-
AMMA dataset
The dataset used in the paper for protein representation learning, consisting of 120k sequence, structure, and function triplets. -
EMPIAR-10029
The EMPIAR-10029 dataset is used to test the ability of TARGET-VAE to predict rotation and translation of objects in images. -
EMPIAR-10025
The EMPIAR-10025 dataset is used to test the ability of TARGET-VAE to predict rotation and translation of objects in images. -
OmegaFold dataset
The OmegaFold dataset is used for protein structure prediction. -
ProteinMPNN dataset
The ProteinMPNN dataset is used for inverse folding and protein structure prediction. -
CATH dataset
The CATH dataset provides a de-duplicated set of protein structural folds spanning a wide range of functions. -
AlphaFoldDB
The dataset used in the paper for secondary structure-guided novel protein sequence generation with latent graph diffusion.