gcorso/DiffDock
DiffDock uses score-based diffusion models to predict how small molecules bind to proteins, achieving state-of-the-art molecular docking performance.
Not currently ranked — collecting fresh signals.
star history
DiffDock applies diffusion model techniques to molecular docking, predicting binding conformations between proteins and small molecules. It leverages score-based generative models operating on non-Euclidean geometric representations of molecular structures. The 2024 release (DiffDock-L) improves performance and generalization through enhanced model architecture, and is available via Docker and a HuggingFace web interface.
Frequently asked
- What is gcorso/DiffDock?
- DiffDock uses score-based diffusion models to predict how small molecules bind to proteins, achieving state-of-the-art molecular docking performance.
- Is DiffDock open source?
- Yes — gcorso/DiffDock is open source, released under the MIT license.
- What language is DiffDock written in?
- gcorso/DiffDock is primarily written in Python.
- How popular is DiffDock?
- gcorso/DiffDock has 1.5k stars on GitHub.
- Where can I find DiffDock?
- gcorso/DiffDock is on GitHub at https://github.com/gcorso/DiffDock.