as yellow circles and β-bulges as stars. The “corners” in the β-sheet resulting from the presence of glycine kinks are shown as vertical dashed lines. C: barrel circumference; D: distance between strands.

Figure 2:. Folding, stability and structure of design BB1.

a, In silico folding energy landscape. Each grey dot indicates the result of an independent ab initio folding calculation; black dots show results of refinement trajectories starting from design model and dark grey dots from lowest energy ab initio models. b, Size-exclusion chromatogram of the purified monomer (14 kD). c, Far-UV CD spectra at 25°C (grey line), 95°C (black dashed line) and cooled back to 25°C (black dotted line). d, Near-UV CD spectra in Tris buffer (grey line) and 7M GuHCl (black line). e, Cooperative unfolding in GuHCl monitored by near-UV CD signal at 285 nm (grey line) and tryptophan fluorescence (black line). f-j, Superpositions of the crystal structure (grey) and the design model (pink): overall backbone superposition(f); section along the β-barrel axis showing the rotameric states of core residues(g); one of the top loop with a G1 β-bulge(h); and equatorial cross-section of the β-barrel, showing the geometry of the interior volume (i) . The glycine kinks are shown as sticks. The bottom of the panel shows the cross-section of the three closest native β-barrel structures based on TM-score (PDB IDs: 1JMX (0.77); 4IL6(chain O) (0.73); 1PBY (0.71)). (j) One of the bottom loops with a classic β-bulge. (k) Crystal structure and 2mFo − DFc electron density of the tryptophan corner, contoured at 1.5σ.

Figure 3:. Computational design and structural validation of β-barrels with recessed cavities for ligand binding.

a, (Left) Ensembles of side chains generated by the RIF docking method making hydrogen bonding (upper left) and hydrophobic interactions (lower left) with DFHBI (green); pre-generated interacting rotamers are shown in grey with backbone Cα highlighted by magenta spheres. (Right) Ensemble of 200 β-barrel backbones, with Cα atoms surrounding the binding cleft indicated by magenta spheres. b, Each ligand/scaffold pair (left) with multiple ligand-coordinating interactions from RIF docking is subjected to Rosetta energy-based sequence design calculations (right): positions around the ligand (light purple, above the dashed line) are optimized for ligand binding; the bottom of the barrel (dark grey, below the dashed line), for protein stability. c, (Left) Crystal structure (cyan cartoon with grey surface) of b10 with a recessed binding pocket filled with water molecules (red spheres). (Middle) b10 design model backbone (silver) superimposed on the crystal structure (cyan). (Right) Comparison of crystal structure and design model for two different barrel cross sections (indicated by dashed lines); glycine Cα atoms are indicated by spheres in the upper layer.

Figure 4:. Sequence dependence of fold and function.

Each position was mutated one at a time to each of the other 19 amino acids, and the resulting library subjected to selection for fluorescence or stability to proteases. a, (Upper) b11L5F backbone model colored by relative fluorescence activation score at each position. Blue positions are strongly conserved during yeast selection; red positions are frequently substituted by other amino acids. Residues buried in the design model are much more conserved than solvent exposed residues. (Lower) All the mutations to the glycine kinks (spheres in the upper model) and tryptophan (W) corner considerably reduced fluorescence; the shape of the designed structure is critical for the designed function. b & c, Bottom (b) and top (c) comparisons of b11L5F side chains colored by relative fluorescence activation scores (upper row) and stability scores (lower row). In the bottom of the barrel, core residues were strongly conserved in both the function and stability selections (b); in the top barrel there is a clear function-stability trade-off with the key DFHBI interacting residues critical for function but far from optimal for stability (c, substitution patterns at these positions are shown on the right). Fluorescence activation and stability scores were derived from n=2 biologically independent experiments with >10-fold sequencing coverage. Standard deviation and confidence interval are provided in Extended Data Fig. 7.

Figure 5:. Structure and function of mFAPs.

a & b, 2Fo − Fc omit electron density in the mFAP1-DFHBI complex crystal structure contoured at 1.0σ. DFHBI is clearly in the planar Z conformation rather than the non-fluorescent twisted conformations (a). The planar conformation is stabilized by closely interacting residues (b). c, Superposition of mFAP1 design model (silver) and the crystal structure (green). Hydrogen bonds coordinating DFHBI are indicated with dashed lines. d, Fluorescence emission spectra of 0.5µM DFHBI with or without 5µM mFAPs, excited at 467nm. e & f, Confocal micrographs of E.coli cells expressing mFAP2 in the presence of DFHBI (e) and yeast cells displaying Aga2p-mFAP2 fusion proteins on the cell surface (f). Scale bars: 20 μm(e), 10 μm(f). g & h, Overlay of widefield epifluorescence (green) and brightfield (gray) images of fixed COS-7 cells expressing sec61β-mFAP1 (g) and mito-mFAP2 (h, mito- = mitochondrial targeting sequence) with zoomed-in views of the fluorescence in the boxed regions. Scale bars: 20 μm (g&h), 3 μm (zoomed-in views). n=2 biological replicates were performed with similar observation.

Figure 6:. Comparison of structures of GFP and mFAP1

a, Surface mesh and ribbon representations of structures of GFP (left, PDB ID: 1EMA) and the computationally designed mFAP1 (right) with the chromophores embedded in the protein (green spheres). GFP, a product of natural evolution, has more than twice the number of residues, and a taller (top panel) and wider (bottom panel) barrel. Resolved water molecules in the crystal structures are shown as light purple spheres. b, Close-up of chromophore binding interactions in GFP (left) and mFAP1 (right).