Table of contents
Generative molecular docking
DiffDock
DiffDock: Deep Confident Steps to New Pockets: Strategies for Docking Generalization
Paper GitHub HuggingFace >Docker
Fast and easy to use docking method. Requires as little as a protein structure and molecule SMILES to go started. Note that DiffDock was updated in February 2024, with the updated version named DiffDock-L. Additional information about the original version and manuscript can be found in the GitHub repository.
I have created the linked DiffDock-L Docker image. You can find detailed instructions in the Docker Hub page. That said, the official GitHub repository has a Dockerfile to run the webserver DiffDock version. It should be straightforward to have it edited to run DiffDock on the commandline.
DynamicBind
DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model
A molecular docking method in which both the protein and the ligand are docked in a flexible manner.
I am in the process of creating a Docker image for DynamicBind. Will update shortly.
NeuralPLexer
NeuralPLexer: State-specific protein–ligand complex structure prediction with a multiscale deep generative model
Physical docking
OpenBPMD
Open Binding Pose Metadynamics: An Effective Approach for the Ranking of Protein–Ligand Binding Poses
GNINA
GNINA 1.0: molecular docking with deep learning
Cloud-Bind
A repository with a couple of different Colab notebooks 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).
hgbrian/biocolabs
A collection of Colab notebooks, including some related to molecular docking.
DOCKSTRING
DOCKSTRING: easy molecular docking yields better benchmarks for ligand design