Structure Prediction

Visualize the 3D structures of your protein sequences using open source models like ESMfold, Lin et al. (2023).  ESMFold leverages the ESM2 protein language model to derive meaningful representations from the protein sequence. Subsequently, the ESMFold structure prediction neural network employs these representations to directly forecast the 3D coordinates of the protein’s constituent atoms. For detailed information about the model, please refer here.  The ESMfold model can also be accessed via REST APIs or our python client. 

Input Protein Sequence

Start by accessing the Protein Structure Visualization feature on our platform and input your protein sequence. Simply type it in or upload a .fasta file containing the sequence data.

Model Training

Once your sequence is entered, click the “Next” button to proceed. This will initiate the ESMfold model to begin its analysis.The model will process your data, interpreting the sequence to predict the 3D folding structure.

Explore 3D Visualization

After the model has completed its training, you’ll be presented with a 3D visualization of the protein structure. This visualization is powered by the Mol* Viewer tool, Sehnal et al. (2021) (, which allows you to interactively explore the structure. Use the tools provided by the Mol* Viewer to zoom, rotate, and pan through the 3D structure. 


If you wish to save or share the 3D structure, you can export it as a .pdb file.


To view your previously generated structure, under the ‘History’ section, select the previous jobs by the file name or date of creation. 


Lin, Zeming, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, et al. 2023. “Evolutionary-Scale Prediction of Atomic-Level Protein Structure with a Language Model.” Science 379 (6637): 1123–30.
Sehnal, David, Sebastian Bittrich, Mandar Deshpande, Radka Svobodová, Karel Berka, Václav Bazgier, Sameer Velankar, Stephen K Burley, Jaroslav Koča, and Alexander S Rose. 2021. “Mol* Viewer: Modern Web App for 3D Visualization and Analysis of Large Biomolecular Structures.” Nucleic Acids Res. 49 (W1): W431–37.