Published January 21, 2023
| Version v1
Dataset
Open
Data for "Deep Generative Priors for Biomolecular 3D Heterogeneous Reconstruction from Cryo-EM Projections" Part I
Creators
-
1.
University of Toronto
- 2. Hitachi High-Technologies Canada, Inc. based out of Victoria, BC
Description
Simulated datasets with uniformly distributed discrete states. Particle stacks, poses, CTFs and .star are available: (particle images downsampled to 256x256, original images 300x300x1.5A/pix available upon request)
- One_rect: 49,973 particle images
- Two_circles: 49,761 particle images
- Three_rect: 50,260 particle images
Results of aforementioned simulated datasets with:
- Trained models (weights, latent encodings, config)
- Reconstructed density maps for 121 discrete states (ground-truth .mrc/.pdb, LSGM-SPR result only due to space limit)
- Analyze results (PCA-map, U-map, 10d z-alignment)
Related resources:
- Original paper (Journal of Structural Biology): Deep Generative Priors for Biomolecular 3D Heterogeneous Reconstruction from Cryo-EM Projections
- Github link: https://github.com/benjamin3344/DGP-SPR
- Datasets part II: 10.5281/zenodo.10574539