Catalytic divergencies in the mechanism of L-arginine hydroxylating nonheme iron enzymes

Abstract

Many enzymes in nature utilize a free arginine (L-Arg) amino acid to initiate the biosynthesis of natural products. Examples include nitric oxide synthases, which generate NO from L-Arg for blood pressure control, and various arginine hydroxylases involved in antibiotic biosynthesis. Among the groups of arginine hydroxylases, several enzymes utilize a nonheme iron(II) active site and let L-Arg react with dioxygen and α-ketoglutarate to perform either C₃-hydroxylation, C₄-hydroxylation, C₅-hydroxylation, or C₄-C₅-desaturation. How these seemingly similar enzymes can react with high specificity and selectivity to form different products remains unknown. Over the past few years, our groups have investigated the mechanisms of L-Arg-activating nonheme iron dioxygenases, including the viomycin biosynthesis enzyme VioC, the naphthyridinomycin biosynthesis enzyme NapI, and the streptothricin biosynthesis enzyme OrfP, using computational approaches and applied molecular dynamics, quantum mechanics on cluster models, and quantum mechanics/molecular mechanics (QM/MM) approaches. These studies not only highlight the differences in substrate and oxidant binding and positioning but also emphasize on electronic and electrostatic differences in the substrate-binding pockets of the enzymes. In particular, due to charge differences in the active site structures, there are changes in the local electric field and electric dipole moment orientations that either strengthen or weaken specific substrate C-H bonds. The local field effects, therefore, influence and guide reaction selectivity and specificity and give the enzymes their unique reactivity patterns. Computational work using either QM/MM or density functional theory (DFT) on cluster models can provide valuable insights into catalytic reaction mechanisms and produce accurate and reliable data that can be used to engineer proteins and synthetic catalysts to perform novel reaction pathways.

Keywords: QM/MM; cluster models; dioxygenases; enzyme catalysis; inorganic reaction mechanisms; iron enzymes.

SCHEME 1

Enzymatic conversion of L-Arg by various Fe/αKG-dependent enzymes and obtained products.

FIGURE 1

Crystal structure coordinates of (A) VioC (PDB ID: 6ALM), (B) OrfP (PDB ID: 4M2E), (C) NapI (PDB ID: 6DAW), and (D) EFE (PDB ID: 6VP4).

SCHEME 2

Consensus catalytic cycle of nonheme iron/αKG-dependent dioxygenases for L-Arg hydroxylation. αKG stands for α-ketoglutarate, Succ represents succinate.

FIGURE 2

Overlay of the crystal structure coordinates of VioC (PDB ID: 6ALM) and NapI (PDB ID: 6DAW).

SCHEME 3

Radical reaction mechanism of L-Arg hydroxylation by VioC and L-Arg desaturation by NapI.

FIGURE 3

Relative free energy (ΔG) landscape for L-Arg hydroxylation at the C₃ and C₄ positions and desaturation across the C₃−C₄ bond by an iron(IV)-oxo species of a VioC model complex using calculations on the cluster model shown on the left. Free energies are expressed in kcal mol⁻¹ and represent energies as obtained with UB3LYP-D3/BS2//UB3LYP/BS1 with solvent, zero-point energies, and thermal and entropic corrections included at 298 K. BS1 refers to LANL2DZ with core potential on iron and 6-31G* on the rest of the atoms, while a BS2 basis set has LACV3P+ with core potential on iron and 6-311+G* on the rest of the atoms. Data can be obtained from Ali et al. (2021a).

FIGURE 4

QM/MM calculated relative free energy (ΔG) landscape for L-Arg hydroxylation at the C₄ and C₅ positions and desaturation across the C₄−C₅ bond by an iron(IV)-oxo species of a NapI model complex. The QM region is shown on the left. Free energies are expressed in kcal mol⁻¹ and represent energies as obtained with UB3LYP-D3/BS2//UB3LYP/BS1 with solvent, zero-point energies, and thermal and entropic corrections included at 298 K. BS1 refers to LANL2DZ with core potential on iron and 6-31G* on the rest of the atoms, while a BS2 basis set has LACV3P+ with core potential on iron and 6-311+G* on the rest of the atoms. Data can be obtained from Ali et al. (2023).

FIGURE 5

Optimized transition state structures for hydrogen atom abstraction steps from L-Arg by NapI (part (A)), VioC (part (B)), and OrfP (part (C)) enzymes with bond lengths in Å and angles in degrees. (A) QM/MM (UB3LYP/BS1:Amber) optimized transition states for NapI. (B, C) DFT cluster model calculated at the UB3LYP/BS1 level of theory.

FIGURE 6

Electron transfer pathways and change in electronic configuration and the oxidation state of intermediates during L-Arg desaturation and hydroxylation in NapI.

FIGURE 7

(A) Gas-phase bond dissociation free energies of C−H/N−H bonds in an isolated L-Arg molecule calculated at the UB3LYP/6-311+G* level of theory. (B) Electric field effects along the molecular z-axis and the changes in bond dissociation free energies calculated at the UB3LYP/6-311+G* level of theory.

FIGURE 8

Electric dipole moment (vector in red) and substrate-binding pocket electric field gradients with diatomic sticks with blue representing a positive direction and those with red representing the negative direction. (A) Dipole moment and field gradients for NapI. (B) Dipole moment and field gradients for VioC.