Overview

DiffDock is a generative diffusion model for drug discovery in molecular blind docking.

DiffDock consists of two models: the Score and Confidence models. The Score model generates a series of potential poses for protein-ligand binding by running a reverse diffusion process.

DiffDock does not require any information about a binding pocket. During its diffusion process, the molecule's position relative to the protein, its orientation, and the torsion angles are allowed to change. Running the learned reverse diffusion process transforms a distribution of noisy prior molecule poses to the one learned by the model. As a result, it outputs many sampled poses and ranks them via its confidence model.

Leveraging the same neural-network architecture designed in the original DiffDock by MIT, the model v2.2.0 is trained by NVIDIA using PLINDER and SAIR, a state-of-art dataset of well curated and labeled protein-ligand complexes, which therefore, delivers a much higher accuracy for molecular docking tasks.

The container components are ready for commercial/non-commercial use.

Third-Party Community Consideration

This model uses the DiffDock neural network architecture originally designed by MIT. NVIDIA has trained this version (v2.2.0) using NVIDIA-curated datasets (PLINDER and SAIR) to improve accuracy for molecular docking tasks.

License / Terms of Use

GOVERNING TERMS: Use of this NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products. Use of this model is governed by the NVIDIA Open Model License. Additional Information: MIT.

You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.

Deployment Geography

Global

Use Case

DiffDock empowers researchers and commercial users in Drug Discovery, Computational Chemistry, and Digital Biology to generate accurate protein–ligand binding poses without requiring predefined binding pocket information. Trained on NVIDIA-curated datasets (PLINDER and SAIR) using a robust diffusion-based generative framework, DiffDock delivers high-quality pose predictions suitable for early hit discovery, virtual screening, and structure-based design workflows. The model produces multiple candidate poses and ranks them using an integrated confidence module, enabling reliable prioritization of ligands across large-scale docking pipelines.

Release Date

build.nvidia.com 7/6/2026 via build.nvidia.com
NGC 7/6/2026 via catalog.ngc.nvidia.com

Program Classes:

The NIM contains the DiffDock model, including DiffDock inference code, model weights (checkpoint). The model (checkpoint) is pulled automatically at NIM startup.

Deployment Details:

The DiffDock NIM is deployed by pulling and running the container in an environment with appropriate credentials. For instructions to pull and run, hardware requirements, and NVIDIA GPU support matrix, see DiffDock NIM Docs.

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster inference times compared to CPU-only solutions

References:

@inproceedings{corso2023diffdock,
    title={DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking}, 
    author = {Corso, Gabriele and Stärk, Hannes and Jing, Bowen and Barzilay, Regina and Jaakkola, Tommi},
    booktitle={International Conference on Learning Representations (ICLR)},
    year={2023}
}

Container Version(s):

DiffDock v2.3.0

Security Common Vulnerabilities and Exposures (CVEs)

Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.

Users are responsible for ensuring the physical properties of model-generated molecules are appropriately evaluated and comply with applicable safety regulations and ethical standards.

Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Get Help

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more DiffDock NIM Docs.

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.