Our training pipeline uses the CATH 4.2 dataset curated by [Ingraham, et al, NeurIPS 2019](https://github.com/jingraham/neurips19-graph-protein-design). We provide code to train, validate, and test the model on this dataset. We also provide a pretrained model in models/cath_pretrained. If you want to test a trained model on new structures, see the section "Using the CPD model" below.