GraphINVENT-lite is a platform for graph-based molecular generation and optimization. It uses a tiered deep neural network architecture to probabilistically generate new molecules a single bond at a time, and reinforcement learning to guide the model towards better molecules. GraphINVENT-lite captures the core functionalities of GraphINVENT in a smaller, more user-friendly package.
- Anaconda or Miniconda with Python 3.6 or 3.8.
- (for GPU-training only) CUDA-enabled GPU.
For detailed guides on how to use GraphINVENT, see the tutorials.
An example training set is available in ./data/gdb13_1K/. It is a small (1K) subset of GDB-13 and is already preprocessed.
Contributions are welcome in the form of issues or pull requests. To report a bug, please submit an issue. Thank you to everyone who has used the code and provided feedback thus far.
If you use GraphINVENT-lite in your research, please see the original GraphINVENT repository for how to cite the work, author information, and more.
GraphINVENT is licensed under the MIT license and is free and provided as-is.