TorchDrug is an open-source project on GitHub with about 1,588 stars, most recently updated in 2024. TorchDrug is a powerful and flexible machine learning platform for drug discovery, built on PyTorch. Developed by the Deep Graph Learning group, it packages graph neural network models, molecule and protein datasets, and benchmark tasks so researchers can prototype AI models for chemistry and biology faster.
Published on GitHub under the Apache-2.0 license, TorchDrug has attracted a community of about 1,588 stars, which places it among the more visible open-source AI projects in its niche. Development was still active as of 2024, based on the repository’s latest updates. Because the full source code is public, teams can audit how it works, adapt it to their own stack, and self-host it rather than depending on a closed hosted product.
The repository is tagged with topics including deep-learning, drug-discovery, graph-neural-networks, pytorch, which gives a quick picture of where it fits in the open-source AI ecosystem. New users can explore the examples and documentation in the repository to understand the main workflows before integrating it into their own projects, and the public issue tracker shows what the maintainers are actively working on and what the community is asking for.
TorchDrug is Apache-2.0 open source and free to use for research and product development.
TorchDrug is best suited for computational chemists, bioinformaticians and ML researchers applying graph learning to molecules, proteins and drug discovery problems. Anyone evaluating it should start with the GitHub repository, where the documentation, examples and issue tracker show exactly what the current version can do.