Covalent Modeling

Now Available on Superbio.ai

April 14, 2025

SieveStack’s proprietary tool for covalent modeling is now available through our partner,  Superbio.ai.

Covalent inhibitors have made a remarkable comeback in recent drug discovery — targeting KRAS(G12C), EGFR, BTK, and SARS-CoV-2’s main protease, to name a few. These molecules typically feature reactive functional groups (warheads) that form covalent bonds with target residues, improving potency and residence time over reversible compounds. [1]

Challenges in Covalent Modeling

  • Reactive warheads must be positioned close to a suitable nucleophile

  • Non-covalent portions of the ligand must be stable and well-optimized

  • Reaction geometry must allow for feasible covalent bond formation

  • Protein flexibility is critical to capture realistic binding modes

At SieveStack, we’ve developed an internal toolchain to address these requirements. It integrates physics-based simulation, flexible side-chain modeling, and automated scoring to evaluate covalent binding poses. To support broader use, the tool has now been deployed on Superbio.ai’s cloud platform.

Examples

To demonstrate the utility of our tool, we applied it to several well-characterized covalent inhibitors. In these cases, the predicted ligand poses closely matched the experimental co-crystal structures, with RMSD values under 1Å. The following examples highlight accurate reproduction of covalent binding modes across high-value targets, consistent with crystallographic data.

Legend

Tan - Protein, empirical
Blue - Ligand, empirical
Pink - Ligand, predicted

Target: BTK
Covalent Ligand: Zanubrutinib
PDB Code: 6J6M

Target: K-Ras G12C
Covalent Ligand: ARS-1620
PDB Code: 5V9U

Target: SARS-CoV-2 Main Protease
Covalent Ligand: Nirmatrelvir
PDB Code: 8DZ2

Target: BTK
Covalent Ligand: LOU064 (Remibrutinib)
PDB Code: 6TFP

App Features

  • Covalent docking to a specified residue

  • Side-chain flexibility during pose generation

  • Physics-based scoring across parallel simulations

Results include docked PDB files and a CSV report with predicted affinities and related metrics.

Try it on Superbio.ai!

References

  1. Boike, Lydia, et al. "Advances in covalent drug discovery." Nature Reviews Drug Discovery 21, no. 12 (2022): 881-898.

  2. De Vita, Elena. "10 years into the resurgence of covalent drugs." Future Medicinal Chemistry 13, no. 2 (2021): 193-210.

  3. Sotriffer, Christoph. "Docking of covalent ligands: challenges and approaches." Molecular Informatics 37, no. 9-10 (2018): 1800062.

  4. Schaefer, Daniel, and Xinlai Cheng. "Recent advances in covalent drug discovery." Pharmaceuticals 16, no. 5 (2023): 663.

  5. Oyedele, Abdul-Quddus, et al. "Docking covalent targets for drug discovery..." Molecular Diversity 27, no. 4 (2023): 1879-1903.

  6. Stanzione, Francesca, et al. "Use of molecular docking computational tools..." Progress in Medicinal Chemistry 60 (2021): 273-343.

  7. Lu, Wenchao, et al. "Fragment-based covalent ligand discovery." RSC Chemical Biology 2, no. 2 (2021): 354-367.

  8. Hillebrand, Laura, et al. "Emerging and Re-emerging Warheads..." Journal of Medicinal Chemistry 67, no. 10 (2024): 7668-7758.