Harnessing calcineurin-FK506-FKBP12 crystal structures from invasive fungal pathogens to develop antifungal agents

Abstract

Calcineurin is important for fungal virulence and a potential antifungal target, but compounds targeting calcineurin, such as FK506, are immunosuppressive. Here we report the crystal structures of calcineurin catalytic (CnA) and regulatory (CnB) subunits complexed with FK506 and the FK506-binding protein (FKBP12) from human fungal pathogens (Aspergillus fumigatus, Candida albicans, Cryptococcus neoformans and Coccidioides immitis). Fungal calcineurin complexes are similar to the mammalian complex, but comparison of fungal and human FKBP12 (hFKBP12) reveals conformational differences in the 40s and 80s loops. NMR analysis, molecular dynamic simulations, and mutations of the A. fumigatus CnA/CnB-FK506-FKBP12-complex identify a Phe88 residue, not conserved in hFKBP12, as critical for binding and inhibition of fungal calcineurin. These differences enable us to develop a less immunosuppressive FK506 analog, APX879, with an acetohydrazine substitution of the C22-carbonyl of FK506. APX879 exhibits reduced immunosuppressive activity and retains broad-spectrum antifungal activity and efficacy in a murine model of invasive fungal infection.

Fig. 1

Crystal structures of fungal CN–FK506-FKBP12 complexes. a Overlay of fungal CNs with the bovine complex (bovine: PDB 1TCO gray; fungal: CnA red, CnB blue, FKBP12 green and FK506 in orange). b RMSD of fungal CN complexes to the bovine complex and isolated components with Homo sapiens CN complex (CnA/CnB; PDB 4OR9) and H. sapiens FKBP12 (PDB 2PPN) in parentheses. c Alignment of human and fungal FKBP12s. Residues within 5 Å of FK506 are highlighted yellow. Non-conserved residues in fungi are highlighted green. d Structural comparison of variable residues in A. fumigatus (colored as in a; PDB 6TZ7) and H. sapiens FKBP12 (colored yellow; PDB 2PPN). Note that both AfFKBP12 F22 and Q50 reside distal (>10 Å) to the FKBP12-FK506-binding site on CnA or CnB (panel 1). The side-chains of AfFKBP12 R55 and hFKBP12 E55 are near the BBH and CnB, but face away from FK506 and do not make conserved contacts to CnA/CnB other than a distal main-chain carbonyl interaction with FK506 (panel 3). See also Supplementary Fig. 1 and Supplementary Tables 1 and 2

Fig. 2

Structural implication of AfFKBP12 mutations. a NMR analysis showing chemical shifts induced by FK506 binding to A. fumigatus (red) and human (black) FKBP12. b Growth of the Affkbp12 mutants in the absence and presence of FK506 for 5 days at 37 °C. c Microscopic localization AfFKBP12 mutated proteins in vivo in the absence or presence of FK506. Arrows show nuclear localization of AfFKBP12. Arrowheads indicate binding of AfFKBP12 to CN at the hyphal septum (d F22T, e Q50M, f R55E, g F88H). The FK506-binding pocket of WT (blue surface) and the pocket resulting from the mutation (red surface) are shown. Mutation site is denoted with an “*” and shown in stick format (red bar in bar graph), while residues comprising the binding pocket are shown in orange lines (black bars in bar graph). The stability and quality of the simulation is shown in the Cα RMSD plot. h The all atom (top) and backbone (bottom) RMSD denoting the structural variation due to the mutation compared to the WT structure (5HWB). See also Supplementary Figs. 1 and 3

Fig. 3

X-ray and MD-simulated structures of A. fumigatus and human CN-complex. a Conformational rotation of FKBP12 about the FK506-binding pocket comparing the X-ray characterized and MD characterized CnA (red)/CnB(blue)–FKBP12 [olive (X-ray) and green (MD simulated)]–FK506 complex. b Conformational rotation of FKBP12 about the FK506-binding pocket comparing the MD characterized A. fumigatus complex and the MD characterized human CnA (red)/CnB(blue)–FKBP12 [green (A. fumigatus) and yellow (human)]–FK506 complex. Rotation in a and b are depicted by dashed arrow lines color coded based on the FKBP12 coloring in each panel. c Growth of the A. fumigatus strain expressing codon-optimized hFKBP12 in the absence and presence of FK506 for 5 days at 37 °C. d Microscopic localization hFKBP12-GFP in A. fumigatus in the absence or presence of FK506. Arrows show nuclear localization of hFKBP12. Arrowheads indicate the binding of hFKBP12 to CN at the hyphal septum. e Center of mass (COM) distances between different chains convey the stability of the complexes over the last 100 ns; top—CnA to FKBP12, middle—CnA to FK506, and bottom—FKBP12 to FK506. See also Supplementary Figs. 4 and 5

Fig. 4

FK506 susceptibility and structural implication of hFKBP12 mutants. a Growth of the hFKBP12 mutants in the absence and presence of FK506 for 3 days at 37 °C (b K48Q, c Q50M, d K48Q–Q50M, e H88F) The FK506-binding pocket of WT (blue surface) and the pocket resulting from the mutation (red surface) are shown. Mutation site is denoted with a “*” and shown in stick format (red bar in bar graph), while residues comprising the binding pocket are shown in orange lines (black bars in bar graph). Stability and quality of the simulation is shown in the Cα RMSD plot. f All atom (top) and backbone (bottom) RMSD denoting the structural variation due to the mutation compared to the WT structure (1FKF-monomer). See also Supplementary Figs. 6 and 11

Fig. 5

Binding of FKBP12–FK506 to A. fumigatus CN. a Cartoon representation of A. fumigatus WT AfFKBP12–FK506 complex binding to A. fumigatus CN (CnA/CnB) from the MD simulation. Cartoon representations colored as follows: CnA (red), CnB (blue), AfFKBP12 (green), and FK506 (orange sticks and spheres). b Cartoon representation of Human hFKBP12:FK506 complex binding to A. fumigatus CnA/CnB from the MD simulation. Cartoon representations colored as follows: CnA (red), CnB (blue), hFKBP12 (yellow), and FK506 (orange sticks and spheres). Residue labels are shown for clarity and colored to the same color as their protein. Residues (those with more than 2000 contacts in the last 100 ns of the simulation) depicted as lines are contacts between either FKBP12 and CnA or CnB, while sticks are contacts between FK506 and CnA or CnB. Valence states are shown for label clarity. Bar graphs denote all contacts within 6 Å during the last 100 ns of each simulation; top bar graph, FKBP12 contacts to CnA (black) and CnB (red); middle graph, CnA contacts to FKBP12 (black), and FK506 (red), slanted lines denote residues 201–324 to which there are no contacts in CnA; bottom graph, CnB contacts to FKBP12 (black), and FK506 (red). See also Supplementary Figs. 7 and 8 and Supplementary Table 2

Fig. 6

The FK506 analog APX879 has reduced immunosuppressive activity. a Chemical structures of FK506 (left) and APX879 (right) with modified C22 indicated in blue. b Model of APX879 bound to A. fumigatus CN–FKBP12 complex. APX879 was overlaid on FK506 in the A. fumigatus crystal structure and steric clashes with the acetohydrazine substitution were minimized manually. The oxygen atom donated by the substitution was placed such that it occupies a similar space to the conserved water bound to the BBH. c Naive primary murine CD4⁺ T cells (from C57BL/6 mice) activated and differentiated in vitro and treated with FK506 have a reduced fraction of IL-2-producing cells than those treated with APX879. Dose response curves demonstrate an over 70-fold decrease in IL-2 production for FK506 compared to APX879. Note that the plot is showing a 95% confidence interval for the four-parameter curve fit, error bars for individual points represent the standard error value. The IC50 range is 0.17–0.21 for FK506 and 10.7–16.9 for APX879. d, e T helper cells (d) and germinal center (GC) B cells (e) collected from lymph nodes of mice treated for 8 days with vehicle, 5 mg/kg FK506, or 20 mg/kg APX879. Lymph nodes were collected 7 days following immunization with NP-OVA to stimulate T cell-dependent GC-B cell response. Error bars indicate boot strapped 95% confidence intervals. See also Supplementary Fig. 9

Fig. 7

Efficacy of APX879 in cryptococcal model of murine invasive fungal infection. a, b Survival curve of mice infected intranasally with C. neoformans WT (H99) and treated daily with indicated antifungal drugs. Treatment was halted at day 14 and animals were monitored for survival. Survival curves analyzed using log-rank Mantel–Cox test. c Fungal burdens in brain, lung, and spleen of H99 infected and drug-treated animals. **P < 0.01, ***P < 0.001. Lower error bars that exceeded the y-axis limits were excluded. See also Supplementary Fig. 10