microsoft/Graphormer
A deep learning package for molecular modeling using graph neural network transformer architectures.
Not currently ranked — collecting fresh signals.
star history
Graphormer is a general-purpose deep learning backbone designed for molecular modeling tasks. It leverages graph transformer architectures to accelerate AI-driven research in molecule science, including drug discovery and material discovery. The package supports pre-trained models, interfaces with popular graph libraries (PyG, DGL, OGB), and was the winning solution in the Open Catalyst Challenge.
Frequently asked
- What is microsoft/Graphormer?
- A deep learning package for molecular modeling using graph neural network transformer architectures.
- Is Graphormer open source?
- Yes — microsoft/Graphormer is open source, released under the MIT license.
- What language is Graphormer written in?
- microsoft/Graphormer is primarily written in Python.
- How popular is Graphormer?
- microsoft/Graphormer has 2.5k stars on GitHub.
- Where can I find Graphormer?
- microsoft/Graphormer is on GitHub at https://github.com/microsoft/Graphormer.