polyid 0.1.1.1

Methods to train message passing neural network models on polymer structures.

PolyID^TM provides a framework for building, training, and predicting polymer properities using graph neural networks. The codes leverages nfp, for building tensorflow-based message-passing neural networ, and m2p, for building polymer structures. To understand and use the pipeline, the following examples have been provided:

1. Building polymer structures: examples/example_generate_polymer_structures.ipynb
2. Checking domain of validity: examples/example_determine_domain-of-validity.ipynb
3. Training a graph neural network: examples/example_generate_and_train_models.ipynb
4. Predicting with the trained model: examples/example_predict_with_trained_models.ipynb

Details for the methods are forthcoming in an upcoming manuscript.