Uni-Dock is a GPU-accelerated molecular docking program developed by DP Technology. It supports various scoring functions including vina, vinardo, and ad4. Uni-Dock achieves more than 2000-fold speed-up on V100 GPU with high-accuracy compared with the AutoDock Vina running in single CPU core. The paper has been accepted by JCTC (doi: 10.1021/acs.jctc.2c01145).

Uni-Dock joins the DeepModeling community, a community devoted of AI for science, as an incubating level project. Learn more about DeepModeling

Please check unidock folder for installing instructions, source codes, and usage.

Uni-Dock Tools is a Python package developed to handle the inputs and outputs of Uni-Dock. It is committed to support more input formats and scoring functions. We hope it could be an easy-to-use virtual screening workflow for users with diversed backgrounds.

Please check unidock_tools folder for installing instructions, source codes, and usage.

To evaluate the performance and accuracy under a uniform standard, we created Uni-Dock Benchmarks based on public datasets and papers. The benchmarks are publicly available at https://github.com/dptech-corp/Uni-Dock-Benchmarks.

• 2024-02-29: Release Uni-Dock v1.1 and Uni-Dock Tools.
• 2023-08-21: Upload source codes of Uni-Dock.
• 2023-08-14: Add Uni-Dock Tools to support SDF format input for vina and vinardo scoring functions.

If you used Uni-Dock in your work, please cite:

Yu, Y., Cai, C., Wang, J., Bo, Z., Zhu, Z., & Zheng, H. (2023). Uni-Dock: GPU-Accelerated Docking Enables Ultralarge Virtual Screening. Journal of Chemical Theory and Computation. https://doi.org/10.1021/acs.jctc.2c01145