Sequence-free domain discovery from cryo-EM density.
Paper · CryoNet.Discovery identifies protein structures from cryo-EM density maps across resolutions through cross-modal recognition.
Input a density map
Upload a low-resolution density region, search structural space without a sequence, and inspect a ranked shortlist with local fitting results.
Density-native search
Start from a cryo-EM map instead of a sequence. The server infers density embeddings and retrieves candidate structures from multiple database regimes.
Full ranked candidate list
The result viewer keeps the full top-100 ranked candidate list. Local structures can be viewed and downloaded; candidates without local PDB files remain linked to their source database page.
Built for real screening
One interface covers small curated databases and large-scale AFDB/ESM spaces, so the same page supports validation and exploratory discovery.
Submit A Discovery Job
Upload one cryo-EM density map, choose a target search space, and receive ranked domain candidates together with local fitting outputs where source structures are available.
How To Use It
Reference
CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps , Muzhi Dai, Zhuoer Dong, Weining Fu, Kui Xu#, and Qiangfeng Cliff Zhang#, (2025), the 39rd AAAI Conference on Artificial Intelligence (AAAI), 39, 1.
Dai, M., Xu, K., Fei, Y., Zhang, Y., Yang, R., Lei, J., & Zhang, Q. C. (2026). CryoNet.Discovery identifies protein structures from cryo-EM density maps across resolutions through cross-modal recognition . LangTaoSha Preprint Server.