/Cloud-Bind

Cloud-based Drug Binding Structure Prediction

Primary LanguageJupyter NotebookMIT LicenseMIT

Cloud-Bind

Cloud-based Drug Binding Structure Prediction

Hi there!

This is a repository where you can find a Jupyter notebook scripts for running GNINA (molecular docking program with integrated support for scoring and optimizing ligands using convolutional neural networks), Uni-Dock (GPU-accelerated molecular docking program) and OpenBPMD (evaluating ligand pose stability using metadynamics) on Google Colab.

The main goal of this work is to demonstrate how to harness the power of cloud-computing in a cheap and yet feasible fashion.

  1. GNINA Open In Colab - Using GNINA to perform molecular docking calculations with integrated support for scoring and optimizing ligands using convolutional neural networks.
  2. GNINA+MD Open In Colab - Using GNINA to perform molecular docking calculations and OpenMM to run molecular dynamics simulations.
  3. GNINA+OpenBPMD Open In Colab - Using GNINA to perform molecular docking calculations and OpenBPMD to evaluate binding pose with metadynamics (BPMD).
  4. Uni-Dock Open In Colab - Using Uni-Dock to perform GPU-accelerated molecular docking calculations. It supports various scoring functions including vina and vinardo.
  5. Uni-Dock+MD Open In Colab - Using Uni-Dock to perform GPU-accelerated molecular docking calculations and OpenMM to run molecular dynamics simulations.
  6. Uni-Dock+OpenBPMD Open In Colab - Using Uni-Dock to perform GPU-accelerated molecular docking calculations and OpenBPMD to evaluate binding pose with metadynamics (BPMD).

Bugs

Acknowledgments

  • We would like to thank the GNINA team for doing an excellent job open sourcing the software.
  • We would like to thank the Uni-Dock team for doing an excellent job open sourcing the software.
  • We would like to thank the OpenBPMD team for their open source implementation of binding pose metadynamics (BPMD).
  • We would like to thank the Roitberg team for developing the fantastic TorchANI.
  • We would like to thank @ruiz_moreno_aj for his work on Jupyter Dock
  • We would like to thank the ChemosimLab (@ChemosimLab) team for their incredible ProLIF (Protein-Ligand Interaction Fingerprints) tool.
  • Also, credit to David Koes for his awesome py3Dmol plugin.
  • Finally, we would like to thank Making it rain team, Pablo R. Arantes (@pablitoarantes), Marcelo D. Polêto (@mdpoleto), Conrado Pedebos (@ConradoPedebos) and Rodrigo Ligabue-Braun (@ligabue_braun), for their amazing work.
  • A Cloud-Bind by Pablo R. Arantes (@pablitoarantes)

How should I reference this work?

  • If you’re using GNINA, please also cite:
    McNutt et al. "GNINA 1.0: molecular docking with deep learning."
    Journal of Cheminformatics (2021) doi: 10.1186/s13321-021-00522-2

  • If you’re using Uni-Dock, please also cite:
    Yu et al. "Uni-Dock: GPU-Accelerated Docking Enables Ultralarge Virtual Screening."
    Journal of Chemical Theory and Computation (2023) doi: 10.1021/acs.jctc.2c01145

  • If you’re using Molecular Dynamics Notebook, please also cite:
    Arantes et al. "Making it rain: cloud-based molecular simulations for everyone."
    Journal of Chemical Information and Modeling (2021) doi: 10.1021/acs.jcim.1c00998

  • If you’re using OpenBPMD, please cite:
    Clark et al. "Prediction of Protein–Ligand Binding Poses via a Combination of Induced Fit Docking and Metadynamics Simulations."
    Journal of Chemical Theory and Computation (2016) doi: 10.1021/acs.jctc.6b00201

    Lukauskis et al. "Open Binding Pose Metadynamics: An Effective Approach for the Ranking of Protein–Ligand Binding Poses."
    Journal of Chemical Information and Modeling (2022) doi: 10.1021/acs.jcim.2c01142