Fragment binding to the Nsp3 macrodomain of SARS-CoV-2 identified through crystallographic screening and computational docking

Abstract

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) macrodomain within the nonstructural protein 3 counteracts host-mediated antiviral adenosine diphosphate-ribosylation signaling. This enzyme is a promising antiviral target because catalytic mutations render viruses nonpathogenic. Here, we report a massive crystallographic screening and computational docking effort, identifying new chemical matter primarily targeting the active site of the macrodomain. Crystallographic screening of 2533 diverse fragments resulted in 214 unique macrodomain-binders. An additional 60 molecules were selected from docking more than 20 million fragments, of which 20 were crystallographically confirmed. X-ray data collection to ultra-high resolution and at physiological temperature enabled assessment of the conformational heterogeneity around the active site. Several fragment hits were confirmed by solution binding using three biophysical techniques (differential scanning fluorimetry, homogeneous time-resolved fluorescence, and isothermal titration calorimetry). The 234 fragment structures explore a wide range of chemotypes and provide starting points for development of potent SARS-CoV-2 macrodomain inhibitors.

Fig. 1. Overview of the fragment discovery approach for SARS-CoV-2 Nsp3 Mac1 presented in this study.

(A) Surface representation of Nsp3 Mac1 with ADPr bound (cyan) in a deep and open binding cleft. (B) Nsp3 Mac1 has (ADP-ribosyl)hydrolase activity, which removes ADP-ribosylation modifications attached to host and pathogen targets. ADPr is conjugated through C1 of the distal ribose. (C) Summary of the fragment discovery campaign presented in this work. Three fragment libraries were screened by crystallography: two general-purpose [XChem and University of California San Francisco (UCSF)] and a third bespoke library of 60 compounds, curated for Mac1 by molecular docking of more than 20 million fragments. Crystallographic studies identified 214 unique fragments binding to Mac1, while the molecular docking effort yielded 20 crystallographically confirmed hits. Several crystallographic and docking fragments were validated by isothermal titration calorimetry (ITC), differential scanning fluorimetry (DSF), and a HTRF-based ADPr-peptide displacement assay.

Fig. 2. Crystallographic screening identified 234 fragments bound to Mac1.

(A, C, and E) Histograms showing the resolution of the crystallographic fragment screening data. The resolution of datasets where fragments were identified are shown with blue bars. (B, D, and F) Surface representation of Mac1 with fragments shown as sticks. (G) The Mac1 active site can be divided on the basis of the interactions made with ADPr. The “catalytic” site recognizes the distal ribose and phosphate portion of the ADPr and harbors the catalytic residue Asn⁴⁰ (10). The “adenosine” site recognizes adenine and the proximal ribose. The number of fragments binding in each site is indicated. (H) Summary of the fragments screened by x-ray crystallography, including the number of BM scaffolds and anionic fragments identified as hits in each screen. “Processed datasets” refers to the number of datasets that were analyzed for fragment binding with PanDDA. Of the datasets collected for 2954 fragments, 211 (7.1%) were not analyzed because of data pathologies.

Fig. 3. Docking hits confirmed by high-resolution crystal structures.

The protein structure (PDB 6W02) (34) prepared for virtual screens is shown in green, predicted binding poses are shown in blue, the crystal protein structures are shown in gray, and the solved fragment poses are shown in yellow, with alternative conformations shown in light pink. PanDDA event maps are shown as a blue mesh. Event maps were calculated before ligand modeling, and the maps are free from model bias toward any ligand (39). Protein-ligand hydrogen bonds predicted by docking or observed in crystal structures are colored light blue or black, respectively. Hungarian RMSD values are presented between docked and crystallographically determined ligand poses (binding poses for additional docking hits are shown in fig. S7).

Fig. 4. Fragments binding to the adenine subsite.

(A) Stick representation showing the interaction of the adenosine moiety of ADPr with Mac1. The key hydrogen bonds are shown as dashed lines. (B) Plot of the distances shown in (A) for all fragment hits. The distances, truncated to 10 Å, are for the closest noncarbon fragment atom. (C) Stick representation showing all fragments interacting with Asp²²-N, Ile²³-N, or Ala¹⁵⁴-O. The surface is “sliced” down a plane passing through Asp²². (D) Structures of the nine unique motifs that make at least two hydrogen bonds to the adenine subsite. Colored circles match the interactions listed in (A) and (B). The number of fragments identified for each motif are listed in parentheses. (E) Examples of the nine structural motifs. The fragment is shown with yellow sticks and the PanDDA event map is shown as a blue mesh. ADPr is shown as cyan transparent sticks. The apo structure is shown with dark gray transparent sticks.

Fig. 5. Fragments binding to the oxyanion subsite.

(A) Stick representation showing the interaction of ADPr with the oxyanion subsite of Mac1. The water molecule bridging the ribose moiety and the oxyanion subsite is shown as a blue sphere. (B) Plot of the distances highlighted in (A) for all fragment hits. Distances were calculated as described for Fig. 4B. (C) Stick representation showing all fragments interacting with Phe¹⁵⁶-N and Asp¹⁵⁷-N. Fragments are colored by secondary binding site with blue as phosphate, black as lower, and yellow as adenine. The surface is sliced across a plane passing through Phe¹⁵⁶ (white surface and gray interior). (D) Structures of the five structural motifs that bind the oxyanion site. (E) Examples of the five motifs. Three examples of motif I are shown, where the fragment also interacts with the phosphate, adenine, or lower subsite. The fragment is shown with yellow sticks, and the PanDDA event map is shown for reference as a blue mesh. ADPr is shown with transparent cyan sticks. The apo structure is shown with transparent gray sticks.

Fig. 6. Fragments targeting the catalytic and potential allosteric sites are sparsely populated compared to the adenosine site.

(A) Surface representation showing fragments that bind near the catalytic site. The fragment POB0135 (PDB 5S3W) bridges the gap between Asn⁴⁰ and Lys¹⁰² via a hydrogen bond and a salt bridge, respectively. Although eight fragments bind in the outer subsite, the fragment POB0135 makes the highest-quality interactions. No fragments bind in the ribose subsite. The fragment ZINC331715 (PDB 5RVI) inserts into the phosphate subsite between Ile¹³¹ and Gly⁴⁷. (B) Left: The K90 site is connected to the adenosine site by the Asp²²-Val³⁰ α helix. Right: Surface representation showing two fragments that bind to the K90 site. Hydrogen bonds are shown as dashed black lines. The fragment Z1741966151 (PDB 5S3B) is partially inserted in a nearby pocket (inset).

Fig. 7. Experimentally observed conformational heterogeneity is sampled by various fragments.

(A) Plots of side-chain RMSF for the 117 fragment structures from the UCSF screen using P4₃ crystals. (B) Stick representation showing all fragments (black sticks) within 3.5 Å of the Asp²² carboxylate and 4 Å of the Phe¹⁵⁶ ring (white sticks). (C) Structural heterogeneity in the previously reported Mac1 structures. (D) The Phe¹⁵⁶ side chain is captured in three conformations in the C2 apo structure. Electron density maps (2mF_O-DF_C) are contoured at 0.5 σ (blue surface) and 1 σ (blue mesh). For reference, ADPr is shown with blue sticks. (E) Plots of side-chain RMSD for Asp²² and Phe¹⁵⁶ from the Mac1 apo structure as a function of ligand-protein distance. Structures were aligned by their Cα atoms, before RMSDs were calculated for the Asp²² carboxylate and the Phe¹⁵⁶ aromatic carbons. (F) Fragment binding exploits preexisting conformational heterogeneity in the Phe¹⁵⁶ side chain. The apo structure is shown with dark transparent gray sticks in each panel, and the conformational changes are annotated with arrows. (G) Stick representation showing all fragments (black sticks) in the outer subsite of the catalytic site. (H) Conformational heterogeneity of residues in the catalytic site of the previously reported Mac1 crystal structures. (I) ADPr binding induces a coupled conformational change in the Phe¹³², Asn⁹⁹, and Lys¹⁰² side chains, as well as a 2-Å shift in the Phe¹³² loop. Electron density maps (2mF_O-DF_C) are contoured at 1.5 σ (blue surface) and 4 σ (blue mesh). (J) Mac1 structures determined at 100 and 310 K using C2 crystals.

Fig. 8. Water networks in the active site are displaced and used by fragments for bridging interactions.

(A) Water networks in the apo enzyme (P4₃ crystal form). Waters are shown as blue spheres, with electron density contoured at 5.0 σ (blue mesh) and 1.5 σ (blue surface). Hydrogen bonds are shown as dashed lines (distances are 2.6 to 3 Å). (B) Water networks in the Mac1-ADPr complex. ADPr is shown as cyan sticks. Conformational changes upon ADPr binding are highlighted with black arrows. (C) Comparison of crystallographic B-factors of water molecules in the catalytic site and adenosine site. The range and 95% confidence interval are shown. (D) Examples of the role of water networks in fragment binding. Left: ZINC340465 (PDB 5RSV) forms a single hydrogen bond to the protein (green dashed line) but forms five hydrogen bonds via water molecules. Right: Although few fragments of hydrogen bond directly to the backbone oxygen of Ala¹⁵⁴, several fragments interact with this residue via bridging water molecules (red dashed line) including ZINC89254160_N3 (PDB 5RSJ). (E) Plot showing all water molecules that lie within 3.5 Å of a noncarbon fragment atom. Water molecules are shown as blue spheres, with the major clusters circled. The cluster highlighted with a red arrow bridges fragments and the Ala¹⁵⁴ backbone oxygen.

Fig. 9. Biophysical corroboration of solution binding of crystallographic fragment hits by DSF, ITC, and ADPr-peptide displacement assay.

Top: (A to F) Performance of the most potent fragment hits in DSF, ITC, and ADPr-peptide displacement assay compared to ADPr. (C) Normalized raw DSF relative fluorescence unit (RFU) data demonstrate canonical unfolding curves and minimal compound-associated curve shape aberrations. Gradient color scales, 0 mM (yellow) and 3 mM (purple). (D) Tm_a elevation reveals Mac1 stabilization through fragment binding. Data points represent the means ± SD for triplicate measurements at each compound concentration. (E) Integrated heat peaks measured by ITC as a function of compound:protein molar ratio. The black line represents a nonlinear fit using a single-site binding model. (F) Peptide displacement assay measures ADPr-peptide displacement (i.e., % competition) from Mac1 by ligand. Data points represent the means ± SD for duplicate measurements at each compound concentration, and the black line represents a nonlinear fit using a sigmoidal dose-response equation constrained to 0 and 100% competition. (G) Summary of solution binding data for fragments from top panels. ΔTm_a values are given for the highest compound concentration in this assay (means ± SD). For the ITC and peptide displacement experiments, parameters obtained by nonlinear regression are given (±estimated SE). (H) Additional fragment hits showing Mac1 peptide competition.

Fig. 10. Fragments bridging multiple adenosine sites provide direct merging opportunities.

(A) Sliced view of the adenosine site (white surface and gray interior) and a symmetry mate (blue surface and interior) showing the deep pocket created by crystal packing in the P4₃ crystals. The 66 fragments that hydrogen bond with the Lys¹¹ backbone nitrogen are shown as sticks. (B) Plot showing distances between the symmetry mate (Lys¹¹-N) and the adenine subsite (Asp²²-Oδ, Ile²³-N, and Ala¹⁵⁴-O) for all fragments identified in the adenosine site. Dotted lines show the 3.5-Å cutoff used to classify hydrogen bonds. (C) An example showing 1 of the 24 fragments that bound in the adenosine site, yet only formed a hydrogen bond with the symmetry mate. (D) An example of one of the fragments that bridged the 9- to 11-Å gap between the adenine subsite and the symmetry mate. (E and F) Opportunities for fragment linking and merging. Adjacent or overlapping fragments were initially merged into a single new compound. Examples of readily available make-on-demand compounds are shown.