CryoREAD is a computational tool using deep learning to automatically build full DNA/RNA atomic structure from cryo-EM map at resolution 0-5A.
It outputs a file in .pdb format that records the modeled DNA/RNA structure from the input cryo-EM map. For cryo-EM map includes proteins, it only modeled the DNA/RNA structures in the complex. If you want to model the full complex, please try ComplexModeler(

Our results webpage comprises three tabs: Results Visualization, Output Logs, and Job Configuration.

Results Visualization:
The "Result Visualization" panel contains the DNA/RNA structure modeled by CryoREAD. In the right panel, you can also click "Download Outputs" button to download the modeled structure. The downloaded structure is in .pdb format, you can use PyMol/Coot/Chimera to visualize it or refine it based on your expertise.
Additionally, you can visualize the map online by clicking the "Show map" button. Once loaded, the default contour level matches your input; however, you can make adjustments by clicking the "..." button beside "isosurface." Within the "Type: Isosurface" option, you can modify the iso-surface value and opacity by scrolling through the bar for precise adjustments. This feature allows you to assess the alignment between the modeled structure and the map.

Output Logs:
The 'Output Logs' panel compiles all outputs generated by the scripts.
If you're interested in monitoring the job's progress during execution, this section provides a comprehensive overview.

Job Configuration:
In the 'Job Configuration' panel, you'll find the input parameters used for this specific job. These records serve to maintain a log of your submitted input for reference.

Problem Debugging:
For any troubleshooting needs: Should you encounter any issues, please don't hesitate to contact us via email to report the problems. When sending an email, kindly use the subject line format 'CryoREAD problem: [jobid]', where [jobid] corresponds to the job displayed in the title. This specific identification helps us efficiently locate and debug jobs in the backend, ensuring a prompt response to your concerns.


CryoREAD is a de novo DNA/RNA structure modeling tool using deep learning for a cryo-EM map of up to 10 Å resolution.

CryoREAD was originally developed for modeling for maps up to 5 Å resolution, but now we upgraded the neural network to better predict nucleotides up to 10 Å.

If encounter problems, please contact Daisuke Kihara ( or Xiao Wang (

Example EMD-21051
Input Map file:21051.mrc

Input Sequence file:21051.fasta

Contour level: 0.6

Resolution: 3.7

Result Example:Result Example
Tutorial VideoTutorial PPT Tutorial Web.

CryoREAD algorithm (20-min video)


Please simply click "Schedule Job" when you filled all input fields.

Please make sure your contour level is lower than your focused region. This is absolute density threshold, not standard deviation.

If you are not sure, just use threshold 0, our model can automatically detect the structure regions.

CryoREAD is originally designed for maps at a resolution better than 5 Å. Now it is extended for up to a 10 Å resolution, although a higher accuracy is expected for maps better than 5 Å.

Resolution information is needed for refinement by phenix.real_space_refine.

If you do not know sequence information, you can skip to upload the fasta file.

We accept fasta files that includes proteins, where protein sequence will be automatically ignored. If it has multiple copies of the same nucleic acid sequence (homo-multimer), include the sequence exactly the number of times corresponding to the copies in the complex.