Protein Structure Datasets for Protein Workshop

Raw + Processed Datasets used in the ProteinWorkshop Representation Learning Benchmark

Includes datasets from:

* The Antibody Developability dataset from Chen et al. (https://doi.org/10.1101/2020.06.18.159798)

* CATH from Ingraham et al. (https://www.mit.edu/~vgarg/GenerativeModelsForProteinDesign.pdf)

* CCPDB datasets from Agrawal et al. (https://doi.org/10.1093/database/bay142)

* The Deep Sea Proteins dataset from Sieg et al. (https://doi.org/10.1002/prot.26337)

* Reaction Class prediction from Hermosilla et al. (https://doi.org/10.48550/arXiv.2007.06252)

* FoldClassification from Hou et al. (https://doi.org/10.1093/bioinformatics/btx780)

* MaSIF Site dataset from Gainza et al. (https://doi.org/10.1038/s41592-019-0666-6)

* Metal3d Dataset from Duerr et al. (https://doi.org/10.1038/s41467-023-37870-6)

* Post-translational Modification Dataset from Yan et al. (https://doi.org/10.1016/j.crmeth.2023.100430)