CryoNet
CryoNet is a new fully differentiable neural network based method to directly identify the 3D atomic model from cryo-EM density map. CryoNet takes the cryo-EM density map and the corresponding sequence as the input, and learns the matches through the a transformer and generates the full atomic model. CryoNet is fast and accurate. Here we provide a demo to show how it works.
Welcome to give us feedback CryoNet@cryonet.ai or (Kui Xu: xukui@tsinghua.edu.cn).
CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map Restraints , Fuyao Huang*, Xiaozhu Yu*, Kui Xu#, and Qiangfeng Cliff Zhang#, (2026), International Conference on Learning Representations, ICLR
CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models , Weining Fu*, Kai Shu*, Kui Xu#, and Qiangfeng Cliff Zhang#, (2026), International Conference on Learning Representations, ICLR
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
CryoRes: Local Resolution Estimation of Cryo-EM Density Maps by Deep Learning , Muzhi Dai, Zhuoer Dong, Kui Xu#, and Qiangfeng Cliff Zhang#, (2023), Journal of Molecular Biology, 435(9)
A2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes , Kui Xu, Zhe Wang, Jianping Shi, Hongsheng Li and Qiangfeng Cliff Zhang, (2019), the 33rd AAAI Conference on Artificial Intelligence (AAAI), 33, 1230-1237