Sampled Structures from Diffusion Models for Protein SHAPES

Data associated with SHAPES (Structural and Hierarchical Assessment of Proteins with Embedding Similarity)

rmsd.tar.gz : RMSD and TM scores of ESMFold predicted structures with original designed backbones.

mpnn.tar.gz : ProteinMPNN designed sequences.

raster.tar.gz : CATH and sampled structures annotated with the grid square label after rasterization. Also includes the specific structures which are displayed in the raster plots.

dssp.tar.gz : Secondary structure frequences computed by DSSP.

samples.tar.gz : All sampled structures.

Due to size, the ESMFold predicted structures for eight ProteinMPNN-designed sequences per sampled backbone are not included.

Code: proteinshapes-main.zip