The evolution of multiple active site configurations in a designed enzyme

Abstract

Developments in computational chemistry, bioinformatics, and laboratory evolution have facilitated the de novo design and catalytic optimization of enzymes. Besides creating useful catalysts, the generation and iterative improvement of designed enzymes can provide valuable insight into the interplay between the many phenomena that have been suggested to contribute to catalysis. In this work, we follow changes in conformational sampling, electrostatic preorganization, and quantum tunneling along the evolutionary trajectory of a designed Kemp eliminase. We observe that in the Kemp Eliminase KE07, instability of the designed active site leads to the emergence of two additional active site configurations. Evolutionary conformational selection then gradually stabilizes the most efficient configuration, leading to an improved enzyme. This work exemplifies the link between conformational plasticity and evolvability and demonstrates that residues remote from the active sites of enzymes play crucial roles in controlling and shaping the active site for efficient catalysis.

Fig. 1

Reaction scheme for the Kemp elimination of 5-nitrobenzisoxazole. The nucleophilic oxygen atom of the base (B) donates electrons to the electrophilic 3′-H of 5-nitrobenzisoxazole and the electronegative oxygen atom of the isoxazole group forms a hydrogen bond with an acid (A) (1), forming a transition state in which the C−H and N−O bonds are weakened (2). The removal of the 3′-H from the substrate leads to an anionic phenoxide intermediate, which is then protonated, forming the final product (3)

Fig. 2

Crystal structures of different KE07 variants with and without ligand. a R1 in configuration A with bound product after substrate soaking. b R5 in configuration A with bound product after substrate soaking. c R5 in configuration B with bound MPD after cryoprotection. d R5 in configuration B with both MPD and substrate bound after substrate soaking. e R7 in configuration A with bound Bis-Tris molecule after cryoprotection. f R7 in configuration C with bound product after substrate soaking. g R7-2 in configuration B with bound hexahistidine tag from an adjacent protein chain after cryoprotection. h R7-2 in configuration C with bound product after substrate soaking, minor occupancy of configuration A is also observed. Ligands and alternative conformations of residues are shown as pink sticks. The mF_o-DF_c omit maps are shown as green meshes and contoured at 3.0σ. The 2mF_o-DF_c maps are shown as blue meshes and contoured at 1.0σ. PDB ID of the structures: a (5D2W), b (6DKV), c (6C7M), d (6DNJ), e (6CAI), f (6DC1), g (5D38), h (6CT3)

Fig. 3

Molecular dynamics and tryptophan fluorescence of KE07 variants. Conformational sampling of a Trp50 and b Glu101 during KE07 evolution in Hamiltonian replica exchange molecular dynamics (HREX-MD) simulations and c tryptophan fluorescence spectra over a temperature range 283−323 K. The dihedral angle distributions of Trp50 (a) and Glu101 (b) of the KE07 variants (R1 to R7-2) are shown. Initial Trp50 conformations, together with the backbone RMSD profiles, are shown in Supplementary Fig. 7. The atoms used for dihedral angle analysis are χ1: N:CA:CB:CG, χ2: CA:CB:CG:CD1 of Trp50 (a). χ2: CA:CB:CG:CD, χ3: CB:CG:CD:OE1 of Glu101. The protein structures indicate the labeling used for the different Trp50 and Glu101 conformers sampled by KE07 variants. c Fluorescence emission spectra (excitation at 280 nm) were measured at 283−323 K (temperatures for each spectra are indicated with different colors). The fluorescence spectra of Trp50Ala mutants (R1_Trp50Ala and R7-2_Trp50Ala) are shown in Supplementary Fig. 3

Fig. 4

Snapshots of three different binding modes from computer simulations. A comparison of representative structures of the equilibrated a−c Michaelis complexes and d−f transition state structures for the Kemp elimination of 5-nitrobenzisoxazole catalyzed by (a, d, green sticks) R7 with Trp50 in conformation A (b, e, pink sticks) R7-2 with Trp50 in conformation B, and (c, f, cyan sticks) R7-2 with Trp50 in conformation C. This figure highlights the shift in substrate position and key interacting residues upon rotation of the Trp50 side chain. The snapshots shown here correspond to the top ranked cluster obtained by RMSD clustering of the EVB simulations, as described in the Methods

Fig. 5

Preorganization and primary kinetic isotope effects in KE07 evolution. Activation energy KIEs (a) and pre-exponential factor KIEs (b). Error bars denote propagated standard errors in the fitted parameters to Arrhenius plot (Supplementary Fig. 11) from three independent experiments