Published December 17, 2025
| Version v1
Dataset
Open
Sim2Struct-1000: A synthetic dataset for extreme compositional heterogeneity
Authors/Creators
-
1.
Princeton University
-
2.
Stanford University
Description
Synthetic cryo-EM dataset with simulated compositional heterogeneity and their ground truth density maps and poses
Dataset for "CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks", to appear in CVPR 2026
Files
Sim2Struct-1000.zip
Files
(69.3 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:11ce761cd36c7969dd3e54acdadb6b83
|
69.3 GB | Preview Download |
Additional details
Identifiers
- arXiv
- arXiv:2512.06332
Related works
- Is described by
- Preprint: arXiv:2512.06332 (arXiv)
Dates
- Accepted
-
2026-02-27
Software
- Repository URL
- https://github.com/ml-struct-bio/cryoHYPE
- Programming language
- Python
- Development Status
- Active